Reinstated LogisticRegression.threshold Param for binary compatibility. Param thresholds overrides threshold, if set.
CC: mengxr dbtsai feynmanliang
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#8079 from jkbradley/logreg-reinstate-threshold.
From JIRA: Currently, Params.copyValues copies default parameter values to the paramMap of the target instance, rather than the defaultParamMap. It should copy to the defaultParamMap because explicitly setting a parameter can change the semantics.
This issue arose in SPARK-9789, where 2 params "threshold" and "thresholds" for LogisticRegression can have mutually exclusive values. If thresholds is set, then fit() will copy the default value of threshold as well, easily resulting in inconsistent settings for the 2 params.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#8115 from jkbradley/copyvalues-fix.
Went thru the history of changes the file MLUtils.scala and picked up the version that the change went in.
Author: Sudhakar Thota <sudhakarthota@yahoo.com>
Author: Sudhakar Thota <sudhakarthota@sudhakars-mbp-2.usca.ibm.com>
Closes#7436 from sthota2014/SPARK-8925_thotas.
1. Add “asymmetricDocConcentration” and revert docConcentration changes. If the (internal) doc concentration vector is a single value, “getDocConcentration" returns it. If it is a constant vector, getDocConcentration returns the first item, and fails otherwise.
2. Give `LDAModel.gammaShape` a default value in `LDAModel` concrete class constructors.
jkbradley
Author: Feynman Liang <fliang@databricks.com>
Closes#8077 from feynmanliang/SPARK-9788 and squashes the following commits:
6b07bc8 [Feynman Liang] Code review changes
9d6a71e [Feynman Liang] Add asymmetricAlpha alias
bf4e685 [Feynman Liang] Asymmetric docConcentration
4cab972 [Feynman Liang] Default gammaShape
Adds unit test for `equals` on `mllib.linalg.Matrix` class and `equals` to both `SparseMatrix` and `DenseMatrix`. Supports equality testing between `SparseMatrix` and `DenseMatrix`.
mengxr
Author: Feynman Liang <fliang@databricks.com>
Closes#8042 from feynmanliang/SPARK-9750 and squashes the following commits:
bb70d5e [Feynman Liang] Breeze compare for dense matrices as well, in case other is sparse
ab6f3c8 [Feynman Liang] Sparse matrix compare for equals
22782df [Feynman Liang] Add equality based on matrix semantics, not representation
78f9426 [Feynman Liang] Add casts
43d28fa [Feynman Liang] Fix failing test
6416fa0 [Feynman Liang] Add failing sparse matrix equals tests
As a precursor to adding a public constructor add an option to handle unseen values by skipping rather than throwing an exception (default remains throwing an exception),
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7266 from holdenk/SPARK-8764-string-indexer-should-take-option-to-handle-unseen-values and squashes the following commits:
38a4de9 [Holden Karau] fix long line
045bf22 [Holden Karau] Add a second b entry so b gets 0 for sure
81dd312 [Holden Karau] Update the docs for handleInvalid param to be more descriptive
7f37f6e [Holden Karau] remove extra space (scala style)
414e249 [Holden Karau] And switch to using handleInvalid instead of skipInvalid
1e53f9b [Holden Karau] update the param (codegen side)
7a22215 [Holden Karau] fix typo
100a39b [Holden Karau] Merge in master
aa5b093 [Holden Karau] Since we filter we should never go down this code path if getSkipInvalid is true
75ffa69 [Holden Karau] Remove extra newline
d69ef5e [Holden Karau] Add a test
b5734be [Holden Karau] Add support for unseen labels
afecd4e [Holden Karau] Add a param to skip invalid entries.
Implements the transforms which are defined by SQL statement.
Currently we only support SQL syntax like 'SELECT ... FROM __THIS__'
where '__THIS__' represents the underlying table of the input dataset.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7465 from yanboliang/spark-8345 and squashes the following commits:
b403fcb [Yanbo Liang] address comments
0d4bb15 [Yanbo Liang] a better transformSchema() implementation
51eb9e7 [Yanbo Liang] Add an SQL node as a feature transformer
Adds method documentations back to `MultivariateOnlineSummarizer`, which were present in 1.4 but disappeared somewhere along the way to 1.5.
jkbradley
Author: Feynman Liang <fliang@databricks.com>
Closes#8045 from feynmanliang/SPARK-9755 and squashes the following commits:
af67fde [Feynman Liang] Add MultivariateOnlineSummarizer docs
Small documentation cleanups, including:
* Adds documentation for `pi` and `theta`
* setParam to `setModelType`
Author: Feynman Liang <fliang@databricks.com>
Closes#8047 from feynmanliang/SPARK-9719 and squashes the following commits:
b372438 [Feynman Liang] Clean up naive bayes doc
These should be made private until there is a public constructor for providing `rootNode: Node` to use these constructors.
jkbradley
Author: Feynman Liang <fliang@databricks.com>
Closes#8046 from feynmanliang/SPARK-9756 and squashes the following commits:
2cbdf08 [Feynman Liang] Make RFRegressionModel aux constructor private
a06f596 [Feynman Liang] Make constructors in ML decision trees private
A minor typo (centriod -> centroid). Readable variable names help every users.
Author: Bertrand Dechoux <BertrandDechoux@users.noreply.github.com>
Closes#8037 from BertrandDechoux/kmeans-typo and squashes the following commits:
47632fe [Bertrand Dechoux] centriod typo
Resubmit of [https://github.com/apache/spark/pull/6906] for adding single-vec predict to GMMs
CC: dkobylarz mengxr
To be merged with master and branch-1.5
Primary author: dkobylarz
Author: Dariusz Kobylarz <darek.kobylarz@gmail.com>
Closes#8039 from jkbradley/gmm-predict-vec and squashes the following commits:
bfbedc4 [Dariusz Kobylarz] [SPARK-8481] [MLlib] GaussianMixtureModel predict accepting single vector
This PR contains the following changes:
* add `featureIndex` to handle vector features (in order to chain isotonic regression easily with output from logistic regression
* make getter/setter names consistent with params
* remove inheritance from Regressor because it is tricky to handle both `DoubleType` and `VectorType`
* simplify test data generation
jkbradley zapletal-martin
Author: Xiangrui Meng <meng@databricks.com>
Closes#7952 from mengxr/SPARK-9493 and squashes the following commits:
8818ac3 [Xiangrui Meng] address comments
05e2216 [Xiangrui Meng] address comments
8d08090 [Xiangrui Meng] add featureIndex to handle vector features make getter/setter names consistent with params remove inheritance from Regressor
After https://github.com/apache/spark/pull/7263 it is pretty straightforward to Python wrappers.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7930 from MechCoder/spark-9533 and squashes the following commits:
1bea394 [MechCoder] make getVectors a lazy val
5522756 [MechCoder] [SPARK-9533] [PySpark] [ML] Add missing methods in Word2Vec ML
I have added support for stats in LogisticRegression. The API is similar to that of LinearRegression with LogisticRegressionTrainingSummary and LogisticRegressionSummary
I have some queries and asked them inline.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7538 from MechCoder/log_reg_stats and squashes the following commits:
2e9f7c7 [MechCoder] Change defs into lazy vals
d775371 [MechCoder] Clean up class inheritance
9586125 [MechCoder] Add abstraction to handle Multiclass Metrics
40ad8ef [MechCoder] minor
640376a [MechCoder] remove unnecessary dataframe stuff and add docs
80d9954 [MechCoder] Added tests
fbed861 [MechCoder] DataFrame support for metrics
70a0fc4 [MechCoder] [SPARK-9112] [ML] Implement Stats for LogisticRegression
Add VectorSlicer transformer to spark.ml, with features specified as either indices or names. Transfers feature attributes for selected features.
Updated version of [https://github.com/apache/spark/pull/5731]
CC: yinxusen This updates your PR. You'll still be the primary author of this PR.
CC: mengxr
Author: Xusen Yin <yinxusen@gmail.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7972 from jkbradley/yinxusen-SPARK-5895 and squashes the following commits:
b16e86e [Joseph K. Bradley] fixed scala style
71c65d2 [Joseph K. Bradley] fix import order
86e9739 [Joseph K. Bradley] cleanups per code review
9d8d6f1 [Joseph K. Bradley] style fix
83bc2e9 [Joseph K. Bradley] Updated VectorSlicer
98c6939 [Xusen Yin] fix style error
ecbf2d3 [Xusen Yin] change interfaces and params
f6be302 [Xusen Yin] Merge branch 'master' into SPARK-5895
e4781f2 [Xusen Yin] fix commit error
fd154d7 [Xusen Yin] add test suite of vector slicer
17171f8 [Xusen Yin] fix slicer
9ab9747 [Xusen Yin] add vector slicer
aa5a0bf [Xusen Yin] add vector slicer
mengxr
Author: Feynman Liang <fliang@databricks.com>
Closes#7974 from feynmanliang/SPARK-9657 and squashes the following commits:
7ca533f [Feynman Liang] Fix return type of getMaxPatternLength
mengxr This adds the `BlockMatrix` to PySpark. I have the conversions to `IndexedRowMatrix` and `CoordinateMatrix` ready as well, so once PR #7554 is completed (which relies on PR #7746), this PR can be finished.
Author: Mike Dusenberry <mwdusenb@us.ibm.com>
Closes#7761 from dusenberrymw/SPARK-6486_Add_BlockMatrix_to_PySpark and squashes the following commits:
27195c2 [Mike Dusenberry] Adding one more check to _convert_to_matrix_block_tuple, and a few minor documentation changes.
ae50883 [Mike Dusenberry] Minor update: BlockMatrix should inherit from DistributedMatrix.
b8acc1c [Mike Dusenberry] Moving BlockMatrix to pyspark.mllib.linalg.distributed, updating the logic to match that of the other distributed matrices, adding conversions, and adding documentation.
c014002 [Mike Dusenberry] Using properties for better documentation.
3bda6ab [Mike Dusenberry] Adding documentation.
8fb3095 [Mike Dusenberry] Small cleanup.
e17af2e [Mike Dusenberry] Adding BlockMatrix to PySpark.
This is a major refactoring of the PrefixSpan implementation. It contains the following changes:
1. Expand prefix with one item at a time. The existing implementation generates all subsets for each itemset, which might have scalability issue when the itemset is large.
2. Use a new internal format. `<(12)(31)>` is represented by `[0, 1, 2, 0, 1, 3, 0]` internally. We use `0` because negative numbers are used to indicates partial prefix items, e.g., `_2` is represented by `-2`.
3. Remember the start indices of all partial projections in the projected postfix to help next projection.
4. Reuse the original sequence array for projected postfixes.
5. Use `Prefix` IDs in aggregation rather than its content.
6. Use `ArrayBuilder` for building primitive arrays.
7. Expose `maxLocalProjDBSize`.
8. Tests are not changed except using `0` instead of `-1` as the delimiter.
`Postfix`'s API doc should be a good place to start.
Closes#7594
feynmanliang zhangjiajin
Author: Xiangrui Meng <meng@databricks.com>
Closes#7937 from mengxr/SPARK-9540 and squashes the following commits:
2d0ec31 [Xiangrui Meng] address more comments
48f450c [Xiangrui Meng] address comments from Feynman; fixed a bug in project and added a test
65f90e8 [Xiangrui Meng] naming and documentation
8afc86a [Xiangrui Meng] refactor impl
All compressed sensing applications, and some of the regression use-cases will have better result by turning the feature scaling off. However, if we implement this naively by training the dataset without doing any standardization, the rate of convergency will not be good. This can be implemented by still standardizing the training dataset but we penalize each component differently to get effectively the same objective function but a better numerical problem. As a result, for those columns with high variances, they will be penalized less, and vice versa. Without this, since all the features are standardized, so they will be penalized the same.
In R, there is an option for this.
standardize
Logical flag for x variable standardization, prior to fitting the model sequence. The coefficients are always returned on the original scale. Default is standardize=TRUE. If variables are in the same units already, you might not wish to standardize. See details below for y standardization with family="gaussian".
Note that the primary author for this PR is holdenk
Author: Holden Karau <holden@pigscanfly.ca>
Author: DB Tsai <dbt@netflix.com>
Closes#7875 from dbtsai/SPARK-8522 and squashes the following commits:
e856036 [DB Tsai] scala doc
596e96c [DB Tsai] minor
bbff347 [DB Tsai] naming
baa0805 [DB Tsai] touch up
d6234ba [DB Tsai] Merge branch 'master' into SPARK-8522-Disable-Linear_featureScaling-Spark-8601-in-Linear_regression
6b1dc09 [Holden Karau] Merge branch 'master' into SPARK-8522-Disable-Linear_featureScaling-Spark-8601-in-Linear_regression
332f140 [Holden Karau] Merge in master
eebe10a [Holden Karau] Use same comparision operator throughout the test
3f92935 [Holden Karau] merge
b83a41e [Holden Karau] Expand the tests and make them similar to the other PR also providing an option to disable standardization (but for LoR).
0c334a2 [Holden Karau] Remove extra line
99ce053 [Holden Karau] merge in master
e54a8a9 [Holden Karau] Fix long line
e47c574 [Holden Karau] Add support for L2 without standardization.
55d3a66 [Holden Karau] Add standardization param for linear regression
00a1dc5 [Holden Karau] Add the param to the linearregression impl
Update BinaryClassificationEvaluator to use setRawPredictionCol, rather than setScoreCol. Deprecated setScoreCol.
I don't think setScoreCol was actually used anywhere (based on search).
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7921 from jkbradley/binary-eval-rawpred and squashes the following commits:
e5d7dfa [Joseph K. Bradley] Update BinaryClassificationEvaluator to use setRawPredictionCol
This PR adds the RowMatrix, IndexedRowMatrix, and CoordinateMatrix distributed matrices to PySpark. Each distributed matrix class acts as a wrapper around the Scala/Java counterpart by maintaining a reference to the Java object. New distributed matrices can be created using factory methods added to DistributedMatrices, which creates the Java distributed matrix and then wraps it with the corresponding PySpark class. This design allows for simple conversion between the various distributed matrices, and lets us re-use the Scala code. Serialization between Python and Java is implemented using DataFrames as needed for IndexedRowMatrix and CoordinateMatrix for simplicity. Associated documentation and unit-tests have also been added. To facilitate code review, this PR implements access to the rows/entries as RDDs, the number of rows & columns, and conversions between the various distributed matrices (not including BlockMatrix), and does not implement the other linear algebra functions of the matrices, although this will be very simple to add now.
Author: Mike Dusenberry <mwdusenb@us.ibm.com>
Closes#7554 from dusenberrymw/SPARK-6485_Add_CoordinateMatrix_RowMatrix_IndexedMatrix_to_PySpark and squashes the following commits:
bb039cb [Mike Dusenberry] Minor documentation update.
b887c18 [Mike Dusenberry] Updating the matrix conversion logic again to make it even cleaner. Now, we allow the 'rows' parameter in the constructors to be either an RDD or the Java matrix object. If 'rows' is an RDD, we create a Java matrix object, wrap it, and then store that. If 'rows' is a Java matrix object of the correct type, we just wrap and store that directly. This is only for internal usage, and publicly, we still require 'rows' to be an RDD. We no longer store the 'rows' RDD, and instead just compute it from the Java object when needed. The point of this is that when we do matrix conversions, we do the conversion on the Scala/Java side, which returns a Java object, so we should use that directly, but exposing 'java_matrix' parameter in the public API is not ideal. This non-public feature of allowing 'rows' to be a Java matrix object is documented in the '__init__' constructor docstrings, which are not part of the generated public API, and doctests are also included.
7f0dcb6 [Mike Dusenberry] Updating module docstring.
cfc1be5 [Mike Dusenberry] Use 'new SQLContext(matrix.rows.sparkContext)' rather than 'SQLContext.getOrCreate', as the later doesn't guarantee that the SparkContext will be the same as for the matrix.rows data.
687e345 [Mike Dusenberry] Improving conversion performance. This adds an optional 'java_matrix' parameter to the constructors, and pulls the conversion logic out into a '_create_from_java' function. Now, if the constructors are given a valid Java distributed matrix object as 'java_matrix', they will store those internally, rather than create a new one on the Scala/Java side.
3e50b6e [Mike Dusenberry] Moving the distributed matrices to pyspark.mllib.linalg.distributed.
308f197 [Mike Dusenberry] Using properties for better documentation.
1633f86 [Mike Dusenberry] Minor documentation cleanup.
f0c13a7 [Mike Dusenberry] CoordinateMatrix should inherit from DistributedMatrix.
ffdd724 [Mike Dusenberry] Updating doctests to make documentation cleaner.
3fd4016 [Mike Dusenberry] Updating docstrings.
27cd5f6 [Mike Dusenberry] Simplifying input conversions in the constructors for each distributed matrix.
a409cf5 [Mike Dusenberry] Updating doctests to be less verbose by using lists instead of DenseVectors explicitly.
d19b0ba [Mike Dusenberry] Updating code and documentation to note that a vector-like object (numpy array, list, etc.) can be used in place of explicit Vector object, and adding conversions when necessary to RowMatrix construction.
4bd756d [Mike Dusenberry] Adding param documentation to IndexedRow and MatrixEntry.
c6bded5 [Mike Dusenberry] Move conversion logic from tuples to IndexedRow or MatrixEntry types from within the IndexedRowMatrix and CoordinateMatrix constructors to separate _convert_to_indexed_row and _convert_to_matrix_entry functions.
329638b [Mike Dusenberry] Moving the Experimental tag to the top of each docstring.
0be6826 [Mike Dusenberry] Simplifying doctests by removing duplicated rows/entries RDDs within the various tests.
c0900df [Mike Dusenberry] Adding the colons that were accidentally not inserted.
4ad6819 [Mike Dusenberry] Documenting the and parameters.
3b854b9 [Mike Dusenberry] Minor updates to documentation.
10046e8 [Mike Dusenberry] Updating documentation to use class constructors instead of the removed DistributedMatrices factory methods.
119018d [Mike Dusenberry] Adding static methods to each of the distributed matrix classes to consolidate conversion logic.
4d7af86 [Mike Dusenberry] Adding type checks to the constructors. Although it is slightly verbose, it is better for the user to have a good error message than a cryptic stacktrace.
93b6a3d [Mike Dusenberry] Pulling the DistributedMatrices Python class out of this pull request.
f6f3c68 [Mike Dusenberry] Pulling the DistributedMatrices Scala class out of this pull request.
6a3ecb7 [Mike Dusenberry] Updating pattern matching.
08f287b [Mike Dusenberry] Slight reformatting of the documentation.
a245dc0 [Mike Dusenberry] Updating Python doctests for compatability between Python 2 & 3. Since Python 3 removed the idea of a separate 'long' type, all values that would have been outputted as a 'long' (ex: '4L') will now be treated as an 'int' and outputed as one (ex: '4'). The doctests now explicitly convert to ints so that both Python 2 and 3 will have the same output. This is fine since the values are all small, and thus can be easily represented as ints.
4d3a37e [Mike Dusenberry] Reformatting a few long Python doctest lines.
7e3ca16 [Mike Dusenberry] Fixing long lines.
f721ead [Mike Dusenberry] Updating documentation for each of the distributed matrices.
ab0e8b6 [Mike Dusenberry] Updating unit test to be more useful.
dda2f89 [Mike Dusenberry] Added wrappers for the conversions between the various distributed matrices. Added logic to be able to access the rows/entries of the distributed matrices, which requires serialization through DataFrames for IndexedRowMatrix and CoordinateMatrix types. Added unit tests.
0cd7166 [Mike Dusenberry] Implemented the CoordinateMatrix API in PySpark, following the idea of the IndexedRowMatrix API, including using DataFrames for serialization.
3c369cb [Mike Dusenberry] Updating the architecture a bit to make conversions between the various distributed matrix types easier. The different distributed matrix classes are now only wrappers around the Java objects, and take the Java object as an argument during construction. This way, we can call for example on an , which returns a reference to a Java RowMatrix object, and then construct a PySpark RowMatrix object wrapped around the Java object. This is analogous to the behavior of PySpark RDDs and DataFrames. We now delegate creation of the various distributed matrices from scratch in PySpark to the factory methods on .
4bdd09b [Mike Dusenberry] Implemented the IndexedRowMatrix API in PySpark, following the idea of the RowMatrix API. Note that for the IndexedRowMatrix, we use DataFrames to serialize the data between Python and Scala/Java, so we accept PySpark RDDs, then convert to a DataFrame, then convert back to RDDs on the Scala/Java side before constructing the IndexedRowMatrix.
23bf1ec [Mike Dusenberry] Updating documentation to add PySpark RowMatrix. Inserting newline above doctest so that it renders properly in API docs.
b194623 [Mike Dusenberry] Updating design to have a PySpark RowMatrix simply create and keep a reference to a wrapper over a Java RowMatrix. Updating DistributedMatrices factory methods to accept numRows and numCols with default values. Updating PySpark DistributedMatrices factory method to simply create a PySpark RowMatrix. Adding additional doctests for numRows and numCols parameters.
bc2d220 [Mike Dusenberry] Adding unit tests for RowMatrix methods.
d7e316f [Mike Dusenberry] Implemented the RowMatrix API in PySpark by doing the following: Added a DistributedMatrices class to contain factory methods for creating the various distributed matrices. Added a factory method for creating a RowMatrix from an RDD of Vectors. Added a createRowMatrix function to the PythonMLlibAPI to interface with the factory method. Added DistributedMatrix, DistributedMatrices, and RowMatrix classes to the pyspark.mllib.linalg api.
Small cleanups to recent LDA additions and docs.
CC: feynmanliang
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7916 from jkbradley/lda-cleanups and squashes the following commits:
f7021d9 [Joseph K. Bradley] broadcasting large matrices for LDA in local model and online learning
97947aa [Joseph K. Bradley] a few more cleanups
5b03f88 [Joseph K. Bradley] reverted split of lda log likelihood
c566915 [Joseph K. Bradley] small edit to make review easier
63f6c7d [Joseph K. Bradley] clarified log likelihood for lda models
This PR replaces the old "threshold" with a generalized "thresholds" Param. We keep getThreshold,setThreshold for backwards compatibility for binary classification.
Note that the primary author of this PR is holdenk
Author: Holden Karau <holden@pigscanfly.ca>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7909 from jkbradley/holdenk-SPARK-8069-add-cutoff-aka-threshold-to-random-forest and squashes the following commits:
3952977 [Joseph K. Bradley] fixed pyspark doc test
85febc8 [Joseph K. Bradley] made python unit tests a little more robust
7eb1d86 [Joseph K. Bradley] small cleanups
6cc2ed8 [Joseph K. Bradley] Fixed remaining merge issues.
0255e44 [Joseph K. Bradley] Many cleanups for thresholds, some more tests
7565a60 [Holden Karau] fix pep8 style checks, add a getThreshold method similar to our LogisticRegression.scala one for API compat
be87f26 [Holden Karau] Convert threshold to thresholds in the python code, add specialized support for Array[Double] to shared parems codegen, etc.
6747dad [Holden Karau] Override raw2prediction for ProbabilisticClassifier, fix some tests
25df168 [Holden Karau] Fix handling of thresholds in LogisticRegression
c02d6c0 [Holden Karau] No default for thresholds
5e43628 [Holden Karau] CR feedback and fixed the renamed test
f3fbbd1 [Holden Karau] revert the changes to random forest :(
51f581c [Holden Karau] Add explicit types to public methods, fix long line
f7032eb [Holden Karau] Fix a java test bug, remove some unecessary changes
adf15b4 [Holden Karau] rename the classifier suite test to ProbabilisticClassifierSuite now that we only have it in Probabilistic
398078a [Holden Karau] move the thresholding around a bunch based on the design doc
4893bdc [Holden Karau] Use numtrees of 3 since previous result was tied (one tree for each) and the switch from different max methods picked a different element (since they were equal I think this is ok)
638854c [Holden Karau] Add a scala RandomForestClassifierSuite test based on corresponding python test
e09919c [Holden Karau] Fix return type, I need more coffee....
8d92cac [Holden Karau] Use ClassifierParams as the head
3456ed3 [Holden Karau] Add explicit return types even though just test
a0f3b0c [Holden Karau] scala style fixes
6f14314 [Holden Karau] Since hasthreshold/hasthresholds is in root classifier now
ffc8dab [Holden Karau] Update the sharedParams
0420290 [Holden Karau] Allow us to override the get methods selectively
978e77a [Holden Karau] Move HasThreshold into classifier params and start defining the overloaded getThreshold/getThresholds functions
1433e52 [Holden Karau] Revert "try and hide threshold but chainges the API so no dice there"
1f09a2e [Holden Karau] try and hide threshold but chainges the API so no dice there
efb9084 [Holden Karau] move setThresholds only to where its used
6b34809 [Holden Karau] Add a test with thresholding for the RFCS
74f54c3 [Holden Karau] Fix creation of vote array
1986fa8 [Holden Karau] Setting the thresholds only makes sense if the underlying class hasn't overridden predict, so lets push it down.
2f44b18 [Holden Karau] Add a global default of null for thresholds param
f338cfc [Holden Karau] Wait that wasn't a good idea, Revert "Some progress towards unifying threshold and thresholds"
634b06f [Holden Karau] Some progress towards unifying threshold and thresholds
85c9e01 [Holden Karau] Test passes again... little fnur
099c0f3 [Holden Karau] Move thresholds around some more (set on model not trainer)
0f46836 [Holden Karau] Start adding a classifiersuite
f70eb5e [Holden Karau] Fix test compile issues
a7d59c8 [Holden Karau] Move thresholding into Classifier trait
5d999d2 [Holden Karau] Some more progress, start adding a test (maybe try and see if we can find a better thing to use for the base of the test)
1fed644 [Holden Karau] Use thresholds to scale scores in random forest classifcation
31d6bf2 [Holden Karau] Start threading the threshold info through
0ef228c [Holden Karau] Add hasthresholds
Enable most javac lint warnings; fix a lot of build warnings. In a few cases, touch up surrounding code in the process.
I'll explain several of the changes inline in comments.
Author: Sean Owen <sowen@cloudera.com>
Closes#7862 from srowen/SPARK-9534 and squashes the following commits:
ea51618 [Sean Owen] Enable most javac lint warnings; fix a lot of build warnings. In a few cases, touch up surrounding code in the process.
Add missing methods
1. getVectors
2. findSynonyms
to W2Vec scala and python API
mengxr
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7263 from MechCoder/missing_methods_w2vec and squashes the following commits:
149d5ca [MechCoder] minor doc
69d91b7 [MechCoder] [SPARK-8874] [ML] Add missing methods in Word2Vec
Add Python API for RFormula. Similar to other feature transformers in Python. This is just a thin wrapper over the Scala implementation. ericl MechCoder
Author: Xiangrui Meng <meng@databricks.com>
Closes#7879 from mengxr/SPARK-9544 and squashes the following commits:
3d5ff03 [Xiangrui Meng] add an doctest for . and -
5e969a5 [Xiangrui Meng] fix pydoc
1cd41f8 [Xiangrui Meng] organize imports
3c18b10 [Xiangrui Meng] add Python API for RFormula
Added featureImportance to RandomForestClassifier and Regressor.
This follows the scikit-learn implementation here: [a95203b249/sklearn/tree/_tree.pyx (L3341)]
CC: yanboliang Would you mind taking a look? Thanks!
Author: Joseph K. Bradley <joseph@databricks.com>
Author: Feynman Liang <fliang@databricks.com>
Closes#7838 from jkbradley/dt-feature-importance and squashes the following commits:
72a167a [Joseph K. Bradley] fixed unit test
86cea5f [Joseph K. Bradley] Modified RF featuresImportances to return Vector instead of Map
5aa74f0 [Joseph K. Bradley] finally fixed unit test for real
33df5db [Joseph K. Bradley] fix unit test
42a2d3b [Joseph K. Bradley] fix unit test
fe94e72 [Joseph K. Bradley] modified feature importance unit tests
cc693ee [Feynman Liang] Add classifier tests
79a6f87 [Feynman Liang] Compare dense vectors in test
21d01fc [Feynman Liang] Added failing SKLearn test
ac0b254 [Joseph K. Bradley] Added featureImportance to RandomForestClassifier/Regressor. Need to add unit tests
RandomForestClassifier now outputs rawPrediction based on tree probabilities, plus probability column computed from normalized rawPrediction.
CC: holdenk
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7859 from jkbradley/rf-prob and squashes the following commits:
6c28f51 [Joseph K. Bradley] Changed RandomForestClassifier to extend ProbabilisticClassifier
1. Use `PrefixSpanModel` to wrap the frequent sequences.
2. Define `FreqSequence` to wrap each frequent sequence, which contains a Java-friendly method `javaSequence`
3. Overload `run` for Java users.
4. Added a unit test in Java to check Java compatibility.
zhangjiajin feynmanliang
Author: Xiangrui Meng <meng@databricks.com>
Closes#7869 from mengxr/SPARK-9527 and squashes the following commits:
4345594 [Xiangrui Meng] add PrefixSpanModel and make PrefixSpan Java friendly
mengxr Please review after #7818 merges and master is rebased.
Continues work by rikima
Closes#7400
Author: Feynman Liang <fliang@databricks.com>
Author: masaki rikitoku <rikima3132@gmail.com>
Closes#7837 from feynmanliang/SPARK-7400-genericItems and squashes the following commits:
8b2c756 [Feynman Liang] Remove orig
92443c8 [Feynman Liang] Style fixes
42c6349 [Feynman Liang] Style fix
14e67fc [Feynman Liang] Generic prefixSpan itemtypes
b3b21e0 [Feynman Liang] Initial support for generic itemtype in public api
b86e0d5 [masaki rikitoku] modify to support generic item type
Remove ScalaDoc that suggests describeTopics and topDocumentsPerTopic are approximate.
cc jkbradley
Author: Meihua Wu <meihuawu@umich.edu>
Closes#7858 from rotationsymmetry/SPARK-9530 and squashes the following commits:
b574923 [Meihua Wu] Remove ScalaDoc that suggests describeTopics and topDocumentsPerTopic are approximate.
jira: https://issues.apache.org/jira/browse/SPARK-8169
stop words: http://en.wikipedia.org/wiki/Stop_words
StopWordsRemover takes a string array column and outputs a string array column with all defined stop words removed. The transformer should also come with a standard set of stop words as default.
Currently I used a minimum stop words set since on some [case](http://nlp.stanford.edu/IR-book/html/htmledition/dropping-common-terms-stop-words-1.html), small set of stop words is preferred.
ASCII char has been tested, Yet I cannot check it in due to style check.
Further thought,
1. Maybe I should use OpenHashSet. Is it recommended?
2. Currently I leave the null in input array untouched, i.e. Array(null, null) => Array(null, null).
3. If the current stop words set looks too limited, any suggestion for replacement? We can have something similar to the one in [SKlearn](https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/feature_extraction/stop_words.py).
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#6742 from hhbyyh/stopwords and squashes the following commits:
fa959d8 [Yuhao Yang] separating udf
f190217 [Yuhao Yang] replace default list and other small fix
04403ab [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into stopwords
b3aa957 [Yuhao Yang] add stopWordsRemover
mengxr Extends PrefixSpan to non-temporal itemsets. Continues work by zhangjiajin
* Internal API uses List[Set[Int]] which is likely not efficient; will need to refactor during QA
Closes#7646
Author: zhangjiajin <zhangjiajin@huawei.com>
Author: Feynman Liang <fliang@databricks.com>
Author: zhang jiajin <zhangjiajin@huawei.com>
Closes#7818 from feynmanliang/SPARK-8999-nonTemporal and squashes the following commits:
4ded81d [Feynman Liang] Replace all filters to filter nonempty
350e67e [Feynman Liang] Code review feedback
03156ca [Feynman Liang] Fix tests, drop delimiters at boundaries of sequences
d1fe0ed [Feynman Liang] Remove comments
86ca4e5 [Feynman Liang] Fix style
7c7bf39 [Feynman Liang] Fixed itemSet sequences
6073b10 [Feynman Liang] Basic itemset functionality, failing test
1a7fb48 [Feynman Liang] Add delimiter to results
5db00aa [Feynman Liang] Working for items, not itemsets
6787716 [Feynman Liang] Working on temporal sequences
f1114b9 [Feynman Liang] Add -1 delimiter
00fe756 [Feynman Liang] Reset base files for rebase
f486dcd [zhangjiajin] change maxLocalProjDBSize and fix a bug (remove -3 from frequent items).
60a0b76 [zhangjiajin] fixed a scala style error.
740c203 [zhangjiajin] fixed a scala style error.
5785cb8 [zhangjiajin] support non-temporal sequence
a5d649d [zhangjiajin] restore original version
09dc409 [zhangjiajin] Merge branch 'master' of https://github.com/apache/spark into multiItems_2
ae8c02d [zhangjiajin] Fixed some Scala style errors.
216ab0c [zhangjiajin] Support non-temporal sequence in PrefixSpan
b572f54 [zhangjiajin] initialize file before rebase.
f06772f [zhangjiajin] fix a scala style error.
a7e50d4 [zhangjiajin] Add feature: Collect enough frequent prefixes before projection in PrefixSpan.
c1d13d0 [zhang jiajin] Delete PrefixspanSuite.scala
d9d8137 [zhang jiajin] Delete Prefixspan.scala
c6ceb63 [zhangjiajin] Add new algorithm PrefixSpan and test file.
It is useful to convert the encoded indices back to their string representation for result inspection. We can add a function which creates an inverse transformation.
Author: Holden Karau <holden@pigscanfly.ca>
Closes#6339 from holdenk/SPARK-7446-inverse-transform-for-string-indexer and squashes the following commits:
7cdf915 [Holden Karau] scala style comment fix
b9cffb6 [Holden Karau] Update the labels param to have the metadata note
6a38edb [Holden Karau] Setting the default needs to come after the value gets defined
9e241d8 [Holden Karau] use Array.empty
21c8cfa [Holden Karau] Merge branch 'master' into SPARK-7446-inverse-transform-for-string-indexer
64dd3a3 [Holden Karau] Merge branch 'master' into SPARK-7446-inverse-transform-for-string-indexer
4f06c59 [Holden Karau] Fix comment styles, use empty array as the default, etc.
a60c0e3 [Holden Karau] CR feedback (remove old constructor, add a note about use of setLabels)
1987b95 [Holden Karau] Use default copy
71e8d66 [Holden Karau] Make labels a local param for StringIndexerInverse
8450d0b [Holden Karau] Use the labels param in StringIndexerInverse
7464019 [Holden Karau] Add a labels param
868b1a9 [Holden Karau] Update scaladoc since we don't have labelsCol anymore
5aa38bf [Holden Karau] Add an inverse test using only meta data, pass labels when calling inverse method
f3e0c64 [Holden Karau] CR feedback
ebed932 [Holden Karau] Add Experimental tag and some scaladocs. Also don't require that the inputCol has the metadata on it, instead have the labelsCol specified when creating the inverse.
03ebf95 [Holden Karau] Add explicit type for invert function
ecc65e0 [Holden Karau] Read the metadata correctly, use the array, pass the test
a42d773 [Holden Karau] Fix test to supply cols as per new invert method
16cc3c3 [Holden Karau] Add an invert method
d4bcb20 [Holden Karau] Make the inverse string indexer into a transformer (still needs test updates but compiles)
e8bf3ad [Holden Karau] Merge branch 'master' into SPARK-7446-inverse-transform-for-string-indexer
c3fdee1 [Holden Karau] Some WIP refactoring based on jkbradley's CR feedback. Definite work-in-progress
557bef8 [Holden Karau] Instead of using a private inverse transform, add an invert function so we can use it in a pipeline
88779c1 [Holden Karau] fix long line
78b28c1 [Holden Karau] Finish reverse part and add a test :)
bb16a6a [Holden Karau] Some progress
This PR adds a `MapData` as internal representation of map type in Spark SQL, and provides a default implementation with just 2 `ArrayData`.
After that, we have specialized getters for all internal type, so I removed generic getter in `ArrayData` and added specialized `toArray` for it.
Also did some refactor and cleanup for `InternalRow` and its subclasses.
Author: Wenchen Fan <cloud0fan@outlook.com>
Closes#7799 from cloud-fan/map-data and squashes the following commits:
77d482f [Wenchen Fan] fix python
e8f6682 [Wenchen Fan] skip MapData equality check in HiveInspectorSuite
40cc9db [Wenchen Fan] add toString
6e06ec9 [Wenchen Fan] some more cleanup
a90aca1 [Wenchen Fan] add MapData
Adds `alpha` (document-topic Dirichlet parameter) hyperparameter optimization to `OnlineLDAOptimizer` following Huang: Maximum Likelihood Estimation of Dirichlet Distribution Parameters. Also introduces a private `setSampleWithReplacement` to `OnlineLDAOptimizer` for unit testing purposes.
Author: Feynman Liang <fliang@databricks.com>
Closes#7836 from feynmanliang/SPARK-8936-alpha-optimize and squashes the following commits:
4bef484 [Feynman Liang] Documentation improvements
c3c6c1d [Feynman Liang] Fix docs
151e859 [Feynman Liang] Fix style
fa77518 [Feynman Liang] Hyperparameter optimization
Make NaiveBayesModel support predicting class probabilities, inherit from ProbabilisticClassificationModel.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7672 from yanboliang/spark-9308 and squashes the following commits:
25e224c [Yanbo Liang] raw2probabilityInPlace should operate in-place
3ee56d6 [Yanbo Liang] change predictRaw and raw2probabilityInPlace
c07e7a2 [Yanbo Liang] ml.NaiveBayesModel support predicting class probabilities
Add topDocumentsPerTopic to DistributedLDAModel.
Add ScalaDoc and unit tests.
Author: Meihua Wu <meihuawu@umich.edu>
Closes#7769 from rotationsymmetry/SPARK-9246 and squashes the following commits:
1029e79c [Meihua Wu] clean up code comments
a023b82 [Meihua Wu] Update tests to use Long for doc index.
91e5998 [Meihua Wu] Use Long for doc index.
b9f70cf [Meihua Wu] Revise topDocumentsPerTopic
26ff3f6 [Meihua Wu] Add topDocumentsPerTopic, scala doc and unit tests
jkbradley Exposes `bound` (variational log likelihood bound) through public API as `logLikelihood`. Also adds unit tests, some DRYing of `LDASuite`, and includes unit tests mentioned in #7760
Author: Feynman Liang <fliang@databricks.com>
Closes#7801 from feynmanliang/SPARK-9481-logLikelihood and squashes the following commits:
6d1b2c9 [Feynman Liang] Negate perplexity definition
5f62b20 [Feynman Liang] Add logLikelihood
Decision tree support predict class probabilities.
Implement the prediction probabilities function referred the old DecisionTree API and the [sklean API](https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/tree/tree.py#L593).
I make the DecisionTreeClassificationModel inherit from ProbabilisticClassificationModel, make the predictRaw to return the raw counts vector and make raw2probabilityInPlace/predictProbability return the probabilities for each prediction.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7694 from yanboliang/spark-6885 and squashes the following commits:
08d5b7f [Yanbo Liang] fix ImpurityStats null parameters and raw2probabilityInPlace sum = 0 issue
2174278 [Yanbo Liang] solve merge conflicts
7e90ba8 [Yanbo Liang] fix typos
33ae183 [Yanbo Liang] fix annotation
ff043d3 [Yanbo Liang] raw2probabilityInPlace should operate in-place
c32d6ce [Yanbo Liang] optimize calculateImpurityStats function again
6167fb0 [Yanbo Liang] optimize calculateImpurityStats function
fbbe2ec [Yanbo Liang] eliminate duplicated struct and code
beb1634 [Yanbo Liang] try to eliminate impurityStats for each LearningNode
99e8943 [Yanbo Liang] code optimization
5ec3323 [Yanbo Liang] implement InformationGainAndImpurityStats
227c91b [Yanbo Liang] refactor LearningNode to store ImpurityCalculator
d746ffc [Yanbo Liang] decision tree support predict class probabilities
jira: https://issues.apache.org/jira/browse/SPARK-9231
Helper method in DistributedLDAModel of this form:
```
/**
* For each document, return the top k weighted topics for that document.
* return RDD of (doc ID, topic indices, topic weights)
*/
def topTopicsPerDocument(k: Int): RDD[(Long, Array[Int], Array[Double])]
```
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#7785 from hhbyyh/topTopicsPerdoc and squashes the following commits:
30ad153 [Yuhao Yang] small fix
fd24580 [Yuhao Yang] add topTopics per document to DistributedLDAModel
This pull request contains the following feature for ML:
- Multilayer Perceptron classifier
This implementation is based on our initial pull request with bgreeven: https://github.com/apache/spark/pull/1290 and inspired by very insightful suggestions from mengxr and witgo (I would like to thank all other people from the mentioned thread for useful discussions). The original code was extensively tested and benchmarked. Since then, I've addressed two main requirements that prevented the code from merging into the main branch:
- Extensible interface, so it will be easy to implement new types of networks
- Main building blocks are traits `Layer` and `LayerModel`. They are used for constructing layers of ANN. New layers can be added by extending the `Layer` and `LayerModel` traits. These traits are private in this release in order to save path to improve them based on community feedback
- Back propagation is implemented in general form, so there is no need to change it (optimization algorithm) when new layers are implemented
- Speed and scalability: this implementation has to be comparable in terms of speed to the state of the art single node implementations.
- The developed benchmark for large ANN shows that the proposed code is on par with C++ CPU implementation and scales nicely with the number of workers. Details can be found here: https://github.com/avulanov/ann-benchmark
- DBN and RBM by witgo https://github.com/witgo/spark/tree/ann-interface-gemm-dbn
- Dropout https://github.com/avulanov/spark/tree/ann-interface-gemm
mengxr and dbtsai kindly agreed to perform code review.
Author: Alexander Ulanov <nashb@yandex.ru>
Author: Bert Greevenbosch <opensrc@bertgreevenbosch.nl>
Closes#7621 from avulanov/SPARK-2352-ann and squashes the following commits:
4806b6f [Alexander Ulanov] Addressing reviewers comments.
a7e7951 [Alexander Ulanov] Default blockSize: 100. Added documentation to blockSize parameter and DataStacker class
f69bb3d [Alexander Ulanov] Addressing reviewers comments.
374bea6 [Alexander Ulanov] Moving ANN to ML package. GradientDescent constructor is now spark private.
43b0ae2 [Alexander Ulanov] Addressing reviewers comments. Adding multiclass test.
9d18469 [Alexander Ulanov] Addressing reviewers comments: unnecessary copy of data in predict
35125ab [Alexander Ulanov] Style fix in tests
e191301 [Alexander Ulanov] Apache header
a226133 [Alexander Ulanov] Multilayer Perceptron regressor and classifier
support ml.NaiveBayes for Python
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7568 from yanboliang/spark-9214 and squashes the following commits:
5ee3fd6 [Yanbo Liang] fix typos
3ecd046 [Yanbo Liang] fix typos
f9c94d1 [Yanbo Liang] change lambda_ to smoothing and fix other issues
180452a [Yanbo Liang] fix typos
7dda1f4 [Yanbo Liang] support ml.NaiveBayes for Python
Improve error message when number of examples is less than arity of high-arity categorical feature
CC jkbradley is this about what you had in mind? I know it's a starter, but was on my list to close out in the short term.
Author: Sean Owen <sowen@cloudera.com>
Closes#7800 from srowen/SPARK-9077 and squashes the following commits:
b8f6cdb [Sean Owen] Improve error message when number of examples is less than arity of high-arity categorical feature
Add checkpointing to GradientBoostedTrees, GBTClassifier, GBTRegressor
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7804 from jkbradley/gbt-checkpoint3 and squashes the following commits:
3fbd7ba [Joseph K. Bradley] tiny fix
b3e160c [Joseph K. Bradley] unset checkpoint dir after test
9cc3a04 [Joseph K. Bradley] added checkpointing to GBTs
Author: martinzapletal <zapletal-martin@email.cz>
Closes#7517 from zapletal-martin/SPARK-8671-isotonic-regression-api and squashes the following commits:
8c435c1 [martinzapletal] Review https://github.com/apache/spark/pull/7517 feedback update.
bebbb86 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-8671-isotonic-regression-api
b68efc0 [martinzapletal] Added tests for param validation.
07c12bd [martinzapletal] Comments and refactoring.
834fcf7 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-8671-isotonic-regression-api
b611fee [martinzapletal] SPARK-8671. Added first version of isotonic regression to pipeline API
See https://issues.apache.org/jira/browse/SPARK-9479 for the failure cause.
The PR includes the following changes:
1. Make ReceiverTrackerSuite create StreamingContext in the test body.
2. Fix places that don't stop StreamingContext. I verified no SparkContext was stopped in the shutdown hook locally after this fix.
3. Fix an issue that `ReceiverTracker.endpoint` may be null.
4. Make sure stopping SparkContext in non-main thread won't fail other tests.
Author: zsxwing <zsxwing@gmail.com>
Closes#7797 from zsxwing/fix-ReceiverTrackerSuite and squashes the following commits:
3a4bb98 [zsxwing] Fix another potential NPE
d7497df [zsxwing] Fix ReceiverTrackerSuite; make sure StreamingContext in tests is closed
jkbradley Changes the current hacky string-comparison for vector compares.
Author: Feynman Liang <fliang@databricks.com>
Closes#7775 from feynmanliang/SPARK-9454-ldasuite-vector-compare and squashes the following commits:
bd91a82 [Feynman Liang] Remove println
905c76e [Feynman Liang] Fix string compare in distributed EM
2f24c13 [Feynman Liang] Improve LDASuite tests
Check that SparseVector size is at least as big as the number of indices/values provided. And add tests for constructor checks.
CC MechCoder jkbradley -- I am not sure if a change needs to also happen in the Python API? I didn't see it had any similar checks to begin with, but I don't know it well.
Author: Sean Owen <sowen@cloudera.com>
Closes#7794 from srowen/SPARK-9277 and squashes the following commits:
e8dc31e [Sean Owen] Fix scalastyle
6ffe34a [Sean Owen] Check that SparseVector size is at least as big as the number of indices/values provided. And add tests for constructor checks.
Add unit tests for running LDA with empty documents.
Both EMLDAOptimizer and OnlineLDAOptimizer are tested.
feynmanliang
Author: Meihua Wu <meihuawu@umich.edu>
Closes#7620 from rotationsymmetry/SPARK-9225 and squashes the following commits:
3ed7c88 [Meihua Wu] Incorporate reviewer's further comments
f9432e8 [Meihua Wu] Incorporate reviewer's comments
8e1b9ec [Meihua Wu] Merge remote-tracking branch 'upstream/master' into SPARK-9225
ad55665 [Meihua Wu] Add unit tests for running LDA with empty documents
A trivial fix for the comments of RegexTokenizer.
Maybe this is too small, yet I just noticed it and think it can be quite misleading. I can create a jira if necessary.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#7791 from hhbyyh/docFix and squashes the following commits:
cdf2542 [Yuhao Yang] minor fix on tokenizer doc
Continuation of work by zhangjiajin
Closes#7412
Author: zhangjiajin <zhangjiajin@huawei.com>
Author: Feynman Liang <fliang@databricks.com>
Author: zhang jiajin <zhangjiajin@huawei.com>
Closes#7783 from feynmanliang/SPARK-8998-improve-distributed and squashes the following commits:
a61943d [Feynman Liang] Collect small patterns to local
4ddf479 [Feynman Liang] Parallelize freqItemCounts
ad23aa9 [zhang jiajin] Merge pull request #1 from feynmanliang/SPARK-8998-collectBeforeLocal
87fa021 [Feynman Liang] Improve extend prefix readability
c2caa5c [Feynman Liang] Readability improvements and comments
1235cfc [Feynman Liang] Use Iterable[Array[_]] over Array[Array[_]] for database
da0091b [Feynman Liang] Use lists for prefixes to reuse data
cb2a4fc [Feynman Liang] Inline code for readability
01c9ae9 [Feynman Liang] Add getters
6e149fa [Feynman Liang] Fix splitPrefixSuffixPairs
64271b3 [zhangjiajin] Modified codes according to comments.
d2250b7 [zhangjiajin] remove minPatternsBeforeLocalProcessing, add maxSuffixesBeforeLocalProcessing.
b07e20c [zhangjiajin] Merge branch 'master' of https://github.com/apache/spark into CollectEnoughPrefixes
095aa3a [zhangjiajin] Modified the code according to the review comments.
baa2885 [zhangjiajin] Modified the code according to the review comments.
6560c69 [zhangjiajin] Add feature: Collect enough frequent prefixes before projection in PrefixeSpan
a8fde87 [zhangjiajin] Merge branch 'master' of https://github.com/apache/spark
4dd1c8a [zhangjiajin] initialize file before rebase.
078d410 [zhangjiajin] fix a scala style error.
22b0ef4 [zhangjiajin] Add feature: Collect enough frequent prefixes before projection in PrefixSpan.
ca9c4c8 [zhangjiajin] Modified the code according to the review comments.
574e56c [zhangjiajin] Add new object LocalPrefixSpan, and do some optimization.
ba5df34 [zhangjiajin] Fix a Scala style error.
4c60fb3 [zhangjiajin] Fix some Scala style errors.
1dd33ad [zhangjiajin] Modified the code according to the review comments.
89bc368 [zhangjiajin] Fixed a Scala style error.
a2eb14c [zhang jiajin] Delete PrefixspanSuite.scala
951fd42 [zhang jiajin] Delete Prefixspan.scala
575995f [zhangjiajin] Modified the code according to the review comments.
91fd7e6 [zhangjiajin] Add new algorithm PrefixSpan and test file.
PeriodicGraphCheckpointer was introduced for Latent Dirichlet Allocation (LDA), but it was meant to be generalized to work with Graphs, RDDs, and other data structures based on RDDs. This PR generalizes it.
For those who are not familiar with the periodic checkpointer, it tries to automatically handle persisting/unpersisting and checkpointing/removing checkpoint files in a lineage of RDD-based objects.
I need it generalized to use with GradientBoostedTrees [https://issues.apache.org/jira/browse/SPARK-6684]. It should be useful for other iterative algorithms as well.
Changes I made:
* Copied PeriodicGraphCheckpointer to PeriodicCheckpointer.
* Within PeriodicCheckpointer, I created abstract methods for the basic operations (checkpoint, persist, etc.).
* The subclasses for Graphs and RDDs implement those abstract methods.
* I copied the test suite for the graph checkpointer and made tiny modifications to make it work for RDDs.
To review this PR, I recommend doing 2 diffs:
(1) diff between the old PeriodicGraphCheckpointer.scala and the new PeriodicCheckpointer.scala
(2) diff between the 2 test suites
CCing andrewor14 in case there are relevant changes to checkpointing.
CCing feynmanliang in case you're interested in learning about checkpointing.
CCing mengxr for final OK.
Thanks all!
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7728 from jkbradley/gbt-checkpoint and squashes the following commits:
d41902c [Joseph K. Bradley] Oops, forgot to update an extra time in the checkpointer tests, after the last commit. I'll fix that. I'll also make some of the checkpointer methods protected, which I should have done before.
32b23b8 [Joseph K. Bradley] fixed usage of checkpointer in lda
0b3dbc0 [Joseph K. Bradley] Changed checkpointer constructor not to take initial data.
568918c [Joseph K. Bradley] Generalized PeriodicGraphCheckpointer to PeriodicCheckpointer, with subclasses for RDDs and Graphs.
jira: https://issues.apache.org/jira/browse/SPARK-7368
Add QR decomposition for RowMatrix.
I'm not sure what's the blueprint about the distributed Matrix from community and whether this will be a desirable feature , so I sent a prototype for discussion. I'll go on polish the code and provide ut and performance statistics if it's acceptable.
The implementation refers to the [paper: https://www.cs.purdue.edu/homes/dgleich/publications/Benson%202013%20-%20direct-tsqr.pdf]
Austin R. Benson, David F. Gleich, James Demmel. "Direct QR factorizations for tall-and-skinny matrices in MapReduce architectures", 2013 IEEE International Conference on Big Data, which is a stable algorithm with good scalability.
Currently I tried it on a 400000 * 500 rowMatrix (16 partitions) and it can bring down the computation time from 8.8 mins (using breeze.linalg.qr.reduced) to 2.6 mins on a 4 worker cluster. I think there will still be some room for performance improvement.
Any trial and suggestion is welcome.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#5909 from hhbyyh/qrDecomposition and squashes the following commits:
cec797b [Yuhao Yang] remove unnecessary qr
0fb1012 [Yuhao Yang] hierarchy R computing
3fbdb61 [Yuhao Yang] update qr to indirect and add ut
0d913d3 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into qrDecomposition
39213c3 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into qrDecomposition
c0fc0c7 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into qrDecomposition
39b0b22 [Yuhao Yang] initial draft for discussion
jkbradley MechCoder
Resolves blocking issue for SPARK-6793. Please review after #7705 is merged.
Author: Feynman Liang <fliang@databricks.com>
Closes#7757 from feynmanliang/SPARK-9940-localSaveLoad and squashes the following commits:
d0d8cf4 [Feynman Liang] Fix thisClassName
0f30109 [Feynman Liang] Fix tests after changing LDAModel public API
dc61981 [Feynman Liang] Add hyperparams to LocalLDAModel save/load
Implement the classification trait for RandomForestClassifiers. The plan is to use this in the future to providing thresholding for RandomForestClassifiers (as well as other classifiers that implement that trait).
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7432 from holdenk/SPARK-9016-make-random-forest-classifiers-implement-classification-trait and squashes the following commits:
bf22fa6 [Holden Karau] Add missing imports for testing suite
e948f0d [Holden Karau] Check the prediction generation from rawprediciton
25320c3 [Holden Karau] Don't supply numClasses when not needed, assert model classes are as expected
1a67e04 [Holden Karau] Use old decission tree stuff instead
673e0c3 [Holden Karau] Merge branch 'master' into SPARK-9016-make-random-forest-classifiers-implement-classification-trait
0d15b96 [Holden Karau] FIx typo
5eafad4 [Holden Karau] add a constructor for rootnode + num classes
fc6156f [Holden Karau] scala style fix
2597915 [Holden Karau] take num classes in constructor
3ccfe4a [Holden Karau] Merge in master, make pass numClasses through randomforest for training
222a10b [Holden Karau] Increase numtrees to 3 in the python test since before the two were equal and the argmax was selecting the last one
16aea1c [Holden Karau] Make tests match the new models
b454a02 [Holden Karau] Make the Tree classifiers extends the Classifier base class
77b4114 [Holden Karau] Import vectors lib
Author: Bimal Tandel <bimal@bimal-MBP.local>
Closes#7730 from BimalTandel/branch_spark_8921 and squashes the following commits:
3ea230a [Bimal Tandel] Spark 8921 add @since tags
This PR introduces save / load for GMM's in python API.
Also I refactored `GaussianMixtureModel` and inherited it from `JavaModelWrapper` with model being `GaussianMixtureModelWrapper`, a wrapper which provides convenience methods to `GaussianMixtureModel` (due to serialization and deserialization issues) and I moved the creation of gaussians to the scala backend.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7617 from MechCoder/python_gmm_save_load and squashes the following commits:
9c305aa [MechCoder] [SPARK-7105] [PySpark] [MLlib] Support model save/load in GMM
Author: vinodkc <vinod.kc.in@gmail.com>
Closes#7325 from vinodkc/add_since_mllib.recommendation and squashes the following commits:
93156f2 [vinodkc] Changed 0.8.0 to 0.9.1
c413350 [vinodkc] Added @since
This adds StringType feature support via OneHotEncoder. As part of this task it was necessary to change RFormula to an Estimator, so that factor levels could be determined from the training dataset.
Not sure if I am using uids correctly here, would be good to get reviewer help on that.
cc mengxr
Umbrella design doc: https://docs.google.com/document/d/10NZNSEurN2EdWM31uFYsgayIPfCFHiuIu3pCWrUmP_c/edit#
Author: Eric Liang <ekl@databricks.com>
Closes#7574 from ericl/string-features and squashes the following commits:
f99131a [Eric Liang] comments
0bf3c26 [Eric Liang] update docs
c302a2c [Eric Liang] fix tests
9d1ac82 [Eric Liang] Merge remote-tracking branch 'upstream/master' into string-features
e713da3 [Eric Liang] comments
4d79193 [Eric Liang] revert to seq + distinct
169a085 [Eric Liang] tweak functional test
a230a47 [Eric Liang] Merge branch 'master' into string-features
72bd6f3 [Eric Liang] fix merge
d841cec [Eric Liang] Merge branch 'master' into string-features
5b2c4a2 [Eric Liang] Mon Jul 20 18:45:33 PDT 2015
b01c7c5 [Eric Liang] add test
8a637db [Eric Liang] encoder wip
a1d03f4 [Eric Liang] refactor into estimator
Use Vector.argmax call instead of converting to dense vector before calculating predictions.
Author: George Dittmar <georgedittmar@gmail.com>
Closes#7670 from GeorgeDittmar/sprk-7423 and squashes the following commits:
e796747 [George Dittmar] Changing ClassificationModel and ProbabilisticClassificationModel to use Vector.argmax instead of converting to DenseVector
jira: https://issues.apache.org/jira/browse/SPARK-9337
Word2Vec should throw exception when vocabulary is empty
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#7660 from hhbyyh/ut4Word2vec and squashes the following commits:
17a18cb [Yuhao Yang] add ut for word2vec
Currently UnsafeRow cannot support a generic getter. However, if the data type is known, we can support a generic getter.
Author: Reynold Xin <rxin@databricks.com>
Closes#7666 from rxin/generic-getter-with-datatype and squashes the following commits:
ee2874c [Reynold Xin] Add a default implementation for getStruct.
1e109a0 [Reynold Xin] [SPARK-9350][SQL] Introduce an InternalRow generic getter that requires a DataType.
033ee88 [Reynold Xin] Removed getAs in non test code.
Word2Vec used to convert from an Array[Float] representation to a Map[String, Array[Float]] and then back to an Array[Float] through Word2VecModel.
This prevents this conversion while still supporting the older method of supplying a Map.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5748 from MechCoder/spark-7045 and squashes the following commits:
e308913 [MechCoder] move docs
5703116 [MechCoder] minor
fa04313 [MechCoder] style fixes
b1d61c4 [MechCoder] better errors and tests
3b32c8c [MechCoder] [SPARK-7045] Avoid intermediate representation when creating model
This makes it easier to test all the class variables of the DistributedLDAmodel.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7573 from MechCoder/lda_test and squashes the following commits:
2f1a293 [MechCoder] [SPARK-9222] [MLlib] Make class instantiation variables in DistributedLDAModel private[clustering]
I also changed InternalRow's size/length function to numFields, to make it more obvious that it is not about bytes, but the number of fields.
Author: Reynold Xin <rxin@databricks.com>
Closes#7626 from rxin/internalRow and squashes the following commits:
e124daf [Reynold Xin] Fixed test case.
805ceb7 [Reynold Xin] Commented out the failed test suite.
f8a9ca5 [Reynold Xin] Fixed more bugs. Still at least one more remaining.
76d9081 [Reynold Xin] Fixed data sources.
7807f70 [Reynold Xin] Fixed DataFrameSuite.
cb60cd2 [Reynold Xin] Code review & small bug fixes.
0a2948b [Reynold Xin] Fixed style.
3280d03 [Reynold Xin] [SPARK-9285][SQL] Remove InternalRow's inheritance from Row.
The base classifier input and output columns are ignored in favor of the ones specified in OneVsRest.
Author: Ram Sriharsha <rsriharsha@hw11853.local>
Closes#6631 from harsha2010/SPARK-8092 and squashes the following commits:
6591dc6 [Ram Sriharsha] add documentation for params
b7024b1 [Ram Sriharsha] cleanup
f0e2bfb [Ram Sriharsha] merge with master
108d3d7 [Ram Sriharsha] merge with master
4f74126 [Ram Sriharsha] Allow label/ features columns to be configurable
Romove Decimal.Unlimited (change to support precision up to 38, to match with Hive and other databases).
In order to keep backward source compatibility, Decimal.Unlimited is still there, but change to Decimal(38, 18).
If no precision and scale is provide, it's Decimal(10, 0) as before.
Author: Davies Liu <davies@databricks.com>
Closes#7605 from davies/decimal_unlimited and squashes the following commits:
aa3f115 [Davies Liu] fix tests and style
fb0d20d [Davies Liu] address comments
bfaae35 [Davies Liu] fix style
df93657 [Davies Liu] address comments and clean up
06727fd [Davies Liu] Merge branch 'master' of github.com:apache/spark into decimal_unlimited
4c28969 [Davies Liu] fix tests
8d783cc [Davies Liu] fix tests
788631c [Davies Liu] fix double with decimal in Union/except
1779bde [Davies Liu] fix scala style
c9c7c78 [Davies Liu] remove Decimal.Unlimited
Removed varargs annotation from Params.setDefault taking multiple params.
Though varargs is technically correct, it often requires that developers do clean assembly, rather than (not clean) assembly, which is a nuisance during development.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7604 from jkbradley/params-setdefault-varargs and squashes the following commits:
6016dc6 [Joseph K. Bradley] removed varargs annotation from Params.setDefault taking multiple params
Spark has an option called spark.localExecution.enabled; according to the docs:
> Enables Spark to run certain jobs, such as first() or take() on the driver, without sending tasks to the cluster. This can make certain jobs execute very quickly, but may require shipping a whole partition of data to the driver.
This feature ends up adding quite a bit of complexity to DAGScheduler, especially in the runLocallyWithinThread method, but as far as I know nobody uses this feature (I searched the mailing list and haven't seen any recent mentions of the configuration nor stacktraces including the runLocally method). As a step towards scheduler complexity reduction, I propose that we remove this feature and all code related to it for Spark 1.5.
This pull request simply brings #7484 up to date.
Author: Josh Rosen <joshrosen@databricks.com>
Author: Reynold Xin <rxin@databricks.com>
Closes#7585 from rxin/remove-local-exec and squashes the following commits:
84bd10e [Reynold Xin] Python fix.
1d9739a [Reynold Xin] Merge pull request #7484 from JoshRosen/remove-localexecution
eec39fa [Josh Rosen] Remove allowLocal(); deprecate user-facing uses of it.
b0835dc [Josh Rosen] Remove local execution code in DAGScheduler
8975d96 [Josh Rosen] Remove local execution tests.
ffa8c9b [Josh Rosen] Remove documentation for configuration
I've seen a few cases in the past few weeks that the compiler is throwing warnings that are caused by legitimate bugs. This patch upgrades warnings to errors, except deprecation warnings.
Note that ideally we should be able to mark deprecation warnings as errors as well. However, due to the lack of ability to suppress individual warning messages in the Scala compiler, we cannot do that (since we do need to access deprecated APIs in Hadoop).
Most of the work are done by ericl.
Author: Reynold Xin <rxin@databricks.com>
Author: Eric Liang <ekl@databricks.com>
Closes#7598 from rxin/warnings and squashes the following commits:
beb311b [Reynold Xin] Fixed tests.
542c031 [Reynold Xin] Fixed one more warning.
87c354a [Reynold Xin] Fixed all non-deprecation warnings.
78660ac [Eric Liang] first effort to fix warnings
- [X] Added TrainValidationSplit for hyper-parameter tuning. It randomly splits the input dataset into train and validation and use evaluation metric on the validation set to select the best model. It should be similar to CrossValidator, but simpler and less expensive.
- [X] Simplified replacement of https://github.com/apache/spark/pull/6996
Author: martinzapletal <zapletal-martin@email.cz>
Closes#7337 from zapletal-martin/SPARK-8484-TrainValidationSplit and squashes the following commits:
cafc949 [martinzapletal] Review comments https://github.com/apache/spark/pull/7337.
511b398 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-8484-TrainValidationSplit
f4fc9c4 [martinzapletal] SPARK-8484 Resolved feedback to https://github.com/apache/spark/pull/7337
00c4f5a [martinzapletal] SPARK-8484. Styling.
d699506 [martinzapletal] SPARK-8484. Styling.
93ed2ee [martinzapletal] Styling.
3bc1853 [martinzapletal] SPARK-8484. Styling.
2aa6f43 [martinzapletal] SPARK-8484. Added TrainValidationSplit for hyper-parameter tuning. It randomly splits the input dataset into train and validation and use evaluation metric on the validation set to select the best model.
21662eb [martinzapletal] SPARK-8484. Added TrainValidationSplit for hyper-parameter tuning. It randomly splits the input dataset into train and validation and use evaluation metric on the validation set to select the best model.
There are a few memory limits that people hit often and that we could
make higher, especially now that memory sizes have grown.
- spark.akka.frameSize: This defaults at 10 but is often hit for map
output statuses in large shuffles. This memory is not fully allocated
up-front, so we can just make this larger and still not affect jobs
that never sent a status that large. We increase it to 128.
- spark.executor.memory: Defaults at 512m, which is really small. We
increase it to 1g.
Author: Matei Zaharia <matei@databricks.com>
Closes#7586 from mateiz/configs and squashes the following commits:
ce0038a [Matei Zaharia] [SPARK-9244] Increase some memory defaults
Modify `LDA` to take asymmetric document-topic prior distributions and `OnlineLDAOptimizer` to use the asymmetric prior during variational inference.
This PR only generalizes `OnlineLDAOptimizer` and the associated `LocalLDAModel`; `EMLDAOptimizer` and `DistributedLDAModel` still only support symmetric `alpha` (checked during `EMLDAOptimizer.initialize`).
Author: Feynman Liang <fliang@databricks.com>
Closes#7575 from feynmanliang/SPARK-8536-LDA-asymmetric-priors and squashes the following commits:
af8fbb7 [Feynman Liang] Fix merge errors
ef5821d [Feynman Liang] Merge remote-tracking branch 'apache/master' into SPARK-8536-LDA-asymmetric-priors
58f1d7b [Feynman Liang] Fix from review feedback
a6dcf70 [Feynman Liang] Change docConcentration interface and move LDAOptimizer validation to initialize, add sad path tests
72038ff [Feynman Liang] Add tests referenced against gensim
d4284fa [Feynman Liang] Generalize OnlineLDA to asymmetric priors, no tests
In-place updates, reduce number of transposes, and vectorize operations in OnlineLDA implementation.
Author: Feynman Liang <fliang@databricks.com>
Closes#7454 from feynmanliang/OnlineLDA-perf-improvements and squashes the following commits:
78b0f5a [Feynman Liang] Make in-place variables vals, fix BLAS error
7f62a55 [Feynman Liang] --amend
c62cb1e [Feynman Liang] Outer product for stats, revert Range slicing
aead650 [Feynman Liang] Range slice, in-place update, reduce transposes
Add support for saving and loading LDA both the local and distributed versions.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6948 from MechCoder/lda_save_load and squashes the following commits:
49bcdce [MechCoder] minor style fixes
cc14054 [MechCoder] minor
4587d1d [MechCoder] Minor changes
c753122 [MechCoder] Load and save the model in private methods
2782326 [MechCoder] [SPARK-5989] Model save/load for LDA
Created since tags for methods in mllib.classification
Author: petz2000 <petz2000@gmail.com>
Closes#7371 from petz2000/add_since_mllib.classification and squashes the following commits:
39fe291 [petz2000] Removed whitespace in block comment
c9b1e03 [petz2000] Removed @since tags again from protected and private methods
cd759b6 [petz2000] Added @since tags to methods
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7553 from holdenk/SPARK-9204-add-default-params-test-to-linear-regression and squashes the following commits:
630ba19 [Holden Karau] style fix
faa08a3 [Holden Karau] Add default params test for linearyregression suite
This exposes the SparkR:::glm() and SparkR:::predict() APIs. It was necessary to change RFormula to silently drop the label column if it was missing from the input dataset, which is kind of a hack but necessary to integrate with the Pipeline API.
The umbrella design doc for MLlib + SparkR integration can be viewed here: https://docs.google.com/document/d/10NZNSEurN2EdWM31uFYsgayIPfCFHiuIu3pCWrUmP_c/edit
mengxr
Author: Eric Liang <ekl@databricks.com>
Closes#7483 from ericl/spark-8774 and squashes the following commits:
3dfac0c [Eric Liang] update
17ef516 [Eric Liang] more comments
1753a0f [Eric Liang] make glm generic
b0f50f8 [Eric Liang] equivalence test
550d56d [Eric Liang] export methods
c015697 [Eric Liang] second pass
117949a [Eric Liang] comments
5afbc67 [Eric Liang] test label columns
6b7f15f [Eric Liang] Fri Jul 17 14:20:22 PDT 2015
3a63ae5 [Eric Liang] Fri Jul 17 13:41:52 PDT 2015
ce61367 [Eric Liang] Fri Jul 17 13:41:17 PDT 2015
0299c59 [Eric Liang] Fri Jul 17 13:40:32 PDT 2015
e37603f [Eric Liang] Fri Jul 17 12:15:03 PDT 2015
d417d0c [Eric Liang] Merge remote-tracking branch 'upstream/master' into spark-8774
29a2ce7 [Eric Liang] Merge branch 'spark-8774-1' into spark-8774
d1959d2 [Eric Liang] clarify comment
2db68aa [Eric Liang] second round of comments
dc3c943 [Eric Liang] address comments
5765ec6 [Eric Liang] fix style checks
1f361b0 [Eric Liang] doc
d33211b [Eric Liang] r support
fb0826b [Eric Liang] [SPARK-8774] Add R model formula with basic support as a transformer
Fix BLAS.gemm to update matrix C when alpha==0 and beta!=1
Also include unit tests to verify the fix.
mengxr brkyvz
Author: Meihua Wu <meihuawu@umich.edu>
Closes#7503 from rotationsymmetry/fix_BLAS_gemm and squashes the following commits:
fce199c [Meihua Wu] Fix BLAS.gemm to update C when alpha==0 and beta!=1
Python API for the KS-test
Statistics.kolmogorovSmirnovTest(data, distName, *params)
I'm not quite sure how to support the callable function since it is not serializable.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7430 from MechCoder/spark-8996 and squashes the following commits:
2dd009d [MechCoder] minor
021d233 [MechCoder] Remove one wrapper and other minor stuff
49d07ab [MechCoder] [SPARK-8996] [MLlib] Python API for Kolmogorov-Smirnov Test
Modifying Vector, DenseVector, and SparseVector to implement argmax functionality. This work is to set the stage for changes to be done in Spark-7423.
Author: George Dittmar <georgedittmar@gmail.com>
Author: George <dittmar@Georges-MacBook-Pro.local>
Author: dittmarg <george.dittmar@webtrends.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#6112 from GeorgeDittmar/SPARK-7422 and squashes the following commits:
3e0a939 [George Dittmar] Merge pull request #1 from mengxr/SPARK-7422
127dec5 [Xiangrui Meng] update argmax impl
2ea6a55 [George Dittmar] Added MimaExcludes for Vectors.argmax
98058f4 [George Dittmar] Merge branch 'master' of github.com:apache/spark into SPARK-7422
5fd9380 [George Dittmar] fixing style check error
42341fb [George Dittmar] refactoring arg max check to better handle zero values
b22af46 [George Dittmar] Fixing spaces between commas in unit test
f2eba2f [George Dittmar] Cleaning up unit tests to be fewer lines
aa330e3 [George Dittmar] Fixing some last if else spacing issues
ac53c55 [George Dittmar] changing dense vector argmax unit test to be one line call vs 2
d5b5423 [George Dittmar] Fixing code style and updating if logic on when to check for zero values
ee1a85a [George Dittmar] Cleaning up unit tests a bit and modifying a few cases
3ee8711 [George Dittmar] Fixing corner case issue with zeros in the active values of the sparse vector. Updated unit tests
b1f059f [George Dittmar] Added comment before we start arg max calculation. Updated unit tests to cover corner cases
f21dcce [George Dittmar] commit
af17981 [dittmarg] Initial work fixing bug that was made clear in pr
eeda560 [George] Fixing SparseVector argmax function to ignore zero values while doing the calculation.
4526acc [George] Merge branch 'master' of github.com:apache/spark into SPARK-7422
df9538a [George] Added argmax to sparse vector and added unit test
3cffed4 [George] Adding unit tests for argmax functions for Dense and Sparse vectors
04677af [George] initial work on adding argmax to Vector and SparseVector
I Implemented the KMeans API for spark.ml Pipelines. But it doesn't include clustering abstractions for spark.ml (SPARK-7610). It would fit for another issues. And I'll try it later, since we are trying to add the hierarchical clustering algorithms in another issue. Thanks.
[SPARK-7879] KMeans API for spark.ml Pipelines - ASF JIRA https://issues.apache.org/jira/browse/SPARK-7879
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes#6756 from yu-iskw/SPARK-7879 and squashes the following commits:
be752de [Yu ISHIKAWA] Add assertions
a14939b [Yu ISHIKAWA] Fix the dashed line's length in pyspark.ml.rst
4c61693 [Yu ISHIKAWA] Remove the test about whether "features" and "prediction" columns exist or not in Python
fb2417c [Yu ISHIKAWA] Use getInt, instead of get
f397be4 [Yu ISHIKAWA] Switch the comparisons.
ca78b7d [Yu ISHIKAWA] Add the Scala docs about the constraints of each parameter.
effc650 [Yu ISHIKAWA] Using expertSetParam and expertGetParam
c8dc6e6 [Yu ISHIKAWA] Remove an unnecessary test
19a9d63 [Yu ISHIKAWA] Include spark.ml.clustering to python tests
1abb19c [Yu ISHIKAWA] Add the statements about spark.ml.clustering into pyspark.ml.rst
f8338bc [Yu ISHIKAWA] Add the placeholders in Python
4a03003 [Yu ISHIKAWA] Test for contains in Python
6566c8b [Yu ISHIKAWA] Use `get`, instead of `apply`
288e8d5 [Yu ISHIKAWA] Using `contains` to check the column names
5a7d574 [Yu ISHIKAWA] Renamce `validateInitializationMode` to `validateInitMode` and remove throwing exception
97cfae3 [Yu ISHIKAWA] Fix the type of return value of `KMeans.copy`
e933723 [Yu ISHIKAWA] Remove the default value of seed from the Model class
978ee2c [Yu ISHIKAWA] Modify the docs of KMeans, according to mllib's KMeans
2ec80bc [Yu ISHIKAWA] Fit on 1 line
e186be1 [Yu ISHIKAWA] Make a few variables, setters and getters be expert ones
b2c205c [Yu ISHIKAWA] Rename the method `getInitializationSteps` to `getInitSteps` and `setInitializationSteps` to `setInitSteps` in Scala and Python
f43f5b4 [Yu ISHIKAWA] Rename the method `getInitializationMode` to `getInitMode` and `setInitializationMode` to `setInitMode` in Scala and Python
3cb5ba4 [Yu ISHIKAWA] Modify the description about epsilon and the validation
4fa409b [Yu ISHIKAWA] Add a comment about the default value of epsilon
2f392e1 [Yu ISHIKAWA] Make some variables `final` and Use `IntParam` and `DoubleParam`
19326f8 [Yu ISHIKAWA] Use `udf`, instead of callUDF
4d2ad1e [Yu ISHIKAWA] Modify the indentations
0ae422f [Yu ISHIKAWA] Add a test for `setParams`
4ff7913 [Yu ISHIKAWA] Add "ml.clustering" to `javacOptions` in SparkBuild.scala
11ffdf1 [Yu ISHIKAWA] Use `===` and the variable
220a176 [Yu ISHIKAWA] Set a random seed in the unit testing
92c3efc [Yu ISHIKAWA] Make the points for a test be fewer
c758692 [Yu ISHIKAWA] Modify the parameters of KMeans in Python
6aca147 [Yu ISHIKAWA] Add some unit testings to validate the setter methods
687cacc [Yu ISHIKAWA] Alias mllib.KMeans as MLlibKMeans in KMeansSuite.scala
a4dfbef [Yu ISHIKAWA] Modify the last brace and indentations
5bedc51 [Yu ISHIKAWA] Remve an extra new line
444c289 [Yu ISHIKAWA] Add the validation for `runs`
e41989c [Yu ISHIKAWA] Modify how to validate `initStep`
7ea133a [Yu ISHIKAWA] Change how to validate `initMode`
7991e15 [Yu ISHIKAWA] Add a validation for `k`
c2df35d [Yu ISHIKAWA] Make `predict` private
93aa2ff [Yu ISHIKAWA] Use `withColumn` in `transform`
d3a79f7 [Yu ISHIKAWA] Remove the inhefited docs
e9532e1 [Yu ISHIKAWA] make `parentModel` of KMeansModel private
8559772 [Yu ISHIKAWA] Remove the `paramMap` parameter of KMeans
6684850 [Yu ISHIKAWA] Rename `initializationSteps` to `initSteps`
99b1b96 [Yu ISHIKAWA] Rename `initializationMode` to `initMode`
79ea82b [Yu ISHIKAWA] Modify the parameters of KMeans docs
6569bcd [Yu ISHIKAWA] Change how to set the default values with `setDefault`
20a795a [Yu ISHIKAWA] Change how to set the default values with `setDefault`
11c2a12 [Yu ISHIKAWA] Limit the imports
badb481 [Yu ISHIKAWA] Alias spark.mllib.{KMeans, KMeansModel}
f80319a [Yu ISHIKAWA] Rebase mater branch and add copy methods
85d92b1 [Yu ISHIKAWA] Add `KMeans.setPredictionCol`
aa9469d [Yu ISHIKAWA] Fix a python test suite error caused by python 3.x
c2d6bcb [Yu ISHIKAWA] ADD Java test suites of the KMeans API for spark.ml Pipeline
598ed2e [Yu ISHIKAWA] Implement the KMeans API for spark.ml Pipelines in Python
63ad785 [Yu ISHIKAWA] Implement the KMeans API for spark.ml Pipelines in Scala
Broadcast of ensemble models in transformImpl before call to predict
Author: Bryan Cutler <bjcutler@us.ibm.com>
Closes#6300 from BryanCutler/bcast-ensemble-models-7127 and squashes the following commits:
86e73de [Bryan Cutler] [SPARK-7127] Replaced deprecated callUDF with udf
40a139d [Bryan Cutler] Merge branch 'master' into bcast-ensemble-models-7127
9afad56 [Bryan Cutler] [SPARK-7127] Simplified calls by overriding transformImpl and using broadcasted model in callUDF to make prediction
1f34be4 [Bryan Cutler] [SPARK-7127] Removed accidental newline
171a6ce [Bryan Cutler] [SPARK-7127] Used modelAccessor parameter in predictImpl to access broadcasted model
6fd153c [Bryan Cutler] [SPARK-7127] Applied broadcasting to remaining ensemble models
aaad77b [Bryan Cutler] [SPARK-7127] Removed abstract class for broadcasting model, instead passing a prediction function as param to transform
83904bb [Bryan Cutler] [SPARK-7127] Adding broadcast of model before prediction in RandomForestClassifier
Make the definition of residuals in Spark consistent with literature. We have been using `prediction - label` for residuals, but literature usually defines `residual = label - prediction`.
Author: Feynman Liang <fliang@databricks.com>
Closes#7435 from feynmanliang/SPARK-9090-Fix-LinearRegressionSummary-Residuals and squashes the following commits:
f4b39d8 [Feynman Liang] Fix doc
bc12a92 [Feynman Liang] Tweak EnsembleTestHelper and SquaredError residuals
63f0d60 [Feynman Liang] Fix definition of residual
jira: https://issues.apache.org/jira/browse/SPARK-9062
Currently output type of Tokenizer is Array(String, false), which is not compatible with Word2Vec and Other transformers since their input type is Array(String, true). Seq[String] in udf will be treated as Array(String, true) by default.
I'm not sure what's the recommended way for Tokenizer to handle the null value in the input. Any suggestion will be welcome.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#7414 from hhbyyh/tokenizer and squashes the following commits:
c01bd7a [Yuhao Yang] change output type of tokenizer
fix wrong annotation of RFormula.formula
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7470 from yanboliang/RFormula and squashes the following commits:
61f1919 [Yanbo Liang] fix wrong annotation
Measure lower and upper bounds for task time and use them for validation. This PR also implements `Stopwatch.toString`. This suite should finish in less than 1 second.
jkbradley pwendell
Author: Xiangrui Meng <meng@databricks.com>
Closes#7457 from mengxr/SPARK-9126 and squashes the following commits:
4b40faa [Xiangrui Meng] simplify tests
739f5bd [Xiangrui Meng] do not assert on time taken by Thread.sleep()
This PR copies the RandomForest implementation from spark.mllib to spark.ml. Note that this includes the DecisionTree implementation, but not the GradientBoostedTrees one (which will come later).
I essentially copied a minimal amount of code to spark.ml, removed the use of bins (and only used splits), and modified code only as much as necessary to get it to compile. The spark.ml implementation still uses some spark.mllib classes (privately), which can be moved in future PRs.
This refactoring will be helpful in extending the node representation to include more information, such as class probabilities.
Specifically:
* Copied code from spark.mllib to spark.ml:
* mllib.tree.DecisionTree, mllib.tree.RandomForest copied to ml.tree.impl.RandomForest (main implementation)
* NodeIdCache (needed to use splits instead of bins)
* TreePoint (use splits instead of bins)
* Added ml.tree.LearningNode used in RandomForest training (needed vars)
* Removed bins from implementation, and only used splits
* Small fix in JavaDecisionTreeRegressorSuite
CC: mengxr manishamde codedeft chouqin
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7294 from jkbradley/dt-move-impl and squashes the following commits:
48749be [Joseph K. Bradley] cleanups based on code review, mostly style
bea9703 [Joseph K. Bradley] scala style fixes. added some scala doc
4e6d2a4 [Joseph K. Bradley] removed unnecessary use of copyValues, setParent for trees
9a4d721 [Joseph K. Bradley] cleanups. removed InfoGainStats from ml, using old one for now.
836e7d4 [Joseph K. Bradley] Fixed test suite failures
bd5e063 [Joseph K. Bradley] fixed bucketizing issue
0df3759 [Joseph K. Bradley] Need to remove use of Bucketizer
d5224a9 [Joseph K. Bradley] modified tree and forest to use moved impl
cc01823 [Joseph K. Bradley] still editing RF to get it to work
19143fb [Joseph K. Bradley] More progress, but not done yet. Rebased with master after 1.4 release.
Add stopwatches for easy instrumentation of MLlib algorithms. This is based on the `TimeTracker` used in decision trees. The distributed version uses Spark accumulator. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#7415 from mengxr/SPARK-9018 and squashes the following commits:
40b4347 [Xiangrui Meng] == -> ===
c477745 [Xiangrui Meng] address Joseph's comments
f981a49 [Xiangrui Meng] add stopwatches
This implements minimal R formula support as a feature transformer. Both numeric and string labels are supported, but features must be numeric for now.
cc mengxr
Author: Eric Liang <ekl@databricks.com>
Closes#7381 from ericl/spark-8774-1 and squashes the following commits:
d1959d2 [Eric Liang] clarify comment
2db68aa [Eric Liang] second round of comments
dc3c943 [Eric Liang] address comments
5765ec6 [Eric Liang] fix style checks
1f361b0 [Eric Liang] doc
fb0826b [Eric Liang] [SPARK-8774] Add R model formula with basic support as a transformer
Fixes implementation of `explainedVariance` and `r2` to be consistent with their definitions as described in [SPARK-9005](https://issues.apache.org/jira/browse/SPARK-9005).
Author: Feynman Liang <fliang@databricks.com>
Closes#7361 from feynmanliang/SPARK-9005-RegressionMetrics-bugs and squashes the following commits:
f1112fc [Feynman Liang] Add explainedVariance formula
1a3d098 [Feynman Liang] SROwen code review comments
08a0e1b [Feynman Liang] Fix pyspark tests
db8605a [Feynman Liang] Style fix
bde9761 [Feynman Liang] Fix RegressionMetrics tests, relax assumption predictor is unbiased
c235de0 [Feynman Liang] Fix RegressionMetrics tests
4c4e56f [Feynman Liang] Fix RegressionMetrics computation of explainedVariance and r2
This allows Kmeans to be initialized using an existing set of cluster centers provided as a KMeansModel object. This mode of initialization performs a single run.
Author: FlytxtRnD <meethu.mathew@flytxt.com>
Closes#6737 from FlytxtRnD/Kmeans-8018 and squashes the following commits:
94b56df [FlytxtRnD] style correction
ef95ee2 [FlytxtRnD] style correction
c446c58 [FlytxtRnD] documentation and numRuns warning change
06d13ef [FlytxtRnD] numRuns corrected
d12336e [FlytxtRnD] numRuns variable modifications
07f8554 [FlytxtRnD] remove setRuns from setIntialModel
e721dfe [FlytxtRnD] Merge remote-tracking branch 'upstream/master' into Kmeans-8018
242ead1 [FlytxtRnD] corrected == to === in assert
714acb5 [FlytxtRnD] added numRuns
60c8ce2 [FlytxtRnD] ignore runs parameter and initialModel test suite changed
582e6d9 [FlytxtRnD] Merge remote-tracking branch 'upstream/master' into Kmeans-8018
3f5fc8e [FlytxtRnD] test case modified and one runs condition added
cd5dc5c [FlytxtRnD] Merge remote-tracking branch 'upstream/master' into Kmeans-8018
16f1b53 [FlytxtRnD] Merge branch 'Kmeans-8018', remote-tracking branch 'upstream/master' into Kmeans-8018
e9c35d7 [FlytxtRnD] Remove getInitialModel and match cluster count criteria
6959861 [FlytxtRnD] Accept initial cluster centers in KMeans
I implemented the Python API for LDA. But I didn't implemented a method for `LDAModel.describeTopics()`, beause it's a little hard to implement it now. And adding document about that and an example code would fit for another issue.
TODO: LDAModel.describeTopics() in Python must be also implemented. But it would be nice to fit for another issue. Implementing it is a little hard, since the return value of `describeTopics` in Scala consists of Tuple classes.
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes#6791 from yu-iskw/SPARK-6259 and squashes the following commits:
6855f59 [Yu ISHIKAWA] LDA inherits object
28bd165 [Yu ISHIKAWA] Change the place of testing code
d7a332a [Yu ISHIKAWA] Remove the doc comment about the optimizer's default value
083e226 [Yu ISHIKAWA] Add the comment about the supported values and the default value of `optimizer`
9f8bed8 [Yu ISHIKAWA] Simplify casting
faa9764 [Yu ISHIKAWA] Add some comments for the LDA paramters
98f645a [Yu ISHIKAWA] Remove the interface for `describeTopics`. Because it is not implemented.
57ac03d [Yu ISHIKAWA] Remove the unnecessary import in Python unit testing
73412c3 [Yu ISHIKAWA] Fix the typo
2278829 [Yu ISHIKAWA] Fix the indentation
39514ec [Yu ISHIKAWA] Modify how to cast the input data
8117e18 [Yu ISHIKAWA] Fix the validation problems by `lint-scala`
77fd1b7 [Yu ISHIKAWA] Not use LabeledPoint
68f0653 [Yu ISHIKAWA] Support some parameters for `ALS.train()` in Python
25ef2ac [Yu ISHIKAWA] Resolve conflicts with rebasing
Add predictProbabilities to Naive Bayes, return class probabilities.
Continues https://github.com/apache/spark/pull/6761
Author: Sean Owen <sowen@cloudera.com>
Closes#7376 from srowen/SPARK-4362 and squashes the following commits:
23d5a76 [Sean Owen] Fix model.labels -> model.theta
95d91fb [Sean Owen] Check that predicted probabilities sum to 1
b32d1c8 [Sean Owen] Add predictProbabilities to Naive Bayes, return class probabilities
Removed private[ml] from Generated documentation
Author: Vinod K C <vinod.kc@huawei.com>
Closes#7367 from vinodkc/fix_sharedparmascodegen and squashes the following commits:
4fa3c8f [Vinod K C] Adding auto generated code
7e19025 [Vinod K C] Removed private[ml]
Made default impl of Params.validateParams empty
CC mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7349 from jkbradley/pipeline-small-cleanups and squashes the following commits:
4e0f013 [Joseph K. Bradley] small cleanups after SPARK-5956
Add parallel PrefixSpan algorithm and test file.
Support non-temporal sequences.
Author: zhangjiajin <zhangjiajin@huawei.com>
Author: zhang jiajin <zhangjiajin@huawei.com>
Closes#7258 from zhangjiajin/master and squashes the following commits:
ca9c4c8 [zhangjiajin] Modified the code according to the review comments.
574e56c [zhangjiajin] Add new object LocalPrefixSpan, and do some optimization.
ba5df34 [zhangjiajin] Fix a Scala style error.
4c60fb3 [zhangjiajin] Fix some Scala style errors.
1dd33ad [zhangjiajin] Modified the code according to the review comments.
89bc368 [zhangjiajin] Fixed a Scala style error.
a2eb14c [zhang jiajin] Delete PrefixspanSuite.scala
951fd42 [zhang jiajin] Delete Prefixspan.scala
575995f [zhangjiajin] Modified the code according to the review comments.
91fd7e6 [zhangjiajin] Add new algorithm PrefixSpan and test file.
This contribution is my original work and I license it to the project under it's open source license.
Author: jose.cambronero <jose.cambronero@cloudera.com>
Closes#6994 from josepablocam/master and squashes the following commits:
bbb30b1 [jose.cambronero] renamed KSTestResult to KolmogorovSmirnovTestResult, to stay consistent with method name
0d0c201 [jose.cambronero] kstTest -> kolmogorovSmirnovTest in statistics.md
1f56371 [jose.cambronero] changed ksTest in public API to kolmogorovSmirnovTest for clarity
a48ae7b [jose.cambronero] refactor code to account for serializable RealDistribution. Reuse testOneSample( _, cdf)
1bb44bd [jose.cambronero] style and doc changes. Factored out ks test into 2 separate tests
2ec2aa6 [jose.cambronero] initialize to stdnormal when no params passed (and log). Change unit tests to approximate equivalence rather than strict
a4bc0c7 [jose.cambronero] changed ksTest(data, distName) to ksTest(data, distName, params*) after api discussions. Changed tests and docs accordingly
7e66f57 [jose.cambronero] copied implementation note to public api docs, and added @see for links to wiki info
e760ebd [jose.cambronero] line length changes to fit style check
3288e42 [jose.cambronero] addressed style changes, correctness change to simpler approach, and fixed edge case for foldLeft in searchOneSampleCandidates when a partition is empty
9026895 [jose.cambronero] addressed style changes, correctness change to simpler approach, and fixed edge case for foldLeft in searchOneSampleCandidates when a partition is empty
1226b30 [jose.cambronero] reindent multi-line lambdas, prior intepretation of style guide was wrong on my part
9c0f1af [jose.cambronero] additional style changes incorporated and added documentation to mllib statistics docs
3f81ad2 [jose.cambronero] renamed ks1 sample test for clarity
992293b [jose.cambronero] Style changes as per comments and added implementation note explaining the distributed approach.
6a4784f [jose.cambronero] specified what distributions are available for the convenience method ksTest(data, name) (solely standard normal)
4b8ba61 [jose.cambronero] fixed off by 1/N in cases when post-constant adjustment ecdf is above cdf, but prior to adj it was below
0b5e8ec [jose.cambronero] changed KS one sample test to perform just 1 distributed pass (in addition to the sorting pass), operates on each partition separately. Implementation of Sandy Ryza's algorithm
16b5c4c [jose.cambronero] renamed dat to data and eliminated recalc of RDD size by sharing as argument between empirical and evalOneSampleP
c18dc66 [jose.cambronero] removed ksTestOpt from API and changed comments in HypothesisTestSuite accordingly
f6951b6 [jose.cambronero] changed style and some comments based on feedback from pull request
b9cff3a [jose.cambronero] made small changes to pass style check
ce8e9a1 [jose.cambronero] added kstest testing in HypothesisTestSuite
4da189b [jose.cambronero] added user facing ks test functions
c659ea1 [jose.cambronero] created KS test class
13dfe4d [jose.cambronero] created test result class for ks test
Author: rahulpalamuttam <rahulpalamut@gmail.com>
Closes#7341 from rahulpalamuttam/TaggingMLlibfpm and squashes the following commits:
bef2843 [rahulpalamuttam] fix @since tags in mmlib.fpm
cd86252 [rahulpalamuttam] Add @since tags to mllib.fpm
Author: Jonathan Alter <jonalter@users.noreply.github.com>
Closes#7093 from jonalter/SPARK-7977 and squashes the following commits:
ccd44cc [Jonathan Alter] Changed println to log in ThreadingSuite
7fcac3e [Jonathan Alter] Reverting to println in ThreadingSuite
10724b6 [Jonathan Alter] Changing some printlns to logs in tests
eeec1e7 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
0b1dcb4 [Jonathan Alter] More println cleanup
aedaf80 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
925fd98 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
0c16fa3 [Jonathan Alter] Replacing some printlns with logs
45c7e05 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
5c8e283 [Jonathan Alter] Allowing println in audit-release examples
5b50da1 [Jonathan Alter] Allowing printlns in example files
ca4b477 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
83ab635 [Jonathan Alter] Fixing new printlns
54b131f [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
1cd8a81 [Jonathan Alter] Removing some unnecessary comments and printlns
b837c3a [Jonathan Alter] Disallowing println
Cleanup tests from SPARK 8700.
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7335 from holdenk/SPARK-8913-cleanup-tests-from-SPARK-8700-logistic-regression-r2-really-logistic-regression-this-time and squashes the following commits:
e5e2c5f [Holden Karau] Simplify LogisticRegression suite to use Vector <-> Vector comparisions instead of comparing element by element
Adds results (e.g. objective value at each iteration, residuals) on training and user-specified test sets for LinearRegressionModel.
Notes to Reviewers:
* Are the `*TrainingResults` and `Results` classes too specialized for `LinearRegressionModel`? Where would be an appropriate level of abstraction?
* Please check `transient` annotations are correct; the datasets should not be copied and kept during serialization.
* Any thoughts on `RDD`s versus `DataFrame`s? If using `DataFrame`s, suggested schemas for each intermediate step? Also, how to create a "local DataFrame" without a `sqlContext`?
Author: Feynman Liang <fliang@databricks.com>
Closes#7099 from feynmanliang/SPARK-8538 and squashes the following commits:
d219fa4 [Feynman Liang] Update docs
4a42680 [Feynman Liang] Change Summary to hold values, move transient annotations down to metrics and predictions DF
6300031 [Feynman Liang] Code review changes
0a5e762 [Feynman Liang] Fix build error
e71102d [Feynman Liang] Merge branch 'master' into SPARK-8538
3367489 [Feynman Liang] Merge branch 'master' into SPARK-8538
70f267c [Feynman Liang] Make TrainingSummary transient and remove Serializable from *Summary and RegressionMetrics
1d9ea42 [Feynman Liang] Fix failing Java test
a65dfda [Feynman Liang] Make TrainingSummary and metrics serializable, prediction dataframe transient
0a605d8 [Feynman Liang] Replace Params from LinearRegression*Summary with private constructor vals
c2fe835 [Feynman Liang] Optimize imports
02d8a70 [Feynman Liang] Add Params to LinearModel*Summary, refactor tests and add test for evaluate()
8f999f4 [Feynman Liang] Refactor from jkbradley code review
072e948 [Feynman Liang] Style
509ae36 [Feynman Liang] Use DFs and localize serialization to LinearRegressionModel
9509c79 [Feynman Liang] Fix imports
b2bbaa3 [Feynman Liang] Refactored LinearRegressionResults API to be more private
ffceaec [Feynman Liang] Merge branch 'master' into SPARK-8538
1cedb2b [Feynman Liang] Add test for decreasing objective trace
dab0aff [Feynman Liang] Add LinearRegressionTrainingResults tests, make test suite code copy+pasteable
97b0a81 [Feynman Liang] Add LinearRegressionModel.evaluate() to get results on test sets
dc51bce [Feynman Liang] Style guide fixes
521f397 [Feynman Liang] Use RDD[(Double, Double)] instead of DF
2ff5710 [Feynman Liang] Add training results and model summary to ML LinearRegression
Simplify model weight assertions to use vector comparision, switch to using absTol when comparing with 0.0 intercepts
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7327 from holdenk/SPARK-8913-cleanup-tests-from-SPARK-8700-logistic-regression and squashes the following commits:
5bac185 [Holden Karau] Simplify model weight assertions to use vector comparision, switch to using absTol when comparing with 0.0 intercepts
jira: https://issues.apache.org/jira/browse/SPARK-8703
Converts a text document to a sparse vector of token counts.
I can further add an estimator to extract vocabulary from corpus if that's appropriate.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#7084 from hhbyyh/countVectorization and squashes the following commits:
5f3f655 [Yuhao Yang] text change
24728e4 [Yuhao Yang] style improvement
576728a [Yuhao Yang] rename to model and some fix
1deca28 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into countVectorization
99b0c14 [Yuhao Yang] undo extension from HashingTF
12c2dc8 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into countVectorization
7ee1c31 [Yuhao Yang] extends HashingTF
809fb59 [Yuhao Yang] minor fix for ut
7c61fb3 [Yuhao Yang] add countVectorizer
This PR fixes the converter for Python DataFrame, especially for DecimalType
Closes#7106
Author: Davies Liu <davies@databricks.com>
Closes#7131 from davies/decimal_python and squashes the following commits:
4d3c234 [Davies Liu] Merge branch 'master' of github.com:apache/spark into decimal_python
20531d6 [Davies Liu] Merge branch 'master' of github.com:apache/spark into decimal_python
7d73168 [Davies Liu] fix conflit
6cdd86a [Davies Liu] Merge branch 'master' of github.com:apache/spark into decimal_python
7104e97 [Davies Liu] improve type infer
9cd5a21 [Davies Liu] run python tests with SPARK_PREPEND_CLASSES
829a05b [Davies Liu] fix UDT in python
c99e8c5 [Davies Liu] fix mima
c46814a [Davies Liu] convert decimal for Python DataFrames
Distribute expensive portions of computation for Gaussian mixture components (in particular, pre-computation of `MultivariateGaussian.rootSigmaInv`, the inverse covariance matrix and covariance determinant) across executors. Repost of PR#4654.
Notes for reviewers:
* What should be the policy for when to distribute computation. Always? When numClusters > threshold? User-specified param?
TODO:
* Performance testing and comparison for large number of clusters
Author: Feynman Liang <fliang@databricks.com>
Closes#7166 from feynmanliang/GMM_parallel_mixtures and squashes the following commits:
4f351fa [Feynman Liang] Update heuristic and scaladoc
5ea947e [Feynman Liang] Fix parallelization logic
00eb7db [Feynman Liang] Add helper method for GMM's M step, remove distributeGaussians flag
e7c8127 [Feynman Liang] Add distributeGaussians flag and tests
1da3c7f [Feynman Liang] Distribute mixtures
Adds FPGrowth.generateAssociationRules to public API for generating association rules after mining frequent itemsets.
Author: Feynman Liang <fliang@databricks.com>
Closes#7271 from feynmanliang/SPARK-8877 and squashes the following commits:
83b8baf [Feynman Liang] Add API Doc
867abff [Feynman Liang] Add FPGrowth.generateAssociationRules and change access modifiers for AssociationRules
All compressed sensing applications, and some of the regression use-cases will have better result by turning the feature scaling off. However, if we implement this naively by training the dataset without doing any standardization, the rate of convergency will not be good. This can be implemented by still standardizing the training dataset but we penalize each component differently to get effectively the same objective function but a better numerical problem. As a result, for those columns with high variances, they will be penalized less, and vice versa. Without this, since all the features are standardized, so they will be penalized the same.
In R, there is an option for this.
`standardize`
Logical flag for x variable standardization, prior to fitting the model sequence. The coefficients are always returned on the original scale. Default is standardize=TRUE. If variables are in the same units already, you might not wish to standardize. See details below for y standardization with family="gaussian".
+cc holdenk mengxr jkbradley
Author: DB Tsai <dbt@netflix.com>
Closes#7080 from dbtsai/lors and squashes the following commits:
877e6c7 [DB Tsai] repahse the doc
7cf45f2 [DB Tsai] address feedback
78d75c9 [DB Tsai] small change
c2c9e60 [DB Tsai] style
6e1a8e0 [DB Tsai] first commit
Author: Kashif Rasul <kashif.rasul@gmail.com>
Closes#7269 from kashif/SPARK-8872 and squashes the following commits:
2d5457f [Kashif Rasul] added R code for FP Int type
3de6808 [Kashif Rasul] added verification results from R for FPGrowthSuite
In LinearRegression and LogisticRegression, we use Breeze's optimizers (LBFGS and OWLQN). We check the State.value to see the current objective. However, Breeze's documentation makes it sound like value and adjustedValue differ for some optimizers, possibly including OWLQN: 26faf62286/math/src/main/scala/breeze/optimize/FirstOrderMinimizer.scala (L36)
If that is the case, then we should use adjustedValue instead of value. This is relevant to SPARK-8538 and SPARK-8539, where we will provide the objective trace to the user.
Author: DB Tsai <dbt@netflix.com>
Closes#7245 from dbtsai/SPARK-8845 and squashes the following commits:
fa4c91e [DB Tsai] address feedback
e6caac1 [DB Tsai] java style multiline comment
b10c574 [DB Tsai] address feedback
c9ff81e [DB Tsai] first commit
Add std, mean to StandardScalerModel
getVectors, findSynonyms to Word2Vec Model
setFeatures and getFeatures to hashingTF
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7086 from MechCoder/missing_model_methods and squashes the following commits:
9fbae90 [MechCoder] Add type
6e3d6b2 [MechCoder] [SPARK-8704] Add missing methods in StandardScaler (ML and PySpark)
Distributed generation of single-consequent association rules from a RDD of frequent itemsets. Tests referenced against `R`'s implementation of A Priori in [arules](http://cran.r-project.org/web/packages/arules/index.html).
Author: Feynman Liang <fliang@databricks.com>
Closes#7005 from feynmanliang/fp-association-rules-distributed and squashes the following commits:
466ced0 [Feynman Liang] Refactor AR generation impl
73c1cff [Feynman Liang] Make rule attributes public, remove numTransactions from FreqItemset
80f63ff [Feynman Liang] Change default confidence and optimize imports
04cf5b5 [Feynman Liang] Code review with @mengxr, add R to tests
0cc1a6a [Feynman Liang] Java compatibility test
f3c14b5 [Feynman Liang] Fix MiMa test
764375e [Feynman Liang] Fix tests
1187307 [Feynman Liang] Almost working tests
b20779b [Feynman Liang] Working implementation
5395c4e [Feynman Liang] Fix imports
2d34405 [Feynman Liang] Partial implementation of distributed ar
83ace4b [Feynman Liang] Local rule generation without pruning complete
69c2c87 [Feynman Liang] Working local implementation, now to parallelize../..
4e1ec9a [Feynman Liang] Pull FreqItemsets out, refactor type param, tests
69ccedc [Feynman Liang] First implementation of association rule generation
Add numNodes and depth to treeModels, add treeWeights to ensemble Models.
Add __repr__ to all models.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#7095 from MechCoder/missing_methods_tree and squashes the following commits:
23b08be [MechCoder] private [spark]
38a0860 [MechCoder] rename pyTreeWeights to javaTreeWeights
6d16ad8 [MechCoder] Fix Python 3 Error
47d7023 [MechCoder] Use np.allclose and treeEnsembleModel -> TreeEnsembleMethods
819098c [MechCoder] [SPARK-8711] [ML] Add additional methods ot PySpark ML tree models
Add Java unit test for PCA transformer
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7184 from yanboliang/spark-8788 and squashes the following commits:
9d1a2af [Yanbo Liang] address comments
b34451f [Yanbo Liang] Add Java unit test for PCA transformer
See the jira https://issues.apache.org/jira/browse/SPARK-5562
Author: Alok Singh <singhal@Aloks-MacBook-Pro.local>
Author: Alok Singh <singhal@aloks-mbp.usca.ibm.com>
Author: Alok Singh <“singhal@us.ibm.com”>
Closes#7064 from aloknsingh/aloknsingh_SPARK-5562 and squashes the following commits:
259a0a7 [Alok Singh] change as per the comments by @jkbradley
be48491 [Alok Singh] [SPARK-5562][MLlib] re-order import in alphabhetical order
c01311b [Alok Singh] [SPARK-5562][MLlib] fix the newline typo
b271c8a [Alok Singh] [SPARK-5562][Mllib] As per github discussion with jkbradley. We would like to simply things.
7c06251 [Alok Singh] [SPARK-5562][MLlib] modified the JavaLDASuite for test passing
c710cb6 [Alok Singh] fix the scala code style to have space after :
2572a08 [Alok Singh] [SPARK-5562][MLlib] change the import xyz._ to the import xyz.{c1, c2} ..
ab55fbf [Alok Singh] [SPARK-5562][MLlib] Change as per Sean Owen's comments https://github.com/apache/spark/pull/7064/files#diff-9236d23975e6f5a5608ffc81dfd79146
9f4f9ea [Alok Singh] [SPARK-5562][MLlib] LDA should handle empty document.
This reverts commit 25f574eb9a. After speaking to some users and developers, we realized that FP-growth doesn't meet the requirement for frequent sequence mining. PrefixSpan (SPARK-6487) would be the correct algorithm for it. feynmanliang
Author: Xiangrui Meng <meng@databricks.com>
Closes#7240 from mengxr/SPARK-7212.revert and squashes the following commits:
2b3d66b [Xiangrui Meng] Revert "[SPARK-7212] [MLLIB] Add sequence learning flag"
Author: Joshi <rekhajoshm@gmail.com>
Author: Rekha Joshi <rekhajoshm@gmail.com>
Closes#5992 from rekhajoshm/fix/SPARK-7137 and squashes the following commits:
8c42b57 [Joshi] update checkInputColumn to print more info if needed
33ddd2e [Joshi] update checkInputColumn to print more info if needed
acf3e17 [Joshi] update checkInputColumn to print more info if needed
8993c0e [Joshi] SPARK-7137: Add checkInputColumn back to Params and print more info
e3677c9 [Rekha Joshi] Merge pull request #1 from apache/master
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes#6821 from yu-iskw/SPARK-7104 and squashes the following commits:
975136b [Yu ISHIKAWA] Organize import
0ef58b6 [Yu ISHIKAWA] Use rmtree, instead of removedirs
cb21653 [Yu ISHIKAWA] Add an explicit type for `Word2VecModelWrapper.save`
1d468ef [Yu ISHIKAWA] [SPARK-7104][MLlib] Support model save/load in Python's Word2Vec
GrandientDescent can receive convergence tolerance value. Default value is 0.0.
When loss value becomes less than the tolerance which is set by user, iteration is terminated.
Author: lewuathe <lewuathe@me.com>
Closes#3636 from Lewuathe/gd-convergence-tolerance and squashes the following commits:
0b8a9a8 [lewuathe] Update doc
ce91b15 [lewuathe] Merge branch 'master' into gd-convergence-tolerance
4f22c2b [lewuathe] Modify based on SPARK-1503
5e47b82 [lewuathe] Merge branch 'master' into gd-convergence-tolerance
abadb7e [lewuathe] Fix LassoSuite
8fadebd [lewuathe] Fix failed unit tests
ee5de46 [lewuathe] Merge branch 'master' into gd-convergence-tolerance
8313ba2 [lewuathe] Fix styles
0ead94c [lewuathe] Merge branch 'master' into gd-convergence-tolerance
a94cfd5 [lewuathe] Modify some styles
3aef0a2 [lewuathe] Modify converged logic to do relative comparison
f7b19d5 [lewuathe] [SPARK-3382] Clarify comparison logic
e6c9cd2 [lewuathe] [SPARK-3382] Compare with the diff of solution vector
4b125d2 [lewuathe] [SPARK3382] Fix scala style
e7c10dd [lewuathe] [SPARK-3382] format improvements
f867eea [lewuathe] [SPARK-3382] Modify warning message statements
b9d5e61 [lewuathe] [SPARK-3382] should compare diff inside loss history and convergence tolerance
5433f71 [lewuathe] [SPARK-3382] GradientDescent convergence tolerance
Matrices allow zeros to be stored in values. Sometimes a method is handy to check if the numNonZeros are same as number of Active values.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6904 from MechCoder/nnz_matrix and squashes the following commits:
252c6b7 [MechCoder] Add to MiMa excludes
e2390f5 [MechCoder] Use count instead of foreach
2f62b2f [MechCoder] Add to MiMa excludes
d6e96ef [MechCoder] [SPARK-8479] Add numNonzeros and numActives to linalg.Matrices
JIRA: https://issues.apache.org/jira/browse/SPARK-8708
Previously the partitions of ratings are only based on the given products. So if the `usersProducts` given for prediction contains only few products or even one product, the generated ratings will be pushed into few or single partition and can't use high parallelism.
The following codes are the example reported in the JIRA. Because it asks the predictions for users on product 2. There is only one partition in the result.
>>> r1 = (1, 1, 1.0)
>>> r2 = (1, 2, 2.0)
>>> r3 = (2, 1, 2.0)
>>> r4 = (2, 2, 2.0)
>>> r5 = (3, 1, 1.0)
>>> ratings = sc.parallelize([r1, r2, r3, r4, r5], 5)
>>> users = ratings.map(itemgetter(0)).distinct()
>>> model = ALS.trainImplicit(ratings, 1, seed=10)
>>> predictions_for_2 = model.predictAll(users.map(lambda u: (u, 2)))
>>> predictions_for_2.glom().map(len).collect()
[0, 0, 3, 0, 0]
This PR uses user and product instead of only product to partition the ratings.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes#7121 from viirya/mfm_fix_partition and squashes the following commits:
779946d [Liang-Chi Hsieh] Calculate approximate numbers of users and products in one pass.
4336dc2 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into mfm_fix_partition
83e56c1 [Liang-Chi Hsieh] Instead of additional join, use the numbers of users and products to decide how to perform join.
b534dc8 [Liang-Chi Hsieh] Paritition ratings based on both users and products.
I added the code,
// see [SPARK-8647], this achieves the needed constant hash code without constant no.
override def hashCode(): Int = this.getClass.getName.hashCode()
does getting the constant hash code as per jira
Author: Alok Singh <singhal@Aloks-MacBook-Pro.local>
Closes#7146 from aloknsingh/aloknsingh_SPARK-8647 and squashes the following commits:
e58bccf [Alok Singh] [SPARK-8647][MLlib] to avoid the class derivation issues, change the constant hashCode to override def hashCode(): Int = classOf[MatrixUDT].getName.hashCode()
43cdb89 [Alok Singh] [SPARK-8647][MLlib] Potential issue with constant hashCode
I've updated default values in comments, documentation, and in the command line builder to be 1g based on comments in the JIRA. I've also updated most usages to point at a single variable defined in the Utils.scala and JavaUtils.java files. This wasn't possible in all cases (R, shell scripts etc.) but usage in most code is now pointing at the same place.
Please let me know if I've missed anything.
Will the spark-shell use the value within the command line builder during instantiation?
Author: Ilya Ganelin <ilya.ganelin@capitalone.com>
Closes#7132 from ilganeli/SPARK-3071 and squashes the following commits:
4074164 [Ilya Ganelin] String fix
271610b [Ilya Ganelin] Merge branch 'SPARK-3071' of github.com:ilganeli/spark into SPARK-3071
273b6e9 [Ilya Ganelin] Test fix
fd67721 [Ilya Ganelin] Update JavaUtils.java
26cc177 [Ilya Ganelin] test fix
e5db35d [Ilya Ganelin] Fixed test failure
39732a1 [Ilya Ganelin] merge fix
a6f7deb [Ilya Ganelin] Created default value for DRIVER MEM in Utils that's now used in almost all locations instead of setting manually in each
09ad698 [Ilya Ganelin] Update SubmitRestProtocolSuite.scala
19b6f25 [Ilya Ganelin] Missed one doc update
2698a3d [Ilya Ganelin] Updated default value for driver memory
'>' symbols removed from comments in LogisticRegressionSuite.scala, for ease of copypaste
also single-lined the multiline commands (is this desirable, or does it violate style?)
Author: Rosstin <asterazul@gmail.com>
Closes#7167 from Rosstin/SPARK-8660-2 and squashes the following commits:
f4b9bc8 [Rosstin] SPARK-8660 restored character limit on multiline comments in LogisticRegressionSuite.scala
fe6b112 [Rosstin] SPARK-8660 > symbols removed from LogisticRegressionSuite.scala for easy of copypaste
39ddd50 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8661
5a05dee [Rosstin] SPARK-8661 for LinearRegressionSuite.scala, changed javadoc-style comments to regular multiline comments to make it easier to copy-paste the R code.
bb9a4b1 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8660
242aedd [Rosstin] SPARK-8660, changed comment style from JavaDoc style to normal multiline comment in order to make copypaste into R easier, in file classification/LogisticRegressionSuite.scala
2cd2985 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
21ac1e5 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
6c18058 [Rosstin] fixed minor typos in docs/README.md and docs/api.md
Rename DiscreteCosineTransformer and related classes to DCT.
Author: Feynman Liang <fliang@databricks.com>
Closes#7138 from feynmanliang/dct-features and squashes the following commits:
e547b3e [Feynman Liang] Fix renaming bug
9d5c9e4 [Feynman Liang] Lowercase JavaDCTSuite variable
f9a8958 [Feynman Liang] Remove old files
f8fe794 [Feynman Liang] Merge branch 'master' into dct-features
894d0b2 [Feynman Liang] Rename DiscreteCosineTransformer to DCT
433dbc7 [Feynman Liang] Test refactoring
91e9636 [Feynman Liang] Style guide and test helper refactor
b5ac19c [Feynman Liang] Use Vector types, add Java test
530983a [Feynman Liang] Tests for other numeric datatypes
195d7aa [Feynman Liang] Implement support for arbitrary numeric types
95d4939 [Feynman Liang] Working DCT for 1D Doubles
I'm sorry that I made https://github.com/apache/spark/pull/6949 closed by mistake.
I pushed codes again.
And, I added a test code.
>
There is a bug that `U.numCols() = self.nCols` in `IndexedRowMatrix.computeSVD()`
It should have been `U.numCols() = k = svd.U.numCols()`
>
```
self = U * sigma * V.transpose
(m x n) = (m x n) * (k x k) * (k x n) //ASIS
-->
(m x n) = (m x k) * (k x k) * (k x n) //TOBE
```
Author: lee19 <lee19@live.co.kr>
Closes#6953 from lee19/MLlibBugfix and squashes the following commits:
c1812a0 [lee19] [SPARK-8563] [MLlib] Used nRows instead of numRows() to reduce a burden.
4b9803b [lee19] [SPARK-8563] [MLlib] Fixed a build error.
c2ccd89 [lee19] Added a unit test that validates matrix sizes of svd for [SPARK-8563][MLlib]
8373424 [lee19] [SPARK-8563][MLlib] Fixed a bug so that IndexedRowMatrix.computeSVD().U.numCols = k
Changed GBTRegressor so it does NOT threshold the prediction. Added test which fails with bug but works after fix.
CC: feynmanliang mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#7134 from jkbradley/gbrt-fix and squashes the following commits:
613b90e [Joseph K. Bradley] Changed GBTRegressor so it does NOT threshold the prediction
jira: https://issues.apache.org/jira/browse/SPARK-7514
Add a popular scaling method to feature component, which is commonly known as min-max normalization or Rescaling.
Core function is,
Normalized(x) = (x - min) / (max - min) * scale + newBase
where `newBase` and `scale` are parameters (type Double) of the `VectorTransformer`. `newBase` is the new minimum number for the features, and `scale` controls the ranges after transformation. This is a little complicated than the basic MinMax normalization, yet it provides flexibility so that users can control the range more specifically. like [0.1, 0.9] in some NN application.
For case that `max == min`, 0.5 is used as the raw value. (0.5 * scale + newBase)
I'll add UT once the design got settled ( and this is not considered as too naive)
reference:
http://en.wikipedia.org/wiki/Feature_scalinghttp://stn.spotfire.com/spotfire_client_help/index.htm#norm/norm_scale_between_0_and_1.htm
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#6039 from hhbyyh/minMaxNorm and squashes the following commits:
f942e9f [Yuhao Yang] add todo for metadata
8b37bbc [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
4894dbc [Yuhao Yang] add copy
fa2989f [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
29db415 [Yuhao Yang] add clue and minor adjustment
5b8f7cc [Yuhao Yang] style fix
9b133d0 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
22f20f2 [Yuhao Yang] style change and bug fix
747c9bb [Yuhao Yang] add ut and remove mllib version
a5ba0aa [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
585cc07 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
1c6dcb1 [Yuhao Yang] minor change
0f1bc80 [Yuhao Yang] add MinMaxScaler to ml
8e7436e [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
3663165 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into minMaxNorm
1247c27 [Yuhao Yang] some comments improvement
d285a19 [Yuhao Yang] initial checkin for minMaxNorm
Implementation and tests for Discrete Cosine Transformer.
Author: Feynman Liang <fliang@databricks.com>
Closes#6894 from feynmanliang/dct-features and squashes the following commits:
433dbc7 [Feynman Liang] Test refactoring
91e9636 [Feynman Liang] Style guide and test helper refactor
b5ac19c [Feynman Liang] Use Vector types, add Java test
530983a [Feynman Liang] Tests for other numeric datatypes
195d7aa [Feynman Liang] Implement support for arbitrary numeric types
95d4939 [Feynman Liang] Working DCT for 1D Doubles
Add PCA transformer for ML pipeline
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7065 from yanboliang/spark-8664 and squashes the following commits:
4afae45 [Yanbo Liang] address comments
e9effd7 [Yanbo Liang] Add PCA transformer
for mllib/src/test/scala/org/apache/spark/ml/regression/LinearRegressionSuite.scala, changed javadoc-style comments to regular multiline comments, to make copy-pasting R code more simple
Author: Rosstin <asterazul@gmail.com>
Closes#7098 from Rosstin/SPARK-8661 and squashes the following commits:
5a05dee [Rosstin] SPARK-8661 for LinearRegressionSuite.scala, changed javadoc-style comments to regular multiline comments to make it easier to copy-paste the R code.
bb9a4b1 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8660
242aedd [Rosstin] SPARK-8660, changed comment style from JavaDoc style to normal multiline comment in order to make copypaste into R easier, in file classification/LogisticRegressionSuite.scala
2cd2985 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
21ac1e5 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
6c18058 [Rosstin] fixed minor typos in docs/README.md and docs/api.md
Converted JavaDoc style comments in mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala to regular multiline comments, to make copy-pasting R commands easier.
Author: Rosstin <asterazul@gmail.com>
Closes#7096 from Rosstin/SPARK-8660 and squashes the following commits:
242aedd [Rosstin] SPARK-8660, changed comment style from JavaDoc style to normal multiline comment in order to make copypaste into R easier, in file classification/LogisticRegressionSuite.scala
2cd2985 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
21ac1e5 [Rosstin] Merge branch 'master' of github.com:apache/spark into SPARK-8639
6c18058 [Rosstin] fixed minor typos in docs/README.md and docs/api.md
Follow up of [SPARK-8356](https://issues.apache.org/jira/browse/SPARK-8356) and #6902.
Removes the unit test for the now deprecated ```callUdf```
Unit test in SQLQuerySuite now uses ```udf``` instead of ```callUDF```
Replaced ```callUDF``` by ```udf``` where possible in mllib
Author: BenFradet <benjamin.fradet@gmail.com>
Closes#6993 from BenFradet/SPARK-8575 and squashes the following commits:
26f5a7a [BenFradet] 2 spaces instead of 1
1ddb452 [BenFradet] renamed initUDF in order to be consistent in OneVsRest
48ca15e [BenFradet] used vector type tag for udf call in VectorIndexer
0ebd0da [BenFradet] replace the now deprecated callUDF by udf in VectorIndexer
8013409 [BenFradet] replaced the now deprecated callUDF by udf in Predictor
94345b5 [BenFradet] unifomized udf calls in ProbabilisticClassifier
1305492 [BenFradet] uniformized udf calls in Classifier
a672228 [BenFradet] uniformized udf calls in OneVsRest
49e4904 [BenFradet] Revert "removal of the unit test for the now deprecated callUdf"
bbdeaf3 [BenFradet] fixed syntax for init udf in OneVsRest
fe2a10b [BenFradet] callUDF => udf in ProbabilisticClassifier
0ea30b3 [BenFradet] callUDF => udf in Classifier where possible
197ec82 [BenFradet] callUDF => udf in OneVsRest
84d6780 [BenFradet] modified unit test in SQLQuerySuite to use udf instead of callUDF
477709f [BenFradet] removal of the unit test for the now deprecated callUdf
Python support for Power Iteration Clustering
https://issues.apache.org/jira/browse/SPARK-5962
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6992 from yanboliang/pyspark-pic and squashes the following commits:
6b03d82 [Yanbo Liang] address comments
4be4423 [Yanbo Liang] Python support for Power Iteration Clustering
Support mining of ordered frequent item sequences.
Author: Feynman Liang <fliang@databricks.com>
Closes#6997 from feynmanliang/fp-sequence and squashes the following commits:
7c14e15 [Feynman Liang] Improve scalatests with R code and Seq
0d3e4b6 [Feynman Liang] Fix python test
ce987cb [Feynman Liang] Backwards compatibility aux constructor
34ef8f2 [Feynman Liang] Fix failing test due to reverse orderering
f04bd50 [Feynman Liang] Naming, add ordered to FreqItemsets, test ordering using Seq
648d4d4 [Feynman Liang] Test case for frequent item sequences
252a36a [Feynman Liang] Add sequence learning flag
Spark's tests currently depend on `mockito-all`, which bundles Hamcrest and Objenesis classes. Instead, it should depend on `mockito-core`, which declares those libraries as Maven dependencies. This is necessary in order to fix a dependency conflict that leads to a NoSuchMethodError when using certain Hamcrest matchers.
See https://github.com/mockito/mockito/wiki/Declaring-mockito-dependency for more details.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7061 from JoshRosen/mockito-core-instead-of-all and squashes the following commits:
70eccbe [Josh Rosen] Depend on mockito-core instead of mockito-all.
Add a param to disable linear feature scaling (to be implemented later in linear & logistic regression). Done as a seperate PR so we can use same param & not conflict while working on the sub-tasks.
Author: Holden Karau <holden@pigscanfly.ca>
Closes#7024 from holdenk/SPARK-8522-Disable-Linear_featureScaling-Spark-8613-Add-param and squashes the following commits:
ce8931a [Holden Karau] Regenerate the sharedParams code
fa6427e [Holden Karau] update text for standardization param.
7b24a2b [Holden Karau] generate the new standardization param
3c190af [Holden Karau] Add the standardization param to sharedparamscodegen
Keep the same naming conventions for PythonMLLibAPI.
Only the following three functions is different from others
```scala
trainNaiveBayes
trainGaussianMixture
trainWord2Vec
```
So change them to
```scala
trainNaiveBayesModel
trainGaussianMixtureModel
trainWord2VecModel
```
It does not affect any users and public APIs, only to make better understand for developer and code hacker.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#7011 from yanboliang/py-mllib-api-rename and squashes the following commits:
771ffec [Yanbo Liang] rename some functions of PythonMLLibAPI
fix LabeledPoint parser when there is a whitespace between label and features vector, e.g.
(y, [x1, x2, x3])
Author: Oleksiy Dyagilev <oleksiy_dyagilev@epam.com>
Closes#6954 from fe2s/SPARK-8525 and squashes the following commits:
0755b9d [Oleksiy Dyagilev] [SPARK-8525][MLLIB] addressing comment, removing dep on commons-lang
c1abc2b [Oleksiy Dyagilev] [SPARK-8525][MLLIB] fix LabeledPoint parser when there is a whitespace on specific position
It is useful to generate linear data for easy testing of linear models and in general. Scala already has it. This is just a wrapper around the Scala code.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6715 from MechCoder/generate_linear_input and squashes the following commits:
6182884 [MechCoder] Minor changes
8bda047 [MechCoder] Minor style fixes
0f1053c [MechCoder] [SPARK-8265] Add LinearDataGenerator to pyspark.mllib.utils
Author: Holden Karau <holden@pigscanfly.ca>
Closes#6927 from holdenk/SPARK-7888-Be-able-to-disable-intercept-in-Linear-Regression-in-ML-package and squashes the following commits:
0ad384c [Holden Karau] Add MiMa excludes
4016fac [Holden Karau] Switch to wild card import, remove extra blank lines
ae5baa8 [Holden Karau] CR feedback, move the fitIntercept down rather than changing ymean and etc above
f34971c [Holden Karau] Fix some more long lines
319bd3f [Holden Karau] Fix long lines
3bb9ee1 [Holden Karau] Update the regression suite tests
7015b9f [Holden Karau] Our code performs the same with R, except we need more than one data point but that seems reasonable
0b0c8c0 [Holden Karau] fix the issue with the sample R code
e2140ba [Holden Karau] Add a test, it fails!
5e84a0b [Holden Karau] Write out thoughts and use the correct trait
91ffc0a [Holden Karau] more murh
006246c [Holden Karau] murp?
Author: Holden Karau <holden@pigscanfly.ca>
Closes#6331 from holdenk/SPARK-7781-GradientBoostedTrees.trainRegressor-missing-max-bins and squashes the following commits:
2894695 [Holden Karau] remove extra blank line
2573e8d [Holden Karau] Update the scala side of the pythonmllibapi and make the test a bit nicer too
3a09170 [Holden Karau] add maxBins to to the train method as well
af7f274 [Holden Karau] Add maxBins to GradientBoostedTrees.trainRegressor and correctly mention the default of 32 in other places where it mentioned 100
Implementation of n-gram feature transformer for ML.
Author: Feynman Liang <fliang@databricks.com>
Closes#6887 from feynmanliang/ngram-featurizer and squashes the following commits:
d2c839f [Feynman Liang] Make n > input length yield empty output
9fadd36 [Feynman Liang] Add empty and corner test cases, fix names and spaces
fe93873 [Feynman Liang] Implement n-gram feature transformer
Updated `Attribute.fromStructField` to allow any `NumericType`, rather than just `DoubleType`, and added unit tests for a few of the other NumericTypes.
Author: Mike Dusenberry <dusenberrymw@gmail.com>
Closes#6540 from dusenberrymw/SPARK-7426_AttributeFactory.fromStructField_Should_Allow_NumericTypes and squashes the following commits:
87fecb3 [Mike Dusenberry] Updated Attribute.fromStructField to allow any NumericType, rather than just DoubleType, and added unit tests for a few of the other NumericTypes.
Python API for PCA and PCAModel
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6315 from yanboliang/spark-7604 and squashes the following commits:
1d58734 [Yanbo Liang] remove transform() in PCAModel, use default behavior
4d9d121 [Yanbo Liang] Python API for PCA and PCAModel
JIRA: https://issues.apache.org/jira/browse/SPARK-8468
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#6905 from viirya/cv_min and squashes the following commits:
930d3db [Liang-Chi Hsieh] Fix python unit test and add document.
d632135 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into cv_min
16e3b2c [Liang-Chi Hsieh] Take the negative instead of reciprocal.
c3dd8d9 [Liang-Chi Hsieh] For comments.
b5f52c1 [Liang-Chi Hsieh] Add param to CrossValidator for choosing whether to maximize evaulation value.
Python bindings for StreamingKMeans
Will change status to MRG once docs, tests and examples are updated.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6499 from MechCoder/spark-4118 and squashes the following commits:
7722d16 [MechCoder] minor style fixes
51052d3 [MechCoder] Doc fixes
2061a76 [MechCoder] Add tests for simultaneous training and prediction Minor style fixes
81482fd [MechCoder] minor
5d9fe61 [MechCoder] predictOn should take into account the latest model
8ab9e89 [MechCoder] Fix Python3 error
a9817df [MechCoder] Better tests and minor fixes
c80e451 [MechCoder] Add ignore_unicode_prefix
ee8ce16 [MechCoder] Update tests, doc and examples
4b1481f [MechCoder] Some changes and tests
d8b066a [MechCoder] [SPARK-4118] [MLlib] [PySpark] Python bindings for StreamingKMeans
Python API for org.apache.spark.mllib.feature.ElementwiseProduct
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6346 from MechCoder/spark-7605 and squashes the following commits:
79d1ef5 [MechCoder] Consistent and support list / array types
5f81d81 [MechCoder] [SPARK-7605] [MLlib] Python API for ElementwiseProduct
MatrixUDT was recently coded in scala. This has been ported to PySpark
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6354 from MechCoder/spark-6390 and squashes the following commits:
fc4dc1e [MechCoder] Better error message
c940a44 [MechCoder] Added test
aa9c391 [MechCoder] Add pyUDT to MatrixUDT
62a2a7d [MechCoder] [SPARK-6390] Port MatrixUDT to PySpark
Check then make the MLlib Python classification and regression doc to be as complete as the Scala doc.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6460 from yanboliang/spark-7916 and squashes the following commits:
f8deda4 [Yanbo Liang] trigger jenkins
6dc4d99 [Yanbo Liang] address comments
ce2a43e [Yanbo Liang] truncate too long line and remove extra sparse
3eaf6ad [Yanbo Liang] MLlib Python doc parity check for classification and regression
MLUtils.appendBias method is heavily used in creating intercepts for linear models.
This method uses Breeze's vector concatenation which is very slow compared to the plain
System.arrayCopy. This improvement is to change the implementation to use System.arrayCopy.
I saw the following performance improvements after the change:
Benchmark with mnist dataset for 50 times:
MLUtils.appendBias (SparseVector Before): 47320 ms
MLUtils.appendBias (SparseVector After): 1935 ms
MLUtils.appendBias (DenseVector Before): 5340 ms
MLUtils.appendBias (DenseVector After): 4080 ms
This is almost a 24 times performance boost for SparseVectors.
Author: Roger Menezes <rmenezes@netflix.com>
Closes#6768 from rogermenezes/improve-append-bias and squashes the following commits:
4e42f75 [Roger Menezes] address feedback
e999d79 [Roger Menezes] first commit
Test cases for both StreamingLinearRegression and StreamingLogisticRegression, and code fix.
Edit:
This contribution is my original work and I license the work to the project under the project's open source license.
Author: Paavo <pparkkin@gmail.com>
Closes#6713 from pparkkin/streamingmodel-empty-rdd and squashes the following commits:
ff5cd78 [Paavo] Update strings to use interpolation.
db234cf [Paavo] Use !rdd.isEmpty.
54ad89e [Paavo] Test case for empty stream.
393e36f [Paavo] Ignore empty RDDs.
0bfc365 [Paavo] Test case for empty stream.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6720 from MechCoder/empty_model_check and squashes the following commits:
3a07de5 [MechCoder] Remove construct to get weights in StreamingLinearAlgorithm
This makes the constructor callable in Python. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#6709 from mengxr/SPARK-8168 and squashes the following commits:
f871de4 [Xiangrui Meng] Add Python friendly constructor to PipelineModel
1. Prevent creating a map of data to find numFeatures
2. If model is empty, then initialize with a zero vector of numFeature
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6684 from MechCoder/spark-8140 and squashes the following commits:
7fbf5f9 [MechCoder] [SPARK-8140] Remove empty model check in StreamingLinearAlgorithm And other minor cosmits
Python API for KernelDensity
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6387 from MechCoder/spark-7639 and squashes the following commits:
17abc62 [MechCoder] add tests
2de6540 [MechCoder] style tests
bf4acc0 [MechCoder] Added doctests
84359d5 [MechCoder] [SPARK-7639] Python API for KernelDensity
Added stats from cross validation as a val in the cross validation model to save them for user access.
Author: leahmcguire <lmcguire@salesforce.com>
Closes#5915 from leahmcguire/saveCVmetrics and squashes the following commits:
49b507b [leahmcguire] fixed tyle error
67537b1 [leahmcguire] rebased
85907f0 [leahmcguire] fixed name
59987cc [leahmcguire] changed param name and test according to comments
36e71e3 [leahmcguire] rebasing
4b8223e [leahmcguire] fixed name
4ddffc6 [leahmcguire] changed param name and test according to comments
3a995da [leahmcguire] Added stats from cross validation as a val in the cross validation model to save them for user access
This is just a workaround to a bigger problem. Some pipeline stages may not be effective during prediction, and they should not complain about missing required columns, e.g. `StringIndexerModel`. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6595 from mengxr/SPARK-8051 and squashes the following commits:
b6a36b9 [Xiangrui Meng] add doc
f143fd4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-8051
8ee7c7e [Xiangrui Meng] use SparkFunSuite
e112394 [Xiangrui Meng] make StringIndexerModel silent if input column does not exist
Java-friendly APIs added:
* GaussianMixture.run()
* GaussianMixtureModel.predict()
* DistributedLDAModel.javaTopicDistributions()
* StreamingKMeans: trainOn, predictOn, predictOnValues
* Statistics.corr
* params
* added doc to w() since Java docs do not inherit doc
* removed non-Java-friendly w() from StringArrayParam and DoubleArrayParam
* made DoubleArrayParam Java-friendly w() actually Java-friendly
I generated the doc and verified all changes.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6562 from jkbradley/java-api-1.4 and squashes the following commits:
c16821b [Joseph K. Bradley] Small fixes based on code review.
d955581 [Joseph K. Bradley] unit test fixes
29b6b0d [Joseph K. Bradley] small fixes
fe6dcfe [Joseph K. Bradley] Added several Java-friendly APIs + unit tests: NaiveBayes, GaussianMixture, LDA, StreamingKMeans, Statistics.corr, params
Author: Patrick Wendell <patrick@databricks.com>
Closes#6328 from pwendell/spark-1.5-update and squashes the following commits:
2f42d02 [Patrick Wendell] A few more excludes
4bebcf0 [Patrick Wendell] Update to RC4
61aaf46 [Patrick Wendell] Using new release candidate
55f1610 [Patrick Wendell] Another exclude
04b4f04 [Patrick Wendell] More issues with transient 1.4 changes
36f549b [Patrick Wendell] [SPARK-7801] [BUILD] Updating versions to SPARK 1.5.0
jira: https://issues.apache.org/jira/browse/SPARK-7983
Customers frequently use zero-based indices in their LIBSVM files. No warnings or errors from Spark will be reported during their computation afterwards, and usually it will lead to wired result for many algorithms (like GBDT).
add a quick check.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#6538 from hhbyyh/loadSVM and squashes the following commits:
79d9c11 [Yuhao Yang] optimization as respond to comments
4310710 [Yuhao Yang] merge conflict
96460f1 [Yuhao Yang] merge conflict
20a2811 [Yuhao Yang] use require
6e4f8ca [Yuhao Yang] add check for ascending order
9956365 [Yuhao Yang] add ut for 0-based loadlibsvm exception
5bd1f9a [Yuhao Yang] add require for one-based in loadLIBSVM
I searched the Spark codebase for all occurrences of "scalingVector"
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6596 from jkbradley/scalingVec-rename and squashes the following commits:
d3812f8 [Joseph K. Bradley] renamed scalingVector to scalingVec
This patch significantly refactors CatalystTypeConverters to both clean up the code and enable these conversions to work with future Project Tungsten features.
At a high level, I've reorganized the code so that all functions dealing with the same type are grouped together into type-specific subclasses of `CatalystTypeConveter`. In addition, I've added new methods that allow the Catalyst Row -> Scala Row conversions to access the Catalyst row's fields through type-specific `getTYPE()` methods rather than the generic `get()` / `Row.apply` methods. This refactoring is a blocker to being able to unit test new operators that I'm developing as part of Project Tungsten, since those operators may output `UnsafeRow` instances which don't support the generic `get()`.
The stricter type usage of types here has uncovered some bugs in other parts of Spark SQL:
- #6217: DescribeCommand is assigned wrong output attributes in SparkStrategies
- #6218: DataFrame.describe() should cast all aggregates to String
- #6400: Use output schema, not relation schema, for data source input conversion
Spark SQL current has undefined behavior for what happens when you try to create a DataFrame from user-specified rows whose values don't match the declared schema. According to the `createDataFrame()` Scaladoc:
> It is important to make sure that the structure of every [[Row]] of the provided RDD matches the provided schema. Otherwise, there will be runtime exception.
Given this, it sounds like it's technically not a break of our API contract to fail-fast when the data types don't match. However, there appear to be many cases where we don't fail even though the types don't match. For example, `JavaHashingTFSuite.hasingTF` passes a column of integers values for a "label" column which is supposed to contain floats. This column isn't actually read or modified as part of query processing, so its actual concrete type doesn't seem to matter. In other cases, there could be situations where we have generic numeric aggregates that tolerate being called with different numeric types than the schema specified, but this can be okay due to numeric conversions.
In the long run, we will probably want to come up with precise semantics for implicit type conversions / widening when converting Java / Scala rows to Catalyst rows. Until then, though, I think that failing fast with a ClassCastException is a reasonable behavior; this is the approach taken in this patch. Note that certain optimizations in the inbound conversion functions for primitive types mean that we'll probably preserve the old undefined behavior in a majority of cases.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#6222 from JoshRosen/catalyst-converters-refactoring and squashes the following commits:
740341b [Josh Rosen] Optimize method dispatch for primitive type conversions
befc613 [Josh Rosen] Add tests to document Option-handling behavior.
5989593 [Josh Rosen] Use new SparkFunSuite base in CatalystTypeConvertersSuite
6edf7f8 [Josh Rosen] Re-add convertToScala(), since a Hive test still needs it
3f7b2d8 [Josh Rosen] Initialize converters lazily so that the attributes are resolved first
6ad0ebb [Josh Rosen] Fix JavaHashingTFSuite ClassCastException
677ff27 [Josh Rosen] Fix null handling bug; add tests.
8033d4c [Josh Rosen] Fix serialization error in UserDefinedGenerator.
85bba9d [Josh Rosen] Fix wrong input data in InMemoryColumnarQuerySuite
9c0e4e1 [Josh Rosen] Remove last use of convertToScala().
ae3278d [Josh Rosen] Throw ClassCastException errors during inbound conversions.
7ca7fcb [Josh Rosen] Comments and cleanup
1e87a45 [Josh Rosen] WIP refactoring of CatalystTypeConverters
This is scala example code for both linear and logistic regression. Python and Java versions are to be added.
Author: DB Tsai <dbt@netflix.com>
Closes#6576 from dbtsai/elasticNetExample and squashes the following commits:
e7ca406 [DB Tsai] fix test
6bb6d77 [DB Tsai] fix suite and remove duplicated setMaxIter
136e0dd [DB Tsai] address feedback
1ec29d4 [DB Tsai] fix style
9462f5f [DB Tsai] add example
The temporary column should be dropped after we get the prediction column. harsha2010
Author: Xiangrui Meng <meng@databricks.com>
Closes#6592 from mengxr/SPARK-8049 and squashes the following commits:
1d89107 [Xiangrui Meng] use SparkFunSuite
6ee70de [Xiangrui Meng] drop tmp col from OneVsRest output
Updating ML Doc's *"Estimator, Transformer, and Param"* example to use `model.extractParamMap` instead of `model.fittingParamMap`, which no longer exists.
mengxr, I believe this addresses (part of) the *update documentation* TODO list item from [PR 5820](https://github.com/apache/spark/pull/5820).
Author: Mike Dusenberry <dusenberrymw@gmail.com>
Closes#6514 from dusenberrymw/Fix_ML_Doc_Estimator_Transformer_Param_Example and squashes the following commits:
6366e1f [Mike Dusenberry] Updating instances of model.extractParamMap to model.parent.extractParamMap, since the Params of the parent Estimator could possibly differ from thos of the Model.
d850e0e [Mike Dusenberry] Removing all references to "fittingParamMap" throughout Spark, since it has been removed.
0480304 [Mike Dusenberry] Updating the ML Doc "Estimator, Transformer, and Param" Java example to use model.extractParamMap() instead of model.fittingParamMap(), which no longer exists.
7d34939 [Mike Dusenberry] Updating ML Doc "Estimator, Transformer, and Param" example to use model.extractParamMap instead of model.fittingParamMap, which no longer exists.
This PR adds a Java unit test and user guide for `StringIndexer`. I put it before `OneHotEncoder` because they are closely related. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6561 from mengxr/SPARK-7582 and squashes the following commits:
4bba4f1 [Xiangrui Meng] fix example
ba1cd1b [Xiangrui Meng] fix style
7fa18d1 [Xiangrui Meng] add user guide for StringIndexer
136cb93 [Xiangrui Meng] add a Java unit test for StringIndexer
This PR adds a section in the user guide for `VectorAssembler` with code examples in Python/Java/Scala. It also adds a unit test in Java.
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6556 from mengxr/SPARK-7584 and squashes the following commits:
11313f6 [Xiangrui Meng] simplify Java example
0cd47f3 [Xiangrui Meng] update user guide
fd36292 [Xiangrui Meng] update Java unit test
ce61ca0 [Xiangrui Meng] add Java unit test for VectorAssembler
e399942 [Xiangrui Meng] scala/python example code
Author: Reynold Xin <rxin@databricks.com>
Closes#6534 from rxin/whitespace-mllib and squashes the following commits:
38926e3 [Reynold Xin] [SPARK-3850] Trim trailing spaces for MLlib.
The MLlib ChiSqSelector class is not serializable, and so the example in the ChiSqSelector documentation fails. Also, that example is missing the import of ChiSqSelector.
This PR makes ChiSqSelector extend Serializable in MLlib, and adds the ChiSqSelector import statement to the associated example in the documentation.
Author: Mike Dusenberry <dusenberrymw@gmail.com>
Closes#6462 from dusenberrymw/Make_ChiSqSelector_Serializable_and_Fix_Related_Docs_Example and squashes the following commits:
9cb2f94 [Mike Dusenberry] Make MLlib ChiSqSelector Serializable.
d9003bf [Mike Dusenberry] Add missing import in MLlib ChiSqSelector Docs Scala example.
This patch fixes a build break in maven caused by #6441.
Note that this patch reverts the changes in flume-sink because
this module does not currently depend on Spark core, but the
tests require it. There is not an easy way to make this work
because mvn test dependencies are not transitive (MNG-1378).
For now, we will leave the one test suite in flume-sink out
until we figure out a better solution. This patch is mainly
intended to unbreak the maven build.
Author: Andrew Or <andrew@databricks.com>
Closes#6511 from andrewor14/fix-build-mvn and squashes the following commits:
3d53643 [Andrew Or] [HOT FIX#6441] Fix maven build failures
Right now `unit-tests.log` are not of much value because we can't tell where the test boundaries are easily. This patch adds log statements before and after each test to outline the test boundaries, e.g.:
```
===== TEST OUTPUT FOR o.a.s.serializer.KryoSerializerSuite: 'kryo with parallelize for primitive arrays' =====
15/05/27 12:36:39.596 pool-1-thread-1-ScalaTest-running-KryoSerializerSuite INFO SparkContext: Starting job: count at KryoSerializerSuite.scala:230
15/05/27 12:36:39.596 dag-scheduler-event-loop INFO DAGScheduler: Got job 3 (count at KryoSerializerSuite.scala:230) with 4 output partitions (allowLocal=false)
15/05/27 12:36:39.596 dag-scheduler-event-loop INFO DAGScheduler: Final stage: ResultStage 3(count at KryoSerializerSuite.scala:230)
15/05/27 12:36:39.596 dag-scheduler-event-loop INFO DAGScheduler: Parents of final stage: List()
15/05/27 12:36:39.597 dag-scheduler-event-loop INFO DAGScheduler: Missing parents: List()
15/05/27 12:36:39.597 dag-scheduler-event-loop INFO DAGScheduler: Submitting ResultStage 3 (ParallelCollectionRDD[5] at parallelize at KryoSerializerSuite.scala:230), which has no missing parents
...
15/05/27 12:36:39.624 pool-1-thread-1-ScalaTest-running-KryoSerializerSuite INFO DAGScheduler: Job 3 finished: count at KryoSerializerSuite.scala:230, took 0.028563 s
15/05/27 12:36:39.625 pool-1-thread-1-ScalaTest-running-KryoSerializerSuite INFO KryoSerializerSuite:
***** FINISHED o.a.s.serializer.KryoSerializerSuite: 'kryo with parallelize for primitive arrays' *****
...
```
Author: Andrew Or <andrew@databricks.com>
Closes#6441 from andrewor14/demarcate-tests and squashes the following commits:
879b060 [Andrew Or] Fix compile after rebase
d622af7 [Andrew Or] Merge branch 'master' of github.com:apache/spark into demarcate-tests
017c8ba [Andrew Or] Merge branch 'master' of github.com:apache/spark into demarcate-tests
7790b6c [Andrew Or] Fix tests after logical merge conflict
c7460c0 [Andrew Or] Merge branch 'master' of github.com:apache/spark into demarcate-tests
c43ffc4 [Andrew Or] Fix tests?
8882581 [Andrew Or] Fix tests
ee22cda [Andrew Or] Fix log message
fa9450e [Andrew Or] Merge branch 'master' of github.com:apache/spark into demarcate-tests
12d1e1b [Andrew Or] Various whitespace changes (minor)
69cbb24 [Andrew Or] Make all test suites extend SparkFunSuite instead of FunSuite
bbce12e [Andrew Or] Fix manual things that cannot be covered through automation
da0b12f [Andrew Or] Add core tests as dependencies in all modules
f7d29ce [Andrew Or] Introduce base abstract class for all test suites
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6497 from MechCoder/spark-7946 and squashes the following commits:
2fdd0a3 [MechCoder] Add non-regression test
8c988c6 [MechCoder] [SPARK-7946] DecayFactor wrongly set in StreamingKMeans
This PR contains two major changes to `OneHotEncoder`:
1. more robust handling of ML attributes. If the input attribute is unknown, we look at the values to get the max category index
2. change `includeFirst` to `dropLast` and leave the default to `true`. There are couple benefits:
a. consistent with other tutorials of one-hot encoding (or dummy coding) (e.g., http://www.ats.ucla.edu/stat/mult_pkg/faq/general/dummy.htm)
b. keep the indices unmodified in the output vector. If we drop the first, all indices will be shifted by 1.
c. If users use `StringIndex`, the last element is the least frequent one.
Sorry for including two changes in one PR! I'll update the user guide in another PR.
jkbradley sryza
Author: Xiangrui Meng <meng@databricks.com>
Closes#6466 from mengxr/SPARK-7912 and squashes the following commits:
a280dca [Xiangrui Meng] fix tests
d8f234d [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7912
171b276 [Xiangrui Meng] mention the difference between our impl vs sklearn's
00dfd96 [Xiangrui Meng] update OneHotEncoder in Python
208ddad [Xiangrui Meng] update OneHotEncoder to handle ML attributes and change includeFirst to dropLast
Expose user/item factors in DataFrames. This is to be more consistent with the pipeline API. It also helps maintain consistent APIs across languages. This PR also removed fitting params from `ALSModel`.
coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#6468 from mengxr/SPARK-7922 and squashes the following commits:
7bfb1d5 [Xiangrui Meng] update ALSModel in PySpark
1ba5607 [Xiangrui Meng] use DataFrames for user/item factors in ALS
`VectorAssembler` should carry over ML attributes. For unknown attributes, we assume numeric values. This PR handles the following cases:
1. DoubleType with ML attribute: carry over
2. DoubleType without ML attribute: numeric value
3. Scalar type: numeric value
4. VectorType with all ML attributes: carry over and update names
5. VectorType with number of ML attributes: assume all numeric
6. VectorType without ML attributes: check the first row and get the number of attributes
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6452 from mengxr/SPARK-7198 and squashes the following commits:
a9d2469 [Xiangrui Meng] add space
facdb1f [Xiangrui Meng] VectorAssembler should output ML attributes
~~A PythonUDT shouldn't be serialized into external Scala types in PythonRDD. I'm not sure whether this should fix one of the bugs related to SQL UDT/UDF in PySpark.~~
The fix above didn't work. So I added a workaround for this. If a Python UDF is applied to a Python UDT. This will put the Python SQL types as inputs. Still incorrect, but at least it doesn't throw exceptions on the Scala side. davies harsha2010
Author: Xiangrui Meng <meng@databricks.com>
Closes#6442 from mengxr/SPARK-7903 and squashes the following commits:
c257d2a [Xiangrui Meng] add a workaround for VectorUDT
With descent coverage of feature transformers, algorithms, and model tuning support, it is time to graduate `spark.ml` from alpha. This PR changes all `AlphaComponent` annotations to either `DeveloperApi` or `Experimental`, depending on whether we expect a class/method to be used by end users (who use the pipeline API to assemble/tune their ML pipelines but not to create new pipeline components.) `UnaryTransformer` becomes a `DeveloperApi` in this PR.
jkbradley harsha2010
Author: Xiangrui Meng <meng@databricks.com>
Closes#6417 from mengxr/SPARK-7748 and squashes the following commits:
effbccd [Xiangrui Meng] organize imports
c15028e [Xiangrui Meng] added missing docs
1b2e5f8 [Xiangrui Meng] update package doc
73ca791 [Xiangrui Meng] alpha -> ex/dev for the rest
93819db [Xiangrui Meng] alpha -> ex/dev in ml.param
55ca073 [Xiangrui Meng] alpha -> ex/dev in ml.feature
83572f1 [Xiangrui Meng] add Experimental and DeveloperApi tags (wip)
The densities in KernelDensity are scaled down by
(number of parallel processes X number of points). It should be just no.of samples. This results in broken tests in KernelDensitySuite which haven't been tested properly.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#6383 from MechCoder/spark-7844 and squashes the following commits:
ab81302 [MechCoder] Math->math
9b8ed50 [MechCoder] Make one pass to update count
a92fe50 [MechCoder] [SPARK-7844] Fix broken tests in KernelDensity
Added user guide sections with code examples.
Also added small Java unit tests to test Java example in guide.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6127 from jkbradley/feature-guide-2 and squashes the following commits:
cd47f4b [Joseph K. Bradley] Updated based on code review
f16bcec [Joseph K. Bradley] Fixed merge issues and update Python examples print calls for Python 3
0a862f9 [Joseph K. Bradley] Added Normalizer, StandardScaler to ml-features doc, plus small Java unit tests
a21c2d6 [Joseph K. Bradley] Updated ml-features.md with IDF
This PR updates `HashingTF` to output ML attributes that tell the number of features in the output column. We need to expand `UnaryTransformer` to support output metadata. A `df outputMetadata: Metadata` is not sufficient because the metadata may also depends on the input data. Though this is not true for `HashingTF`, I think it is reasonable to update `UnaryTransformer` in a separate PR. `checkParams` is added to verify common requirements for params. I will send a separate PR to use it in other test suites. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6308 from mengxr/SPARK-7219 and squashes the following commits:
9bd2922 [Xiangrui Meng] address comments
e82a68a [Xiangrui Meng] remove sqlContext from test suite
995535b [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7219
2194703 [Xiangrui Meng] add test for attributes
178ae23 [Xiangrui Meng] update HashingTF with tests
91a6106 [Xiangrui Meng] WIP
The previous default is `{gaps: false, pattern: "\\p{L}+|[^\\p{L}\\s]+"}`. The default pattern is hard to understand. This PR changes the default to `{gaps: true, pattern: "\\s+"}`. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6330 from mengxr/SPARK-7794 and squashes the following commits:
5ee7cde [Xiangrui Meng] update RegexTokenizer default settings
We removed `varargs` due to Java compilation issues. That was a false alarm because I didn't run `build/sbt clean`. So this PR reverts the changes. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6320 from mengxr/SPARK-7498 and squashes the following commits:
74a7259 [Xiangrui Meng] add varargs back to setDefault
Added VectorIndexer section to ML user guide. Also added javaCategoryMaps() method and Java unit test for it.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6255 from jkbradley/vector-indexer-guide and squashes the following commits:
dbb8c4c [Joseph K. Bradley] simplified VectorIndexerModel.javaCategoryMaps
f692084 [Joseph K. Bradley] Added VectorIndexer section to ML user guide. Also added javaCategoryMaps() method and Java unit test for it.
same issue and fix as in Spark-7694.
Author: Shuo Xiang <shuoxiangpub@gmail.com>
Closes#6321 from coderxiang/nb and squashes the following commits:
a5e6de4 [Shuo Xiang] use getOrElse for svmmodel.tostring
2cb0177 [Shuo Xiang] Merge remote-tracking branch 'upstream/master' into nb
5f109b4 [Shuo Xiang] Merge remote-tracking branch 'upstream/master'
c5c5bfe [Shuo Xiang] Merge remote-tracking branch 'upstream/master'
98804c9 [Shuo Xiang] fix bug in topBykey and update test
to be consistent with other string names in MLlib. This PR also updates the implementation to use vals instead of hardcoded strings. jkbradley leahmcguire
Author: Xiangrui Meng <meng@databricks.com>
Closes#6277 from mengxr/SPARK-7752 and squashes the following commits:
f38b662 [Xiangrui Meng] add another case _ back in test
ae5c66a [Xiangrui Meng] model type -> modelType
711d1c6 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7752
40ae53e [Xiangrui Meng] fix Java test suite
264a814 [Xiangrui Meng] add case _ back
3c456a8 [Xiangrui Meng] update NB user guide
17bba53 [Xiangrui Meng] update naive Bayes to use lowercase model type strings
Update `KernelDensity` API to make it extensible to different kernels in the future. `bandwidth` is used instead of `standardDeviation`. The static `kernelDensity` method is removed from `Statistics`. The implementation is updated using BLAS, while the algorithm remains the same. sryza srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes#6279 from mengxr/SPARK-7753 and squashes the following commits:
4cdfadc [Xiangrui Meng] add example code in the doc
767fd5a [Xiangrui Meng] update KernelDensity API
to simplify test suites that require a SQLContext.
Author: Xiangrui Meng <meng@databricks.com>
Closes#6303 from mengxr/SPARK-7774 and squashes the following commits:
0622b5a [Xiangrui Meng] update some other test suites
e1f9b8d [Xiangrui Meng] add sqlContext to MLlibTestSparkContext
Set a default value for `outputCol` instead of forcing users to name it. This is useful for intermediate transformers in the pipeline. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6289 from mengxr/SPARK-7762 and squashes the following commits:
54edebc [Xiangrui Meng] merge master
bff8667 [Xiangrui Meng] update unit test
171246b [Xiangrui Meng] add unit test for outputCol
a4321bd [Xiangrui Meng] set default value for outputCol
Minor updates to the spark.mllib APIs:
1. Add `DeveloperApi` to `PMMLExportable` and add `Experimental` to `toPMML` methods.
2. Mention `RankingMetrics.of` in the `RankingMetrics` constructor.
Author: Xiangrui Meng <meng@databricks.com>
Closes#6280 from mengxr/SPARK-7537 and squashes the following commits:
1bd2583 [Xiangrui Meng] organize imports
94afa7a [Xiangrui Meng] mark all toPMML methods experimental
4c40da1 [Xiangrui Meng] mention the factory method for RankingMetrics for Java users
88c62d0 [Xiangrui Meng] add DeveloperApi to PMMLExportable
Add MultilabelMetrics in PySpark/MLlib
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6276 from yanboliang/spark-6094 and squashes the following commits:
b8e3343 [Yanbo Liang] Add MultilabelMetrics in PySpark/MLlib
JIRA issue [link](https://issues.apache.org/jira/browse/SPARK-7663).
We should check the model size of word2vec, to prevent the unexpected empty.
CC srowen.
Author: Xusen Yin <yinxusen@gmail.com>
Closes#6228 from yinxusen/SPARK-7663 and squashes the following commits:
21770c5 [Xusen Yin] check the vocab size
54ae63e [Xusen Yin] add requirement for word2vec model
CC jkbradley.
JIRA [issue](https://issues.apache.org/jira/browse/SPARK-7586).
Author: Xusen Yin <yinxusen@gmail.com>
Closes#6181 from yinxusen/SPARK-7586 and squashes the following commits:
77014c5 [Xusen Yin] comment fix
57a4c07 [Xusen Yin] small fix for docs
1178c8f [Xusen Yin] remove the correctness check in java suite
1c3f389 [Xusen Yin] delete sbt commit
1af152b [Xusen Yin] check python example code
1b5369e [Xusen Yin] add docs of word2vec
Changed shared param HasSeed to have default based on hashCode of class name, instead of random number.
Also, removed fixed random seeds from Word2Vec and ALS.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6251 from jkbradley/scala-fixed-seed and squashes the following commits:
0e37184 [Joseph K. Bradley] Fixed Word2VecSuite, ALSSuite in spark.ml to use original fixed random seeds
678ec3a [Joseph K. Bradley] Removed fixed random seeds from Word2Vec and ALS. Changed shared param HasSeed to have default based on hashCode of class name, instead of random number.
Made Model.parent transient. Added Model.hasParent to test for null parent
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5914 from jkbradley/parent-optional and squashes the following commits:
d501774 [Joseph K. Bradley] Made Model.parent transient. Added Model.hasParent to test for null parent
JIRA [here](https://issues.apache.org/jira/browse/SPARK-7581).
CC jkbradley
Author: Xusen Yin <yinxusen@gmail.com>
Closes#6113 from yinxusen/SPARK-7581 and squashes the following commits:
1a7d80d [Xusen Yin] merge with master
892a8e9 [Xusen Yin] fix python 3 compatibility
ec935bf [Xusen Yin] small fix
3e9fa1d [Xusen Yin] delete note
69fcf85 [Xusen Yin] simplify and add python example
81d21dc [Xusen Yin] add programming guide for Polynomial Expansion
40babfb [Xusen Yin] add java test suite for PolynomialExpansion
JIRA: https://issues.apache.org/jira/browse/SPARK-7681
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#6209 from viirya/sparsevector_gemv and squashes the following commits:
ce0bb8b [Liang-Chi Hsieh] Still need to scal y when beta is 0.0 because it clears out y.
b890e63 [Liang-Chi Hsieh] Do not delete multiply for DenseVector.
57a8c1e [Liang-Chi Hsieh] Add MimaExcludes for v1.4.
458d1ae [Liang-Chi Hsieh] List DenseMatrix.multiply and SparseMatrix.multiply to MimaExcludes too.
054f05d [Liang-Chi Hsieh] Fix scala style.
410381a [Liang-Chi Hsieh] Address comments. Make Matrix.multiply more generalized.
4616696 [Liang-Chi Hsieh] Add support for SparseVector with SparseMatrix.
5d6d07a [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into sparsevector_gemv
c069507 [Liang-Chi Hsieh] Add SparseVector support for gemv with DenseMatrix.
This PR makes pipeline stages in Python copyable and hence simplifies some implementations. It also includes the following changes:
1. Rename `paramMap` and `defaultParamMap` to `_paramMap` and `_defaultParamMap`, respectively.
2. Accept a list of param maps in `fit`.
3. Use parent uid and name to identify param.
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6088 from mengxr/SPARK-7380 and squashes the following commits:
413c463 [Xiangrui Meng] remove unnecessary doc
4159f35 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7380
611c719 [Xiangrui Meng] fix python style
68862b8 [Xiangrui Meng] update _java_obj initialization
927ad19 [Xiangrui Meng] fix ml/tests.py
0138fc3 [Xiangrui Meng] update feature transformers and fix a bug in RegexTokenizer
9ca44fb [Xiangrui Meng] simplify Java wrappers and add tests
c7d84ef [Xiangrui Meng] update ml/tests.py to test copy params
7e0d27f [Xiangrui Meng] merge master
46840fb [Xiangrui Meng] update wrappers
b6db1ed [Xiangrui Meng] update all self.paramMap to self._paramMap
46cb6ed [Xiangrui Meng] merge master
a163413 [Xiangrui Meng] fix style
1042e80 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7380
9630eae [Xiangrui Meng] fix Identifiable._randomUID
13bd70a [Xiangrui Meng] update ml/tests.py
64a536c [Xiangrui Meng] use _fit/_transform/_evaluate to simplify the impl
02abf13 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into copyable-python
66ce18c [Joseph K. Bradley] some cleanups before sending to Xiangrui
7431272 [Joseph K. Bradley] Rebased with master
The `toString` method of `LogisticRegressionModel` calls `get` method on an Option (threshold) without a safeguard. In spark-shell, the following code `val model = algorithm.run(data).clearThreshold()` in lbfgs code will fail as `toString `method will be called right after `clearThreshold()` to show the results in the REPL.
Author: Shuo Xiang <shuoxiangpub@gmail.com>
Closes#6224 from coderxiang/getorelse and squashes the following commits:
d5f53c9 [Shuo Xiang] use getOrElse for getting the threshold of LR model
5f109b4 [Shuo Xiang] Merge remote-tracking branch 'upstream/master'
c5c5bfe [Shuo Xiang] Merge remote-tracking branch 'upstream/master'
98804c9 [Shuo Xiang] fix bug in topBykey and update test
Author: Reynold Xin <rxin@databricks.com>
Closes#6211 from rxin/mllib-reader and squashes the following commits:
79a2cb9 [Reynold Xin] [SPARK-7654][MLlib] Migrate MLlib to the DataFrame reader/writer API.
reservoir feature sample by using existing api
Author: AiHe <ai.he@ussuning.com>
Closes#5988 from AiHe/reservoir and squashes the following commits:
e7a41ac [AiHe] remove non-robust testing case
28ffb9a [AiHe] set seed as rng.nextLong
37459e1 [AiHe] set fixed seed
1e98a4c [AiHe] [MLLIB][tree] Add reservoir sample in RandomForest
JIRA: https://issues.apache.org/jira/browse/SPARK-7668
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#6188 from viirya/fix_matrix_map and squashes the following commits:
2a7cc97 [Liang-Chi Hsieh] Preserve isTransposed property for Matrix after calling map function.
Implement Python API for major disparities of GaussianMixture cluster algorithm between Scala & Python
```scala
GaussianMixture
setInitialModel
GaussianMixtureModel
k
```
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6087 from yanboliang/spark-6258 and squashes the following commits:
b3af21c [Yanbo Liang] fix typo
2b645c1 [Yanbo Liang] fix doc
638b4b7 [Yanbo Liang] address comments
b5bcade [Yanbo Liang] GaussianMixture Python API parity check
A param instance is strongly attached to an parent in the current implementation. So if we make a copy of an estimator or a transformer in pipelines and other meta-algorithms, it becomes error-prone to copy the params to the copied instances. In this PR, a param is identified by its parent's UID and the param name. So it becomes loosely attached to its parent and all its derivatives. The UID is preserved during copying or fitting. All components now have a default constructor and a constructor that takes a UID as input. I keep the constructors for Param in this PR to reduce the amount of diff and moved `parent` as a mutable field.
This PR still needs some clean-ups, and there are several spark.ml PRs pending. I'll try to get them merged first and then update this PR.
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6019 from mengxr/SPARK-7407 and squashes the following commits:
c4c8120 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7407
520f0a2 [Xiangrui Meng] address comments
2569168 [Xiangrui Meng] fix tests
873caca [Xiangrui Meng] fix tests in OneVsRest; fix a racing condition in shouldOwn
409ea08 [Xiangrui Meng] minor updates
83a163c [Xiangrui Meng] update JavaDeveloperApiExample
5db5325 [Xiangrui Meng] update OneVsRest
7bde7ae [Xiangrui Meng] merge master
697fdf9 [Xiangrui Meng] update Bucketizer
7b4f6c2 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7407
629d402 [Xiangrui Meng] fix LRSuite
154516f [Xiangrui Meng] merge master
aa4a611 [Xiangrui Meng] fix examples/compile
a4794dd [Xiangrui Meng] change Param to use to reduce the size of diff
fdbc415 [Xiangrui Meng] all tests passed
c255f17 [Xiangrui Meng] fix tests in ParamsSuite
818e1db [Xiangrui Meng] merge master
e1160cf [Xiangrui Meng] fix tests
fbc39f0 [Xiangrui Meng] pass test:compile
108937e [Xiangrui Meng] pass compile
8726d39 [Xiangrui Meng] use parent uid in Param
eaeed35 [Xiangrui Meng] update Identifiable
Author: DB Tsai <dbt@netflix.com>
Closes#6137 from dbtsai/clean and squashes the following commits:
185816d [DB Tsai] fix compilication issue
f418d08 [DB Tsai] first commit
This is similar to the changes to k-means, which gives us better control on the performance. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#6128 from mengxr/SPARK-7612 and squashes the following commits:
b5c24c5 [Xiangrui Meng] merge master
a90e3ec [Xiangrui Meng] update NB training to use mllib's BLAS
Author: leahmcguire <lmcguire@salesforce.com>
Closes#6073 from leahmcguire/binaryCheckNB and squashes the following commits:
b8442c2 [leahmcguire] changed to if else for value checks
911bf83 [leahmcguire] undid reformat
4eedf1e [leahmcguire] moved bernoulli check
9ee9e84 [leahmcguire] fixed style error
3f3b32c [leahmcguire] fixed zero one check so only called in combiner
831fd27 [leahmcguire] got test working
f44bb3c [leahmcguire] removed changes from CV branch
67253f0 [leahmcguire] added check to bernoulli to ensure feature values are zero or one
f191c71 [leahmcguire] fixed name
58d060b [leahmcguire] changed param name and test according to comments
04f0d3c [leahmcguire] Added stats from cross validation as a val in the cross validation model to save them for user access
Added `ml.feature.Bucketizer` to PySpark.
cc mengxr
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#6124 from brkyvz/ml-bucket and squashes the following commits:
05285be [Burak Yavuz] added sphinx doc
6abb6ed [Burak Yavuz] added support for Bucketizer
`RankingMetrics` contains a ClassTag, which is hard to create in Java. This PR adds a factory method `of` for Java users. coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#6098 from mengxr/SPARK-7528 and squashes the following commits:
e5d57ae [Xiangrui Meng] make RankingMetrics Java-friendly
Minor cleanups discussed with [~mengxr]:
* move OneVsRest from reduction to classification sub-package
* make model constructor private
Some doc cleanups too
CC: harsha2010 Could you please verify this looks OK? Thanks!
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6097 from jkbradley/onevsrest-cleanup and squashes the following commits:
4ecd48d [Joseph K. Bradley] org imports
430b065 [Joseph K. Bradley] moved OneVsRest from reduction subpackage to classification. small java doc style fixes
9f8b9b9 [Joseph K. Bradley] Small cleanups to OneVsRest. Made model constructor private to ml package.
Added feature transformer subsection to spark.ml guide, with HashingTF and Tokenizer. Added JavaHashingTFSuite to test Java examples in new guide.
I've run Scala, Python examples in the Spark/PySpark shells. I ran the Java examples via the test suite (with small modifications for printing).
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6093 from jkbradley/hashingtf-guide and squashes the following commits:
d5d213f [Joseph K. Bradley] small fix
dd6e91a [Joseph K. Bradley] fixes from code review of user guide
33c3ff9 [Joseph K. Bradley] small fix
bc6058c [Joseph K. Bradley] fix link
361a174 [Joseph K. Bradley] Added subsection for feature transformers to spark.ml guide, with HashingTF and Tokenizer. Added JavaHashingTFSuite to test Java examples in new guide
`scala.Math` is deprecated since 2.8. This PR only touchs `Math` usages in MLlib. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#6092 from mengxr/SPARK-7571 and squashes the following commits:
fe8f8d3 [Xiangrui Meng] Math -> math
We make special treatment for +inf in `Bucketizer`. This could be simplified by always including the largest split value in the last bucket. E.g., (x1, x2, x3) defines buckets [x1, x2) and [x2, x3]. This shouldn't affect user code much, and there are applications that need to include the right-most value. For example, we can bucketize ratings from 0 to 10 to bad, neutral, and good with splits 0, 4, 6, 10. It may reads weird if the users need to put 0, 4, 6, 10.1 (or 11).
This also update the impl to use `Arrays.binarySearch` and `withClue` in test.
yinxusen jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#6075 from mengxr/SPARK-7559 and squashes the following commits:
e28f910 [Xiangrui Meng] update bucketizer impl
The sbt part of the build is hacky; it basically tricks sbt
into generating the zip by using a generator, but returns
an empty list for the generated files so that nothing is
actually added to the assembly.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#6022 from vanzin/SPARK-7485 and squashes the following commits:
22c1e04 [Marcelo Vanzin] Remove unneeded code.
4893622 [Marcelo Vanzin] [SPARK-7485] [build] Remove pyspark files from assembly.
JIRA issue [here](https://issues.apache.org/jira/browse/SPARK-5893).
One thing to make clear, the `buckets` parameter, which is an array of `Double`, performs as split points. Say,
```scala
buckets = Array(-0.5, 0.0, 0.5)
```
splits the real number into 4 ranges, (-inf, -0.5], (-0.5, 0.0], (0.0, 0.5], (0.5, +inf), which is encoded as 0, 1, 2, 3.
Author: Xusen Yin <yinxusen@gmail.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5980 from yinxusen/SPARK-5893 and squashes the following commits:
dc8c843 [Xusen Yin] Merge pull request #4 from jkbradley/yinxusen-SPARK-5893
1ca973a [Joseph K. Bradley] one more bucketizer test
34f124a [Joseph K. Bradley] Removed lowerInclusive, upperInclusive params from Bucketizer, and used splits instead.
eacfcfa [Xusen Yin] change ML attribute from splits into buckets
c3cc770 [Xusen Yin] add more unit test for binary search
3a16cc2 [Xusen Yin] refine comments and names
ac77859 [Xusen Yin] fix style error
fb30d79 [Xusen Yin] fix and test binary search
2466322 [Xusen Yin] refactor Bucketizer
11fb00a [Xusen Yin] change it into an Estimator
998bc87 [Xusen Yin] check buckets
4024cf1 [Xusen Yin] add test suite
5fe190e [Xusen Yin] add bucketizer
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#6044 from yanboliang/spark-6092 and squashes the following commits:
726a9b1 [Yanbo Liang] add newRankingMetrics
33f649c [Yanbo Liang] Add RankingMetrics in PySpark/MLlib
I implement a simple PCA wrapper for easy transform of vectors by PCA for example LabeledPoint or another complicated structure.
Example of usage:
```
import org.apache.spark.mllib.regression.LinearRegressionWithSGD
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.feature.PCA
val data = sc.textFile("data/mllib/ridge-data/lpsa.data").map { line =>
val parts = line.split(',')
LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble)))
}.cache()
val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
val training = splits(0).cache()
val test = splits(1)
val pca = PCA.create(training.first().features.size/2, data.map(_.features))
val training_pca = training.map(p => p.copy(features = pca.transform(p.features)))
val test_pca = test.map(p => p.copy(features = pca.transform(p.features)))
val numIterations = 100
val model = LinearRegressionWithSGD.train(training, numIterations)
val model_pca = LinearRegressionWithSGD.train(training_pca, numIterations)
val valuesAndPreds = test.map { point =>
val score = model.predict(point.features)
(score, point.label)
}
val valuesAndPreds_pca = test_pca.map { point =>
val score = model_pca.predict(point.features)
(score, point.label)
}
val MSE = valuesAndPreds.map{case(v, p) => math.pow((v - p), 2)}.mean()
val MSE_pca = valuesAndPreds_pca.map{case(v, p) => math.pow((v - p), 2)}.mean()
println("Mean Squared Error = " + MSE)
println("PCA Mean Squared Error = " + MSE_pca)
```
Author: Kirill A. Korinskiy <catap@catap.ru>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4304 from catap/pca and squashes the following commits:
501bcd9 [Joseph K. Bradley] Small updates: removed k from Java-friendly PCA fit(). In PCASuite, converted results to set for comparison. Added an error message for bad k in PCA.
9dcc02b [Kirill A. Korinskiy] [SPARK-5521] fix scala style
1892a06 [Kirill A. Korinskiy] [SPARK-5521] PCA wrapper for easy transform vectors
In SPARK-7429 and PR https://github.com/apache/spark/pull/5960, I added the varargs annotation to Params.setDefault which takes a variable number of ParamPairs. It worked locally and on Jenkins for me.
However, mengxr reported issues compiling on his machine. So I'm reverting the change introduced in https://github.com/apache/spark/pull/5960 by removing varargs.
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#6021 from jkbradley/revert-varargs and squashes the following commits:
098ed39 [Joseph K. Bradley] removed varargs annotation from Params.setDefaults taking multiple ParamPairs
1) Handle scaling and addBias internally.
2) L1/L2 elasticnet using OWLQN optimizer.
Author: DB Tsai <dbt@netflix.com>
Closes#5967 from dbtsai/lor and squashes the following commits:
fa029bb [DB Tsai] made the bound smaller
0806002 [DB Tsai] better initial intercept and more test
5c31824 [DB Tsai] fix import
c387e25 [DB Tsai] Merge branch 'master' into lor
c84e931 [DB Tsai] Made MultiClassSummarizer private
f98e711 [DB Tsai] address feedback
a784321 [DB Tsai] fix style
8ec65d2 [DB Tsai] remove new line
f3f8c88 [DB Tsai] add more tests and they match R which is good. fix a bug
34705bc [DB Tsai] first commit
Adds Python Api for `ALS` under `ml.recommendation` in PySpark. Also adds seed as a settable parameter in the Scala Implementation of ALS.
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#6015 from brkyvz/ml-rec and squashes the following commits:
be6e931 [Burak Yavuz] addressed comments
eaed879 [Burak Yavuz] readd numFeatures
0bd66b1 [Burak Yavuz] fixed seed
7f6d964 [Burak Yavuz] merged master
52e2bda [Burak Yavuz] added ALS
Add a Python API for mllib.feature.ChiSqSelector
https://issues.apache.org/jira/browse/SPARK-5913
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5939 from yanboliang/spark-5913 and squashes the following commits:
cdaac99 [Yanbo Liang] Python API for ChiSqSelector
Implemented python wrappers for Scala functions that don't exist in `ml.features`
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#5991 from brkyvz/ml-feat-PR and squashes the following commits:
adcca55 [Burak Yavuz] add regex tokenizer to __all__
b91cb44 [Burak Yavuz] addressed comments
bd39fd2 [Burak Yavuz] remove addition
b82bd7c [Burak Yavuz] Parity in PySpark for ml.features
the toArray function of the BoundedPriorityQueue does not necessarily preserve order. Add a counter-example as the test, which would fail the original impl.
Author: Shuo Xiang <shuoxiangpub@gmail.com>
Closes#5990 from coderxiang/topbykey-test and squashes the following commits:
98804c9 [Shuo Xiang] fix bug in topBykey and update test
The compression is based on storage. brkyvz
Author: Xiangrui Meng <meng@databricks.com>
Closes#5985 from mengxr/SPARK-6948 and squashes the following commits:
df56a00 [Xiangrui Meng] update python tests
6d90d45 [Xiangrui Meng] compress vectors in VectorAssembler
https://issues.apache.org/jira/browse/SPARK-6093
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5941 from yanboliang/spark-6093 and squashes the following commits:
6934af3 [Yanbo Liang] change to @property
aac3bc5 [Yanbo Liang] Add RegressionMetrics in PySpark/MLlib
The wrapper required the implementation of the `ArrayParam`, because `Array[T]` is hard to obtain from Python. `ArrayParam` has an extra function called `wCast` which is an internal function to obtain `Array[T]` from `Seq[T]`
Author: Burak Yavuz <brkyvz@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#5930 from brkyvz/ml-feat and squashes the following commits:
73e745f [Burak Yavuz] Merge pull request #3 from mengxr/SPARK-7388
c221db9 [Xiangrui Meng] overload StringArrayParam.w
c81072d [Burak Yavuz] addressed comments
99c2ebf [Burak Yavuz] add to python_shared_params
39ecb07 [Burak Yavuz] fix scalastyle
7f7ea2a [Burak Yavuz] [SPARK-7388][SPARK-7383] wrapper for VectorAssembler in Python
Params.setDefault taking a set of ParamPairs should be annotated with varargs. I thought it would not work before, but it apparently does.
CrossValidator.transform should call transformSchema since the underlying Model might be a PipelineModel
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5960 from jkbradley/params-cleanups and squashes the following commits:
118b158 [Joseph K. Bradley] Params.setDefault taking a set of ParamPairs should be annotated with varargs. I thought it would not work before, but it apparently does. CrossValidator.transform should call transformSchema since the underlying Model might be a PipelineModel
Small changes, primarily to allow us more flexibility in the future:
* Rename "tau_0" to "tau0"
* Mark LDAOptimizer trait sealed and DeveloperApi.
* Mark LDAOptimizer subclasses as final.
* Mark setOptimizer (the one taking an LDAOptimizer) and getOptimizer as DeveloperApi since we may need to change them in the future
CC: hhbyyh
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5956 from jkbradley/onlinelda-cleanups and squashes the following commits:
f4be508 [Joseph K. Bradley] added newline
f4003e4 [Joseph K. Bradley] Changes: * Rename "tau_0" to "tau0" * Mark LDAOptimizer trait sealed and DeveloperApi. * Mark LDAOptimizer subclasses as final. * Mark setOptimizer (the one taking an LDAOptimizer) and getOptimizer as DeveloperApi since we may need to change them in the future
Changes:
* Update protected prediction methods, following design doc. **<--most interesting change**
* Changed abstract classes for Estimator and Model to be public. Added DeveloperApi tag. (I kept the traits for Estimator/Model Params private.)
* Changed ProbabilisticClassificationModel method names to use probability instead of probabilities.
CC: mengxr shivaram etrain
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5913 from jkbradley/public-dev-api and squashes the following commits:
e9aa0ea [Joseph K. Bradley] moved findMax to DenseVector and renamed to argmax. fixed bug for vector of length 0
15b9957 [Joseph K. Bradley] renamed probabilities to probability in method names
5cda84d [Joseph K. Bradley] regenerated sharedParams
7d1877a [Joseph K. Bradley] Made spark.ml prediction abstractions public. Organized their prediction methods for efficient computation of multiple output columns.
Since CrossValidator is a meta algorithm, we copy the implementation in Python. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5926 from mengxr/SPARK-6940 and squashes the following commits:
6af181f [Xiangrui Meng] add TODOs
8285134 [Xiangrui Meng] update doc
060f7c3 [Xiangrui Meng] update doctest
acac727 [Xiangrui Meng] add keyword args
cdddecd [Xiangrui Meng] add CrossValidator in Python
This patch adds a one hot encoder for categorical features. Planning to add documentation and another test after getting feedback on the approach.
A couple choices made here:
* There's an `includeFirst` option which, if false, creates numCategories - 1 columns and, if true, creates numCategories columns. The default is true, which is the behavior in scikit-learn.
* The user is expected to pass a `Seq` of category names when instantiating a `OneHotEncoder`. These can be easily gotten from a `StringIndexer`. The names are used for the output column names, which take the form colName_categoryName.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#5500 from sryza/sandy-spark-5888 and squashes the following commits:
f383250 [Sandy Ryza] Infer label names automatically
6e257b9 [Sandy Ryza] Review comments
7c539cf [Sandy Ryza] Vector transformers
1c182dd [Sandy Ryza] SPARK-5888. [MLLIB]. Add OneHotEncoder as a Transformer
Require non empty input rdd such that we can take the first labeledpoint and get the feature size
Author: Alain <aihe@usc.edu>
Author: aihe@usc.edu <aihe@usc.edu>
Closes#5810 from AiHe/decisiontree-issue and squashes the following commits:
3b1d08a [aihe@usc.edu] [MLLIB][tree] merge the assertion into the evaluation of numFeatures
cf2e567 [Alain] [MLLIB][tree] Use a rdd api to verify size of input rdd > 0 when building meta data
b448f47 [Alain] [MLLIB][tree] Verify size of input rdd > 0 when building meta data
The following items are added to Python kmeans:
kmeans - setEpsilon, setInitializationSteps
KMeansModel - computeCost, k
Author: Hrishikesh Subramonian <hrishikesh.subramonian@flytxt.com>
Closes#5647 from FlytxtRnD/newPyKmeansAPI and squashes the following commits:
b9e451b [Hrishikesh Subramonian] set seed to fixed value in doc test
5fd3ced [Hrishikesh Subramonian] doc test corrections
20b3c68 [Hrishikesh Subramonian] python 3 fixes
4d4e695 [Hrishikesh Subramonian] added arguments in python tests
21eb84c [Hrishikesh Subramonian] Python Kmeans - setEpsilon, setInitializationSteps, k and computeCost added.
Utilities for pickling and unpickling SparseMatrices using SerDe
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5775 from MechCoder/spark-7202 and squashes the following commits:
7e689dc [MechCoder] [SPARK-7202] Add SparseMatrixPickler to SerDe
This PR added `copy(extra: ParamMap): Params` to `Params`, which makes a copy of the current instance with a randomly generated uid and some extra param values. With this change, we only need to implement `fit` and `transform` without extra param values given the default implementation of `fit(dataset, extra)`:
~~~scala
def fit(dataset: DataFrame, extra: ParamMap): Model = {
copy(extra).fit(dataset)
}
~~~
Inside `fit` and `transform`, since only the embedded values are used, I added `$` as an alias for `getOrDefault` to make the code easier to read. For example, in `LinearRegression.fit` we have:
~~~scala
val effectiveRegParam = $(regParam) / yStd
val effectiveL1RegParam = $(elasticNetParam) * effectiveRegParam
val effectiveL2RegParam = (1.0 - $(elasticNetParam)) * effectiveRegParam
~~~
Meta-algorithm like `Pipeline` implements its own `copy(extra)`. So the fitted pipeline model stored all copied stages (no matter whether it is a transformer or a model).
Other changes:
* `Params$.inheritValues` is moved to `Params!.copyValues` and returns the target instance.
* `fittingParamMap` was removed because the `parent` carries this information.
* `validate` was renamed to `validateParams` to be more precise.
TODOs:
* [x] add tests for newly added methods
* [ ] update documentation
jkbradley dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#5820 from mengxr/SPARK-5956 and squashes the following commits:
7bef88d [Xiangrui Meng] address comments
05229c3 [Xiangrui Meng] assert -> assertEquals
b2927b1 [Xiangrui Meng] organize imports
f14456b [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5956
93e7924 [Xiangrui Meng] add tests for hasParam & copy
463ecae [Xiangrui Meng] merge master
2b954c3 [Xiangrui Meng] update Binarizer
465dd12 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5956
282a1a8 [Xiangrui Meng] fix test
819dd2d [Xiangrui Meng] merge master
b642872 [Xiangrui Meng] example code runs
5a67779 [Xiangrui Meng] examples compile
c76b4d1 [Xiangrui Meng] fix all unit tests
0f4fd64 [Xiangrui Meng] fix some tests
9286a22 [Xiangrui Meng] copyValues to trained models
53e0973 [Xiangrui Meng] move inheritValues to Params and rename it to copyValues
9ee004e [Xiangrui Meng] merge copy and copyWith; rename validate to validateParams
d882afc [Xiangrui Meng] test compile
f082a31 [Xiangrui Meng] make Params copyable and simply handling of extra params in all spark.ml components
JIRA: https://issues.apache.org/jira/browse/SPARK-5563
The PR contains the implementation for [Online LDA] (https://www.cs.princeton.edu/~blei/papers/HoffmanBleiBach2010b.pdf) based on the research of Matt Hoffman and David M. Blei, which provides an efficient option for LDA users. Major advantages for the algorithm are the stream compatibility and economic time/memory consumption due to the corpus split. For more details, please refer to the jira.
Online LDA can act as a fast option for LDA, and will be especially helpful for the users who needs a quick result or with large corpus.
Correctness test.
I have tested current PR with https://github.com/Blei-Lab/onlineldavb and the results are identical. I've uploaded the result and code to https://github.com/hhbyyh/LDACrossValidation.
Author: Yuhao Yang <hhbyyh@gmail.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4419 from hhbyyh/ldaonline and squashes the following commits:
1045eec [Yuhao Yang] Merge pull request #2 from jkbradley/hhbyyh-ldaonline2
cf376ff [Joseph K. Bradley] For private vars needed for testing, I made them private and added accessors. Java doesn’t understand package-private tags, so this minimizes the issues Java users might encounter.
6149ca6 [Yuhao Yang] fix for setOptimizer
cf0007d [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
54cf8da [Yuhao Yang] some style change
68c2318 [Yuhao Yang] add a java ut
4041723 [Yuhao Yang] add ut
138bfed [Yuhao Yang] Merge pull request #1 from jkbradley/hhbyyh-ldaonline-update
9e910d9 [Joseph K. Bradley] small fix
61d60df [Joseph K. Bradley] Minor cleanups: * Update *Concentration parameter documentation * EM Optimizer: createVertices() does not need to be a function * OnlineLDAOptimizer: typos in doc * Clean up the core code for online LDA (Scala style)
a996a82 [Yuhao Yang] respond to comments
b1178cf [Yuhao Yang] fit into the optimizer framework
dbe3cff [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
15be071 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
b29193b [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
d19ef55 [Yuhao Yang] change OnlineLDA to class
97b9e1a [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
e7bf3b0 [Yuhao Yang] move to seperate file
f367cc9 [Yuhao Yang] change to optimization
8cb16a6 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
62405cc [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
02d0373 [Yuhao Yang] fix style in comment
f6d47ca [Yuhao Yang] Merge branch 'ldaonline' of https://github.com/hhbyyh/spark into ldaonline
d86cdec [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
a570c9a [Yuhao Yang] use sample to pick up batch
4a3f27e [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline
e271eb1 [Yuhao Yang] remove non ascii
581c623 [Yuhao Yang] seperate API and adjust batch split
37af91a [Yuhao Yang] iMerge remote-tracking branch 'upstream/master' into ldaonline
20328d1 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline i
aa365d1 [Yuhao Yang] merge upstream master
3a06526 [Yuhao Yang] merge with new example
0dd3947 [Yuhao Yang] kMerge remote-tracking branch 'upstream/master' into ldaonline
0d0f3ee [Yuhao Yang] replace random split with sliding
fa408a8 [Yuhao Yang] ssMerge remote-tracking branch 'upstream/master' into ldaonline
45884ab [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline s
f41c5ca [Yuhao Yang] style fix
26dca1b [Yuhao Yang] style fix and make class private
043e786 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaonline s Conflicts: mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala
d640d9c [Yuhao Yang] online lda initial checkin
This is based on #3098 from debasish83.
1. BLAS' GEMM is used to compute inner products.
2. Reverted changes to MovieLensALS. SPARK-4231 should be addressed in a separate PR.
3. ~~Fixed a bug in topByKey~~
Closes#3098
debasish83 coderxiang
Author: Debasish Das <debasish.das@one.verizon.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#5829 from mengxr/SPARK-3066 and squashes the following commits:
22e6a87 [Xiangrui Meng] topByKey was correct. update its usage
389b381 [Xiangrui Meng] fix indentation
49953de [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-3066
cb9799a [Xiangrui Meng] revert MovieLensALS
f864f5e [Xiangrui Meng] update test and fix a bug in topByKey
c5e0181 [Xiangrui Meng] use GEMM and topByKey
3a0c4eb [Debasish Das] updated with spark master
98fa424 [Debasish Das] updated with master
ee99571 [Debasish Das] addressed initial review comments;merged with master;added tests for batch predict APIs in matrix factorization
3f97c49 [Debasish Das] fixed spark coding style for imports
7163a5c [Debasish Das] Added API for batch user and product recommendation; MAP calculation for product recommendation per user using randomized split
d144f57 [Debasish Das] recommendAll API to MatrixFactorizationModel, uses topK finding using BoundedPriorityQueue similar to RDD.top
f38a1b5 [Debasish Das] use sampleByKey for per user sampling
10cbb37 [Debasish Das] provide ratio for topN product validation; generate MAP and prec@k metric for movielens dataset
9fa063e [Debasish Das] import scala.math.round
4bbae0f [Debasish Das] comments fixed as per scalastyle
cd3ab31 [Debasish Das] merged with AbstractParams serialization bug
9b3951f [Debasish Das] validate user/product on MovieLens dataset through user input and compute map measure along with rmse
Author: DB Tsai <dbt@netflix.com>
Closes#5809 from dbtsai/format and squashes the following commits:
6904eed [DB Tsai] triger jenkins
9146e19 [DB Tsai] initial commit
See PDF attached to the JIRA issue 1406.
The contribution is my original work and I license the work to the project under the project's open source license.
Author: Vincenzo Selvaggio <vselvaggio@hotmail.it>
Author: Xiangrui Meng <meng@databricks.com>
Author: selvinsource <vselvaggio@hotmail.it>
Closes#3062 from selvinsource/mllib_pmml_model_export_SPARK-1406 and squashes the following commits:
852aac6 [Vincenzo Selvaggio] [SPARK-1406] Update JPMML version to 1.1.15 in LICENSE file
085cf42 [Vincenzo Selvaggio] [SPARK-1406] Added Double Min and Max Fixed scala style
30165c4 [Vincenzo Selvaggio] [SPARK-1406] Fixed extreme cases for logit
7a5e0ec [Vincenzo Selvaggio] [SPARK-1406] Binary classification for SVM and Logistic Regression
cfcb596 [Vincenzo Selvaggio] [SPARK-1406] Throw IllegalArgumentException when exporting a multinomial logistic regression
25dce33 [Vincenzo Selvaggio] [SPARK-1406] Update code to latest pmml model
dea98ca [Vincenzo Selvaggio] [SPARK-1406] Exclude transitive dependency for pmml model
66b7c12 [Vincenzo Selvaggio] [SPARK-1406] Updated pmml model lib to 1.1.15, latest Java 6 compatible
a0a55f7 [Vincenzo Selvaggio] Merge pull request #2 from mengxr/SPARK-1406
3c22f79 [Xiangrui Meng] more code style
e2313df [Vincenzo Selvaggio] Merge pull request #1 from mengxr/SPARK-1406
472d757 [Xiangrui Meng] fix code style
1676e15 [Vincenzo Selvaggio] fixed scala issue
e2ffae8 [Vincenzo Selvaggio] fixed scala style
b8823b0 [Vincenzo Selvaggio] Merge remote-tracking branch 'upstream/master' into mllib_pmml_model_export_SPARK-1406
b25bbf7 [Vincenzo Selvaggio] [SPARK-1406] Added export of pmml to distributed file system using the spark context
7a949d0 [Vincenzo Selvaggio] [SPARK-1406] Fixed scala style
f46c75c [Vincenzo Selvaggio] [SPARK-1406] Added PMMLExportable to supported models
7b33b4e [Vincenzo Selvaggio] [SPARK-1406] Added a PMMLExportable interface Restructured code in a new package mllib.pmml Supported models implements the new PMMLExportable interface: LogisticRegression, SVM, KMeansModel, LinearRegression, RidgeRegression, Lasso
d559ec5 [Vincenzo Selvaggio] Merge remote-tracking branch 'upstream/master' into mllib_pmml_model_export_SPARK-1406
8fe12bb [Vincenzo Selvaggio] [SPARK-1406] Adjusted logistic regression export description and target categories
03bc3a5 [Vincenzo Selvaggio] added logistic regression
da2ec11 [Vincenzo Selvaggio] [SPARK-1406] added linear SVM PMML export
82f2131 [Vincenzo Selvaggio] Merge remote-tracking branch 'upstream/master' into mllib_pmml_model_export_SPARK-1406
19adf29 [Vincenzo Selvaggio] [SPARK-1406] Fixed scala style
1faf985 [Vincenzo Selvaggio] [SPARK-1406] Added target field to the regression model for completeness Adjusted unit test to deal with this change
3ae8ae5 [Vincenzo Selvaggio] [SPARK-1406] Adjusted imported order according to the guidelines
c67ce81 [Vincenzo Selvaggio] Merge remote-tracking branch 'upstream/master' into mllib_pmml_model_export_SPARK-1406
78515ec [Vincenzo Selvaggio] [SPARK-1406] added pmml export for LinearRegressionModel, RidgeRegressionModel and LassoModel
e29dfb9 [Vincenzo Selvaggio] removed version, by default is set to 4.2 (latest from jpmml) removed copyright
ae8b993 [Vincenzo Selvaggio] updated some commented tests to use the new ModelExporter object reordered the imports
df8a89e [Vincenzo Selvaggio] added pmml version to pmml model changed the copyright to spark
a1b4dc3 [Vincenzo Selvaggio] updated imports
834ca44 [Vincenzo Selvaggio] reordered the import accordingly to the guidelines
349a76b [Vincenzo Selvaggio] new helper object to serialize the models to pmml format
c3ef9b8 [Vincenzo Selvaggio] set it to private
6357b98 [Vincenzo Selvaggio] set it to private
e1eb251 [Vincenzo Selvaggio] removed serialization part, this will be part of the ModelExporter helper object
aba5ee1 [Vincenzo Selvaggio] fixed cluster export
cd6c07c [Vincenzo Selvaggio] fixed scala style to run tests
f75b988 [Vincenzo Selvaggio] Merge remote-tracking branch 'origin/master' into mllib_pmml_model_export_SPARK-1406
07a29bf [selvinsource] Update LICENSE
8841439 [Vincenzo Selvaggio] adjust scala style in order to compile
1433b11 [Vincenzo Selvaggio] complete suite tests
8e71b8d [Vincenzo Selvaggio] kmeans pmml export implementation
9bc494f [Vincenzo Selvaggio] added scala suite tests added saveLocalFile to ModelExport trait
226e184 [Vincenzo Selvaggio] added javadoc and export model type in case there is a need to support other types of export (not just PMML)
a0e3679 [Vincenzo Selvaggio] export and pmml export traits kmeans test implementation
Author: DB Tsai <dbt@netflix.com>
Closes#5794 from dbtsai/clean and squashes the following commits:
ad639dd [DB Tsai] Indentation
834d527 [DB Tsai] Some code clean up.
Main change: Added isValid field to Param. Modified all usages to use isValid when relevant. Added helper methods in ParamValidate.
Also overrode Params.validate() in:
* CrossValidator + model
* Pipeline + model
I made a few updates for the elastic net patch:
* I changed "tol" to "convergenceTol"
* I added some documentation
This PR is Scala + Java only. Python will be in a follow-up PR.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5740 from jkbradley/enforce-validate and squashes the following commits:
ad9c6c1 [Joseph K. Bradley] re-generated sharedParams after merging with current master
76415e8 [Joseph K. Bradley] reverted convergenceTol to tol
af62f4b [Joseph K. Bradley] Removed changes to SparkBuild, python linalg. Fixed test failures. Renamed ParamValidate to ParamValidators. Removed explicit type from ParamValidators calls where possible.
bb2665a [Joseph K. Bradley] merged with elastic net pr
ecda302 [Joseph K. Bradley] fix rat tests, plus add a little doc
6895dfc [Joseph K. Bradley] small cleanups
069ac6d [Joseph K. Bradley] many cleanups
928fb84 [Joseph K. Bradley] Maybe done
a910ac7 [Joseph K. Bradley] still workin
6d60e2e [Joseph K. Bradley] Still workin
b987319 [Joseph K. Bradley] Partly done with adding checks, but blocking on adding checking functionality to Param
dbc9fb2 [Joseph K. Bradley] merged with master. enforcing Params.validate
Changed VectorIndexer so it does not carry non-ML metadata from the input to the output column. Removed ml.util.TestingUtils since VectorIndexer was the only use.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5789 from jkbradley/vector-indexer-metadata and squashes the following commits:
b28e159 [Joseph K. Bradley] Changed VectorIndexer so it does not carry non-ML metadata from the input to the output column. Removed ml.util.TestingUtils since VectorIndexer was the only use.
See JIRA issue [here](https://issues.apache.org/jira/browse/SPARK-6529).
There are some notes:
1. I add `learningRate` in sharedParams since it is a common parameter for ML algorithms.
2. We will not support transform of finding synonyms from a `Vector`, which will support in further JIRA issues.
3. Word2Vec is different with other ML models that its training set and transformed set are different. Its training set is an `RDD[Iterable[String]]` which represents documents, but the transformed set we want is an `RDD[String]` that represents unique words. So you have to switch your `inputCol` in these two stages.
Author: Xusen Yin <yinxusen@gmail.com>
Closes#5596 from yinxusen/SPARK-6529 and squashes the following commits:
ee2b37a [Xusen Yin] merge with former HEAD
4945462 [Xusen Yin] merge with #5626
3bc2cbd [Xusen Yin] change foldLeft to for loop and use blas
5dd4ee7 [Xusen Yin] fix scala style
743e0d5 [Xusen Yin] fix comments and code style
04c48e9 [Xusen Yin] ensure the functionality
a190f2c [Xusen Yin] fix code style and refine the transform function of word2vec
02848fa [Xusen Yin] refine comments
34a55c0 [Xusen Yin] fix errors
109d124 [Xusen Yin] add test suite and pass it
04dde06 [Xusen Yin] add shared params
c594095 [Xusen Yin] add word2vec transformer
23d77fa [Xusen Yin] merge with #5626
e8cfaf7 [Xusen Yin] fix conflict with master
66e7bd3 [Xusen Yin] change foldLeft to for loop and use blas
566ec20 [Xusen Yin] fix scala style
b54399f [Xusen Yin] fix comments and code style
1211e86 [Xusen Yin] ensure the functionality
6b97ec8 [Xusen Yin] fix code style and refine the transform function of word2vec
7cde18f [Xusen Yin] rm sharedParams
618abd0 [Xusen Yin] refine comments
e29680a [Xusen Yin] fix errors
fe3afe9 [Xusen Yin] add test suite and pass it
02767fb [Xusen Yin] add shared params
6a514f1 [Xusen Yin] add word2vec transformer
Added detailed mathematical derivation of how scaling and LeastSquaresAggregator work. Refactored the code so the model is compressed based on the storage. We may try compression based on the prediction time.
Also, I found that diffSum will be always zero mathematically, so no corrections are required.
Author: DB Tsai <dbt@netflix.com>
Closes#5767 from dbtsai/lir-doc and squashes the following commits:
5e346c9 [DB Tsai] refactoring
fc9f582 [DB Tsai] doc
58456d8 [DB Tsai] address feedback
69757b8 [DB Tsai] actually diffSum is mathematically zero! No correction is needed.
5929e49 [DB Tsai] typo
63f7d1e [DB Tsai] Added compression to the model based on storage
203a295 [DB Tsai] Add more documentation to LinearRegression in new ML framework.
mengxr
Author: Xusen Yin <yinxusen@gmail.com>
Closes#5769 from yinxusen/patch-1 and squashes the following commits:
43235f4 [Xusen Yin] Update PearsonCorrelation.scala
f7287ee [Xusen Yin] Fix a typo of "threshold"
Add `compressed` to `Vector` with some other methods: `numActives`, `numNonzeros`, `toSparse`, and `toDense`. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5756 from mengxr/SPARK-6756 and squashes the following commits:
8d4ecbd [Xiangrui Meng] address comment and add mima excludes
da54179 [Xiangrui Meng] add toSparse, toDense, numActives, numNonzeros, and compressed to Vector
Cast numeric types to String for indexing. Boolean type is not handled in this PR. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5753 from mengxr/SPARK-6965 and squashes the following commits:
2e34f3c [Xiangrui Meng] add actual type in the error message
ad938bf [Xiangrui Meng] StringIndexer handles numeric input.
It shouldn't live directly under `spark.ml`.
Author: Xiangrui Meng <meng@databricks.com>
Closes#5749 from mengxr/SPARK-7201 and squashes the following commits:
53847f9 [Xiangrui Meng] move Identifiable to ml.util
The Python SerDe calls `Object.hashCode`, which is very expensive for Vectors. It is not necessary to scan the whole vector, especially for large ones. In this PR, we only scan the first 16 nonzeros. srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes#5697 from mengxr/SPARK-7140 and squashes the following commits:
2abc86d [Xiangrui Meng] typo
8fb7d74 [Xiangrui Meng] update impl
1ebad60 [Xiangrui Meng] only scan the first 16 nonzeros in Vector.hashCode
Author: DB Tsai <dbt@netflix.com>
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#4259 from dbtsai/lir and squashes the following commits:
a81c201 [DB Tsai] add import org.apache.spark.util.Utils back
9fc48ed [DB Tsai] rebase
2178b63 [DB Tsai] add comments
9988ca8 [DB Tsai] addressed feedback and fixed a bug. TODO: documentation and build another synthetic dataset which can catch the bug fixed in this commit.
fcbaefe [DB Tsai] Refactoring
4eb078d [DB Tsai] first commit
jira: https://issues.apache.org/jira/browse/SPARK-7090
LDA was implemented with extensibility in mind. And with the development of OnlineLDA and Gibbs Sampling, we are collecting more detailed requirements from different algorithms.
As Joseph Bradley jkbradley proposed in https://github.com/apache/spark/pull/4807 and with some further discussion, we'd like to adjust the code structure a little to present the common interface and extension point clearly.
Basically class LDA would be a common entrance for LDA computing. And each LDA object will refer to a LDAOptimizer for the concrete algorithm implementation. Users can customize LDAOptimizer with specific parameters and assign it to LDA.
Concrete changes:
1. Add a trait `LDAOptimizer`, which defines the common iterface for concrete implementations. Each subClass is a wrapper for a specific LDA algorithm.
2. Move EMOptimizer to file LDAOptimizer and inherits from LDAOptimizer, rename to EMLDAOptimizer. (in case a more generic EMOptimizer comes in the future)
-adjust the constructor of EMOptimizer, since all the parameters should be passed in through initialState method. This can avoid unwanted confusion or overwrite.
-move the code from LDA.initalState to initalState of EMLDAOptimizer
3. Add property ldaOptimizer to LDA and its getter/setter, and EMLDAOptimizer is the default Optimizer.
4. Change the return type of LDA.run from DistributedLDAModel to LDAModel.
Further work:
add OnlineLDAOptimizer and other possible Optimizers once ready.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#5661 from hhbyyh/ldaRefactor and squashes the following commits:
0e2e006 [Yuhao Yang] respond to review comments
08a45da [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaRefactor
e756ce4 [Yuhao Yang] solve mima exception
d74fd8f [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into ldaRefactor
0bb8400 [Yuhao Yang] refactor LDA with Optimizer
ec2f857 [Yuhao Yang] protoptype for discussion
1. predict(predict.toString) has already output prefix “predict” thus it’s duplicated to print ", predict = " again
2. there are some extra spaces
Author: Alain <aihe@usc.edu>
Closes#5687 from AiHe/tree-node-issue-2 and squashes the following commits:
9862b9a [Alain] Pass scala coding style checking
44ba947 [Alain] Minor][MLLIB] Format toString method in MLLIB
bdc402f [Alain] [Minor][MLLIB] Fix a formatting bug in toString method in Node
426eee7 [Alain] [Minor][MLLIB] Fix a formatting bug in toString method in Node.scala
This is a continuation of [https://github.com/apache/spark/pull/5530] (which was for Decision Trees), but for ensembles: Random Forests and Gradient-Boosted Trees. Please refer to the JIRA [https://issues.apache.org/jira/browse/SPARK-6113], the design doc linked from the JIRA, and the previous PR linked above for design discussions.
This PR follows the example set by the previous PR for Decision Trees. It includes a few cleanups to Decision Trees.
Note: There is one issue which will be addressed in a separate PR: Ensembles' component Models have no parent or fittingParamMap. I plan to submit a separate PR which makes those values in Model be Options. It does not matter much which PR gets merged first.
CC: mengxr manishamde codedeft chouqin
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5626 from jkbradley/dt-api-ensembles and squashes the following commits:
729167a [Joseph K. Bradley] small cleanups based on code review
bbae2a2 [Joseph K. Bradley] Updated per all comments in code review
855aa9a [Joseph K. Bradley] scala style fix
ea3d901 [Joseph K. Bradley] Added GBT to spark.ml, with tests and examples
c0f30c1 [Joseph K. Bradley] Added random forests and test suites to spark.ml. Not tested yet. Need to add example as well
d045ebd [Joseph K. Bradley] some more updates, but far from done
ee1a10b [Joseph K. Bradley] Added files from old PR and did some initial updates.
See [SPARK-6528](https://issues.apache.org/jira/browse/SPARK-6528). Add IDF transformer in ML package.
Author: Xusen Yin <yinxusen@gmail.com>
Closes#5266 from yinxusen/SPARK-6528 and squashes the following commits:
741db31 [Xusen Yin] get param from new paramMap
d169967 [Xusen Yin] add final to param and IDF class
c9c3759 [Xusen Yin] simplify test suite
5867c09 [Xusen Yin] refine IDF transformer with new interfaces
7727cae [Xusen Yin] Merge branch 'master' into SPARK-6528
4338a37 [Xusen Yin] Merge branch 'master' into SPARK-6528
aef2cdf [Xusen Yin] add doc and group for param
5760b49 [Xusen Yin] fix code style
2add691 [Xusen Yin] fix code style and test
03fbecb [Xusen Yin] remove duplicated code
2aa4be0 [Xusen Yin] clean test suite
4802c67 [Xusen Yin] add IDF transformer and test suite
yinxusen
Author: Xiangrui Meng <meng@databricks.com>
Closes#5681 from mengxr/SPARK-7115 and squashes the following commits:
9ac27cd [Xiangrui Meng] skip the very first 1 in poly expansion
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5649 from mengxr/SPARK-7070 and squashes the following commits:
c66023c [Xiangrui Meng] setBeta should call setTopicConcentration
Author: wizz <wizz@wizz-dev01.kawasaki.flab.fujitsu.com>
Closes#5658 from kuromatsu-nobuyuki/SPARK-7085 and squashes the following commits:
6ec2d21 [wizz] Fix miniBatchFraction parameter in train method called with 4 arguments
Author: Reynold Xin <rxin@databricks.com>
Closes#5648 from rxin/vectorAssembler-boolean and squashes the following commits:
1bf3d40 [Reynold Xin] [MLlib] Add support for BooleanType to VectorAssembler.
Author: Reynold Xin <rxin@databricks.com>
Closes#5642 from rxin/mllib-native-type and squashes the following commits:
e23af5b [Reynold Xin] Remove StringType
7cbb205 [Reynold Xin] [SPARK-7066][MLlib] VectorAssembler should use NumericType and StringType, not NativeType.
Author: Reynold Xin <rxin@databricks.com>
Closes#5644 from rxin/mllib-nullable and squashes the following commits:
a727e5b [Reynold Xin] [MLlib] UnaryTransformer nullability should not depend on primitive types.
This does a few clean-ups. With this PR, all spark.ml tree components have ```private[ml]``` constructors.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5567 from jkbradley/dt-api-dt2 and squashes the following commits:
2263b5b [Joseph K. Bradley] Added note about tree example issue.
bb9f610 [Joseph K. Bradley] Small cleanups after original tree API PR
add missing comma and space
Author: Alain <aihe@usc.edu>
Closes#5621 from AiHe/tree-node-issue and squashes the following commits:
159a7bb [Alain] [Minor][MLLIB] Fix a minor formatting bug in toString methods in Node.scala
(cherry picked from commit 4508f01890a723f80d631424ff8eda166a13a727)
Signed-off-by: Xiangrui Meng <meng@databricks.com>
1. Use blas calls to find the dot product between two vectors.
2. Prevent re-computing the L2 norm of the given vector for each word in model.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5467 from MechCoder/spark-6065 and squashes the following commits:
dd0b0b2 [MechCoder] Preallocate wordVectors
ffc9240 [MechCoder] Minor
6b74c81 [MechCoder] Switch back to native blas calls
da1642d [MechCoder] Explicit types and indexing
64575b0 [MechCoder] Save indexedmap and a wordvecmat instead of matrix
fbe0108 [MechCoder] Made the following changes 1. Calculate norms during initialization. 2. Use Blas calls from linalg.blas
1350cf3 [MechCoder] [SPARK-6065] Optimize word2vec.findSynonynms using blas calls
Since sparse matrices now support a isTransposed flag for row major data, DenseMatrices should do the same.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5455 from MechCoder/spark-6845 and squashes the following commits:
525c370 [MechCoder] minor
004a37f [MechCoder] Cast boolean to int
151f3b6 [MechCoder] [WIP] Add isTransposed to pickle DenseMatrix
cc0b90a [MechCoder] [SPARK-6845] Add isTranposed flag to DenseMatrix
Model import/export for IsotonicRegression
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5270 from yanboliang/spark-5990 and squashes the following commits:
872028d [Yanbo Liang] fix code style
f80ec1b [Yanbo Liang] address comments
49600cc [Yanbo Liang] address comments
429ff7d [Yanbo Liang] store each interval as a record
2b2f5a1 [Yanbo Liang] Model import/export for IsotonicRegression
The current implementation call the default constructor of mllib.feature.StandarScaler without the possibility to specify withMean or withStd options.
Author: jrabary <Jaonary@gmail.com>
Closes#4704 from jrabary/master and squashes the following commits:
fae8568 [jrabary] style fix
8896b0e [jrabary] Comments fix
ef96d73 [jrabary] style fix
8e52607 [jrabary] style fix
edd9d48 [jrabary] Fix default param initialization
17e1a76 [jrabary] Fix default param initialization
298f405 [jrabary] Typo fix
45ed914 [jrabary] Add withMean and withStd params to StandarScaler
Title says it all.
cc rxin tdas
Author: zsxwing <zsxwing@gmail.com>
Closes#5554 from zsxwing/SPARK-6979 and squashes the following commits:
5304350 [zsxwing] Fix NotSerializableException
e9d3479 [zsxwing] Add blank lines
633e279 [zsxwing] Fix NotSerializableException
e496ace [zsxwing] Replace JobGenerator.eventActor with EventLoop
ec6ec58 [zsxwing] Fix the import order
ce0fa73 [zsxwing] Replace JobScheduler.eventActor with EventLoop
If `StreamingKMeans` is not `Serializable`, we cannot do checkpoint for applications that using `StreamingKMeans`. So we should make it `Serializable`.
Author: zsxwing <zsxwing@gmail.com>
Closes#5582 from zsxwing/SPARK-6998 and squashes the following commits:
67c2a14 [zsxwing] Make StreamingKMeans 'Serializable'
This is a PR for cleaning up and finalizing the DecisionTree API. PRs for ensembles will follow once this is merged.
### Goal
Here is the description copied from the JIRA (for both trees and ensembles):
> **Issue**: The APIs for DecisionTree and ensembles (RandomForests and GradientBoostedTrees) have been experimental for a long time. The API has become very convoluted because trees and ensembles have many, many variants, some of which we have added incrementally without a long-term design.
> **Proposal**: This JIRA is for discussing changes required to finalize the APIs. After we discuss, I will make a PR to update the APIs and make them non-Experimental. This will require making many breaking changes; see the design doc for details.
> **[Design doc](https://docs.google.com/document/d/1rJ_DZinyDG3PkYkAKSsQlY0QgCeefn4hUv7GsPkzBP4)** : This outlines current issues and the proposed API.
Overall code layout:
* The old API in mllib.tree.* will remain the same.
* The new API will reside in ml.classification.* and ml.regression.*
### Summary of changes
Old API
* Exactly the same, except I made 1 method in Loss private (but that is not a breaking change since that method was introduced after the Spark 1.3 release).
New APIs
* Under Pipeline API
* The new API preserves functionality, except:
* New API does NOT store prob (probability of label in classification). I want to have it store the full vector of probabilities but feel that should be in a later PR.
* Use abstractions for parameters, estimators, and models to avoid code duplication
* Limit parameters to relevant algorithms
* For enum-like types, only expose Strings
* We can make these pluggable later on by adding new parameters. That is a far-future item.
Test suites
* I organized DecisionTreeSuite, but I made absolutely no changes to the tests themselves.
* The test suites for the new API only test (a) similarity with the results of the old API and (b) elements of the new API.
* After code is moved to this new API, we should move the tests from the old suites which test the internals.
### Details
#### Changed names
Parameters
* useNodeIdCache -> cacheNodeIds
#### Other changes
* Split: Changed categories to set instead of list
#### Non-decision tree changes
* AttributeGroup
* Added parentheses to toMetadata, toStructField methods (These were removed in a previous PR, but I ran into 1 issue with the Scala compiler not being able to disambiguate between a toMetadata method with no parentheses and a toMetadata method which takes 1 argument.)
* Attributes
* Renamed: toMetadata -> toMetadataImpl
* Added toMetadata methods which return ML metadata (keyed with “ML_ATTR”)
* NominalAttribute: Added getNumValues method which examines both numValues and values.
* Params.inheritValues: Checks whether the parent param really belongs to the child (to allow Estimator-Model pairs with different sets of parameters)
### Questions for reviewers
* Is "DecisionTreeClassificationModel" too long a name?
* Is this OK in the docs?
```
class DecisionTreeRegressor extends TreeRegressor[DecisionTreeRegressionModel] with DecisionTreeParams[DecisionTreeRegressor] with TreeRegressorParams[DecisionTreeRegressor]
```
### Future
We should open up the abstractions at some point. E.g., it would be useful to be able to set tree-related parameters in 1 place and then pass those to multiple tree-based algorithms.
Follow-up JIRAs will be (in this order):
* Tree ensembles
* Deprecate old tree code
* Move DecisionTree implementation code to new API.
* Move tests from the old suites which test the internals.
* Update programming guide
* Python API
* Change RandomForest* to always use bootstrapping, even when numTrees = 1
* Provide the probability of the predicted label for classification. After we move code to the new API and update it to maintain probabilities for all labels, then we can add the probabilities to the new API.
CC: mengxr manishamde codedeft chouqin MechCoder
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#5530 from jkbradley/dt-api-dt and squashes the following commits:
6aae255 [Joseph K. Bradley] Changed tree abstractions not to take type parameters, and for setters to return this.type instead
ec17947 [Joseph K. Bradley] Updates based on code review. Main changes were: moving public types from ml.impl.tree to ml.tree, modifying CategoricalSplit to take an Array of categories but store a Set internally, making more types sealed or final
5626c81 [Joseph K. Bradley] style fixes
f8fbd24 [Joseph K. Bradley] imported reorg of DecisionTreeSuite from old PR. small cleanups
7ef63ed [Joseph K. Bradley] Added DecisionTreeRegressor, test suites, and example (for real this time)
e11673f [Joseph K. Bradley] Added DecisionTreeRegressor, test suites, and example
119f407 [Joseph K. Bradley] added DecisionTreeClassifier example
0bdc486 [Joseph K. Bradley] fixed issues after param PR was merged
f9fbb60 [Joseph K. Bradley] Done with DecisionTreeClassifier, but no save/load yet. Need to add example as well
2532c9a [Joseph K. Bradley] partial move to spark.ml API, not done yet
c72c1a0 [Joseph K. Bradley] Copied changes for common items, plus DecisionTreeClassifier from original PR
This PR update PySpark to support Python 3 (tested with 3.4).
Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped.
TODO: ec2/spark-ec2.py is not fully tested with python3.
Author: Davies Liu <davies@databricks.com>
Author: twneale <twneale@gmail.com>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#5173 from davies/python3 and squashes the following commits:
d7d6323 [Davies Liu] fix tests
6c52a98 [Davies Liu] fix mllib test
99e334f [Davies Liu] update timeout
b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
cafd5ec [Davies Liu] adddress comments from @mengxr
bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
179fc8d [Davies Liu] tuning flaky tests
8c8b957 [Davies Liu] fix ResourceWarning in Python 3
5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
4006829 [Davies Liu] fix test
2fc0066 [Davies Liu] add python3 path
71535e9 [Davies Liu] fix xrange and divide
5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ed498c8 [Davies Liu] fix compatibility with python 3
820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ad7c374 [Davies Liu] fix mllib test and warning
ef1fc2f [Davies Liu] fix tests
4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
59bb492 [Davies Liu] fix tests
1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ca0fdd3 [Davies Liu] fix code style
9563a15 [Davies Liu] add imap back for python 2
0b1ec04 [Davies Liu] make python examples work with Python 3
d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
a716d34 [Davies Liu] test with python 3.4
f1700e8 [Davies Liu] fix test in python3
671b1db [Davies Liu] fix test in python3
692ff47 [Davies Liu] fix flaky test
7b9699f [Davies Liu] invalidate import cache for Python 3.3+
9c58497 [Davies Liu] fix kill worker
309bfbf [Davies Liu] keep compatibility
5707476 [Davies Liu] cleanup, fix hash of string in 3.3+
8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
f53e1f0 [Davies Liu] fix tests
70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3
a39167e [Davies Liu] support customize class in __main__
814c77b [Davies Liu] run unittests with python 3
7f4476e [Davies Liu] mllib tests passed
d737924 [Davies Liu] pass ml tests
375ea17 [Davies Liu] SQL tests pass
6cc42a9 [Davies Liu] rename
431a8de [Davies Liu] streaming tests pass
78901a7 [Davies Liu] fix hash of serializer in Python 3
24b2f2e [Davies Liu] pass all RDD tests
35f48fe [Davies Liu] run future again
1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py
6e3c21d [Davies Liu] make cloudpickle work with Python3
2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run
1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out
7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work.
b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?).
f40d925 [twneale] xrange --> range
e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206
79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper
2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3
854be27 [Josh Rosen] Run `futurize` on Python code:
7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
Same as #5431 but for Python. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5534 from mengxr/SPARK-6893 and squashes the following commits:
d3b519b [Xiangrui Meng] address comments
ebaccc6 [Xiangrui Meng] style update
fce244e [Xiangrui Meng] update explainParams with test
4d6b07a [Xiangrui Meng] add tests
5294500 [Xiangrui Meng] update default param handling in python
This pr adds informative error messages to all require statements in the Vectors class that did not previously have them. This references [SPARK-6938](https://issues.apache.org/jira/browse/SPARK-6938).
Author: Juliet Hougland <juliet@cloudera.com>
Closes#5532 from jhlch/SPARK-6938 and squashes the following commits:
ab321bb [Juliet Hougland] Remove braces from string interpolation when not required.
1221f94 [Juliet Hougland] All require statements now have an informative error message.
The previous PR https://github.com/apache/spark/pull/4906 helped to extract the learning curve giving the error for each iteration. This continues the work refactoring some code and extending the same logic during training and validation.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5330 from MechCoder/spark-5972 and squashes the following commits:
0b5d659 [MechCoder] minor
32d409d [MechCoder] EvaluateeachIteration and training cache should follow different paths
d542bb0 [MechCoder] Remove unused imports and docs
58f4932 [MechCoder] Remove unpersist
70d3b4c [MechCoder] Broadcast for each tree
5869533 [MechCoder] Access broadcasted values locally and other minor changes
923dbf6 [MechCoder] [SPARK-5972] Cache residuals and gradient in GBT during training and validation
See JIRA issue [SPARK-5988](https://issues.apache.org/jira/browse/SPARK-5988).
Author: Xusen Yin <yinxusen@gmail.com>
Closes#5450 from yinxusen/SPARK-5988 and squashes the following commits:
cb1ecfa [Xusen Yin] change Assignment into case class
b1dd24c [Xusen Yin] add test suite
63c3923 [Xusen Yin] add save load for power iteration clustering
This PR adds string indexer, which takes a column of string labels and outputs a double column with labels indexed by their frequency.
TODOs:
- [x] store feature to index map in output metadata
Author: Xiangrui Meng <meng@databricks.com>
Closes#4735 from mengxr/SPARK-5886 and squashes the following commits:
d82575f [Xiangrui Meng] fix test
700e70f [Xiangrui Meng] rename LabelIndexer to StringIndexer
16a6f8c [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5886
457166e [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5886
f8b30f4 [Xiangrui Meng] update label indexer to output metadata
e81ec28 [Xiangrui Meng] Merge branch 'openhashmap-contains' into SPARK-5886-2
d6e6f1f [Xiangrui Meng] add contains to primitivekeyopenhashmap
748a69b [Xiangrui Meng] add contains to OpenHashMap
def3c5c [Xiangrui Meng] add LabelIndexer
**Ready for review!**
Since the original PR, I moved the code to the spark.ml API and renamed this to VectorIndexer.
This introduces a VectorIndexer class which does the following:
* VectorIndexer.fit(): collect statistics about how many values each feature in a dataset (RDD[Vector]) can take (limited by maxCategories)
* Feature which exceed maxCategories are declared continuous, and the Model will treat them as such.
* VectorIndexerModel.transform(): Convert categorical feature values to corresponding 0-based indices
Design notes:
* This maintains sparsity in vectors by ensuring that categorical feature value 0.0 gets index 0.
* This does not yet support transforming data with new (unknown) categorical feature values. That can be added later.
* This is necessary for DecisionTree and tree ensembles.
Reviewers: Please check my use of metadata and my unit tests for it; I'm not sure if I covered everything in the tests.
Other notes:
* This also adds a public toMetadata method to AttributeGroup (for simpler construction of metadata).
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#3000 from jkbradley/indexer and squashes the following commits:
5956d91 [Joseph K. Bradley] minor cleanups
f5c57a8 [Joseph K. Bradley] added Java test suite
643b444 [Joseph K. Bradley] removed FeatureTests
02236c3 [Joseph K. Bradley] Updated VectorIndexer, ready for PR
286d221 [Joseph K. Bradley] Reworked DatasetIndexer for spark.ml API, and renamed it to VectorIndexer
12e6cf2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into indexer
6d8f3f1 [Joseph K. Bradley] Added partly done DatasetIndexer to spark.ml
6a2f553 [Joseph K. Bradley] Updated TODO for allowUnknownCategories
3f041f8 [Joseph K. Bradley] Final cleanups for DatasetIndexer
038b9e3 [Joseph K. Bradley] DatasetIndexer now maintains sparsity in SparseVector
3a4a0bd [Joseph K. Bradley] Added another test for DatasetIndexer
2006923 [Joseph K. Bradley] DatasetIndexer now passes tests
f409987 [Joseph K. Bradley] partly done with DatasetIndexerSuite
5e7c874 [Joseph K. Bradley] working on DatasetIndexer
This is the sub-task of SPARK-6254.
Wrap missing method for `StandardScalerModel`.
Author: lewuathe <lewuathe@me.com>
Closes#5310 from Lewuathe/SPARK-6643 and squashes the following commits:
fafd690 [lewuathe] Fix for lint-python
bd31a64 [lewuathe] Merge branch 'master' into SPARK-6643
578f5ee [lewuathe] Remove unnecessary class
a38f155 [lewuathe] Merge master
66bb2ab [lewuathe] Fix typos
82683a0 [lewuathe] [SPARK-6643] Implement StandardScalerModel missing methods
cc marmbrus
Author: Volodymyr Lyubinets <vlyubin@gmail.com>
Closes#5279 from vlyubin/speedup and squashes the following commits:
e75a387 [Volodymyr Lyubinets] Changes to ScalaUDF
11a20ec [Volodymyr Lyubinets] Avoid creating a tuple
c327bc9 [Volodymyr Lyubinets] Moved the only remaining function from DataTypeConversions to DateUtils
dec6802 [Volodymyr Lyubinets] Addresed review feedback
74301fa [Volodymyr Lyubinets] Addressed review comments
afa3aa5 [Volodymyr Lyubinets] Minor refactoring, added license, removed debug output
881dc60 [Volodymyr Lyubinets] Moved to a separate module; addressed review comments; one extra place of usage; changed behaviour for Java
8cad6e2 [Volodymyr Lyubinets] Addressed review commments
41b2aa9 [Volodymyr Lyubinets] Creating converters for ScalaReflection stuff, and more
jira: https://issues.apache.org/jira/browse/SPARK-6693
It's kind of annoying when debugging and found you cannot print out the matrix as you want.
original toString of Matrix only print like following,
0.17810102596909183 0.5616906241468385 ... (10 total)
0.9692861997823815 0.015558159784155756 ...
0.8513015122819192 0.031523763918528847 ...
0.5396875653953941 0.3267864552779176 ...
The def toString(maxLines : Int, maxWidth : Int) is useful when debuging, logging and saving matrix to files.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#5344 from hhbyyh/addToString and squashes the following commits:
19a6836 [Yuhao Yang] remove extra line
6314b21 [Yuhao Yang] add exclude
736c324 [Yuhao Yang] add ut and exclude
420da39 [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into addToString
c22f352 [Yuhao Yang] style change
64a9e0f [Yuhao Yang] add specific to string to matrix
Support FPGrowth algorithm in Python API.
Should we remove "Experimental" which were marked for FPGrowth and FPGrowthModel in Scala? jkbradley
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5213 from yanboliang/spark-6264 and squashes the following commits:
ed62ead [Yanbo Liang] trigger jenkins
8ce0359 [Yanbo Liang] fix docstring style
544c725 [Yanbo Liang] address comments
a2d7cf7 [Yanbo Liang] add doc for FPGrowth.train()
dcf7d73 [Yanbo Liang] add python doc
b18fd07 [Yanbo Liang] trigger jenkins
2c951b8 [Yanbo Liang] fix typos
7f62c8f [Yanbo Liang] add fpm to __init__.py
b96206a [Yanbo Liang] Support FPGrowth algorithm in Python API
https://issues.apache.org/jira/browse/SPARK-6758
I am not sure if it is ok to block them in test resources too (as we shade jetty in assembly?).
Author: WangTaoTheTonic <wangtao111@huawei.com>
Closes#5406 from WangTaoTheTonic/SPARK-6758 and squashes the following commits:
e09605b [WangTaoTheTonic] block the right jetty package
So we can turn style checker on for test code.
Author: Reynold Xin <rxin@databricks.com>
Closes#5411 from rxin/test-style-mllib and squashes the following commits:
d8a2569 [Reynold Xin] [SPARK-6765] Fix test code style for mllib.
I have the fit intercept enabled by default for logistic regression, I
wonder what others think here. I understand that it enables allocation
by default which is undesirable, but one needs to have a very strong
reason for not having an intercept term enabled so it is the safer
default from a statistical sense.
Explicitly modeling the intercept by adding a column of all 1s does not
work. I believe the reason is that since the API for
LogisticRegressionWithLBFGS forces column normalization, and a column of all
1s has 0 variance so dividing by 0 kills it.
Author: Omede Firouz <ofirouz@palantir.com>
Closes#5301 from oefirouz/addIntercept and squashes the following commits:
9f1286b [Omede Firouz] [SPARK-6705][MLLIB] Add fitInterceptTerm to LogisticRegression
1d6bd6f [Omede Firouz] [SPARK-6705][MLLIB] Add a fit intercept term to ML LogisticRegression
9963509 [Omede Firouz] [MLLIB] Add fitIntercept to LogisticRegression
2257fca [Omede Firouz] [MLLIB] Add fitIntercept param to logistic regression
329c1e2 [Omede Firouz] [MLLIB] Add fit intercept term
bd9663c [Omede Firouz] [MLLIB] Add fit intercept api to ml logisticregression
Author: Vinod K C <vinod.kc@huawei.com>
Closes#5384 from vinodkc/Suppression_Scala_existential_code and squashes the following commits:
82a3a1f [Vinod K C] Added scala.language.existentials
Use Iterators in columnSimilarities to allow mapPartitionsWithIndex to spill to disk. This could happen in a dense and large column - this way Spark can spill the pairs onto disk instead of building all the pairs before handing them to Spark.
Another PR coming to update documentation.
Author: Reza Zadeh <reza@databricks.com>
Closes#5364 from rezazadeh/optmemsim and squashes the following commits:
47c90ba [Reza Zadeh] Iterators in columnSimilarities for flatMap
This is the sub-task of SPARK-6254.
Wrap missing method for `Word2Vec` and `Word2VecModel`.
Author: lewuathe <lewuathe@me.com>
Closes#5296 from Lewuathe/SPARK-6615 and squashes the following commits:
f14c304 [lewuathe] Reorder tests
1d326b9 [lewuathe] Merge master
e2bedfb [lewuathe] Modify test cases
afb866d [lewuathe] [SPARK-6615] Python API for Word2Vec
There's no corresponding printing in linear regression. Here was my previous PR (something weird happened and I can't reopen it) https://github.com/apache/spark/pull/5272
Author: Omede Firouz <ofirouz@palantir.com>
Closes#5338 from oefirouz/println and squashes the following commits:
3f3dbf4 [Omede Firouz] [MLLIB] Remove println
This builds on my earlier pull requests and turns on the explicit type checking in scalastyle.
Author: Reynold Xin <rxin@databricks.com>
Closes#5342 from rxin/SPARK-6428 and squashes the following commits:
7b531ab [Reynold Xin] import ordering
2d9a8a5 [Reynold Xin] jl
e668b1c [Reynold Xin] override
9b9e119 [Reynold Xin] Parenthesis.
82e0cf5 [Reynold Xin] [SPARK-6428] Turn on explicit type checking for public methods.
This patch fixes a reported bug causing model updates to not properly propagate to model predictions during streaming regression. These minor changes in model declaration fix the problem, and I expanded the tests to include the scenario in which the bug was arising. The two new tests failed prior to the patch and now pass.
cc mengxr
Author: freeman <the.freeman.lab@gmail.com>
Closes#5037 from freeman-lab/train-predict-fix and squashes the following commits:
3af953e [freeman] Expand test coverage to include combined training and prediction
8f84fc8 [freeman] Move model declaration
davies
Author: Xiangrui Meng <meng@databricks.com>
Closes#5318 from mengxr/SPARK-6660 and squashes the following commits:
0f66ec2 [Xiangrui Meng] recognize object arrays
ad8c42f [Xiangrui Meng] add a test for SPARK-6660
This PR changes lambda scaling from number of users/items to number of explicit ratings. The latter is the behavior in 1.2. Slight refactor of NormalEquation to make it independent of ALS models. srowen codexiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#5314 from mengxr/SPARK-6642 and squashes the following commits:
dc655a1 [Xiangrui Meng] relax python tests
f410df2 [Xiangrui Meng] use 1.2 scaling and remove addImplicit from NormalEquation
Word2Vec model now supports saving and loading.
a] The Metadata stored in JSON format consists of "version", "classname", "vectorSize" and "numWords"
b] The data stored in Parquet file format consists of an Array of rows with each row consisting of 2 columns, first being the word: String and the second, an Array of Floats.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5291 from MechCoder/spark-5692 and squashes the following commits:
1142f3a [MechCoder] Add numWords to metaData
bfe4c39 [MechCoder] [SPARK-5692] Word2Vec save/load
Python API parity check for classification and multiclass classification support, major disparities need to be added for Python:
```scala
LogisticRegressionWithLBFGS
setNumClasses
setValidateData
LogisticRegressionModel
getThreshold
numClasses
numFeatures
SVMWithSGD
setValidateData
SVMModel
getThreshold
```
For users the greatest benefit in this PR is multiclass classification was supported by Python API.
Users can train multiclass classification model and use it to predict in pyspark.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5137 from yanboliang/spark-6255 and squashes the following commits:
0bd531e [Yanbo Liang] address comments
444d5e2 [Yanbo Liang] LogisticRegressionModel.predict() optimization
fc7990b [Yanbo Liang] address comments
b0d9c63 [Yanbo Liang] Support Mulinomial LR model predict in Python API
ded847c [Yanbo Liang] Python API parity check for classification (support multiclass classification)
Added optional model type parameter for NaiveBayes training. Can be either Multinomial or Bernoulli.
When Bernoulli is given the Bernoulli smoothing is used for fitting and for prediction as per: http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html.
Default for model is original Multinomial fit and predict.
Added additional testing for Bernoulli and Multinomial models.
Author: leahmcguire <lmcguire@salesforce.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Author: Leah McGuire <lmcguire@salesforce.com>
Closes#4087 from leahmcguire/master and squashes the following commits:
f3c8994 [leahmcguire] changed checks on model type to requires
acb69af [leahmcguire] removed enum type and replaces all modelType parameters with strings
2224b15 [Leah McGuire] Merge pull request #2 from jkbradley/leahmcguire-master
9ad89ca [Joseph K. Bradley] removed old code
6a8f383 [Joseph K. Bradley] Added new model save/load format 2.0 for NaiveBayesModel after modelType parameter was added. Updated tests. Also updated ModelType enum-like type.
852a727 [leahmcguire] merged with upstream master
a22d670 [leahmcguire] changed NaiveBayesModel modelType parameter back to NaiveBayes.ModelType, made NaiveBayes.ModelType serializable, fixed getter method in NavieBayes
18f3219 [leahmcguire] removed private from naive bayes constructor for lambda only
bea62af [leahmcguire] put back in constructor for NaiveBayes
01baad7 [leahmcguire] made fixes from code review
fb0a5c7 [leahmcguire] removed typo
e2d925e [leahmcguire] fixed nonserializable error that was causing naivebayes test failures
2d0c1ba [leahmcguire] fixed typo in NaiveBayes
c298e78 [leahmcguire] fixed scala style errors
b85b0c9 [leahmcguire] Merge remote-tracking branch 'upstream/master'
900b586 [leahmcguire] fixed model call so that uses type argument
ea09b28 [leahmcguire] Merge remote-tracking branch 'upstream/master'
e016569 [leahmcguire] updated test suite with model type fix
85f298f [leahmcguire] Merge remote-tracking branch 'upstream/master'
dc65374 [leahmcguire] integrated model type fix
7622b0c [leahmcguire] added comments and fixed style as per rb
b93aaf6 [Leah McGuire] Merge pull request #1 from jkbradley/nb-model-type
3730572 [Joseph K. Bradley] modified NB model type to be more Java-friendly
b61b5e2 [leahmcguire] added back compatable constructor to NaiveBayesModel to fix MIMA test failure
5a4a534 [leahmcguire] fixed scala style error in NaiveBayes
3891bf2 [leahmcguire] synced with apache spark and resolved merge conflict
d9477ed [leahmcguire] removed old inaccurate comment from test suite for mllib naive bayes
76e5b0f [leahmcguire] removed unnecessary sort from test
0313c0c [leahmcguire] fixed style error in NaiveBayes.scala
4a3676d [leahmcguire] Updated changes re-comments. Got rid of verbose populateMatrix method. Public api now has string instead of enumeration. Docs are updated."
ce73c63 [leahmcguire] added Bernoulli option to niave bayes model in mllib, added optional model type parameter for training. When Bernoulli is given the Bernoulli smoothing is used for fitting and for prediction http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html
This fixes `predictAll` after load. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#5243 from mengxr/SPARK-6571 and squashes the following commits:
82dcaa7 [Xiangrui Meng] use wrapper in MatrixFactorizationModel.load
See [SPARK-6526](https://issues.apache.org/jira/browse/SPARK-6526).
mengxr Should we add test suite for this transformer? There is no test suite for all feature transformers in ML package now.
Author: Xusen Yin <yinxusen@gmail.com>
Closes#5181 from yinxusen/SPARK-6526 and squashes the following commits:
6faa7bf [Xusen Yin] fix style
8a462da [Xusen Yin] remove duplications
ab35ab0 [Xusen Yin] add test suite
bc8cd0f [Xusen Yin] fix comment
79774c9 [Xusen Yin] add Normalizer transformer in ML package
There are any bugs of breeze's SparseVector at 0.11.1. You know, Spark 1.3 depends on breeze 0.11.1. So I think we should upgrade it to 0.11.2.
https://issues.apache.org/jira/browse/SPARK-6341
And thanks you for your great cooperation, David Hall(dlwh)
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes#5222 from yu-iskw/upgrade-breeze and squashes the following commits:
ad8a688 [Yu ISHIKAWA] Upgrade breeze from 0.11.1 to 0.11.2 because of a bug of SparseVector. Thanks you for your great cooperation, David Hall(@dlwh)
minor thing. Let me know if jira is required.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#5207 from hhbyyh/adjustImport and squashes the following commits:
2240121 [Yuhao Yang] remove unused import
Should be self explanatory.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4986 from MechCoder/spark-5987 and squashes the following commits:
7d2cd56 [MechCoder] Iterate over dataframe in a better way
e7a14cb [MechCoder] Minor
33c84f9 [MechCoder] Store as Array[Data] instead of Data[Array]
505bd57 [MechCoder] Rebased over master and used MatrixUDT
7422bb4 [MechCoder] Store sigmas as Array[Double] instead of Array[Array[Double]]
b9794e4 [MechCoder] Minor
cb77095 [MechCoder] [SPARK-5987] Save/load for GaussianMixtureModels
MLlib Python API parity check for Regression, major disparities need to be added for Python list following:
```scala
LinearRegressionWithSGD
setValidateData
LassoWithSGD
setIntercept
setValidateData
RidgeRegressionWithSGD
setIntercept
setValidateData
```
setFeatureScaling is mllib private function which is not needed to expose in pyspark.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#4997 from yanboliang/spark-6256 and squashes the following commits:
102f498 [Yanbo Liang] fix intercept issue & add doc test
1fb7b4f [Yanbo Liang] change 'intercept' to 'addIntercept'
de5ecbc [Yanbo Liang] MLlib Python API parity check for regression
Added a Regex based tokenizer for ml.
Currently the regex is fixed but if I could add a regex type paramater to the paramMap,
changing the tokenizer regex could be a parameter used in the crossValidation.
Also I wonder what would be the best way to add a stop word list.
Author: Augustin Borsu <augustin@sagacify.com>
Author: Augustin Borsu <a.borsu@gmail.com>
Author: Augustin Borsu <aborsu@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#4504 from aborsu985/master and squashes the following commits:
716d257 [Augustin Borsu] Merge branch 'mengxr-SPARK-5566'
cb07021 [Augustin Borsu] Merge branch 'SPARK-5566' of git://github.com/mengxr/spark into mengxr-SPARK-5566
5f09434 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
a164800 [Xiangrui Meng] remove tabs
556aa27 [Xiangrui Meng] Merge branch 'aborsu985-master' into SPARK-5566
9651aec [Xiangrui Meng] update test
f96526d [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5566
2338da5 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
e88d7b8 [Xiangrui Meng] change pattern to a StringParameter; update tests
148126f [Augustin Borsu] Added return type to public functions
12dddb4 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
daf685e [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
6a85982 [Augustin Borsu] Style corrections
38b95a1 [Augustin Borsu] Added Java unit test for RegexTokenizer
b66313f [Augustin Borsu] Modified the pattern Param so it is compiled when given to the Tokenizer
e262bac [Augustin Borsu] Added unit tests in scala
cd6642e [Augustin Borsu] Changed regex to pattern
132b00b [Augustin Borsu] Changed matching to gaps and removed case folding
201a107 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
cb9c9a7 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
d3ef6d3 [Augustin Borsu] Added doc to RegexTokenizer
9082fc3 [Augustin Borsu] Removed stopwords parameters and updated doc
19f9e53 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
f6a5002 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
7f930bb [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
77ff9ca [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
2e89719 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
196cd7a [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
11ca50f [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
9f8685a [Augustin Borsu] RegexTokenizer
9e07a78 [Augustin Borsu] Merge remote-tracking branch 'upstream/master'
9547e9d [Augustin Borsu] RegEx Tokenizer
01cd26f [Augustin Borsu] RegExTokenizer
In GeneralizedLinearAlgorithm ```numFeatures``` is default to -1, we need to update it to correct value when we call run() to train a model.
```LogisticRegressionWithLBFGS.run(input)``` works well, but when we call ```LogisticRegressionWithLBFGS.run(input, initialWeights)``` to train multiclass classification model, it will throw exception due to the numFeatures is not updated.
In this PR, we just update numFeatures at the beginning of GeneralizedLinearAlgorithm.run(input, initialWeights) and add test case.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5167 from yanboliang/spark-6496 and squashes the following commits:
8131c48 [Yanbo Liang] LogisticRegressionWithLBFGS.run(input, initialWeights) should initialize numFeatures
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5118 from MechCoder/spark-6308 and squashes the following commits:
6c8ffab [MechCoder] Add test for simpleString
b966242 [MechCoder] [SPARK-6308] [MLlib][Sql] VectorUDT is displayed as vecto in dtypes
Author: vinodkc <vinod.kc.in@gmail.com>
Closes#5112 from vinodkc/spark_1.3_doc_fixes and squashes the following commits:
2c6aee6 [vinodkc] Spark 1.3 doc fixes
Added evaluateEachIteration to allow the user to manually extract the error for each iteration of GradientBoosting. The internal optimisation can be dealt with later.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4906 from MechCoder/spark-6025 and squashes the following commits:
67146ab [MechCoder] Minor
352001f [MechCoder] Minor
6e8aa10 [MechCoder] Made the following changes Used mapPartition instead of map Refactored computeError and unpersisted broadcast variables
bc99ac6 [MechCoder] Refactor the method and stuff
dbda033 [MechCoder] [SPARK-6025] Add helper method evaluateEachIteration to extract learning curve
Utilities to serialize and deserialize Matrices in MLlib
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#5048 from MechCoder/spark-6309 and squashes the following commits:
05dc6f2 [MechCoder] Hashcode and organize imports
16d5d47 [MechCoder] Test some more
6e67020 [MechCoder] TST: Test using Array conversion instead of equals
7fa7a2c [MechCoder] [SPARK-6309] [SQL] [MLlib] Implement MatrixUDT
Add checkpiontInterval to ALS to prevent:
1. StackOverflow exceptions caused by long lineage,
2. large shuffle files generated during iterations,
3. slow recovery when some node fail.
srowen coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#5076 from mengxr/SPARK-5955 and squashes the following commits:
df56791 [Xiangrui Meng] update impl to reuse code
29affcb [Xiangrui Meng] do not materialize factors in implicit
20d3f7f [Xiangrui Meng] add checkpointInterval to ALS
This PR implements two functions
- `topByKey(num: Int): RDD[(K, Array[V])]` finds the top-k values for each key in a pair RDD. This can be used, e.g., in computing top recommendations.
- `takeOrderedByKey(num: Int): RDD[(K, Array[V])] ` does the opposite of `topByKey`
The `sorted` is used here as the `toArray` method of the PriorityQueue does not return a necessarily sorted array.
Author: Shuo Xiang <shuoxiangpub@gmail.com>
Closes#5075 from coderxiang/topByKey and squashes the following commits:
1611c37 [Shuo Xiang] code clean up
6f565c0 [Shuo Xiang] naming
a80e0ec [Shuo Xiang] typo and warning
82dded9 [Shuo Xiang] Merge remote-tracking branch 'upstream/master' into topByKey
d202745 [Shuo Xiang] move to MLPairRDDFunctions
901b0af [Shuo Xiang] style check
70c6e35 [Shuo Xiang] remove takeOrderedByKey, update doc and test
0895c17 [Shuo Xiang] Merge remote-tracking branch 'upstream/master' into topByKey
b10e325 [Shuo Xiang] Merge remote-tracking branch 'upstream/master' into topByKey
debccad [Shuo Xiang] topByKey
I want to add a checker to turn public type checking on, since future pull requests can accidentally expose a non-public type. This is the first cleanup task.
Author: Reynold Xin <rxin@databricks.com>
Closes#5102 from rxin/mllib-hashcode-publicmethodtypes and squashes the following commits:
617f19e [Reynold Xin] Fixed Scala compilation error.
52bc2d5 [Reynold Xin] [MLlib] Added explicit type for public methods and implemented hashCode when equals is defined.
GLM toString prints out intercept, numFeatures.
For LogisticRegression and SVM model, toString also prints out numClasses, threshold.
GLM toDebugString prints out the whole weights, intercept.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes#5038 from yanboliang/spark-6291 and squashes the following commits:
2f578b0 [Yanbo Liang] code format
78b33f2 [Yanbo Liang] fix typos
1e8a023 [Yanbo Liang] GLM toString & toDebugString
I find it's better to have getter for NumFeatures and addIntercept within GeneralizedLinearAlgorithm during actual usage, otherwise I 'll have to get the value through debug.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#5058 from hhbyyh/addGetLinear and squashes the following commits:
9dc90e8 [Yuhao Yang] add get for GeneralizedLinearAlgo
Use `_py2java` and `_java2py` to convert Python model to/from Java model. yinxusen
Author: Xiangrui Meng <meng@databricks.com>
Closes#5049 from mengxr/SPARK-6226-mengxr and squashes the following commits:
570ba81 [Xiangrui Meng] fix python style
b10b911 [Xiangrui Meng] add save/load in PySpark's KMeansModel
LBFGS uses convergence tolerance. This value should be written in document as an argument.
Author: lewuathe <lewuathe@me.com>
Closes#5033 from Lewuathe/SPARK-6336 and squashes the following commits:
e738b33 [lewuathe] Modify text to be more natural
ac03c3a [lewuathe] Modify documentations
6ccb304 [lewuathe] [SPARK-6336] LBFGS should document what convergenceTol means
Note: not relevant for Python API since it only has a static train method
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4969 from jkbradley/SPARK-6252 and squashes the following commits:
a471d90 [Joseph K. Bradley] small edits from review
63eff48 [Joseph K. Bradley] Added getLambda to Scala NaiveBayes
This continues the work in #4460 from srowen . The design doc is published on the JIRA page with some minor changes.
Short description of ML attributes: https://github.com/apache/spark/pull/4925/files?diff=unified#diff-95e7f5060429f189460b44a3f8731a35R24
More details can be found in the design doc.
srowen Could you help review this PR? There are many lines but most of them are boilerplate code.
Author: Xiangrui Meng <meng@databricks.com>
Author: Sean Owen <sowen@cloudera.com>
Closes#4925 from mengxr/SPARK-4588-new and squashes the following commits:
71d1bd0 [Xiangrui Meng] add JavaDoc for package ml.attribute
617be40 [Xiangrui Meng] remove final; rename cardinality to numValues
393ffdc [Xiangrui Meng] forgot to include Java attribute group tests
b1aceef [Xiangrui Meng] more tests
e7ab467 [Xiangrui Meng] update ML attribute impl
7c944da [Sean Owen] Add FeatureType hierarchy and categorical cardinality
2a21d6d [Sean Owen] Initial draft of FeatureAttributes class
jira: https://issues.apache.org/jira/browse/SPARK-6268
KMeans has many setters for parameters. It should have matching getters.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#4974 from hhbyyh/get4Kmeans and squashes the following commits:
f44d4dc [Yuhao Yang] add experimental to getRuns
f94a3d7 [Yuhao Yang] add get for KMeans
The issue is discussed in https://issues.apache.org/jira/browse/SPARK-5669. Replacing all JBLAS usage by netlib-java gives us a simpler dependency tree and less license issues to worry about. I didn't touch the test scope in this PR. The user guide is not modified to avoid merge conflicts with branch-1.3. srowen ankurdave pwendell
Author: Xiangrui Meng <meng@databricks.com>
Closes#4699 from mengxr/SPARK-5814 and squashes the following commits:
48635c6 [Xiangrui Meng] move netlib-java version to parent pom
ca21c74 [Xiangrui Meng] remove jblas from ml-guide
5f7767a [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5814
c5c4183 [Xiangrui Meng] merge master
0f20cad [Xiangrui Meng] add mima excludes
e53e9f4 [Xiangrui Meng] remove jblas from mllib runtime
ceaa14d [Xiangrui Meng] replace jblas by netlib-java in graphx
fa7c2ca [Xiangrui Meng] move jblas to test scope
Resolve javac, scalac warnings of various types -- deprecations, Scala lang, unchecked cast, etc.
Author: Sean Owen <sowen@cloudera.com>
Closes#4950 from srowen/SPARK-6225 and squashes the following commits:
3080972 [Sean Owen] Ordered imports: Java, Scala, 3rd party, Spark
c67985b [Sean Owen] Resolve javac, scalac warnings of various types -- deprecations, Scala lang, unchecked cast, etc.
This PR adds save/load for K-means as described in SPARK-5986. Python version will be added in another PR.
Author: Xusen Yin <yinxusen@gmail.com>
Closes#4951 from yinxusen/SPARK-5986 and squashes the following commits:
6dd74a0 [Xusen Yin] rewrite some functions and classes
cd390fd [Xusen Yin] add indexed point
b144216 [Xusen Yin] remove invalid comments
dce7055 [Xusen Yin] add save/load for k-means for SPARK-5986
A simple wrapper around the Scala implementation. `DataFrame` is used for serialization/deserialization. Methods that return `RDD`s are not supported in this PR.
davies If we recognize Scala's `Product`s in Py4J, we can easily add wrappers for Scala methods that returns `RDD[(Double, Double)]`. Is it easy to register serializer for `Product` in PySpark?
Author: Xiangrui Meng <meng@databricks.com>
Closes#4863 from mengxr/SPARK-6090 and squashes the following commits:
009a3a3 [Xiangrui Meng] provide schema
dcddab5 [Xiangrui Meng] add a basic BinaryClassificationMetrics to PySpark/MLlib
Option 1 of 2: Convert spark-parent module name to spark-parent_2.10 / spark-parent_2.11
Author: Sean Owen <sowen@cloudera.com>
Closes#4912 from srowen/SPARK-6182.1 and squashes the following commits:
eff60de [Sean Owen] Convert spark-parent module name to spark-parent_2.10 / spark-parent_2.11
LBFGS and OWLQN in Breeze 0.10 has convergence check bug.
This is fixed in 0.11, see the description in Breeze project for detail:
https://github.com/scalanlp/breeze/pull/373#issuecomment-76879760
Author: Xiangrui Meng <meng@databricks.com>
Author: DB Tsai <dbtsai@alpinenow.com>
Author: DB Tsai <dbtsai@dbtsai.com>
Closes#4879 from dbtsai/breeze and squashes the following commits:
d848f65 [DB Tsai] Merge pull request #1 from mengxr/AlpineNow-breeze
c2ca6ac [Xiangrui Meng] upgrade to breeze-0.11.1
35c2f26 [Xiangrui Meng] fix LRSuite
397a208 [DB Tsai] upgrade breeze
Issue: When the Python DecisionTree example in the programming guide is run, it runs out of Java Heap Space when using the default memory settings for the spark shell.
This prints a warning.
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4864 from jkbradley/dt-save-heap and squashes the following commits:
02e8daf [Joseph K. Bradley] fixed based on code review
7ecb1ed [Joseph K. Bradley] Added warnings about memory when calling tree and ensemble model save with too small a Java heap size
This PR contains the following changes:
1. Add a new method, `DataType.equalsIgnoreCompatibleNullability`, which is the middle ground between DataType's equality check and `DataType.equalsIgnoreNullability`. For two data types `from` and `to`, it does `equalsIgnoreNullability` as well as if the nullability of `from` is compatible with that of `to`. For example, the nullability of `ArrayType(IntegerType, containsNull = false)` is compatible with that of `ArrayType(IntegerType, containsNull = true)` (for an array without null values, we can always say it may contain null values). However, the nullability of `ArrayType(IntegerType, containsNull = true)` is incompatible with that of `ArrayType(IntegerType, containsNull = false)` (for an array that may have null values, we cannot say it does not have null values).
2. For the `resolved` field of `InsertIntoTable`, use `equalsIgnoreCompatibleNullability` to replace the equality check of the data types.
3. For our data source write path, when appending data, we always use the schema of existing table to write the data. This is important for parquet, since nullability direct impacts the way to encode/decode values. If we do not do this, we may see corrupted values when reading values from a set of parquet files generated with different nullability settings.
4. When generating a new parquet table, we always set nullable/containsNull/valueContainsNull to true. So, we will not face situations that we cannot append data because containsNull/valueContainsNull in an Array/Map column of the existing table has already been set to `false`. This change makes the whole data pipeline more robust.
5. Update the equality check of JSON relation. Since JSON does not really cares nullability, `equalsIgnoreNullability` seems a better choice to compare schemata from to JSON tables.
JIRA: https://issues.apache.org/jira/browse/SPARK-5950
Thanks viirya for the initial work in #4729.
cc marmbrus liancheng
Author: Yin Huai <yhuai@databricks.com>
Closes#4826 from yhuai/insertNullabilityCheck and squashes the following commits:
3b61a04 [Yin Huai] Revert change on equals.
80e487e [Yin Huai] asNullable in UDT.
587d88b [Yin Huai] Make methods private.
0cb7ea2 [Yin Huai] marmbrus's comments.
3cec464 [Yin Huai] Cheng's comments.
486ed08 [Yin Huai] Merge remote-tracking branch 'upstream/master' into insertNullabilityCheck
d3747d1 [Yin Huai] Remove unnecessary change.
8360817 [Yin Huai] Merge remote-tracking branch 'upstream/master' into insertNullabilityCheck
8a3f237 [Yin Huai] Use equalsIgnoreNullability instead of equality check.
0eb5578 [Yin Huai] Fix tests.
f6ed813 [Yin Huai] Update old parquet path.
e4f397c [Yin Huai] Unit tests.
b2c06f8 [Yin Huai] Ignore nullability in JSON relation's equality check.
8bd008b [Yin Huai] nullable, containsNull, and valueContainsNull will be always true for parquet data.
bf50d73 [Yin Huai] When appending data, we use the schema of the existing table instead of the schema of the new data.
0a703e7 [Yin Huai] Test failed again since we cannot read correct content.
9a26611 [Yin Huai] Make InsertIntoTable happy.
8f19fe5 [Yin Huai] equalsIgnoreCompatibleNullability
4ec17fd [Yin Huai] Failed test.
A simple wrapper to save/load `MatrixFactorizationModel` in Python. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#4811 from mengxr/SPARK-5991 and squashes the following commits:
f135dac [Xiangrui Meng] update save doc
57e5200 [Xiangrui Meng] address comments
06140a4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-5991
282ec8d [Xiangrui Meng] support save/load in PySpark's ALS
Remove unicode characters from MLlib file.
Author: Michael Griffiths <msjgriffiths@gmail.com>
Author: Griffiths, Michael (NYC-RPM) <michael.griffiths@reprisemedia.com>
Closes#4815 from msjgriffiths/SPARK-6063 and squashes the following commits:
bcd7de1 [Griffiths, Michael (NYC-RPM)] Change \u201D quote marks around 'theta' to standard single apostrophe (\x27)
38eb535 [Michael Griffiths] Merge pull request #2 from apache/master
b08e865 [Michael Griffiths] Merge pull request #1 from apache/master
Since the validation error does not change monotonically, in practice, it should be proper to pick the best model when training GradientBoostedTrees with validation instead of stopping it early.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4763 from viirya/gbt_record_model and squashes the following commits:
452e049 [Liang-Chi Hsieh] Address comment.
ea2fae2 [Liang-Chi Hsieh] Pick the best model when training GradientBoostedTrees with validation.
The model trained by ALS requires partitioning information to do quick lookup of a user/item factor for making recommendation on individual requests. In the new implementation, we didn't set partitioners in the factors returned by ALS, which would cause performance regression.
srowen coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#4748 from mengxr/SPARK-5976 and squashes the following commits:
9373a09 [Xiangrui Meng] add partitioner to factors returned by ALS
260f183 [Xiangrui Meng] add a test for partitioner
One can early stop if the decrease in error rate is lesser than a certain tol or if the error increases if the training data is overfit.
This introduces a new method runWithValidation which takes in a pair of RDD's , one for the training data and the other for the validation.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4677 from MechCoder/spark-5436 and squashes the following commits:
1bb21d4 [MechCoder] Combine regression and classification tests into a single one
e4d799b [MechCoder] Addresses indentation and doc comments
b48a70f [MechCoder] COSMIT
b928a19 [MechCoder] Move validation while training section under usage tips
fad9b6e [MechCoder] Made the following changes 1. Add section to documentation 2. Return corresponding to bestValidationError 3. Allow negative tolerance.
55e5c3b [MechCoder] One liner for prevValidateError
3e74372 [MechCoder] TST: Add test for classification
77549a9 [MechCoder] [SPARK-5436] Validate GradientBoostedTrees using runWithValidation
For SPARK-5867:
* The spark.ml programming guide needs to be updated to use the new SQL DataFrame API instead of the old SchemaRDD API.
* It should also include Python examples now.
For SPARK-5892:
* Fix Python docs
* Various other cleanups
BTW, I accidentally merged this with master. If you want to compile it on your own, use this branch which is based on spark/branch-1.3 and cherry-picks the commits from this PR: [https://github.com/jkbradley/spark/tree/doc-review-1.3-check]
CC: mengxr (ML), davies (Python docs)
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4675 from jkbradley/doc-review-1.3 and squashes the following commits:
f191bb0 [Joseph K. Bradley] small cleanups
e786efa [Joseph K. Bradley] small doc corrections
6b1ab4a [Joseph K. Bradley] fixed python lint test
946affa [Joseph K. Bradley] Added sample data for ml.MovieLensALS example. Changed spark.ml Java examples to use DataFrames API instead of sql()
da81558 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into doc-review-1.3
629dbf5 [Joseph K. Bradley] Updated based on code review: * made new page for old migration guides * small fixes * moved inherit_doc in python
b9df7c4 [Joseph K. Bradley] Small cleanups: toDF to toDF(), adding s for string interpolation
34b067f [Joseph K. Bradley] small doc correction
da16aef [Joseph K. Bradley] Fixed python mllib docs
8cce91c [Joseph K. Bradley] GMM: removed old imports, added some doc
695f3f6 [Joseph K. Bradley] partly done trying to fix inherit_doc for class hierarchies in python docs
a72c018 [Joseph K. Bradley] made ChiSqTestResult appear in python docs
b05a80d [Joseph K. Bradley] organize imports. doc cleanups
e572827 [Joseph K. Bradley] updated programming guide for ml and mllib
In the previous version, PIC stores clustering assignments as an `RDD[(Long, Int)]`. This is mapped to `RDD<Tuple2<Object, Object>>` in Java and hence Java users have to cast types manually. We should either create a new method called `javaAssignments` that returns `JavaRDD[(java.lang.Long, java.lang.Int)]` or wrap the result pair in a class. I chose the latter approach in this PR. Now assignments are stored as an `RDD[Assignment]`, where `Assignment` is a class with `id` and `cluster`.
Similarly, in FPGrowth, the frequent itemsets are stored as an `RDD[(Array[Item], Long)]`, which is mapped to `RDD<Tuple2<Object, Object>>`. Though we provide a "Java-friendly" method `javaFreqItemsets` that returns `JavaRDD[(Array[Item], java.lang.Long)]`. It doesn't really work because `Array[Item]` is mapped to `Object` in Java. So in this PR I created a class `FreqItemset` to wrap the results. It has `items` and `freq`, as well as a `javaItems` method that returns `List<Item>` in Java.
I'm not certain that the names I chose are proper: `Assignment`/`id`/`cluster` and `FreqItemset`/`items`/`freq`. Please let me know if there are better suggestions.
CC: jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#4695 from mengxr/SPARK-5900 and squashes the following commits:
865b5ca [Xiangrui Meng] make Assignment serializable
cffa96e [Xiangrui Meng] fix test
9c0e590 [Xiangrui Meng] remove unused Tuple2
1b9db3d [Xiangrui Meng] make PIC and FPGrowth Java-friendly
Another one from JoshRosen 's wish list. The first commit is much smaller and removes 2 of the 4 Clock classes. The second is much larger, necessary for consolidating the streaming one. I put together implementations in the way that seemed simplest. Almost all the change is standardizing class and method names.
Author: Sean Owen <sowen@cloudera.com>
Closes#4514 from srowen/SPARK-4682 and squashes the following commits:
5ed3a03 [Sean Owen] Javadoc Clock classes; make ManualClock private[spark]
169dd13 [Sean Owen] Add support for legacy org.apache.spark.streaming clock class names
277785a [Sean Owen] Reduce the net change in this patch by reversing some unnecessary syntax changes along the way
b5e53df [Sean Owen] FakeClock -> ManualClock; getTime() -> getTimeMillis()
160863a [Sean Owen] Consolidate Streaming Clock class into common util Clock
7c956b2 [Sean Owen] Consolidate Clocks except for Streaming Clock
For users to implement their own PipelineStages, we need to make PipelineStage.transformSchema be public instead of private to ml. This would be nice to include in Spark 1.3
CC: mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4682 from jkbradley/SPARK-5902 and squashes the following commits:
6f02357 [Joseph K. Bradley] Made transformSchema public
0e6d0a0 [Joseph K. Bradley] made implementations of transformSchema protected as well
fdaf26a [Joseph K. Bradley] Made PipelineStage.transformSchema protected instead of private[ml]
Updated PIC user guide to reflect API changes and added a simple Java example. The API is still not very Java-friendly. I created SPARK-5990 for this issue.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4680 from mengxr/SPARK-5897 and squashes the following commits:
847d216 [Xiangrui Meng] apache header
87719a2 [Xiangrui Meng] remove PIC image
2dd921f [Xiangrui Meng] update PIC user guide and add a Java example
Although we've migrated to the DataFrame API, lots of code still uses `rdd` or `srdd` as local variable names. This PR tries to address these naming inconsistencies and some other minor DataFrame related style issues.
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/4670)
<!-- Reviewable:end -->
Author: Cheng Lian <lian@databricks.com>
Closes#4670 from liancheng/df-cleanup and squashes the following commits:
3e14448 [Cheng Lian] Cleans up DataFrame variable names and toDF() calls
For unordered features, it is sufficient to use splits since the threshold of the split corresponds the threshold of the HighSplit of the bin and there is no use of the LowSplit.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4231 from MechCoder/spark-3381 and squashes the following commits:
58c19a5 [MechCoder] COSMIT
c274b74 [MechCoder] Remove unordered feature calculation in labeledPointToTreePoint
b2b9b89 [MechCoder] COSMIT
d3ee042 [MechCoder] [SPARK-3381] [MLlib] Eliminate bins for unordered features
`numFeatures` is only used by multinomial logistic regression. Calling `.first()` for every GLM causes performance regression, especially in Python.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4647 from mengxr/SPARK-5858 and squashes the following commits:
036dc7f [Xiangrui Meng] remove unnecessary first() call
12c5548 [Xiangrui Meng] check numFeatures only once
If we need to transform the input data, we should cache the output to avoid re-computing feature vectors every iteration. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#4593 from mengxr/SPARK-5802 and squashes the following commits:
ae3be84 [Xiangrui Meng] cache transformed data in glm
On a big dataset explicitly unpersist train and validation folds allows to load more data into memory in the next loop iteration. On my environment (single node 8Gb worker RAM, 2 GB dataset file, 3 folds for cross validation), saved more than 5 minutes.
Author: Peter Rudenko <petro.rudenko@gmail.com>
Closes#4595 from petro-rudenko/patch-2 and squashes the following commits:
66a7cfb [Peter Rudenko] Move validationDataset cache to declaration
c5f3265 [Peter Rudenko] [Ml] SPARK-5804 Explicitly manage cache in Crossvalidator k-fold loop
If it's a last estimator in Pipeline there's no need to transform data, since there's no next stage that would consume this data.
Author: Peter Rudenko <petro.rudenko@gmail.com>
Closes#4590 from petro-rudenko/patch-1 and squashes the following commits:
d13ec33 [Peter Rudenko] [Ml] SPARK-5796 Don't transform data on a last estimator in Pipeline
This PR adds three groups to the ScalaDoc: `param`, `setParam`, and `getParam`. Params will show up in the generated Scala API doc as the top group. Setters/getters will be at the bottom.
Preview:
Author: Xiangrui Meng <meng@databricks.com>
Closes#4600 from mengxr/SPARK-5730 and squashes the following commits:
febed9a [Xiangrui Meng] add doc groups to spark.ml components
because ArrayBuffer is not specialized.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4594 from mengxr/SPARK-5803 and squashes the following commits:
1261bd5 [Xiangrui Meng] merge master
a4ea872 [Xiangrui Meng] use ArrayBuilder to build primitive arrays
This PR detaches MLlib model import/export code from SQL's JSON support, and hence unblocks #4544 . yhuai
Author: Xiangrui Meng <meng@databricks.com>
Closes#4555 from mengxr/SPARK-5757 and squashes the following commits:
b0415e8 [Xiangrui Meng] replace SQL JSON usage by json4s
The `initialState` of LDA performs several RDD operations that looks redundant. This pr tries to simplify these operations.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4501 from viirya/sim_lda and squashes the following commits:
4870fe4 [Liang-Chi Hsieh] For comments.
9af1487 [Liang-Chi Hsieh] Refactor initial step of LDA to remove redundant operations.
Do not recursively strip out projects. Only strip the first level project.
```scala
df("colA") + df("colB").as("colC")
```
Previously, the above would construct an invalid plan.
Author: Reynold Xin <rxin@databricks.com>
Closes#4519 from rxin/computability and squashes the following commits:
87ff763 [Reynold Xin] Code review feedback.
015c4fc [Reynold Xin] [SQL][DataFrame] Fix column computability.
Deprecate inferSchema() and applySchema(), use createDataFrame() instead, which could take an optional `schema` to create an DataFrame from an RDD. The `schema` could be StructType or list of names of columns.
Author: Davies Liu <davies@databricks.com>
Closes#4498 from davies/create and squashes the following commits:
08469c1 [Davies Liu] remove Scala/Java API for now
c80a7a9 [Davies Liu] fix hive test
d1bd8f2 [Davies Liu] cleanup applySchema
9526e97 [Davies Liu] createDataFrame from RDD with columns
Following discussion in the Jira.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4459 from MechCoder/sparse_gmm and squashes the following commits:
1b18dab [MechCoder] Rewrite syr for sparse matrices
e579041 [MechCoder] Add test for covariance matrix
5cb370b [MechCoder] Separate tests for sparse data
5e096bd [MechCoder] Alphabetize and correct error message
e180f4c [MechCoder] [SPARK-5021] Gaussian Mixture now supports Sparse Input
This is based on #4444 from jkbradley with the following changes:
1. Node schema updated to
~~~
treeId: int
nodeId: Int
predict/
|- predict: Double
|- prob: Double
impurity: Double
isLeaf: Boolean
split/
|- feature: Int
|- threshold: Double
|- featureType: Int
|- categories: Array[Double]
leftNodeId: Integer
rightNodeId: Integer
infoGain: Double
~~~
2. Some refactor of the implementation.
Closes#4444.
Author: Joseph K. Bradley <joseph@databricks.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#4493 from mengxr/SPARK-5597 and squashes the following commits:
75e3bb6 [Xiangrui Meng] fix style
2b0033d [Xiangrui Meng] update tree export schema and refactor the implementation
45873a2 [Joseph K. Bradley] org imports
1d4c264 [Joseph K. Bradley] Added save/load for tree ensembles
dcdbf85 [Joseph K. Bradley] added save/load for decision tree but need to generalize it to ensembles
Fix ARPACK error code mapping, at least. It's not yet clear whether the error is what we expect from ARPACK. If it isn't, not sure if that's to be treated as an MLlib or Breeze issue.
Author: Sean Owen <sowen@cloudera.com>
Closes#4485 from srowen/SPARK-4900 and squashes the following commits:
7355aa1 [Sean Owen] Fix ARPACK error code mapping
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1093 from sryza/sandy-spark-2149 and squashes the following commits:
5f06b33 [Sandy Ryza] More review comments
0f73060 [Sandy Ryza] Respond to Sean's review comments
0dfa005 [Sandy Ryza] SPARK-2149. Univariate kernel density estimation
Check that size of dense matrix array is not beyond Int.MaxValue in Matrices.* methods. jkbradley this should be an easy one. Review and/or merge as you see fit.
Author: Sean Owen <sowen@cloudera.com>
Closes#4461 from srowen/SPARK-4405 and squashes the following commits:
c67574e [Sean Owen] Check that size of dense matrix array is not beyond Int.MaxValue in Matrices.* methods
This is #4447 with `override`.
Closes#4447
Author: Joseph K. Bradley <joseph@databricks.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#4462 from mengxr/SPARK-5660 and squashes the following commits:
f82c8d6 [Xiangrui Meng] add override to matrix.apply
91cedde [Joseph K. Bradley] made matrix apply public
following #4233. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#4422 from mengxr/SPARK-5598 and squashes the following commits:
a059394 [Xiangrui Meng] SaveLoad not extending Loader
14b7ea6 [Xiangrui Meng] address comments
f487cb2 [Xiangrui Meng] add unit tests
62fc43c [Xiangrui Meng] implement save/load for MFM
...ceed max int.
Large values of k and/or n in EigenValueDecomposition.symmetricEigs will result in array initialization to a value larger than Integer.MAX_VALUE in the following: var v = new Array[Double](n * ncv)
Author: mbittmann <mbittmann@gmail.com>
Author: bittmannm <mark.bittmann@agilex.com>
Closes#4433 from mbittmann/master and squashes the following commits:
ee56e05 [mbittmann] [SPARK-5656] Combine checks into simple message
e49cbbb [mbittmann] [SPARK-5656] Simply error message
860836b [mbittmann] Array size check updates based on code review
a604816 [bittmannm] [SPARK-5656] Fail gracefully for large values of k and/or n that will exceed max int.
Overload `trainOn`, `predictOn`, and `predictOnValues`.
CC freeman-lab
Author: Xiangrui Meng <meng@databricks.com>
Closes#4432 from mengxr/streaming-java and squashes the following commits:
6a79b85 [Xiangrui Meng] add java test for streaming logistic regression
2d7b357 [Xiangrui Meng] organize imports
1f662b3 [Xiangrui Meng] make streaming linear algorithms Java-friendly
`LogisticRegressionModel`'s `predictPoint` should directly use broadcasted weights. This pr also fixes the compilation errors of two unit test suite: `JavaLogisticRegressionSuite ` and `JavaLinearRegressionSuite`.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4429 from viirya/use_bcvalue and squashes the following commits:
5a797e5 [Liang-Chi Hsieh] Use broadcasted weights. Fix compilation error.
This is part (1a) of the updates from the design doc in [https://docs.google.com/document/d/1BH9el33kBX8JiDdgUJXdLW14CA2qhTCWIG46eXZVoJs]
**UPDATE**: Most of the APIs are being kept private[spark] to allow further discussion. Here is a list of changes which are public:
* new output columns: rawPrediction, probabilities
* The “score” column is now called “rawPrediction”
* Classifiers now provide numClasses
* Params.get and .set are now protected instead of private[ml].
* ParamMap now has a size method.
* new classes: LinearRegression, LinearRegressionModel
* LogisticRegression now has an intercept.
### Sketch of APIs (most of which are private[spark] for now)
Abstract classes for learning algorithms (+ corresponding Model abstractions):
* Classifier (+ ClassificationModel)
* ProbabilisticClassifier (+ ProbabilisticClassificationModel)
* Regressor (+ RegressionModel)
* Predictor (+ PredictionModel)
* *For all of these*:
* There is no strongly typed training-time API.
* There is a strongly typed test-time (prediction) API which helps developers implement new algorithms.
Concrete classes: learning algorithms
* LinearRegression
* LogisticRegression (updated to use new abstract classes)
* Also, removed "score" in favor of "probability" output column. Changed BinaryClassificationEvaluator to match. (SPARK-5031)
Other updates:
* params.scala: Changed Params.set/get to be protected instead of private[ml]
* This was needed for the example of defining a class from outside of the MLlib namespace.
* VectorUDT: Will later change from private[spark] to public.
* This is needed for outside users to write their own validateAndTransformSchema() methods using vectors.
* Also, added equals() method.f
* SPARK-4942 : ML Transformers should allow output cols to be turned on,off
* Update validateAndTransformSchema
* Update transform
* (Updated examples, test suites according to other changes)
New examples:
* DeveloperApiExample.scala (example of defining algorithm from outside of the MLlib namespace)
* Added Java version too
Test Suites:
* LinearRegressionSuite
* LogisticRegressionSuite
* + Java versions of above suites
CC: mengxr etrain shivaram
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#3637 from jkbradley/ml-api-part1 and squashes the following commits:
405bfb8 [Joseph K. Bradley] Last edits based on code review. Small cleanups
fec348a [Joseph K. Bradley] Added JavaDeveloperApiExample.java and fixed other issues: Made developer API private[spark] for now. Added constructors Java can understand to specialized Param types.
8316d5e [Joseph K. Bradley] fixes after rebasing on master
fc62406 [Joseph K. Bradley] fixed test suites after last commit
bcb9549 [Joseph K. Bradley] Fixed issues after rebasing from master (after move from SchemaRDD to DataFrame)
9872424 [Joseph K. Bradley] fixed JavaLinearRegressionSuite.java Java sql api
f542997 [Joseph K. Bradley] Added MIMA excludes for VectorUDT (now public), and added DeveloperApi annotation to it
216d199 [Joseph K. Bradley] fixed after sql datatypes PR got merged
f549e34 [Joseph K. Bradley] Updates based on code review. Major ones are: * Created weakly typed Predictor.train() method which is called by fit() so that developers do not have to call schema validation or copy parameters. * Made Predictor.featuresDataType have a default value of VectorUDT. * NOTE: This could be dangerous since the FeaturesType type parameter cannot have a default value.
343e7bd [Joseph K. Bradley] added blanket mima exclude for ml package
82f340b [Joseph K. Bradley] Fixed bug in LogisticRegression (introduced in this PR). Fixed Java suites
0a16da9 [Joseph K. Bradley] Fixed Linear/Logistic RegressionSuites
c3c8da5 [Joseph K. Bradley] small cleanup
934f97b [Joseph K. Bradley] Fixed bugs from previous commit.
1c61723 [Joseph K. Bradley] * Made ProbabilisticClassificationModel into a subclass of ClassificationModel. Also introduced ProbabilisticClassifier. * This was to support output column “probabilityCol” in transform().
4e2f711 [Joseph K. Bradley] rat fix
bc654e1 [Joseph K. Bradley] Added spark.ml LinearRegressionSuite
8d13233 [Joseph K. Bradley] Added methods: * Classifier: batch predictRaw() * Predictor: train() without paramMap ProbabilisticClassificationModel.predictProbabilities() * Java versions of all above batch methods + others
1680905 [Joseph K. Bradley] Added JavaLabeledPointSuite.java for spark.ml, and added constructor to LabeledPoint which defaults weight to 1.0
adbe50a [Joseph K. Bradley] * fixed LinearRegression train() to use embedded paramMap * added Predictor.predict(RDD[Vector]) method * updated Linear/LogisticRegressionSuites
58802e3 [Joseph K. Bradley] added train() to Predictor subclasses which does not take a ParamMap.
57d54ab [Joseph K. Bradley] * Changed semantics of Predictor.train() to merge the given paramMap with the embedded paramMap. * remove threshold_internal from logreg * Added Predictor.copy() * Extended LogisticRegressionSuite
e433872 [Joseph K. Bradley] Updated docs. Added LabeledPointSuite to spark.ml
54b7b31 [Joseph K. Bradley] Fixed issue with logreg threshold being set correctly
0617d61 [Joseph K. Bradley] Fixed bug from last commit (sorting paramMap by parameter names in toString). Fixed bug in persisting logreg data. Added threshold_internal to logreg for faster test-time prediction (avoiding map lookup).
601e792 [Joseph K. Bradley] Modified ParamMap to sort parameters in toString. Cleaned up classes in class hierarchy, before implementing tests and examples.
d705e87 [Joseph K. Bradley] Added LinearRegression and Regressor back from ml-api branch
52f4fde [Joseph K. Bradley] removing everything except for simple class hierarchy for classification
d35bb5d [Joseph K. Bradley] fixed compilation issues, but have not added tests yet
bfade12 [Joseph K. Bradley] Added lots of classes for new ML API:
This is the second part of SPARK-5604, which removes checkpointDir from tree strategies. Note that this is a break change. I will mention it in the migration guide.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4407 from mengxr/SPARK-5604-1 and squashes the following commits:
13a276d [Xiangrui Meng] remove checkpointDir from trees
`checkpointDir` is a Spark global configuration. Users should set it outside LDA. This PR also hides some methods under `private[clustering] object LDA`, so they don't show up in the generated Java doc (SPARK-5610).
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#4390 from mengxr/SPARK-5604 and squashes the following commits:
a34bb39 [Xiangrui Meng] remove checkpointDir from LDA
Because `deleteAllCheckpoints` has IOException potential.
fix issue.
Author: x1- <viva008@gmail.com>
Closes#4347 from x1-/SPARK-5460 and squashes the following commits:
7a3d8de [x1-] change `Try()` to `try catch { case ... }` ar RandomForest.
3a52745 [x1-] modified typo. 'faild' -> 'failed' and remove disused '-'.
1572576 [x1-] Wrapped `Try` around `deleteAllCheckpoints` - RandomForest.
There are no break changes (against 1.2) in this PR. I hide the PythonMLLibAPI, which is only called by Py4J, and renamed `SparseMatrix.diag` to `SparseMatrix.spdiag`. All other changes are documentation and annotations. The `Experimental` tag is removed from `ALS.setAlpha` and `Rating`. One issue not addressed in this PR is the `setCheckpointDir` in `LDA` (https://issues.apache.org/jira/browse/SPARK-5604).
CC: srowen jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#4377 from mengxr/SPARK-5599 and squashes the following commits:
17975dc [Xiangrui Meng] fix tests
4487f20 [Xiangrui Meng] remove experimental tag from each stat method because Statistics is experimental already
3cd969a [Xiangrui Meng] remove freeman (sorry~) from StreamLA public doc
55900f5 [Xiangrui Meng] make IR experimental and update its doc
9b8eed3 [Xiangrui Meng] graduate Rating and setAlpha in ALS
b854d28 [Xiangrui Meng] correct iid doc in RandomRDDs
27f5bdd [Xiangrui Meng] update linalg docs and some new method signatures
371721b [Xiangrui Meng] mark fpg as experimental and update its doc
8aca7ee [Xiangrui Meng] change SLR to experimental and update the doc
ebbb2e9 [Xiangrui Meng] mark PIC experimental and update the doc
7830d3b [Xiangrui Meng] mark GMM experimental
a378496 [Xiangrui Meng] use the correct subscript syntax in PIC
c65c424 [Xiangrui Meng] update LDAModel doc
a213b0c [Xiangrui Meng] update GMM constructor
3993054 [Xiangrui Meng] hide algorithm in SLR
ad6b9ce [Xiangrui Meng] Revert "make ClassificatinModel.predict(JavaRDD) return JavaDoubleRDD"
0054684 [Xiangrui Meng] add doc to LRModel's constructor
a89763b [Xiangrui Meng] make ClassificatinModel.predict(JavaRDD) return JavaDoubleRDD
7c0946c [Xiangrui Meng] hide PythonMLLibAPI
This is a PR for Parquet-based model import/export. Please see the design doc on [the JIRA](https://issues.apache.org/jira/browse/SPARK-4587).
Note: This includes only a subset of regression and classification models:
* NaiveBayes, SVM, LogisticRegression
* LinearRegression, RidgeRegression, Lasso
Follow-up PRs will cover other models.
Sketch of current contents:
* New traits: Saveable, Loader
* Implementations for some algorithms
* Also: Added LogisticRegressionModel.getThreshold method (so that unit test could check the threshold)
CC: mengxr selvinsource
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#4233 from jkbradley/ml-import-export and squashes the following commits:
87c4eb8 [Joseph K. Bradley] small cleanups
12d9059 [Joseph K. Bradley] Many cleanups after code review. Major changes: Storing numFeatures, numClasses in model metadata. Improvements to unit tests
b4ee064 [Joseph K. Bradley] Reorganized save/load for regression and classification. Renamed concepts to Saveable, Loader
a34aef5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into ml-import-export
ee99228 [Joseph K. Bradley] scala style fix
79675d5 [Joseph K. Bradley] cleanups in LogisticRegression after rebasing after multinomial PR
d1e5882 [Joseph K. Bradley] organized imports
2935963 [Joseph K. Bradley] Added save/load and tests for most classification and regression models
c495dba [Joseph K. Bradley] made version for model import/export local to each model
1496852 [Joseph K. Bradley] Added save/load for NaiveBayes
8d46386 [Joseph K. Bradley] Added save/load to NaiveBayes
1577d70 [Joseph K. Bradley] fixed issues after rebasing on master (DataFrame patch)
64914a3 [Joseph K. Bradley] added getThreshold to SVMModel
b1fc5ec [Joseph K. Bradley] small cleanups
418ba1b [Joseph K. Bradley] Added save, load to mllib.classification.LogisticRegressionModel, plus test suite
If `seed` is `None` on the python side, it will pass in as a `null`. So we should use `java.lang.Long` instead of `Long` to take it.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4349 from mengxr/gmm-fix and squashes the following commits:
3be5926 [Xiangrui Meng] fix seed handling in Python GMM
Make FPGrowth.run API take generic item types:
`def run[Item: ClassTag, Basket <: Iterable[Item]](data: RDD[Basket]): FPGrowthModel[Item]`
so that user can invoke it by run[String, Seq[String]], run[Int, Seq[Int]], run[Int, List[Int]], etc.
Scala part is done, while java part is still in progress
Author: Jacky Li <jacky.likun@huawei.com>
Author: Jacky Li <jackylk@users.noreply.github.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#4340 from jackylk/SPARK-5520-WIP and squashes the following commits:
f5acf84 [Jacky Li] Merge pull request #2 from mengxr/SPARK-5520
63073d0 [Xiangrui Meng] update to make generic FPGrowth Java-friendly
737d8bb [Jacky Li] fix scalastyle
793f85c [Jacky Li] add Java test case
7783351 [Jacky Li] add generic support in FPGrowth
Author: Xiangrui Meng <meng@databricks.com>
Closes#4329 from mengxr/streaming-lr and squashes the following commits:
78731e1 [Xiangrui Meng] update streaming linear algorithms
**This PR introduces an API + simple implementation for Latent Dirichlet Allocation (LDA).**
The [design doc for this PR](https://docs.google.com/document/d/1kSsDqTeZMEB94Bs4GTd0mvdAmduvZSSkpoSfn-seAzo) has been updated since I initially posted it. In particular, see the API and Planning for the Future sections.
* Settle on a public API which may eventually include:
* more inference algorithms
* more options / functionality
* Have an initial easy-to-understand implementation which others may improve.
* This is NOT intended to support every topic model out there. However, if there are suggestions for making this extensible or pluggable in the future, that could be nice, as long as it does not complicate the API or implementation too much.
* This may not be very scalable currently. It will be important to check and improve accuracy. For correctness of the implementation, please check against the Asuncion et al. (2009) paper in the design doc.
**Dependency: This makes MLlib depend on GraphX.**
Files and classes:
* LDA.scala (441 lines):
* class LDA (main estimator class)
* LDA.Document (text + document ID)
* LDAModel.scala (266 lines)
* abstract class LDAModel
* class LocalLDAModel
* class DistributedLDAModel
* LDAExample.scala (245 lines): script to run LDA + a simple (private) Tokenizer
* LDASuite.scala (144 lines)
Data/model representation and algorithm:
* Data/model: Uses GraphX, with term vertices + document vertices
* Algorithm: EM, following [Asuncion, Welling, Smyth, and Teh. "On Smoothing and Inference for Topic Models." UAI, 2009.](http://arxiv-web3.library.cornell.edu/abs/1205.2662v1)
* For more details, please see the description in the “DEVELOPERS NOTE” in LDA.scala
Please refer to the JIRA for more discussion + the [design doc for this PR](https://docs.google.com/document/d/1kSsDqTeZMEB94Bs4GTd0mvdAmduvZSSkpoSfn-seAzo)
Here, I list the main changes AFTER the design doc was posted.
Design decisions:
* logLikelihood() computes the log likelihood of the data and the current point estimate of parameters. This is different from the likelihood of the data given the hyperparameters, which would be harder to compute. I’d describe the current approach as more frequentist, whereas the harder approach would be more Bayesian.
* The current API takes Documents as token count vectors. I believe there should be an extended API taking RDD[String] or RDD[Array[String]] in a future PR. I have sketched this out in the design doc (as well as handier versions of getTopics returning Strings).
* Hyperparameters should be set differently for different inference/learning algorithms. See Asuncion et al. (2009) in the design doc for a good demonstration. I encourage good behavior via defaults and warning messages.
Items planned for future PRs:
* perplexity
* API taking Strings
* Should LDA be called LatentDirichletAllocation (and LDAModel be LatentDirichletAllocationModel)?
* Pro: We may someday want LinearDiscriminantAnalysis.
* Con: Very long names
* Should LDA reside in clustering? Or do we want a sub-package?
* mllib.topicmodel
* mllib.clustering.topicmodel
* Does the API seem reasonable and extensible?
* Unit tests:
* Should there be a test which checks a clustering results? E.g., train on a small, fake dataset with 2 very distinct topics/clusters, and ensure LDA finds those 2 topics/clusters. Does that sound useful or too flaky?
This has not been tested much for scaling. I have run it on a laptop for 200 iterations on a 5MB dataset with 1000 terms and 5 topics. Running it for 500 iterations made it fail because of GC problems. I'm running larger scale tests & will put results here, but future PRs may need to improve the scaling.
* dlwh for the initial implementation
* + jegonzal for some code in the initial implementation
* The many contributors towards topic model implementations in Spark which were referenced as a basis for this PR: akopich witgo yinxusen dlwh EntilZha jegonzal IlyaKozlov
* Note: The plan is to include this full list in the authors if this PR gets merged. Please notify me if you prefer otherwise.
CC: mengxr
Authors:
Joseph K. Bradley <joseph@databricks.com>
Joseph Gonzalez <joseph.e.gonzalez@gmail.com>
David Hall <david.lw.hall@gmail.com>
Guoqiang Li <witgo@qq.com>
Xiangrui Meng <meng@databricks.com>
Pedro Rodriguez <pedro@snowgeek.org>
Avanesov Valeriy <acopich@gmail.com>
Xusen Yin <yinxusen@gmail.com>
Closes#2388Closes#4047 from jkbradley/davidhall-lda and squashes the following commits:
77e8814 [Joseph K. Bradley] small doc fix
5c74345 [Joseph K. Bradley] cleaned up doc based on code review
589728b [Joseph K. Bradley] Updates per code review. Main change was in LDAExample for faster vocab computation. Also updated PeriodicGraphCheckpointerSuite.scala to clean up checkpoint files at end
e3980d2 [Joseph K. Bradley] cleaned up PeriodicGraphCheckpointerSuite.scala
74487e5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into davidhall-lda
4ae2a7d [Joseph K. Bradley] removed duplicate graphx dependency in mllib/pom.xml
e391474 [Joseph K. Bradley] Removed LDATiming. Added PeriodicGraphCheckpointerSuite.scala. Small LDA cleanups.
e8d8acf [Joseph K. Bradley] Added catch for BreakIterator exception. Improved preprocessing to reduce passes over data
1a231b4 [Joseph K. Bradley] fixed scalastyle
91aadfe [Joseph K. Bradley] Added Java-friendly run method to LDA. Added Java test suite for LDA. Changed LDAModel.describeTopics to return Java-friendly type
b75472d [Joseph K. Bradley] merged improvements from LDATiming into LDAExample. Will remove LDATiming after done testing
993ca56 [Joseph K. Bradley] * Removed Document type in favor of (Long, Vector) * Changed doc ID restriction to be: id must be nonnegative and unique in the doc (instead of 0,1,2,...) * Add checks for valid ranges of eta, alpha * Rename “LearningState” to “EMOptimizer” * Renamed params: termSmoothing -> topicConcentration, topicSmoothing -> docConcentration * Also added aliases alpha, beta
cb5a319 [Joseph K. Bradley] Added checkpointing to LDA * new class PeriodicGraphCheckpointer * params checkpointDir, checkpointInterval to LDA
43c1c40 [Joseph K. Bradley] small cleanup
0b90393 [Joseph K. Bradley] renamed LDA LearningState.collectTopicTotals to globalTopicTotals
77a2c85 [Joseph K. Bradley] Moved auto term,topic smoothing computation to get*Smoothing methods. Changed word to term in some places. Updated LDAExample to use default smoothing amounts.
fb1e7b5 [Xiangrui Meng] minor
08d59a3 [Xiangrui Meng] reset spacing
9fe0b95 [Xiangrui Meng] optimize aggregateMessages
cec0a9c [Xiangrui Meng] * -> *=
6cb11b0 [Xiangrui Meng] optimize computePTopic
9eb3d02 [Xiangrui Meng] + -> +=
892530c [Xiangrui Meng] use axpy
45cc7f2 [Xiangrui Meng] mapPart -> flatMap
ce53be9 [Joseph K. Bradley] fixed example name
75749e7 [Joseph K. Bradley] scala style fix
9f2a492 [Joseph K. Bradley] Unit tests and fixes for LDA, now ready for PR
377ebd9 [Joseph K. Bradley] separated LDA models into own file. more cleanups before PR
2d40006 [Joseph K. Bradley] cleanups before PR
2891e89 [Joseph K. Bradley] Prepped LDA main class for PR, but some cleanups remain
0cb7187 [Joseph K. Bradley] Added 3 files from dlwh LDA implementation
The only issue is that `analyzeBlock` is removed, which was marked as a developer API. I didn't change other tests in the ALSSuite under `spark.mllib` to ensure that the implementation is correct.
CC: srowen coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#4321 from mengxr/SPARK-5536 and squashes the following commits:
5a3cee8 [Xiangrui Meng] update python tests that are too strict
e840acf [Xiangrui Meng] ignore scala style check for ALS.train
e9a721c [Xiangrui Meng] update mima excludes
9ee6a36 [Xiangrui Meng] merge master
9a8aeac [Xiangrui Meng] update tests
d8c3271 [Xiangrui Meng] remove analyzeBlocks
d68eee7 [Xiangrui Meng] add checkpoint to new ALS
22a56f8 [Xiangrui Meng] wrap old ALS
c387dff [Xiangrui Meng] support random seed
3bdf24b [Xiangrui Meng] make storage level configurable in the new ALS
This adds support for streaming logistic regression with stochastic gradient descent, in the same manner as the existing implementation of streaming linear regression. It is a relatively simple addition because most of the work is already done by the abstract class `StreamingLinearAlgorithm` and existing algorithms and models from MLlib.
The PR includes
- Streaming Logistic Regression algorithm
- Unit tests for accuracy, streaming convergence, and streaming prediction
- An example use
cc mengxr tdas
Author: freeman <the.freeman.lab@gmail.com>
Closes#4306 from freeman-lab/streaming-logisitic-regression and squashes the following commits:
5c2c70b [freeman] Use Option on model
5cca2bc [freeman] Merge remote-tracking branch 'upstream/master' into streaming-logisitic-regression
275f8bd [freeman] Make private to mllib
3926e4e [freeman] Line formatting
5ee8694 [freeman] Experimental tag for docs
2fc68ac [freeman] Fix example formatting
85320b1 [freeman] Fixed line length
d88f717 [freeman] Remove stray comment
59d7ecb [freeman] Add streaming logistic regression
e78fe28 [freeman] Add streaming logistic regression example
321cc66 [freeman] Set private and protected within mllib
As suggested by the paper of Power Iteration Clustering, it is useful to set the initial vector v0 as the degree vector d. This pr tries to add a running method for that.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4301 from viirya/pic_degreevector and squashes the following commits:
7db28fb [Liang-Chi Hsieh] Refactor it to address comments.
19cf94e [Liang-Chi Hsieh] Add an option to select initialization method.
ec88567 [Liang-Chi Hsieh] Run the PIC algorithm with degree vector d as suggected by the PIC paper.
This method survived the code review and it has been there since v1.1.0. It exposes jblas types. Let's remove it from the public API. I think no one calls it directly.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4318 from mengxr/SPARK-5540 and squashes the following commits:
586ade6 [Xiangrui Meng] hide ALS.solveLeastSquares
#1379 is automatically closed by asfgit, and github can not reopen it once it's closed, so this will be the new PR.
Binary Logistic Regression can be extended to Multinomial Logistic Regression by running K-1 independent Binary Logistic Regression models. The following formula is implemented.
http://www.slideshare.net/dbtsai/2014-0620-mlor-36132297/25
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3833 from dbtsai/mlor and squashes the following commits:
4e2f354 [DB Tsai] triger jenkins
697b7c9 [DB Tsai] address some feedback
4ce4d33 [DB Tsai] refactoring
ff843b3 [DB Tsai] rebase
f114135 [DB Tsai] refactoring
4348426 [DB Tsai] Addressed feedback from Sean Owen
a252197 [DB Tsai] first commit
This PR ports the NNLS solver to the new ALS implementation.
CC: coderxiang
Author: Xiangrui Meng <meng@databricks.com>
Closes#4302 from mengxr/SPARK-5513 and squashes the following commits:
4cbdab0 [Xiangrui Meng] fix serialization
88de634 [Xiangrui Meng] add NNLS to ml's ALS
The following is implemented:
1) generic traits for feature selection and filtering
2) trait for feature selection of LabeledPoint with discrete data
3) traits for calculation of contingency table and chi squared
4) class for chi-squared feature selection
5) tests for the above
Needs some optimization in matrix operations.
This request is a try to implement feature selection for MLLIB, the previous work by the issue author izendejas was not finished (https://issues.apache.org/jira/browse/SPARK-1473). This request is also related to data discretization issues: https://issues.apache.org/jira/browse/SPARK-1303 and https://issues.apache.org/jira/browse/SPARK-1216 that weren't merged.
Author: Alexander Ulanov <nashb@yandex.ru>
Closes#1484 from avulanov/featureselection and squashes the following commits:
755d358 [Alexander Ulanov] Addressing reviewers comments @mengxr
a6ad82a [Alexander Ulanov] Addressing reviewers comments @mengxr
714b878 [Alexander Ulanov] Addressing reviewers comments @mengxr
010acff [Alexander Ulanov] Rebase
427ca4e [Alexander Ulanov] Addressing reviewers comments: implement VectorTransformer interface, use Statistics.chiSqTest
f9b070a [Alexander Ulanov] Adding Apache header in tests...
80363ca [Alexander Ulanov] Tests, comments, apache headers and scala style
150a3e0 [Alexander Ulanov] Scala style fix
f356365 [Alexander Ulanov] Chi Squared by contingency table. Refactoring
2bacdc7 [Alexander Ulanov] Combinations and chi-squared values test
66e0333 [Alexander Ulanov] Feature selector, fix of lazyness
aab9b73 [Alexander Ulanov] Feature selection redesign with vigdorchik
e24eee4 [Alexander Ulanov] Traits for FeatureSelection, CombinationsCalculator and FeatureFilter
ca49e80 [Alexander Ulanov] Feature selection filter
2ade254 [Alexander Ulanov] Code style
0bd8434 [Alexander Ulanov] Chi Squared feature selection: initial version
Apriori is the classic algorithm for frequent item set mining in a transactional data set. It will be useful if Apriori algorithm is added to MLLib in Spark. This PR add an implementation for it.
There is a point I am not sure wether it is most efficient. In order to filter out the eligible frequent item set, currently I am using a cartesian operation on two RDDs to calculate the degree of support of each item set, not sure wether it is better to use broadcast variable to achieve the same.
I will add an example to use this algorithm if requires
Author: Jacky Li <jacky.likun@huawei.com>
Author: Jacky Li <jackylk@users.noreply.github.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#2847 from jackylk/apriori and squashes the following commits:
bee3093 [Jacky Li] Merge pull request #1 from mengxr/SPARK-4001
7e69725 [Xiangrui Meng] simplify FPTree and update FPGrowth
ec21f7d [Jacky Li] fix scalastyle
93f3280 [Jacky Li] create FPTree class
d110ab2 [Jacky Li] change test case to use MLlibTestSparkContext
a6c5081 [Jacky Li] Add Parallel FPGrowth algorithm
eb3e4ca [Jacky Li] add FPGrowth
03df2b6 [Jacky Li] refactory according to comments
7b77ad7 [Jacky Li] fix scalastyle check
f68a0bd [Jacky Li] add 2 apriori implemenation and fp-growth implementation
889b33f [Jacky Li] modify per scalastyle check
da2cba7 [Jacky Li] adding apriori algorithm for frequent item set mining in Spark
JIRA link: https://issues.apache.org/jira/browse/SPARK-5406
The code in breeze svd imposes the upper bound for LocalLAPACK in RowMatrix.computeSVD
code from breeze svd (https://github.com/scalanlp/breeze/blob/master/math/src/main/scala/breeze/linalg/functions/svd.scala)
val workSize = ( 3
* scala.math.min(m, n)
* scala.math.min(m, n)
+ scala.math.max(scala.math.max(m, n), 4 * scala.math.min(m, n)
* scala.math.min(m, n) + 4 * scala.math.min(m, n))
)
val work = new Array[Double](workSize)
As a result, 7 * n * n + 4 * n < Int.MaxValue at least (depends on JVM)
In some worse cases, like n = 25000, work size will become positive again (80032704) and bring wired behavior.
The PR is only the beginning, to support Genbase ( an important biological benchmark that would help promote Spark to genetic applications, http://www.paradigm4.com/wp-content/uploads/2014/06/Genomics-Benchmark-Technical-Report.pdf),
which needs to compute svd for matrix up to 60K * 70K. I found many potential issues and would like to know if there's any plan undergoing that would expand the range of matrix computation based on Spark.
Thanks.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#4200 from hhbyyh/rowMatrix and squashes the following commits:
f7864d0 [Yuhao Yang] update auto logic for rowMatrix svd
23860e4 [Yuhao Yang] fix comment style
e48a6e4 [Yuhao Yang] make latent svd computation constraint clear
This PR makes the ALS implementation take generic ID types, e.g., Long and String, and expose it as a developer API.
TODO:
- [x] make sure that specialization works (validated in profiler)
srowen You may like this change:) I hit a Scala compiler bug with specialization. It compiles now but users and items must have the same type. I'm going to check whether specialization really works.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4281 from mengxr/generic-als and squashes the following commits:
96072c3 [Xiangrui Meng] merge master
135f741 [Xiangrui Meng] minor update
c2db5e5 [Xiangrui Meng] make test pass
86588e1 [Xiangrui Meng] use a single ID type for both users and items
74f1f73 [Xiangrui Meng] compile but runtime error at test
e36469a [Xiangrui Meng] add classtags and make it compile
7a5aeb3 [Xiangrui Meng] UserType -> User, ItemType -> Item
c8ee0bc [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into generic-als
72b5006 [Xiangrui Meng] remove generic from pipeline interface
8bbaea0 [Xiangrui Meng] make ALS take generic IDs
This seems complete, the duplication of tests for provided means/variances might be overkill, would appreciate some feedback.
Author: Octavian Geagla <ogeagla@gmail.com>
Closes#4140 from ogeagla/SPARK-5207 and squashes the following commits:
fa64dfa [Octavian Geagla] [SPARK-5207] [MLLIB] [WIP] change StandardScalerModel to take stddev instead of variance
9078fe0 [Octavian Geagla] [SPARK-5207] [MLLIB] [WIP] Incorporate code review feedback: change arg ordering, add dev api annotations, do better null checking, add another test and some doc for this.
997d2e0 [Octavian Geagla] [SPARK-5207] [MLLIB] [WIP] make withMean and withStd public, add constructor which uses defaults, un-refactor test class
64408a4 [Octavian Geagla] [SPARK-5207] [MLLIB] [WIP] change StandardScalerModel contructor to not be private to mllib, added tests for newly-exposed functionality
These are more `javadoc` 8-related changes I spotted while investigating. These should be helpful in any event, but this does not nearly resolve SPARK-3359, which may never be feasible while using `unidoc` and `javadoc` 8.
Author: Sean Owen <sowen@cloudera.com>
Closes#4193 from srowen/SPARK-3359 and squashes the following commits:
5b33f66 [Sean Owen] Additional scaladoc fixes for javadoc 8; still not going to be javadoc 8 compatible
This PR introduces an API for Isotonic regression and one algorithm implementing it, Pool adjacent violators.
The Isotonic regression problem is sufficiently described in [Floudas, Pardalos, Encyclopedia of Optimization](http://books.google.co.uk/books?id=gtoTkL7heS0C&pg=RA2-PA87&lpg=RA2-PA87&dq=pooled+adjacent+violators+code&source=bl&ots=ZzQbZXVJnn&sig=reH_hBV6yIb9BeZNTF9092vD8PY&hl=en&sa=X&ei=WmF2VLiOIZLO7Qa-t4Bo&ved=0CD8Q6AEwBA#v=onepage&q&f=false), [Wikipedia](http://en.wikipedia.org/wiki/Isotonic_regression) or [Stat Wiki](http://stat.wikia.com/wiki/Isotonic_regression).
Pool adjacent violators was introduced by M. Ayer et al. in 1955. A history and development of isotonic regression algorithms is in [Leeuw, Hornik, Mair, Isotone Optimization in R: Pool-Adjacent-Violators Algorithm (PAVA) and Active Set Methods](http://www.jstatsoft.org/v32/i05/paper) and list of available algorithms including their complexity is listed in [Stout, Fastest Isotonic Regression Algorithms](http://web.eecs.umich.edu/~qstout/IsoRegAlg_140812.pdf).
An approach to parallelize the computation of PAV was presented in [Kearsley, Tapia, Trosset, An Approach to Parallelizing Isotonic Regression](http://softlib.rice.edu/pub/CRPC-TRs/reports/CRPC-TR96640.pdf).
The implemented Pool adjacent violators algorithm is based on [Floudas, Pardalos, Encyclopedia of Optimization](http://books.google.co.uk/books?id=gtoTkL7heS0C&pg=RA2-PA87&lpg=RA2-PA87&dq=pooled+adjacent+violators+code&source=bl&ots=ZzQbZXVJnn&sig=reH_hBV6yIb9BeZNTF9092vD8PY&hl=en&sa=X&ei=WmF2VLiOIZLO7Qa-t4Bo&ved=0CD8Q6AEwBA#v=onepage&q&f=false) (Chapter Isotonic regression problems, p. 86) and [Leeuw, Hornik, Mair, Isotone Optimization in R: Pool-Adjacent-Violators Algorithm (PAVA) and Active Set Methods](http://www.jstatsoft.org/v32/i05/paper), also nicely formulated in [Tibshirani, Hoefling, Tibshirani, Nearly-Isotonic Regression](http://www.stat.cmu.edu/~ryantibs/papers/neariso.pdf). Implementation itself inspired by R implementations [Klaus, Strimmer, 2008, fdrtool: Estimation of (Local) False Discovery Rates and Higher Criticism](http://cran.r-project.org/web/packages/fdrtool/index.html) and [R Development Core Team, stats, 2009](https://github.com/lgautier/R-3-0-branch-alt/blob/master/src/library/stats/R/isoreg.R). I ran tests with both these libraries and confirmed they yield the same results. More R implementations referenced in aforementioned [Leeuw, Hornik, Mair, Isotone Optimization in R: Pool-Adjacent-Violators
Algorithm (PAVA) and Active Set Methods](http://www.jstatsoft.org/v32/i05/paper). The implementation is also inspired and cross checked with other implementations: [Ted Harding, 2007](https://stat.ethz.ch/pipermail/r-help/2007-March/127981.html), [scikit-learn](https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/_isotonic.pyx), [Andrew Tulloch, 2014, Julia](https://github.com/ajtulloch/Isotonic.jl/blob/master/src/pooled_pava.jl), [Andrew Tulloch, 2014, c++](https://gist.github.com/ajtulloch/9499872), described in [Andrew Tulloch, Speeding up isotonic regression in scikit-learn by 5,000x](http://tullo.ch/articles/speeding-up-isotonic-regression/), [Fabian Pedregosa, 2012](https://gist.github.com/fabianp/3081831), [Sreangsu Acharyya. libpav](f744bc1b0f/src/pav.h?at=default) and [Gustav Larsson](https://gist.github.com/gustavla/9499068).
Author: martinzapletal <zapletal-martin@email.cz>
Author: Xiangrui Meng <meng@databricks.com>
Author: Martin Zapletal <zapletal-martin@email.cz>
Closes#3519 from zapletal-martin/SPARK-3278 and squashes the following commits:
5a54ea4 [Martin Zapletal] Merge pull request #2 from mengxr/isotonic-fix-java
37ba24e [Xiangrui Meng] fix java tests
e3c0e44 [martinzapletal] Merge remote-tracking branch 'origin/SPARK-3278' into SPARK-3278
d8feb82 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
ded071c [Martin Zapletal] Merge pull request #1 from mengxr/SPARK-3278
4dfe136 [Xiangrui Meng] add cache back
0b35c15 [Xiangrui Meng] compress pools and update tests
35d044e [Xiangrui Meng] update paraPAVA
077606b [Xiangrui Meng] minor
05422a8 [Xiangrui Meng] add unit test for model construction
5925113 [Xiangrui Meng] Merge remote-tracking branch 'zapletal-martin/SPARK-3278' into SPARK-3278
80c6681 [Xiangrui Meng] update IRModel
3da56e5 [martinzapletal] SPARK-3278 fixed indentation error
75eac55 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
88eb4e2 [martinzapletal] SPARK-3278 changes after PR comments https://github.com/apache/spark/pull/3519. Isotonic parameter removed from algorithm, defined behaviour for multiple data points with the same feature value, added tests to verify it
e60a34f [martinzapletal] SPARK-3278 changes after PR comments https://github.com/apache/spark/pull/3519. Styling and comment fixes.
d93c8f9 [martinzapletal] SPARK-3278 changes after PR comments https://github.com/apache/spark/pull/3519. Change to IsotonicRegression api. Isotonic parameter now follows api of other mllib algorithms
1fff77d [martinzapletal] SPARK-3278 changes after PR comments https://github.com/apache/spark/pull/3519. Java api changes, test refactoring, comments and citations, isotonic regression model validations, linear interpolation for predictions
12151e6 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
7aca4cc [martinzapletal] SPARK-3278 comment spelling
9ae9d53 [martinzapletal] SPARK-3278 changes after PR feedback https://github.com/apache/spark/pull/3519. Binary search used for isotonic regression model predictions
fad4bf9 [martinzapletal] SPARK-3278 changes after PR comments https://github.com/apache/spark/pull/3519
ce0e30c [martinzapletal] SPARK-3278 readability refactoring
f90c8c7 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
0d14bd3 [martinzapletal] SPARK-3278 changed Java api to match Scala api's (Double, Double, Double)
3c2954b [martinzapletal] SPARK-3278 Isotonic regression java api
45aa7e8 [martinzapletal] SPARK-3278 Isotonic regression java api
e9b3323 [martinzapletal] Merge branch 'SPARK-3278-weightedLabeledPoint' into SPARK-3278
823d803 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
941fd1f [martinzapletal] SPARK-3278 Isotonic regression java api
a24e29f [martinzapletal] SPARK-3278 refactored weightedlabeledpoint to (double, double, double) and updated api
deb0f17 [martinzapletal] SPARK-3278 refactored weightedlabeledpoint to (double, double, double) and updated api
8cefd18 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278-weightedLabeledPoint
cab5a46 [martinzapletal] SPARK-3278 PR 3519 refactoring WeightedLabeledPoint to tuple as per comments
b8b1620 [martinzapletal] Removed WeightedLabeledPoint. Replaced by tuple of doubles
34760d5 [martinzapletal] Removed WeightedLabeledPoint. Replaced by tuple of doubles
089bf86 [martinzapletal] Removed MonotonicityConstraint, Isotonic and Antitonic constraints. Replced by simple boolean
c06f88c [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
6046550 [martinzapletal] SPARK-3278 scalastyle errors resolved
8f5daf9 [martinzapletal] SPARK-3278 added comments and cleaned up api to consistently handle weights
629a1ce [martinzapletal] SPARK-3278 added isotonic regression for weighted data. Added tests for Java api
05d9048 [martinzapletal] SPARK-3278 isotonic regression refactoring and api changes
961aa05 [martinzapletal] Merge remote-tracking branch 'upstream/master' into SPARK-3278
3de71d0 [martinzapletal] SPARK-3278 added initial version of Isotonic regression algorithm including proposed API
Decoupling the model and the algorithm
Author: Travis Galoppo <tjg2107@columbia.edu>
Closes#4290 from tgaloppo/spark-5400 and squashes the following commits:
9c1534c [Travis Galoppo] Fixed invokation instructions in comments
d848076 [Travis Galoppo] SPARK-5400 Changed name of GaussianMixtureEM to GaussianMixture to separate model from algorithm
Add single pseudo-eigenvector PIC
Including documentations and updated pom.xml with the following codes:
mllib/src/main/scala/org/apache/spark/mllib/clustering/PIClustering.scala
mllib/src/test/scala/org/apache/spark/mllib/clustering/PIClusteringSuite.scala
Author: sboeschhuawei <stephen.boesch@huawei.com>
Author: Fan Jiang <fanjiang.sc@huawei.com>
Author: Jiang Fan <fjiang6@gmail.com>
Author: Stephen Boesch <stephen.boesch@huawei.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#4254 from fjiang6/PIC and squashes the following commits:
4550850 [sboeschhuawei] Removed pic test data
f292f31 [Stephen Boesch] Merge pull request #44 from mengxr/SPARK-4259
4b78aaf [Xiangrui Meng] refactor PIC
24fbf52 [sboeschhuawei] Updated API to be similar to KMeans plus other changes requested by Xiangrui on the PR
c12dfc8 [sboeschhuawei] Removed examples files and added pic_data.txt. Revamped testcases yet to come
92d4752 [sboeschhuawei] Move the Guassian/ Affinity matrix calcs out of PIC. Presently in the test suite
7ebd149 [sboeschhuawei] Incorporate Xiangrui's first set of PR comments except restructure PIC.run to take Graph but do not remove Gaussian
121e4d5 [sboeschhuawei] Remove unused testing data files
1c3a62e [sboeschhuawei] removed matplot.py and reordered all private methods to bottom of PIC
218a49d [sboeschhuawei] Applied Xiangrui's comments - especially removing RDD/PICLinalg classes and making noncritical methods private
43ab10b [sboeschhuawei] Change last two println's to log4j logger
88aacc8 [sboeschhuawei] Add assert to testcase on cluster sizes
24f438e [sboeschhuawei] fixed incorrect markdown in clustering doc
060e6bf [sboeschhuawei] Added link to PIC doc from the main clustering md doc
be659e3 [sboeschhuawei] Added mllib specific log4j
90e7fa4 [sboeschhuawei] Converted from custom Linalg routines to Breeze: added JavaDoc comments; added Markdown documentation
bea48ea [sboeschhuawei] Converted custom Linear Algebra datatypes/routines to use Breeze.
b29c0db [Fan Jiang] Update PIClustering.scala
ace9749 [Fan Jiang] Update PIClustering.scala
a112f38 [sboeschhuawei] Added graphx main and test jars as dependencies to mllib/pom.xml
f656c34 [sboeschhuawei] Added iris dataset
b7dbcbe [sboeschhuawei] Added axes and combined into single plot for matplotlib
a2b1e57 [sboeschhuawei] Revert inadvertent update to KMeans
9294263 [sboeschhuawei] Added visualization/plotting of input/output data
e5df2b8 [sboeschhuawei] First end to end working PIC
0700335 [sboeschhuawei] First end to end working version: but has bad performance issue
32a90dc [sboeschhuawei] Update circles test data values
0ef163f [sboeschhuawei] Added ConcentricCircles data generation and KMeans clustering
3fd5bc8 [sboeschhuawei] PIClustering is running in new branch (up to the pseudo-eigenvector convergence step)
d5aae20 [Jiang Fan] Adding Power Iteration Clustering and Suite test
a3c5fbe [Jiang Fan] Adding Power Iteration Clustering
The `validate` method will allow users to debug their `BlockMatrix`, if operations like `add` or `multiply` return unexpected results. It checks the following properties in a `BlockMatrix`:
- Are the dimensions of the `BlockMatrix` consistent with what the user entered: (`nRows`, `nCols`)
- Are the dimensions of each `MatrixBlock` consistent with what the user entered: (`rowsPerBlock`, `colsPerBlock`)
- Are there blocks with duplicate indices
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#4279 from brkyvz/SPARK-5486 and squashes the following commits:
c152a73 [Burak Yavuz] addressed code review v2
598c583 [Burak Yavuz] merged master
b55ac5c [Burak Yavuz] addressed code review v1
25f083b [Burak Yavuz] simplify implementation
0aa519a [Burak Yavuz] [SPARK-5486] Added validate method to BlockMatrix
to be backward compatible.
Author: Xiangrui Meng <meng@databricks.com>
Closes#4287 from mengxr/SPARK-5496 and squashes the following commits:
a025c53 [Xiangrui Meng] Allow both classification and Classification in Algo for trees.
When the vocabSize\*vectorSize is larger than Int.MaxValue/8, we try to throw a RuntimeException. Because under this circumstance it would definitely throw an OOM when allocating memory to serialize the arrays syn0Global&syn1Global. syn0Global&syn1Global are float arrays. Serializing them should need a byte array of more than 8 times of syn0Global's size.
Also if we catch an OOM even if vocabSize\*vectorSize is less than Int.MaxValue/8, we should give users hints to increase the minCount or decrease the vectorSize.
Author: Joseph J.C. Tang <jinntrance@gmail.com>
Closes#4247 from jinntrance/w2v-fix and squashes the following commits:
b5eb71f [Joseph J.C. Tang] throw a RuntimeException and give users hints regarding the vectorSize&minCount
This PR is implementing the Gradient Boosted Trees for Python API.
Author: Kazuki Taniguchi <kazuki.t.1018@gmail.com>
Closes#3951 from kazk1018/gbt_for_py and squashes the following commits:
620d247 [Kazuki Taniguchi] [SPARK-5094][MLlib] Add Python API for Gradient Boosted Trees
BlockMatrices can now be transposed!
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#4275 from brkyvz/SPARK-5322 and squashes the following commits:
33806ed [Burak Yavuz] added lazy comment
33e9219 [Burak Yavuz] made transpose lazy
5a274cd [Burak Yavuz] added cached tests
5dcf85c [Burak Yavuz] [SPARK-5322] Added transpose functionality to BlockMatrix
looks unnecessary 😀
Author: Yoshihiro Shimizu <shimizu@amoad.com>
Closes#4268 from y-shimizu/remove-return and squashes the following commits:
12be0e9 [Yoshihiro Shimizu] remove 'return'
Turns out Scala does generate static methods for ones defined in a companion object. Finally no need to separate api.java.dsl and api.scala.dsl.
Author: Reynold Xin <rxin@databricks.com>
Closes#4276 from rxin/dsl and squashes the following commits:
30aa611 [Reynold Xin] Add all files.
1a9d215 [Reynold Xin] [SPARK-5445][SQL] Consolidate Java and Scala DSL static methods.
There is only a single `stat.py` file for the `mllib.stat` package. We recently added `MultivariateGaussian` under `mllib.stat.distribution` in Scala/Java. It would be nice to refactor `stat.py` and make it easy to expand. Note that `ChiSqTestResult` is moved from `mllib.stat` to `mllib.stat.test`. The latter is used in Scala/Java. It is only used in the return value of `Statistics.chiSqTest`, so this should be an okay change.
davies
Author: Xiangrui Meng <meng@databricks.com>
Closes#4266 from mengxr/py-stat-refactor and squashes the following commits:
1a5e1db [Xiangrui Meng] refactor stat.py
1. Added foreach, foreachPartition, flatMap to DataFrame.
2. Added col() in dsl.
3. Support renaming columns in toDataFrame.
4. Support type inference on arrays (in addition to Seq).
5. Updated mllib to use the new DSL.
Author: Reynold Xin <rxin@databricks.com>
Closes#4260 from rxin/sql-dsl-update and squashes the following commits:
73466c1 [Reynold Xin] Fixed LogisticRegression. Also added better error message for resolve.
fab3ccc [Reynold Xin] Bug fix.
d31fcd2 [Reynold Xin] Style fix.
62608c4 [Reynold Xin] [SQL] Various DataFrame DSL update.
The conversion methods for `BlockMatrix`. Conversions go through `CoordinateMatrix` in order to cause a shuffle so that intermediate operations will be stored on disk and the expensive initial computation will be mitigated.
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#4256 from brkyvz/SPARK-3977PR and squashes the following commits:
4df37fe [Burak Yavuz] moved TODO inside code block
b049c07 [Burak Yavuz] addressed code review feedback v1
66cb755 [Burak Yavuz] added default toBlockMatrix conversion
851f2a2 [Burak Yavuz] added better comments and checks
cdb9895 [Burak Yavuz] [SPARK-3977] Conversion methods for BlockMatrix to other Distributed Matrices
Also removed the literal implicit transformation since it is pretty scary for API design. Instead, created a new lit method for creating literals. This doesn't break anything from a compatibility perspective because Literal was added two days ago.
Author: Reynold Xin <rxin@databricks.com>
Closes#4241 from rxin/df-docupdate and squashes the following commits:
c0f4810 [Reynold Xin] Fix Python merge conflict.
094c7d7 [Reynold Xin] Minor style fix. Reset Python tests.
3c89f4a [Reynold Xin] Package.
dfe6962 [Reynold Xin] Updated Python aggregate.
5dd4265 [Reynold Xin] Made dsl Java callable.
14b3c27 [Reynold Xin] Fix literal expression for symbols.
68b31cb [Reynold Xin] Literal.
4cfeb78 [Reynold Xin] [SPARK-5097][SQL] Address DataFrame code review feedback.
We have seen many use cases of `treeAggregate`/`treeReduce` outside the ML domain. Maybe it is time to move them to Core. pwendell
Author: Xiangrui Meng <meng@databricks.com>
Closes#4228 from mengxr/SPARK-5430 and squashes the following commits:
20ad40d [Xiangrui Meng] exclude tree* from mima
e89a43e [Xiangrui Meng] fix compile and update java doc
3ae1a4b [Xiangrui Meng] add treeReduce/treeAggregate to Python
6f948c5 [Xiangrui Meng] add treeReduce/treeAggregate to JavaRDDLike
d600b6c [Xiangrui Meng] move treeReduce and treeAggregate to core
This PR adds Python API for ML pipeline and parameters. The design doc can be found on the JIRA page. It includes transformers and an estimator to demo the simple text classification example code.
TODO:
- [x] handle parameters in LRModel
- [x] unit tests
- [x] missing some docs
CC: davies jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Author: Davies Liu <davies@databricks.com>
Closes#4151 from mengxr/SPARK-4586 and squashes the following commits:
415268e [Xiangrui Meng] remove inherit_doc from __init__
edbd6fe [Xiangrui Meng] move Identifiable to ml.util
44c2405 [Xiangrui Meng] Merge pull request #2 from davies/ml
dd1256b [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586
14ae7e2 [Davies Liu] fix docs
54ca7df [Davies Liu] fix tests
78638df [Davies Liu] Merge branch 'SPARK-4586' of github.com:mengxr/spark into ml
fc59a02 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586
1dca16a [Davies Liu] refactor
090b3a3 [Davies Liu] Merge branch 'master' of github.com:apache/spark into ml
0882513 [Xiangrui Meng] update doc style
a4f4dbf [Xiangrui Meng] add unit test for LR
7521d1c [Xiangrui Meng] add unit tests to HashingTF and Tokenizer
ba0ba1e [Xiangrui Meng] add unit tests for pipeline
0586c7b [Xiangrui Meng] add more comments to the example
5153cff [Xiangrui Meng] simplify java models
036ca04 [Xiangrui Meng] gen numFeatures
46fa147 [Xiangrui Meng] update mllib/pom.xml to include python files in the assembly
1dcc17e [Xiangrui Meng] update code gen and make param appear in the doc
f66ba0c [Xiangrui Meng] make params a property
d5efd34 [Xiangrui Meng] update doc conf and move embedded param map to instance attribute
f4d0fe6 [Xiangrui Meng] use LabeledDocument and Document in example
05e3e40 [Xiangrui Meng] update example
d3e8dbe [Xiangrui Meng] more docs optimize pipeline.fit impl
56de571 [Xiangrui Meng] fix style
d0c5bb8 [Xiangrui Meng] a working copy
bce72f4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-4586
17ecfb9 [Xiangrui Meng] code gen for shared params
d9ea77c [Xiangrui Meng] update doc
c18dca1 [Xiangrui Meng] make the example working
dadd84e [Xiangrui Meng] add base classes and docs
a3015cf [Xiangrui Meng] add Estimator and Transformer
46eea43 [Xiangrui Meng] a pipeline in python
33b68e0 [Xiangrui Meng] a working LR
and
[SPARK-5448][SQL] Make CacheManager a concrete class and field in SQLContext
Author: Reynold Xin <rxin@databricks.com>
Closes#4242 from rxin/sqlCleanup and squashes the following commits:
e351cb2 [Reynold Xin] Fixed toDataFrame.
6545c42 [Reynold Xin] More changes.
728c017 [Reynold Xin] [SPARK-5447][SQL] Replaced reference to SchemaRDD with DataFrame.
This pull request includes the abstractions for the distributed BlockMatrix representation.
`BlockMatrix` will allow users to store very large matrices in small blocks of local matrices. Specific partitioners, such as `RowBasedPartitioner` and `ColumnBasedPartitioner`, are implemented in order to optimize addition and multiplication operations that will be added in a following PR.
This work is based on the ml-matrix repo developed at the AMPLab at UC Berkeley, CA.
https://github.com/amplab/ml-matrix
Additional thanks to rezazadeh, shivaram, and mengxr for guidance on the design.
Author: Burak Yavuz <brkyvz@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Author: Burak Yavuz <brkyvz@dn51t42l.sunet>
Author: Burak Yavuz <brkyvz@dn51t4rd.sunet>
Author: Burak Yavuz <brkyvz@dn0a221430.sunet>
Closes#3200 from brkyvz/SPARK-3974 and squashes the following commits:
a8eace2 [Burak Yavuz] Merge pull request #2 from mengxr/brkyvz-SPARK-3974
feb32a7 [Xiangrui Meng] update tests
e1d3ee8 [Xiangrui Meng] minor updates
24ec7b8 [Xiangrui Meng] update grid partitioner
5eecd48 [Burak Yavuz] fixed gridPartitioner and added tests
140f20e [Burak Yavuz] Merge branch 'master' of github.com:apache/spark into SPARK-3974
1694c9e [Burak Yavuz] almost finished addressing comments
f9d664b [Burak Yavuz] updated API and modified partitioning scheme
eebbdf7 [Burak Yavuz] preliminary changes addressing code review
1a63b20 [Burak Yavuz] [SPARK-3974] Remove setPartition method. Isn't required
1e8bb2a [Burak Yavuz] [SPARK-3974] Change return type of cache and persist
239ab4b [Burak Yavuz] [SPARK-3974] Addressed @jkbradley's comments
ba414d2 [Burak Yavuz] [SPARK-3974] fixed frobenius norm
ab6cde0 [Burak Yavuz] [SPARK-3974] Modifications cleaning code up, making size calculation more robust
9ae85aa [Burak Yavuz] [SPARK-3974] Made partitioner a variable inside BlockMatrix instead of a constructor variable
d033861 [Burak Yavuz] [SPARK-3974] Removed SubMatrixInfo and added constructor without partitioner
49b9586 [Burak Yavuz] [SPARK-3974] Updated testing utils from master
645afbe [Burak Yavuz] [SPARK-3974] Pull latest master
b05aabb [Burak Yavuz] [SPARK-3974] Updated tests to reflect changes
19c17e8 [Burak Yavuz] [SPARK-3974] Changed blockIdRow and blockIdCol
589fbb6 [Burak Yavuz] [SPARK-3974] Code review feedback addressed
aa8f086 [Burak Yavuz] [SPARK-3974] Additional comments added
f378e16 [Burak Yavuz] [SPARK-3974] Block Matrix Abstractions ready
b693209 [Burak Yavuz] Ready for Pull request
Support for transposing local matrices added. The `.transpose` function creates a new object re-using the backing array(s) but switches `numRows` and `numCols`. Operations check the flag `.isTransposed` to see whether the indexing in `values` should be modified.
This PR will pave the way for transposing `BlockMatrix`.
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#4109 from brkyvz/SPARK-5321 and squashes the following commits:
87ab83c [Burak Yavuz] fixed scalastyle
caf4438 [Burak Yavuz] addressed code review v3
c524770 [Burak Yavuz] address code review comments 2
77481e8 [Burak Yavuz] fixed MiMa
f1c1742 [Burak Yavuz] small refactoring
ccccdec [Burak Yavuz] fixed failed test
dd45c88 [Burak Yavuz] addressed code review
a01bd5f [Burak Yavuz] [SPARK-5321] Fixed MiMa issues
2a63593 [Burak Yavuz] [SPARK-5321] fixed bug causing failed gemm test
c55f29a [Burak Yavuz] [SPARK-5321] Support for transposing local matrices cleaned up
c408c05 [Burak Yavuz] [SPARK-5321] Support for transposing local matrices added
The current implementation in Vectors.sqdist is not efficient because of allocating temp arrays. There is also a bug in the code `v1.indices.length / v1.size < 0.5`. This pr fixes the bug and refactors sqdist without allocating new arrays.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4217 from viirya/fix_sqdist and squashes the following commits:
e8b0b3d [Liang-Chi Hsieh] For review comments.
314c424 [Liang-Chi Hsieh] Fix sqdist bug.
I've added support for sampling_rate not equal to 1.0 . I have two major questions.
1. A Scala style test is failing, since the number of parameters now exceed 10.
2. I would like suggestions to understand how to test this.
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#4073 from MechCoder/spark-3726 and squashes the following commits:
8012fb2 [MechCoder] Add test in Strategy
e0e0d9c [MechCoder] TST: Add better test
d1df1b2 [MechCoder] Add test to verify subsampling behavior
a7bfc70 [MechCoder] [SPARK-3726] Allow sampling_rate not equal to 1.0
... decision tree model
Labels loaded from libsvm files are mapped to 0.0 if they are negative labels because they should be nonnegative value.
Author: lewuathe <lewuathe@me.com>
Closes#3975 from Lewuathe/map-negative-label-to-positive and squashes the following commits:
12d1d59 [lewuathe] [SPARK-5119] Fix code styles
6d9a18a [lewuathe] [SPARK-5119] Organize test codes
62a150c [lewuathe] [SPARK-5119] Modify Impurities throw exceptions with negatie labels
3336c21 [lewuathe] [SPARK-5119] java.lang.ArrayIndexOutOfBoundsException on trying to train decision tree model
JIRA issue: https://issues.apache.org/jira/browse/SPARK-5384
Currently `Vectors.sqdist` return inconsistent result for sparse/dense vectors when the vectors have different lengths, please refer to JIRA for sample
PR scope:
Unify the sqdist logic for dense/sparse vectors and fix the inconsistency, also remove the possible sparse to dense conversion in the original code.
For reviewers:
Maybe we should first discuss what's the correct behavior.
1. Vectors for sqdist must have the same length, like in breeze?
2. If they can have different lengths, what's the correct result for sqdist? (should the extra part get into calculation?)
I'll update PR with more optimization and additional ut afterwards. Thanks.
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#4183 from hhbyyh/fixDouble and squashes the following commits:
1f17328 [Yuhao Yang] limit PR scope to size constraints only
54cbf97 [Yuhao Yang] fix Vectors.sqdist inconsistence
This PR adds a new ALS implementation to `spark.ml` using the pipeline API, which should be able to scale to billions of ratings. Compared with the ALS under `spark.mllib`, the new implementation
1. uses the same algorithm,
2. uses float type for ratings,
3. uses primitive arrays to avoid GC,
4. sorts and compresses ratings on each block so that we can solve least squares subproblems one by one using only one normal equation instance.
The following figure shows performance comparison on copies of the Amazon Reviews dataset using a 16-node (m3.2xlarge) EC2 cluster (the same setup as in http://databricks.com/blog/2014/07/23/scalable-collaborative-filtering-with-spark-mllib.html):
I keep the `spark.mllib`'s ALS untouched for easy comparison. If the new implementation works well, I'm going to match the features of the ALS under `spark.mllib` and then make it a wrapper of the new implementation, in a separate PR.
TODO:
- [X] Add unit tests for implicit preferences.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3720 from mengxr/SPARK-3541 and squashes the following commits:
1b9e852 [Xiangrui Meng] fix compile
5129be9 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-3541
dd0d0e8 [Xiangrui Meng] simplify test code
c627de3 [Xiangrui Meng] add tests for implicit feedback
b84f41c [Xiangrui Meng] address comments
a76da7b [Xiangrui Meng] update ALS tests
2a8deb3 [Xiangrui Meng] add some ALS tests
857e876 [Xiangrui Meng] add tests for rating block and encoded block
d3c1ac4 [Xiangrui Meng] rename some classes for better code readability add more doc and comments
213d163 [Xiangrui Meng] org imports
771baf3 [Xiangrui Meng] chol doc update
ca9ad9d [Xiangrui Meng] add unit tests for chol
b4fd17c [Xiangrui Meng] add unit tests for NormalEquation
d0f99d3 [Xiangrui Meng] add tests for LocalIndexEncoder
80b8e61 [Xiangrui Meng] fix imports
4937fd4 [Xiangrui Meng] update ALS example
56c253c [Xiangrui Meng] rename product to item
bce8692 [Xiangrui Meng] doc for parameters and project the output columns
3f2d81a [Xiangrui Meng] add doc
1efaecf [Xiangrui Meng] add example code
8ae86b5 [Xiangrui Meng] add a working copy of the new ALS implementation
If a point is selected as new centers for many runs, it would collect many redundant data. This pr refactors it.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#4159 from viirya/small_refactor_kmeans and squashes the following commits:
25487e6 [Liang-Chi Hsieh] Refactor codes to reduce redundant data.
JIRA Issue: https://issues.apache.org/jira/browse/SPARK-5317
When setting the BoostingStrategy.defaultParams("Classification"), It's more straightforward to set it with the Enumeration Algo.Classification, just like BoostingStragety.defaultParams(Algo.Classification).
I overload the method BoostingStragety.defaultParams().
Author: Basin <jpsachilles@gmail.com>
Closes#4103 from Peishen-Jia/stragetyAlgo and squashes the following commits:
87bab1c [Basin] Docs and Code documentations updated.
3b72875 [Basin] defaultParams(algoStr: String) call defaultParams(algo: Algo).
7c1e6ee [Basin] Doc of Java updated. algo -> algoStr instead.
d5c8a2e [Basin] Merge branch 'stragetyAlgo' of github.com:Peishen-Jia/spark into stragetyAlgo
65f96ce [Basin] mllib-ensembles doc modified.
e04a5aa [Basin] boostingstrategy.defaultParam string algo to enumeration.
68cf544 [Basin] mllib-ensembles doc modified.
a4aea51 [Basin] boostingstrategy.defaultParam string algo to enumeration.
This PR ports the following feature implemented in #2634 by derrickburns:
* During k-means|| initialization, we should cache costs (squared distances) previously computed.
It also contains the following optimization:
* aggregate sumCosts directly
* ran multiple (#runs) k-means++ in parallel
I compared the performance locally on mnist-digit. Before this patch:
with this patch:
It is clear that each k-means|| iteration takes about the same amount of time with this patch.
Authors:
Derrick Burns <derrickburns@gmail.com>
Xiangrui Meng <meng@databricks.com>
Closes#4144 from mengxr/SPARK-3424-kmeans-parallel and squashes the following commits:
0a875ec [Xiangrui Meng] address comments
4341bb8 [Xiangrui Meng] do not re-compute point distances during k-means||
This implements the functionality for SPARK-4749 and provides units tests in Scala and PySpark
Author: nate.crosswhite <nate.crosswhite@stresearch.com>
Author: nxwhite-str <nxwhite-str@users.noreply.github.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#3610 from nxwhite-str/master and squashes the following commits:
a2ebbd3 [nxwhite-str] Merge pull request #1 from mengxr/SPARK-4749-kmeans-seed
7668124 [Xiangrui Meng] minor updates
f8d5928 [nate.crosswhite] Addressing PR issues
277d367 [nate.crosswhite] Merge remote-tracking branch 'upstream/master'
9156a57 [nate.crosswhite] Merge remote-tracking branch 'upstream/master'
5d087b4 [nate.crosswhite] Adding KMeans train with seed and Scala unit test
616d111 [nate.crosswhite] Merge remote-tracking branch 'upstream/master'
35c1884 [nate.crosswhite] Add kmeans initial seed to pyspark API
* Transpose is missing from CoordinateMatrix (this is cheap to compute, so it should be there)
* IndexedRowMatrix should be convertable to CoordinateMatrix (conversion added)
Tests for both added.
Author: Reza Zadeh <reza@databricks.com>
Closes#4089 from rezazadeh/matutils and squashes the following commits:
ec5238b [Reza Zadeh] Array -> Iterator to avoid temp array
3ce0b5d [Reza Zadeh] Array -> Iterator
bbc907a [Reza Zadeh] Use 'i' for index, and zipWithIndex
cb10ae5 [Reza Zadeh] remove unnecessary import
a7ae048 [Reza Zadeh] Missing linear algebra utilities
JIRA Issue: https://issues.apache.org/jira/browse/SPARK-5186
Currently SparseVector is using the inherited equals from Vector, which will create a full-size array for even the sparse vector. The pull request contains a specialized equals optimization that improves on both time and space.
1. The implementation will be consistent with the original. Especially it will keep equality comparison between SparseVector and DenseVector.
Author: Yuhao Yang <hhbyyh@gmail.com>
Author: Yuhao Yang <yuhao@yuhaodevbox.sh.intel.com>
Closes#3997 from hhbyyh/master and squashes the following commits:
0d9d130 [Yuhao Yang] function name change and ut update
93f0d46 [Yuhao Yang] unify sparse vs dense vectors
985e160 [Yuhao Yang] improve locality for equals
bdf8789 [Yuhao Yang] improve equals and rewrite hashCode for Vector
a6952c3 [Yuhao Yang] fix scala style for comments
50abef3 [Yuhao Yang] fix ut for sparse vector with explicit 0
f41b135 [Yuhao Yang] iterative equals for sparse vector
5741144 [Yuhao Yang] Specialized equals for SparseVector
This PR modifies GaussianMixtureModel to expose instances of MutlivariateGaussian rather than separate mean and covariance arrays.
Author: Travis Galoppo <tjg2107@columbia.edu>
Closes#4088 from tgaloppo/spark-5019 and squashes the following commits:
3ef6c7f [Travis Galoppo] In GaussianMixtureModel: Changed name of weight, gaussian to weights, gaussians. Other sources modified accordingly.
091e8da [Travis Galoppo] SPARK-5019 - GaussianMixtureModel exposes instances of MultivariateGaussian rather than mean/covariance matrices
JIRA: https://issues.apache.org/jira/browse/SPARK-5282
fix the possible int overflow in the memory computation warning
Author: Yuhao Yang <hhbyyh@gmail.com>
Closes#4069 from hhbyyh/addscStop and squashes the following commits:
e54e5c8 [Yuhao Yang] change to MB based number
7afac23 [Yuhao Yang] 5282: fix int overflow in the warning
Having two versions of the data type APIs (one for Java, one for Scala) requires downstream libraries to also have two versions of the APIs if the library wants to support both Java and Scala. I took a look at the Scala version of the data type APIs - it can actually work out pretty well for Java out of the box.
As part of the PR, I created a sql.types package and moved all type definitions there. I then removed the Java specific data type API along with a lot of the conversion code.
This subsumes https://github.com/apache/spark/pull/3925
Author: Reynold Xin <rxin@databricks.com>
Closes#3958 from rxin/SPARK-5123-datatype-2 and squashes the following commits:
66505cc [Reynold Xin] [SPARK-5123] Expose only one version of the data type APIs (i.e. remove the Java-specific API).
Moving MutlivariateGaussian from private[mllib] to public. The class uses Breeze vectors internally, so this involves creating a public interface using MLlib vectors and matrices.
This initial commit provides public construction, accessors for mean/covariance, density and log-density.
Other potential methods include entropy and sample generation.
Author: Travis Galoppo <tjg2107@columbia.edu>
Closes#3923 from tgaloppo/spark-5018 and squashes the following commits:
2b15587 [Travis Galoppo] Style correction
b4121b4 [Travis Galoppo] Merge remote-tracking branch 'upstream/master' into spark-5018
e30a100 [Travis Galoppo] Made mu, sigma private[mllib] members of MultivariateGaussian Moved MultivariateGaussian (and test suite) from stat.impl to stat.distribution (required updates in GaussianMixture{EM,Model}.scala) Marked MultivariateGaussian as @DeveloperApi Fixed style error
9fa3bb7 [Travis Galoppo] Style improvements
91a5fae [Travis Galoppo] Rearranged equation for part of density function
8c35381 [Travis Galoppo] Fixed accessor methods to match member variable names. Modified calculations to avoid log(pow(x,y)) calculations
0943dc4 [Travis Galoppo] SPARK-5018
4dee9e1 [Travis Galoppo] SPARK-5018
Raise exception when k is non-positive in SVD
Author: MechCoder <manojkumarsivaraj334@gmail.com>
Closes#3945 from MechCoder/spark-4406 and squashes the following commits:
64e6d2d [MechCoder] TST: Add better test errors and messages
12dae73 [MechCoder] [SPARK-4406] FIX: Validate k in SVD
Issues:
* From JIRA: GaussianMixtureEM uses randomness but does not take a random seed. It should take one as a parameter.
* This also makes the test suite flaky since initialization can fail due to stochasticity.
Fix:
* Add random seed
* Use it in test suite
CC: mengxr tgaloppo
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#3981 from jkbradley/gmm-seed and squashes the following commits:
f0df4fd [Joseph K. Bradley] Added seed parameter to GMM. Updated test suite to use seed to prevent flakiness
This pr uses BLAS.dsyr to replace few implementations in GaussianMixtureEM.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#3949 from viirya/blas_dsyr and squashes the following commits:
4e4d6cf [Liang-Chi Hsieh] Add unit test. Rename function name, modify doc and style.
3f57fd2 [Liang-Chi Hsieh] Add BLAS.dsyr and use it in GaussianMixtureEM.
This change does a few things to make the hadoop-provided profile more useful:
- Create new profiles for other libraries / services that might be provided by the infrastructure
- Simplify and fix the poms so that the profiles are only activated while building assemblies.
- Fix tests so that they're able to run when the profiles are activated
- Add a new env variable to be used by distributions that use these profiles to provide the runtime
classpath for Spark jobs and daemons.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#2982 from vanzin/SPARK-4048 and squashes the following commits:
82eb688 [Marcelo Vanzin] Add a comment.
eb228c0 [Marcelo Vanzin] Fix borked merge.
4e38f4e [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9ef79a3 [Marcelo Vanzin] Alternative way to propagate test classpath to child processes.
371ebee [Marcelo Vanzin] Review feedback.
52f366d [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
83099fc [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
7377e7b [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
322f882 [Marcelo Vanzin] Fix merge fail.
f24e9e7 [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
8b00b6a [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9640503 [Marcelo Vanzin] Cleanup child process log message.
115fde5 [Marcelo Vanzin] Simplify a comment (and make it consistent with another pom).
e3ab2da [Marcelo Vanzin] Fix hive-thriftserver profile.
7820d58 [Marcelo Vanzin] Fix CliSuite with provided profiles.
1be73d4 [Marcelo Vanzin] Restore flume-provided profile.
d1399ed [Marcelo Vanzin] Restore jetty dependency.
82a54b9 [Marcelo Vanzin] Remove unused profile.
5c54a25 [Marcelo Vanzin] Fix HiveThriftServer2Suite with *-provided profiles.
1fc4d0b [Marcelo Vanzin] Update dependencies for hive-thriftserver.
f7b3bbe [Marcelo Vanzin] Add snappy to hadoop-provided list.
9e4e001 [Marcelo Vanzin] Remove duplicate hive profile.
d928d62 [Marcelo Vanzin] Redirect child stderr to parent's log.
4d67469 [Marcelo Vanzin] Propagate SPARK_DIST_CLASSPATH on Yarn.
417d90e [Marcelo Vanzin] Introduce "SPARK_DIST_CLASSPATH".
2f95f0d [Marcelo Vanzin] Propagate classpath to child processes during testing.
1adf91c [Marcelo Vanzin] Re-enable maven-install-plugin for a few projects.
284dda6 [Marcelo Vanzin] Rework the "hadoop-provided" profile, add new ones.
...ySpark MLlib
This is a follow up to PR3680 https://github.com/apache/spark/pull/3680 .
Author: RJ Nowling <rnowling@gmail.com>
Closes#3955 from rnowling/spark4891 and squashes the following commits:
1236a01 [RJ Nowling] Fix Python style issues
7a01a78 [RJ Nowling] Fix Python style issues
174beab [RJ Nowling] [SPARK-4891][PySpark][MLlib] Add gamma/log normal/exp dist sampling to PySpark MLlib
Add extractor for SparseVector and DenseVector in MLlib to save some code while performing pattern matching on Vectors. For example, previously we may use:
vec match {
case dv: DenseVector =>
val values = dv.values
...
case sv: SparseVector =>
val indices = sv.indices
val values = sv.values
val size = sv.size
...
}
with extractor it is:
vec match {
case DenseVector(values) =>
...
case SparseVector(size, indices, values) =>
...
}
Author: Shuo Xiang <shuoxiangpub@gmail.com>
Closes#3919 from coderxiang/extractor and squashes the following commits:
359e8d5 [Shuo Xiang] merge master
ca5fc3e [Shuo Xiang] merge master
0b1e190 [Shuo Xiang] use extractor for vectors in RowMatrix.scala
e961805 [Shuo Xiang] use extractor for vectors in StandardScaler.scala
c2bbdaf [Shuo Xiang] use extractor for vectors in IDFscala
8433922 [Shuo Xiang] use extractor for vectors in NaiveBayes.scala and Normalizer.scala
d83c7ca [Shuo Xiang] use extractor for vectors in Vectors.scala
5523dad [Shuo Xiang] Add extractor for SparseVector and DenseVector
When `x` is positive and large, computing `math.log(1 + math.exp(x))` will lead to arithmetic
overflow. This will happen when `x > 709.78` which is not a very large number.
It can be addressed by rewriting the formula into `x + math.log1p(math.exp(-x))` when `x > 0`.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3915 from dbtsai/mathutil and squashes the following commits:
bec6a84 [DB Tsai] remove empty line
3239541 [DB Tsai] revert part of patch into another PR
23144f3 [DB Tsai] doc
49f3658 [DB Tsai] temp
6c29ed3 [DB Tsai] formating
f8447f9 [DB Tsai] address another overflow issue in gradientMultiplier in LOR gradient code
64eefd0 [DB Tsai] first commit
This is a minor pr where I think that we can simply take minus of `margin`, instead of subtracting `margin`.
Mathematically, they are equal. But the modified equation is the common form of logistic loss function and so more readable. It also computes more accurate value as some quick tests show.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#3899 from viirya/logit_func and squashes the following commits:
91a3860 [Liang-Chi Hsieh] Modified for comment.
0aa51e4 [Liang-Chi Hsieh] Further simplified.
72a295e [Liang-Chi Hsieh] Revert LogLoss back and add more considerations in Logistic Loss.
a3f83ca [Liang-Chi Hsieh] Fix a bug.
2bc5712 [Liang-Chi Hsieh] Simplify loss function.
Related to #3643. Follow the previous suggestion to add unit test for `sqdist` in `VectorsSuite`.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#3869 from viirya/sqdist_test and squashes the following commits:
fb743da [Liang-Chi Hsieh] Modified for comment and fix bug.
90a08f3 [Liang-Chi Hsieh] Modified for comment.
39a3ca6 [Liang-Chi Hsieh] Take care of special case.
b789f42 [Liang-Chi Hsieh] More proper unit test with random sparsity pattern.
c36be68 [Liang-Chi Hsieh] Add unit test for sqdist.
MultivariateGaussian was calling both pinv() and det() on the covariance matrix, effectively performing two matrix decompositions. Both values are now computed using the singular value decompositon. Both the pseudo-inverse and the pseudo-determinant are used to guard against singular matrices.
Author: Travis Galoppo <tjg2107@columbia.edu>
Closes#3871 from tgaloppo/spark-5017 and squashes the following commits:
383b5b3 [Travis Galoppo] MultivariateGaussian - minor optimization in density calculation
a5b8bc5 [Travis Galoppo] Added additional points to tests in test suite. Fixed comment in MultivariateGaussian
629d9d0 [Travis Galoppo] Moved some test values from var to val.
dc3d0f7 [Travis Galoppo] Catch potential exception calculating pseudo-determinant. Style improvements.
d448137 [Travis Galoppo] Added test suite for MultivariateGaussian, including test for degenerate case.
1989be0 [Travis Galoppo] SPARK-5017 - Fixed to use SVD to compute determinant and inverse of covariance matrix. Previous code called both pinv() and det(), effectively performing two matrix decompositions. Additionally, the pinv() implementation in Breeze is known to fail for singular matrices.
b4415ea [Travis Galoppo] Merge branch 'spark-5017' of https://github.com/tgaloppo/spark into spark-5017
6f11b6d [Travis Galoppo] SPARK-5017 - Use SVD to compute determinant and inverse of covariance matrix. Code was calling both det() and pinv(), effectively performing two matrix decompositions. Futhermore, Breeze pinv() currently fails for singular matrices.
fd9784c [Travis Galoppo] SPARK-5017 - Use SVD to compute determinant and inverse of covariance matrix
This PR:
- Reenables `surefire`, and copies config from `scalatest` (which is itself an old fork of `surefire`, so similar)
- Tells `surefire` to test only Java tests
- Enables `surefire` and `scalatest` for all children, and in turn eliminates some duplication.
For me this causes the Scala and Java tests to be run once each, it seems, as desired. It doesn't affect the SBT build but works for Maven. I still need to verify that all of the Scala tests and Java tests are being run.
Author: Sean Owen <sowen@cloudera.com>
Closes#3651 from srowen/SPARK-4159 and squashes the following commits:
2e8a0af [Sean Owen] Remove specialized SPARK_HOME setting for REPL, YARN tests as it appears to be obsolete
12e4558 [Sean Owen] Append to unit-test.log instead of overwriting, so that both surefire and scalatest output is preserved. Also standardize/correct comments a bit.
e6f8601 [Sean Owen] Reenable Java tests by reenabling surefire with config cloned from scalatest; centralize test config in the parent
Now that I've implemented the basics here, I'm less convinced there is a need for this change, somehow. Callers can downsample before or after. Really the OOM is not in the ROC curve code, but in code that might `collect()` it for local analysis. Still, might be useful to down-sample since the ROC curve probably never needs millions of points.
This is a first pass. Since the `(score,label)` are already grouped and sorted, I think it's sufficient to just take every Nth such pair, in order to downsample by a factor of N? this is just like retaining every Nth point on the curve, which I think is the goal. All of the data is still used to build the curve of course.
What do you think about the API, and usefulness?
Author: Sean Owen <sowen@cloudera.com>
Closes#3702 from srowen/SPARK-4547 and squashes the following commits:
1d34d05 [Sean Owen] Indent and reorganize numBins scaladoc
692d825 [Sean Owen] Change handling of large numBins, make 2nd consturctor instead of optional param, style change
a03610e [Sean Owen] Add downsamplingFactor to BinaryClassificationMetrics
This PR replaces slow breezeSquaredDistance.
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#3643 from viirya/faster_squareddistance and squashes the following commits:
f28b275 [Liang-Chi Hsieh] Move the implementation to linalg.Vectors and rename as sqdist.
0bc48ee [Liang-Chi Hsieh] Merge branch 'master' into faster_squareddistance
ba34422 [Liang-Chi Hsieh] Fix bug.
91849d0 [Liang-Chi Hsieh] Modified for comment.
44a65ad [Liang-Chi Hsieh] Modified for comments.
35db395 [Liang-Chi Hsieh] Fix bug and some modifications for comments.
f4f5ebb [Liang-Chi Hsieh] Follow BLAS.dot pattern to replace intersect, diff with while-loop.
a36e09f [Liang-Chi Hsieh] Use while-loop to replace foreach for better performance.
d3e0628 [Liang-Chi Hsieh] Make the methods private.
dd415bc [Liang-Chi Hsieh] Consider different cases of SparseVector and DenseVector.
13669db [Liang-Chi Hsieh] Replace breezeSquaredDistance.
To make the functions with the same in "object" effective, specially when using java reflection.
As the "train" function defined in "class DecisionTree" will hide the functions with the same name in "object DecisionTree".
JIRA[SPARK-4998]
Author: Liu Jiongzhou <ljzzju@163.com>
Closes#3836 from ljzzju/master and squashes the following commits:
4e13133 [Liu Jiongzhou] [MLlib]delete the "train" function
New foreachActive method of vector was introduced by SPARK-4431 as more efficient alternative to vector.toBreeze.activeIterator. There are some parts of codebase where it was not yet replaced.
dbtsai
Author: Jakub Dubovsky <dubovsky@avast.com>
Closes#3846 from james64/SPARK-4995-foreachActive and squashes the following commits:
3eb7e37 [Jakub Dubovsky] Scalastyle fix
32fe6c6 [Jakub Dubovsky] activeIterator removed - IndexedRowMatrix.toBreeze
47a4777 [Jakub Dubovsky] activeIterator removed in RowMatrix.toBreeze
90a7d98 [Jakub Dubovsky] activeIterator removed in MLUtils.saveAsLibSVMFile
In #SPARK-4907, we added factor of 2 into the LeastSquaresGradient. We updated the scala doc for lasso and ridge regression here.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3808 from dbtsai/doc and squashes the following commits:
ec3c989 [DB Tsai] first commit
Wanted to customize the private minCount variable in the Word2Vec class. Added
a method to do so.
Author: ganonp <ganonp@gmail.com>
Closes#3693 from ganonp/my-custom-spark and squashes the following commits:
ad534f2 [ganonp] made norm method public
5110a6f [ganonp] Reorganized
854958b [ganonp] Fixed Indentation for setMinCount
12ed8f9 [ganonp] Update Word2Vec.scala
76bdf5a [ganonp] Update Word2Vec.scala
ffb88bb [ganonp] Update Word2Vec.scala
5eb9100 [ganonp] Added setMinCount to Word2Vec.scala
Implementation of Expectation-Maximization for Gaussian Mixture Models.
This is my maiden contribution to Apache Spark, so I apologize now if I have done anything incorrectly; having said that, this work is my own, and I offer it to the project under the project's open source license.
Author: Travis Galoppo <tjg2107@columbia.edu>
Author: Travis Galoppo <travis@localhost.localdomain>
Author: tgaloppo <tjg2107@columbia.edu>
Author: FlytxtRnD <meethu.mathew@flytxt.com>
Closes#3022 from tgaloppo/master and squashes the following commits:
aaa8f25 [Travis Galoppo] MLUtils: changed privacy of EPSILON from [util] to [mllib]
709e4bf [Travis Galoppo] fixed usage line to include optional maxIterations parameter
acf1fba [Travis Galoppo] Fixed parameter comment in GaussianMixtureModel Made maximum iterations an optional parameter to DenseGmmEM
9b2fc2a [Travis Galoppo] Style improvements Changed ExpectationSum to a private class
b97fe00 [Travis Galoppo] Minor fixes and tweaks.
1de73f3 [Travis Galoppo] Removed redundant array from array creation
578c2d1 [Travis Galoppo] Removed unused import
227ad66 [Travis Galoppo] Moved prediction methods into model class.
308c8ad [Travis Galoppo] Numerous changes to improve code
cff73e0 [Travis Galoppo] Replaced accumulators with RDD.aggregate
20ebca1 [Travis Galoppo] Removed unusued code
42b2142 [Travis Galoppo] Added functionality to allow setting of GMM starting point. Added two cluster test to testing suite.
8b633f3 [Travis Galoppo] Style issue
9be2534 [Travis Galoppo] Style issue
d695034 [Travis Galoppo] Fixed style issues
c3b8ce0 [Travis Galoppo] Merge branch 'master' of https://github.com/tgaloppo/spark Adds predict() method
2df336b [Travis Galoppo] Fixed style issue
b99ecc4 [tgaloppo] Merge pull request #1 from FlytxtRnD/predictBranch
f407b4c [FlytxtRnD] Added predict() to return the cluster labels and membership values
97044cf [Travis Galoppo] Fixed style issues
dc9c742 [Travis Galoppo] Moved MultivariateGaussian utility class
e7d413b [Travis Galoppo] Moved multivariate Gaussian utility class to mllib/stat/impl Improved comments
9770261 [Travis Galoppo] Corrected a variety of style and naming issues.
8aaa17d [Travis Galoppo] Added additional train() method to companion object for cluster count and tolerance parameters.
676e523 [Travis Galoppo] Fixed to no longer ignore delta value provided on command line
e6ea805 [Travis Galoppo] Merged with master branch; update test suite with latest context changes. Improved cluster initialization strategy.
86fb382 [Travis Galoppo] Merge remote-tracking branch 'upstream/master'
719d8cc [Travis Galoppo] Added scala test suite with basic test
c1a8e16 [Travis Galoppo] Made GaussianMixtureModel class serializable Modified sum function for better performance
5c96c57 [Travis Galoppo] Merge remote-tracking branch 'upstream/master'
c15405c [Travis Galoppo] SPARK-4156
Addition of a very limited number of local matrix manipulation and generation methods that would be helpful in the further development for algorithms on top of BlockMatrix (SPARK-3974), such as Randomized SVD, and Multi Model Training (SPARK-1486).
The proposed methods for addition are:
For `Matrix`
- map: maps the values in the matrix with a given function. Produces a new matrix.
- update: the values in the matrix are updated with a given function. Occurs in place.
Factory methods for `DenseMatrix`:
- *zeros: Generate a matrix consisting of zeros
- *ones: Generate a matrix consisting of ones
- *eye: Generate an identity matrix
- *rand: Generate a matrix consisting of i.i.d. uniform random numbers
- *randn: Generate a matrix consisting of i.i.d. gaussian random numbers
- *diag: Generate a diagonal matrix from a supplied vector
*These methods already exist in the factory methods for `Matrices`, however for cases where we require a `DenseMatrix`, you constantly have to add `.asInstanceOf[DenseMatrix]` everywhere, which makes the code "dirtier". I propose moving these functions to factory methods for `DenseMatrix` where the putput will be a `DenseMatrix` and the factory methods for `Matrices` will call these functions directly and output a generic `Matrix`.
Factory methods for `SparseMatrix`:
- speye: Identity matrix in sparse format. Saves a ton of memory when dimensions are large, especially in Multi Model Training, where each row requires being multiplied by a scalar.
- sprand: Generate a sparse matrix with a given density consisting of i.i.d. uniform random numbers.
- sprandn: Generate a sparse matrix with a given density consisting of i.i.d. gaussian random numbers.
- diag: Generate a diagonal matrix from a supplied vector, but is memory efficient, because it just stores the diagonal. Again, very helpful in Multi Model Training.
Factory methods for `Matrices`:
- Include all the factory methods given above, but return a generic `Matrix` rather than `SparseMatrix` or `DenseMatrix`.
- horzCat: Horizontally concatenate matrices to form one larger matrix. Very useful in both Multi Model Training, and for the repartitioning of BlockMatrix.
- vertCat: Vertically concatenate matrices to form one larger matrix. Very useful for the repartitioning of BlockMatrix.
The names for these methods were selected from MATLAB
Author: Burak Yavuz <brkyvz@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#3319 from brkyvz/SPARK-4409 and squashes the following commits:
b0354f6 [Burak Yavuz] [SPARK-4409] Incorporated mengxr's code
04c4829 [Burak Yavuz] Merge pull request #1 from mengxr/SPARK-4409
80cfa29 [Xiangrui Meng] minor changes
ecc937a [Xiangrui Meng] update sprand
4e95e24 [Xiangrui Meng] simplify fromCOO implementation
10a63a6 [Burak Yavuz] [SPARK-4409] Fourth pass of code review
f62d6c7 [Burak Yavuz] [SPARK-4409] Modified genRandMatrix
3971c93 [Burak Yavuz] [SPARK-4409] Third pass of code review
75239f8 [Burak Yavuz] [SPARK-4409] Second pass of code review
e4bd0c0 [Burak Yavuz] [SPARK-4409] Modified horzcat and vertcat
65c562e [Burak Yavuz] [SPARK-4409] Hopefully fixed Java Test
d8be7bc [Burak Yavuz] [SPARK-4409] Organized imports
065b531 [Burak Yavuz] [SPARK-4409] First pass after code review
a8120d2 [Burak Yavuz] [SPARK-4409] Finished updates to API according to SPARK-4614
f798c82 [Burak Yavuz] [SPARK-4409] Updated API according to SPARK-4614
c75f3cd [Burak Yavuz] [SPARK-4409] Added JavaAPI Tests, and fixed a couple of bugs
d662f9d [Burak Yavuz] [SPARK-4409] Modified according to remote repo
83dfe37 [Burak Yavuz] [SPARK-4409] Scalastyle error fixed
a14c0da [Burak Yavuz] [SPARK-4409] Initial commit to add methods
There is only one implicit function `toPairDStreamFunctions` in `StreamingContext`. This PR did similar reorganization like [SPARK-4397](https://issues.apache.org/jira/browse/SPARK-4397).
Compiled the following codes with Spark Streaming 1.1.0 and ran it with this PR. Everything is fine.
```Scala
import org.apache.spark._
import org.apache.spark.streaming._
import org.apache.spark.streaming.StreamingContext._
object StreamingApp {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local[2]").setAppName("FileWordCount")
val ssc = new StreamingContext(conf, Seconds(10))
val lines = ssc.textFileStream("/some/path")
val words = lines.flatMap(_.split(" "))
val pairs = words.map(word => (word, 1))
val wordCounts = pairs.reduceByKey(_ + _)
wordCounts.print()
ssc.start()
ssc.awaitTermination()
}
}
```
Author: zsxwing <zsxwing@gmail.com>
Closes#3464 from zsxwing/SPARK-4608 and squashes the following commits:
aa6d44a [zsxwing] Fix a copy-paste error
f74c190 [zsxwing] Merge branch 'master' into SPARK-4608
e6f9cc9 [zsxwing] Update the docs
27833bb [zsxwing] Remove `import StreamingContext._`
c15162c [zsxwing] Reorganize StreamingContext implicit to improve API convenience
There are a number of warnings generated in a normal, successful build right now. They're mostly Java unchecked cast warnings, which can be suppressed. But there's a grab bag of other Scala language warnings and so on that can all be easily fixed. The forthcoming PR fixes about 90% of the build warnings I see now.
Author: Sean Owen <sowen@cloudera.com>
Closes#3157 from srowen/SPARK-4297 and squashes the following commits:
8c9e469 [Sean Owen] Suppress unchecked cast warnings, and several other build warning fixes
In most of the academic paper and algorithm implementations,
people use L = 1/2n ||A weights-y||^2 instead of L = 1/n ||A weights-y||^2
for least-squared loss. See Eq. (1) in http://web.stanford.edu/~hastie/Papers/glmnet.pdf
Since MLlib uses different convention, this will result different residuals and
all the stats properties will be different from GLMNET package in R.
The model coefficients will be still the same under this change.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3746 from dbtsai/lir and squashes the following commits:
19c2e85 [DB Tsai] make stepsize twice to converge to the same solution
0b2c29c [DB Tsai] first commit
...ta generators
This patch adds:
* Exponential, gamma, and log normal generators that wrap Apache Commons math3 to the private API
* Functions for generating exponential, gamma, and log normal RDDs and vector RDDs
* Tests for the above
Author: RJ Nowling <rnowling@gmail.com>
Closes#3680 from rnowling/spark4728 and squashes the following commits:
455f50a [RJ Nowling] Add tests for exponential, gamma, and log normal samplers to JavaRandomRDDsSuite
3e1134a [RJ Nowling] Fix val/var, unncessary creation of Distribution objects when setting seeds, and import line longer than line wrap limits
58f5b97 [RJ Nowling] Fix bounds in tests so they scale with variance, not stdev
84fd98d [RJ Nowling] Add more values for testing distributions.
9f96232 [RJ Nowling] [SPARK-4728] Add exponential, gamma, and log normal sampling to MLlib data generators
The original test doesn't make sense since if you step in, the lossSum is already NaN,
and the coefficients are diverging. That's because the step size is too large for SGD,
so it doesn't work.
The correct behavior is that you should get smaller coefficients than the one
without regularization. Comparing the values using 20000.0 relative error doesn't
make sense as well.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3735 from dbtsai/mlortestfix and squashes the following commits:
b1a3c42 [DB Tsai] first commit
I improved `IDFModel.transform` to allow using a single vector.
[[SPARK-4494] IDFModel.transform() add support for single vector - ASF JIRA](https://issues.apache.org/jira/browse/SPARK-4494)
Author: Yuu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes#3603 from yu-iskw/idf and squashes the following commits:
256ff3d [Yuu ISHIKAWA] Fix typo
a3bf566 [Yuu ISHIKAWA] - Fix typo - Optimize import order - Aggregate the assertion tests - Modify `IDFModel.transform` API for pyspark
d25e49b [Yuu ISHIKAWA] Add the implementation of `IDFModel.transform` for a term frequency vector
and some minor changes in ScalaDoc.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3601 from mengxr/SPARK-4575-fix and squashes the following commits:
c559768 [Xiangrui Meng] minor code update
ce94da8 [Xiangrui Meng] Java Bean -> JavaBean
0b5c182 [Xiangrui Meng] fix links in ml-guide
Documentation:
* Added ml-guide.md, linked from mllib-guide.md
* Updated mllib-guide.md with small section pointing to ml-guide.md
Examples:
* CrossValidatorExample
* SimpleParamsExample
* (I copied these + the SimpleTextClassificationPipeline example into the ml-guide.md)
Bug fixes:
* PipelineModel: did not use ParamMaps correctly
* UnaryTransformer: issues with TypeTag serialization (Thanks to mengxr for that fix!)
CC: mengxr shivaram etrain Documentation for Pipelines: I know the docs are not complete, but the goal is to have enough to let interested people get started using spark.ml and to add more docs once the package is more established/complete.
Author: Joseph K. Bradley <joseph@databricks.com>
Author: jkbradley <joseph.kurata.bradley@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#3588 from jkbradley/ml-package-docs and squashes the following commits:
d393b5c [Joseph K. Bradley] fixed bug in Pipeline (typo from last commit). updated examples for CV and Params for spark.ml
c38469c [Joseph K. Bradley] Updated ml-guide with CV examples
99f88c2 [Joseph K. Bradley] Fixed bug in PipelineModel.transform* with usage of params. Updated CrossValidatorExample to use more training examples so it is less likely to get a 0-size fold.
ea34dc6 [jkbradley] Merge pull request #4 from mengxr/ml-package-docs
3b83ec0 [Xiangrui Meng] replace TypeTag with explicit datatype
41ad9b1 [Joseph K. Bradley] Added examples for spark.ml: SimpleParamsExample + Java version, CrossValidatorExample + Java version. CrossValidatorExample not working yet. Added programming guide for spark.ml, but need to add CrossValidatorExample to it once CrossValidatorExample works.
Major changes:
* Added programming guide sections for tree ensembles
* Added examples for tree ensembles
* Updated DecisionTree programming guide with more info on parameters
* **API change**: Standardized the tree parameter for the number of classes (for classification)
Minor changes:
* Updated decision tree documentation
* Updated existing tree and tree ensemble examples
* Use train/test split, and compute test error instead of training error.
* Fixed decision_tree_runner.py to actually use the number of classes it computes from data. (small bug fix)
Note: I know this is a lot of lines, but most is covered by:
* Programming guide sections for gradient boosting and random forests. (The changes are probably best viewed by generating the docs locally.)
* New examples (which were copied from the programming guide)
* The "numClasses" renaming
I have run all examples and relevant unit tests.
CC: mengxr manishamde codedeft
Author: Joseph K. Bradley <joseph@databricks.com>
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#3461 from jkbradley/ensemble-docs and squashes the following commits:
70a75f3 [Joseph K. Bradley] updated forest vs boosting comparison
d1de753 [Joseph K. Bradley] Added note about toString and toDebugString for DecisionTree to migration guide
8e87f8f [Joseph K. Bradley] Combined GBT and RandomForest guides into one ensembles guide
6fab846 [Joseph K. Bradley] small fixes based on review
b9f8576 [Joseph K. Bradley] updated decision tree doc
375204c [Joseph K. Bradley] fixed python style
2b60b6e [Joseph K. Bradley] merged Java RandomForest examples into 1 file. added header. Fixed small bug in same example in the programming guide.
706d332 [Joseph K. Bradley] updated python DT runner to print full model if it is small
c76c823 [Joseph K. Bradley] added migration guide for mllib
abe5ed7 [Joseph K. Bradley] added examples for random forest in Java and Python to examples folder
07fc11d [Joseph K. Bradley] Renamed numClassesForClassification to numClasses everywhere in trees and ensembles. This is a breaking API change, but it was necessary to correct an API inconsistency in Spark 1.1 (where Python DecisionTree used numClasses but Scala used numClassesForClassification).
cdfdfbc [Joseph K. Bradley] added examples for GBT
6372a2b [Joseph K. Bradley] updated decision tree examples to use random split. tested all of them.
ad3e695 [Joseph K. Bradley] added gbt and random forest to programming guide. still need to update their examples
Have a local reference to `values` and `indices` array in the `Vector` object
so JVM can locate the value with one operation call. See `SPARK-4581`
for similar optimization, and the bytecode analysis.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3577 from dbtsai/blasopt and squashes the following commits:
62d38c4 [DB Tsai] formating
0316cef [DB Tsai] first commit
Note that the usage of `breezeSquaredDistance` in
`org.apache.spark.mllib.util.MLUtils.fastSquaredDistance`
is in the critical path, and `breezeSquaredDistance` is slow.
We should replace it with our own implementation.
Here is the benchmark against mnist8m dataset.
Before
DenseVector: 70.04secs
SparseVector: 59.05secs
With this PR
DenseVector: 30.58secs
SparseVector: 21.14secs
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3565 from dbtsai/kmean and squashes the following commits:
08bc068 [DB Tsai] restyle
de24662 [DB Tsai] address feedback
b185a77 [DB Tsai] cleanup
4554ddd [DB Tsai] first commit
The vector norm in breeze is implemented by `activeIterator` which is known to be very slow.
In this PR, an efficient vector norm is implemented, and with this API, `Normalizer` and
`k-means` have big performance improvement.
Here is the benchmark against mnist8m dataset.
a) `Normalizer`
Before
DenseVector: 68.25secs
SparseVector: 17.01secs
With this PR
DenseVector: 12.71secs
SparseVector: 2.73secs
b) `k-means`
Before
DenseVector: 83.46secs
SparseVector: 61.60secs
With this PR
DenseVector: 70.04secs
SparseVector: 59.05secs
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3462 from dbtsai/norm and squashes the following commits:
63c7165 [DB Tsai] typo
0c3637f [DB Tsai] add import org.apache.spark.SparkContext._ back
6fa616c [DB Tsai] address feedback
9b7cb56 [DB Tsai] move norm to static method
0b632e6 [DB Tsai] kmeans
dbed124 [DB Tsai] style
c1a877c [DB Tsai] first commit
Before we have a full picture of the operators we want to add, it might be safer to hide `Matrix.transposeMultiply` in 1.2.0. Another update we want to change is `Matrix.randn` and `Matrix.rand`, both of which should take a `Random` implementation. Otherwise, it is very likely to produce inconsistent RDDs. I also added some unit tests for matrix factory methods. All APIs are new in 1.2, so there is no incompatible changes.
brkyvz
Author: Xiangrui Meng <meng@databricks.com>
Closes#3468 from mengxr/SPARK-4614 and squashes the following commits:
3b0e4e2 [Xiangrui Meng] add mima excludes
6bfd8a4 [Xiangrui Meng] hide transposeMultiply; add rng to rand and randn; add unit tests
User could construct an MF model directly. I added a note about the performance.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3459 from mengxr/SPARK-4604 and squashes the following commits:
f64bcd3 [Xiangrui Meng] organize imports
ed08214 [Xiangrui Meng] check preconditions and unit tests
a624c12 [Xiangrui Meng] make MatrixFactorizationModel public
Currently, the LogLoss used by GradientBoostedTrees has 2 issues:
* the gradient (and therefore loss) does not match that used by Friedman (1999)
* the error computation uses 0/1 accuracy, not log loss
This PR updates LogLoss.
It also adds some doc for boosting and forests.
I tested it on sample data and made sure the log loss is monotonically decreasing with each boosting iteration.
CC: mengxr manishamde codedeft
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#3439 from jkbradley/gbt-loss-fix and squashes the following commits:
cfec17e [Joseph K. Bradley] removed forgotten temp comments
a27eb6d [Joseph K. Bradley] corrections to last log loss commit
ed5da2c [Joseph K. Bradley] updated LogLoss (boosting) for numerical stability
5e52bff [Joseph K. Bradley] * Removed the 1/2 from SquaredError. This also required updating the test suite since it effectively doubles the gradient and loss. * Added doc for developers within RandomForest. * Small cleanup in test suite (generating data only once)
e57897a [Joseph K. Bradley] Fixed LogLoss for GradientBoostedTrees, and updated doc for losses, forests, and boosting
The following optimizations are done to improve the StandardScaler model
transformation performance.
1) Covert Breeze dense vector to primitive vector to reduce the overhead.
2) Since mean can be potentially a sparse vector, we explicitly convert it to dense primitive vector.
3) Have a local reference to `shift` and `factor` array so JVM can locate the value with one operation call.
4) In pattern matching part, we use the mllib SparseVector/DenseVector instead of breeze's vector to
make the codebase cleaner.
Benchmark with mnist8m dataset:
Before,
DenseVector withMean and withStd: 50.97secs
DenseVector withMean and withoutStd: 42.11secs
DenseVector withoutMean and withStd: 8.75secs
SparseVector withoutMean and withStd: 5.437secs
With this PR,
DenseVector withMean and withStd: 5.76secs
DenseVector withMean and withoutStd: 5.28secs
DenseVector withoutMean and withStd: 5.30secs
SparseVector withoutMean and withStd: 1.27secs
Note that without the local reference copy of `factor` and `shift` arrays,
the runtime is almost three time slower.
DenseVector withMean and withStd: 18.15secs
DenseVector withMean and withoutStd: 18.05secs
DenseVector withoutMean and withStd: 18.54secs
SparseVector withoutMean and withStd: 2.01secs
The following code,
```scala
while (i < size) {
values(i) = (values(i) - shift(i)) * factor(i)
i += 1
}
```
will generate the bytecode
```
L13
LINENUMBER 106 L13
FRAME FULL [org/apache/spark/mllib/feature/StandardScalerModel org/apache/spark/mllib/linalg/Vector org/apache/spark/mllib/linalg/Vector org/apache/spark/mllib/linalg/DenseVector T [D I I] []
ILOAD 7
ILOAD 6
IF_ICMPGE L14
L15
LINENUMBER 107 L15
ALOAD 5
ILOAD 7
ALOAD 5
ILOAD 7
DALOAD
ALOAD 0
INVOKESPECIAL org/apache/spark/mllib/feature/StandardScalerModel.shift ()[D
ILOAD 7
DALOAD
DSUB
ALOAD 0
INVOKESPECIAL org/apache/spark/mllib/feature/StandardScalerModel.factor ()[D
ILOAD 7
DALOAD
DMUL
DASTORE
L16
LINENUMBER 108 L16
ILOAD 7
ICONST_1
IADD
ISTORE 7
GOTO L13
```
, while with the local reference of the `shift` and `factor` arrays, the bytecode will be
```
L14
LINENUMBER 107 L14
ALOAD 0
INVOKESPECIAL org/apache/spark/mllib/feature/StandardScalerModel.factor ()[D
ASTORE 9
L15
LINENUMBER 108 L15
FRAME FULL [org/apache/spark/mllib/feature/StandardScalerModel org/apache/spark/mllib/linalg/Vector [D org/apache/spark/mllib/linalg/Vector org/apache/spark/mllib/linalg/DenseVector T [D I I [D] []
ILOAD 8
ILOAD 7
IF_ICMPGE L16
L17
LINENUMBER 109 L17
ALOAD 6
ILOAD 8
ALOAD 6
ILOAD 8
DALOAD
ALOAD 2
ILOAD 8
DALOAD
DSUB
ALOAD 9
ILOAD 8
DALOAD
DMUL
DASTORE
L18
LINENUMBER 110 L18
ILOAD 8
ICONST_1
IADD
ISTORE 8
GOTO L15
```
You can see that with local reference, the both of the arrays will be in the stack, so JVM can access the value without calling `INVOKESPECIAL`.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3435 from dbtsai/standardscaler and squashes the following commits:
85885a9 [DB Tsai] revert to have lazy in shift array.
daf2b06 [DB Tsai] Address the feedback
cdb5cef [DB Tsai] small change
9c51eef [DB Tsai] style
fc795e4 [DB Tsai] update
5bffd3d [DB Tsai] first commit
This is caused by the miniBatchSize parameter.The number of `RDD.sample` returns is not fixed.
cc mengxr
Author: GuoQiang Li <witgo@qq.com>
Closes#3399 from witgo/GradientDescent and squashes the following commits:
13cb228 [GuoQiang Li] review commit
668ab66 [GuoQiang Li] Double to Long
b6aa11a [GuoQiang Li] Check miniBatchSize is greater than 0
0b5c3e3 [GuoQiang Li] Minor fix
12e7424 [GuoQiang Li] GradientDescent get a wrong gradient value according to the gradient formula, which is caused by the miniBatchSize parameter.
In this refactoring, the performance will be slightly increased due to removing
the overhead from breeze vector. The bottleneck is still in breeze norm
which is implemented by activeIterator.
This inefficiency of breeze norm will be addressed in next PR. At least,
this PR makes the code more consistent in the codebase.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3446 from dbtsai/normalizer and squashes the following commits:
e20a2b9 [DB Tsai] first commit
This is #3309 for the master branch.
e.g. clustering
Author: tkaessmann <tobias.kaessmanns24.com>
Closes#3309 from tkaessmann/branch-1.2 and squashes the following commits:
e3a3142 [tkaessmann] changes the comment for getVectors
58d3d83 [tkaessmann] removes sign from comment
a5be213 [tkaessmann] fixes getVectors to fit code guidelines
3782fa9 [tkaessmann] get raw vectors for further processing
Author: tkaessmann <tobias.kaessmann@s24.com>
Closes#3437 from mengxr/SPARK-4582 and squashes the following commits:
6c666b4 [tkaessmann] get raw vectors for further processing in Word2Vec
This PR change the underline array of DenseVector to numpy.ndarray to avoid the conversion, because most of the users will using numpy.array.
It also improve the serialization of DenseVector.
Before this change:
trial | trainingTime | testTime
-------|--------|--------
0 | 5.126 | 1.786
1 |2.698 |1.693
After the change:
trial | trainingTime | testTime
-------|--------|--------
0 |4.692 |0.554
1 |2.307 |0.525
This could partially fix the performance regression during test.
Author: Davies Liu <davies@databricks.com>
Closes#3420 from davies/ser2 and squashes the following commits:
0e1e6f3 [Davies Liu] fix tests
426f5db [Davies Liu] impove toArray()
44707ec [Davies Liu] add name for ISO-8859-1
fa7d791 [Davies Liu] address comments
1cfb137 [Davies Liu] handle zero sparse vector
2548ee2 [Davies Liu] fix tests
9e6389d [Davies Liu] bugfix
470f702 [Davies Liu] speed up DenseMatrix
f0d3c40 [Davies Liu] speedup SparseVector
ef6ce70 [Davies Liu] speed up dense vector
Previously, we were using Breeze's activeIterator to access the non-zero elements
in dense/sparse vector. Due to the overhead, we switched back to native `while loop`
in #SPARK-4129.
However, #SPARK-4129 requires de-reference the dv.values/sv.values in
each access to the value, which is very expensive. Also, in MultivariateOnlineSummarizer,
we're using Breeze's dense vector to store the partial stats, and this is very expensive compared
with using primitive scala array.
In this PR, efficient foreachActive is implemented to unify the code path for dense and sparse
vector operation which makes codebase easier to maintain. Breeze dense vector is replaced
by primitive array to reduce the overhead further.
Benchmarking with mnist8m dataset on single JVM
with first 200 samples loaded in memory, and repeating 5000 times.
Before change:
Sparse Vector - 30.02
Dense Vector - 38.27
With this PR:
Sparse Vector - 6.29
Dense Vector - 11.72
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#3288 from dbtsai/activeIterator and squashes the following commits:
844b0e6 [DB Tsai] formating
03dd693 [DB Tsai] futher performance tunning.
1907ae1 [DB Tsai] address feedback
98448bb [DB Tsai] Made the override final, and had a local copy of variables which made the accessing a single step operation.
c0cbd5a [DB Tsai] fix a bug
6441f92 [DB Tsai] Finished SPARK-4431
The Pyrolite is pretty slow (comparing to the adhoc serializer in 1.1), it cause much performance regression in 1.2, because we cache the serialized Python object in JVM, deserialize them into Java object in each step.
This PR change to cache the deserialized JavaRDD instead of PythonRDD to avoid the deserialization of Pyrolite. It should have similar memory usage as before, but much faster.
Author: Davies Liu <davies@databricks.com>
Closes#3397 from davies/cache and squashes the following commits:
7f6e6ce [Davies Liu] Update -> Updater
4b52edd [Davies Liu] using named argument
63b984e [Davies Liu] fix
7da0332 [Davies Liu] add unpersist()
dff33e1 [Davies Liu] address comments
c2bdfc2 [Davies Liu] refactor
d572f00 [Davies Liu] Merge branch 'master' into cache
f1063e1 [Davies Liu] cache serialized java object
```
class RandomForestModel
| A model trained by RandomForest
|
| numTrees(self)
| Get number of trees in forest.
|
| predict(self, x)
| Predict values for a single data point or an RDD of points using the model trained.
|
| toDebugString(self)
| Full model
|
| totalNumNodes(self)
| Get total number of nodes, summed over all trees in the forest.
|
class RandomForest
| trainClassifier(cls, data, numClassesForClassification, categoricalFeaturesInfo, numTrees, featureSubsetStrategy='auto', impurity='gini', maxDepth=4, maxBins=32, seed=None):
| Method to train a decision tree model for binary or multiclass classification.
|
| :param data: Training dataset: RDD of LabeledPoint.
| Labels should take values {0, 1, ..., numClasses-1}.
| :param numClassesForClassification: number of classes for classification.
| :param categoricalFeaturesInfo: Map storing arity of categorical features.
| E.g., an entry (n -> k) indicates that feature n is categorical
| with k categories indexed from 0: {0, 1, ..., k-1}.
| :param numTrees: Number of trees in the random forest.
| :param featureSubsetStrategy: Number of features to consider for splits at each node.
| Supported: "auto" (default), "all", "sqrt", "log2", "onethird".
| If "auto" is set, this parameter is set based on numTrees:
| if numTrees == 1, set to "all";
| if numTrees > 1 (forest) set to "sqrt".
| :param impurity: Criterion used for information gain calculation.
| Supported values: "gini" (recommended) or "entropy".
| :param maxDepth: Maximum depth of the tree. E.g., depth 0 means 1 leaf node; depth 1 means
| 1 internal node + 2 leaf nodes. (default: 4)
| :param maxBins: maximum number of bins used for splitting features (default: 100)
| :param seed: Random seed for bootstrapping and choosing feature subsets.
| :return: RandomForestModel that can be used for prediction
|
| trainRegressor(cls, data, categoricalFeaturesInfo, numTrees, featureSubsetStrategy='auto', impurity='variance', maxDepth=4, maxBins=32, seed=None):
| Method to train a decision tree model for regression.
|
| :param data: Training dataset: RDD of LabeledPoint.
| Labels are real numbers.
| :param categoricalFeaturesInfo: Map storing arity of categorical features.
| E.g., an entry (n -> k) indicates that feature n is categorical
| with k categories indexed from 0: {0, 1, ..., k-1}.
| :param numTrees: Number of trees in the random forest.
| :param featureSubsetStrategy: Number of features to consider for splits at each node.
| Supported: "auto" (default), "all", "sqrt", "log2", "onethird".
| If "auto" is set, this parameter is set based on numTrees:
| if numTrees == 1, set to "all";
| if numTrees > 1 (forest) set to "onethird".
| :param impurity: Criterion used for information gain calculation.
| Supported values: "variance".
| :param maxDepth: Maximum depth of the tree. E.g., depth 0 means 1 leaf node; depth 1 means
| 1 internal node + 2 leaf nodes.(default: 4)
| :param maxBins: maximum number of bins used for splitting features (default: 100)
| :param seed: Random seed for bootstrapping and choosing feature subsets.
| :return: RandomForestModel that can be used for prediction
|
```
Author: Davies Liu <davies@databricks.com>
Closes#3320 from davies/forest and squashes the following commits:
8003dfc [Davies Liu] reorder
53cf510 [Davies Liu] fix docs
4ca593d [Davies Liu] fix docs
e0df852 [Davies Liu] fix docs
0431746 [Davies Liu] rebased
2b6f239 [Davies Liu] Merge branch 'master' of github.com:apache/spark into forest
885abee [Davies Liu] address comments
dae7fc0 [Davies Liu] address comments
89a000f [Davies Liu] fix docs
565d476 [Davies Liu] add python api for random forest
There are some inconsistencies in the gradient boosting APIs. The target is a general boosting meta-algorithm, but the implementation is attached to trees. This was partially due to the delay of SPARK-1856. But for the 1.2 release, we should make the APIs consistent.
1. WeightedEnsembleModel -> private[tree] TreeEnsembleModel and renamed members accordingly.
1. GradientBoosting -> GradientBoostedTrees
1. Add RandomForestModel and GradientBoostedTreesModel and hide CombiningStrategy
1. Slightly refactored TreeEnsembleModel (Vote takes weights into consideration.)
1. Remove `trainClassifier` and `trainRegressor` from `GradientBoostedTrees` because they are the same as `train`
1. Rename class `train` method to `run` because it hides the static methods with the same name in Java. Deprecated `DecisionTree.train` class method.
1. Simplify BoostingStrategy and make sure the input strategy is not modified. Users should put algo and numClasses in treeStrategy. We create ensembleStrategy inside boosting.
1. Fix a bug in GradientBoostedTreesSuite with AbsoluteError
1. doc updates
manishamde jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#3374 from mengxr/SPARK-4486 and squashes the following commits:
7097251 [Xiangrui Meng] address joseph's comments
98dea09 [Xiangrui Meng] address manish's comments
4aae3b7 [Xiangrui Meng] add RandomForestModel and GradientBoostedTreesModel, hide CombiningStrategy
ea4c467 [Xiangrui Meng] fix unit tests
751da4e [Xiangrui Meng] rename class method train -> run
19030a5 [Xiangrui Meng] update boosting public APIs
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#3277 from vanzin/version-1.3 and squashes the following commits:
7c3c396 [Marcelo Vanzin] Added temp repo to sbt build.
5f404ff [Marcelo Vanzin] Add another exclusion.
19457e7 [Marcelo Vanzin] Update old version to 1.2, add temporary 1.2 repo.
3c8d705 [Marcelo Vanzin] Workaround for MIMA checks.
e940810 [Marcelo Vanzin] Bumping version to 1.3.0-SNAPSHOT.
```
class LogisticRegressionWithLBFGS
| train(cls, data, iterations=100, initialWeights=None, corrections=10, tolerance=0.0001, regParam=0.01, intercept=False)
| Train a logistic regression model on the given data.
|
| :param data: The training data, an RDD of LabeledPoint.
| :param iterations: The number of iterations (default: 100).
| :param initialWeights: The initial weights (default: None).
| :param regParam: The regularizer parameter (default: 0.01).
| :param regType: The type of regularizer used for training
| our model.
| :Allowed values:
| - "l1" for using L1 regularization
| - "l2" for using L2 regularization
| - None for no regularization
| (default: "l2")
| :param intercept: Boolean parameter which indicates the use
| or not of the augmented representation for
| training data (i.e. whether bias features
| are activated or not).
| :param corrections: The number of corrections used in the LBFGS update (default: 10).
| :param tolerance: The convergence tolerance of iterations for L-BFGS (default: 1e-4).
|
| >>> data = [
| ... LabeledPoint(0.0, [0.0, 1.0]),
| ... LabeledPoint(1.0, [1.0, 0.0]),
| ... ]
| >>> lrm = LogisticRegressionWithLBFGS.train(sc.parallelize(data))
| >>> lrm.predict([1.0, 0.0])
| 1
| >>> lrm.predict([0.0, 1.0])
| 0
| >>> lrm.predict(sc.parallelize([[1.0, 0.0], [0.0, 1.0]])).collect()
| [1, 0]
```
Author: Davies Liu <davies@databricks.com>
Closes#3307 from davies/lbfgs and squashes the following commits:
34bd986 [Davies Liu] Merge branch 'master' of http://git-wip-us.apache.org/repos/asf/spark into lbfgs
5a945a6 [Davies Liu] address comments
941061b [Davies Liu] Merge branch 'master' of github.com:apache/spark into lbfgs
03e5543 [Davies Liu] add it to docs
ed2f9a8 [Davies Liu] add regType
76cd1b6 [Davies Liu] reorder arguments
4429a74 [Davies Liu] Update classification.py
9252783 [Davies Liu] python api for LogisticRegressionWithLBFGS
This PR add setThrehold() and clearThreshold() for LogisticRegressionModel and SVMModel, also support RDD of vector in LogisticRegressionModel.predict(), SVNModel.predict() and NaiveBayes.predict()
Author: Davies Liu <davies@databricks.com>
Closes#3305 from davies/setThreshold and squashes the following commits:
d0b835f [Davies Liu] Merge branch 'master' of github.com:apache/spark into setThreshold
e4acd76 [Davies Liu] address comments
2231a5f [Davies Liu] bugfix
7bd9009 [Davies Liu] address comments
0b0a8a7 [Davies Liu] address comments
c1e5573 [Davies Liu] improve classification
Author: Felix Maximilian Möller <felixmaximilian.moeller@immobilienscout24.de>
Closes#3343 from felixmaximilian/fix-documentation and squashes the following commits:
43dcdfb [Felix Maximilian Möller] Removed the information about the switch implicitPrefs. The parameter implicitPrefs cannot be set in this context because it is inherent true when calling the trainImplicit method.
7d172ba [Felix Maximilian Möller] added missing parameter alpha in doc string.
cc mengxr
Author: GuoQiang Li <witgo@qq.com>
Closes#3281 from witgo/SPARK-4422 and squashes the following commits:
5f1fa5e [GuoQiang Li] import order
50783bd [GuoQiang Li] review commits
7a10123 [GuoQiang Li] In some cases, Vectors.fromBreeze get wrong results.
The current default regParam is 1.0 and regType is claimed to be none in Python (but actually it is l2), while regParam = 0.0 and regType is L2 in Scala. We should make the default values consistent. This PR sets the default regType to L2 and regParam to 0.01. Note that the default regParam value in LIBLINEAR (and hence scikit-learn) is 1.0. However, we use average loss instead of total loss in our formulation. Hence regParam=1.0 is definitely too heavy.
In LinearRegression, we set regParam=0.0 and regType=None, because we have separate classes for Lasso and Ridge, both of which use regParam=0.01 as the default.
davies atalwalkar
Author: Xiangrui Meng <meng@databricks.com>
Closes#3232 from mengxr/SPARK-4372 and squashes the following commits:
9979837 [Xiangrui Meng] update Ridge/Lasso to use default regParam 0.01 cast input arguments
d3ba096 [Xiangrui Meng] change 'none' back to None
1909a6e [Xiangrui Meng] change default regParam to 0.01 and regType to L2 in LR and SVM
Add Java-friendly version of `run` and `predict`, and use bulk prediction in Java unit tests. The user guide update will come later (though we may not save many lines of code there). srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes#3240 from mengxr/SPARK-4378 and squashes the following commits:
6581503 [Xiangrui Meng] check number of predictions
6c8bbd1 [Xiangrui Meng] make ALS more Java-friendly
...e 0 positive or 0 negative examples.
Author: Andrew Bullen <andrew.bullen@workday.com>
Closes#3118 from abull/master and squashes the following commits:
c2bf2b1 [Andrew Bullen] [SPARK-4256] Update Code formatting for BinaryClassificationMetricsSpec
36b0533 [Andrew Bullen] [SYMAN-4256] Extract BinaryClassificationMetricsSuite assertions into private method
4d2f79a [Andrew Bullen] [SPARK-4256] Refactor classification metrics tests - extract comparison functions in test
f411e70 [Andrew Bullen] [SPARK-4256] Define precision as 1.0 when there are no positive examples; update code formatting per pull request comments
d9a09ef [Andrew Bullen] Make Binary Evaluation Metrics functions defined in cases where there are 0 positive or 0 negative examples.
We want to make sure there is at most one spark context inside the same jvm. JoshRosen
Author: Xiangrui Meng <meng@databricks.com>
Closes#3235 from mengxr/SPARK-4373 and squashes the following commits:
6574b69 [Xiangrui Meng] rename LocalSparkContext to MLlibTestSparkContext
913d48d [Xiangrui Meng] make sure there is at most one spark context inside the same jvm
Fix TreeModel.predict() with RDD, added tests for it.
(Also checked that other models don't have this issue)
Author: Davies Liu <davies@databricks.com>
Closes#3230 from davies/predict and squashes the following commits:
81172aa [Davies Liu] fix predict
This PR adds package "org.apache.spark.ml" with pipeline and parameters, as discussed on the JIRA. This is a joint work of jkbradley etrain shivaram and many others who helped on the design, also with help from marmbrus and liancheng on the Spark SQL side. The design doc can be found at:
https://docs.google.com/document/d/1rVwXRjWKfIb-7PI6b86ipytwbUH7irSNLF1_6dLmh8o/edit?usp=sharing
**org.apache.spark.ml**
This is a new package with new set of ML APIs that address practical machine learning pipelines. (Sorry for taking so long!) It will be an alpha component, so this is definitely not something set in stone. The new set of APIs, inspired by the MLI project from AMPLab and scikit-learn, takes leverage on Spark SQL's schema support and execution plan optimization. It introduces the following components that help build a practical pipeline:
1. Transformer, which transforms a dataset into another
2. Estimator, which fits models to data, where models are transformers
3. Evaluator, which evaluates model output and returns a scalar metric
4. Pipeline, a simple pipeline that consists of transformers and estimators
Parameters could be supplied at fit/transform or embedded with components.
1. Param: a strong-typed parameter key with self-contained doc
2. ParamMap: a param -> value map
3. Params: trait for components with parameters
For any component that implements `Params`, user can easily check the doc by calling `explainParams`:
~~~
> val lr = new LogisticRegression
> lr.explainParams
maxIter: max number of iterations (default: 100)
regParam: regularization constant (default: 0.1)
labelCol: label column name (default: label)
featuresCol: features column name (default: features)
~~~
or user can check individual param:
~~~
> lr.maxIter
maxIter: max number of iterations (default: 100)
~~~
**Please start with the example code in test suites and under `org.apache.spark.examples.ml`, where I put several examples:**
1. run a simple logistic regression job
~~~
val lr = new LogisticRegression()
.setMaxIter(10)
.setRegParam(1.0)
val model = lr.fit(dataset)
model.transform(dataset, model.threshold -> 0.8) // overwrite threshold
.select('label, 'score, 'prediction).collect()
.foreach(println)
~~~
2. run logistic regression with cross-validation and grid search using areaUnderROC (default) as the metric
~~~
val lr = new LogisticRegression
val lrParamMaps = new ParamGridBuilder()
.addGrid(lr.regParam, Array(0.1, 100.0))
.addGrid(lr.maxIter, Array(0, 5))
.build()
val eval = new BinaryClassificationEvaluator
val cv = new CrossValidator()
.setEstimator(lr)
.setEstimatorParamMaps(lrParamMaps)
.setEvaluator(eval)
.setNumFolds(3)
val bestModel = cv.fit(dataset)
~~~
3. run a pipeline that consists of a standard scaler and a logistic regression component
~~~
val scaler = new StandardScaler()
.setInputCol("features")
.setOutputCol("scaledFeatures")
val lr = new LogisticRegression()
.setFeaturesCol(scaler.getOutputCol)
val pipeline = new Pipeline()
.setStages(Array(scaler, lr))
val model = pipeline.fit(dataset)
val predictions = model.transform(dataset)
.select('label, 'score, 'prediction)
.collect()
.foreach(println)
~~~
4. a simple text classification pipeline, which recognizes "spark":
~~~
val training = sparkContext.parallelize(Seq(
LabeledDocument(0L, "a b c d e spark", 1.0),
LabeledDocument(1L, "b d", 0.0),
LabeledDocument(2L, "spark f g h", 1.0),
LabeledDocument(3L, "hadoop mapreduce", 0.0)))
val tokenizer = new Tokenizer()
.setInputCol("text")
.setOutputCol("words")
val hashingTF = new HashingTF()
.setInputCol(tokenizer.getOutputCol)
.setOutputCol("features")
val lr = new LogisticRegression()
.setMaxIter(10)
val pipeline = new Pipeline()
.setStages(Array(tokenizer, hashingTF, lr))
val model = pipeline.fit(training)
val test = sparkContext.parallelize(Seq(
Document(4L, "spark i j k"),
Document(5L, "l m"),
Document(6L, "mapreduce spark"),
Document(7L, "apache hadoop")))
model.transform(test)
.select('id, 'text, 'prediction, 'score)
.collect()
.foreach(println)
~~~
Java examples are very similar. I put example code that creates a simple text classification pipeline in Scala and Java, where a simple tokenizer is defined as a transformer outside `org.apache.spark.ml`.
**What are missing now and will be added soon:**
1. ~~Runtime check of schemas. So before we touch the data, we will go through the schema and make sure column names and types match the input parameters.~~
2. ~~Java examples.~~
3. ~~Store training parameters in trained models.~~
4. (later) Serialization and Python API.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3099 from mengxr/SPARK-3530 and squashes the following commits:
2cc93fd [Xiangrui Meng] hide APIs as much as I can
34319ba [Xiangrui Meng] use local instead local[2] for unit tests
2524251 [Xiangrui Meng] rename PipelineStage.transform to transformSchema
c9daab4 [Xiangrui Meng] remove mockito version
1397ab5 [Xiangrui Meng] use sqlContext from LocalSparkContext instead of TestSQLContext
6ffc389 [Xiangrui Meng] try to fix unit test
a59d8b7 [Xiangrui Meng] doc updates
977fd9d [Xiangrui Meng] add scala ml package object
6d97fe6 [Xiangrui Meng] add AlphaComponent annotation
731f0e4 [Xiangrui Meng] update package doc
0435076 [Xiangrui Meng] remove ;this from setters
fa21d9b [Xiangrui Meng] update extends indentation
f1091b3 [Xiangrui Meng] typo
228a9f4 [Xiangrui Meng] do not persist before calling binary classification metrics
f51cd27 [Xiangrui Meng] rename default to defaultValue
b3be094 [Xiangrui Meng] refactor schema transform in lr
8791e8e [Xiangrui Meng] rename copyValues to inheritValues and make it do the right thing
51f1c06 [Xiangrui Meng] remove leftover code in Transformer
494b632 [Xiangrui Meng] compure score once
ad678e9 [Xiangrui Meng] more doc for Transformer
4306ed4 [Xiangrui Meng] org imports in text pipeline
6e7c1c7 [Xiangrui Meng] update pipeline
4f9e34f [Xiangrui Meng] more doc for pipeline
aa5dbd4 [Xiangrui Meng] fix typo
11be383 [Xiangrui Meng] fix unit tests
3df7952 [Xiangrui Meng] clean up
986593e [Xiangrui Meng] re-org java test suites
2b11211 [Xiangrui Meng] remove external data deps
9fd4933 [Xiangrui Meng] add unit test for pipeline
2a0df46 [Xiangrui Meng] update tests
2d52e4d [Xiangrui Meng] add @AlphaComponent to package-info
27582a4 [Xiangrui Meng] doc changes
73a000b [Xiangrui Meng] add schema transformation layer
6736e87 [Xiangrui Meng] more doc / remove HasMetricName trait
80a8b5e [Xiangrui Meng] rename SimpleTransformer to UnaryTransformer
62ca2bb [Xiangrui Meng] check param parent in set/get
1622349 [Xiangrui Meng] add getModel to PipelineModel
a0e0054 [Xiangrui Meng] update StandardScaler to use SimpleTransformer
d0faa04 [Xiangrui Meng] remove implicit mapping from ParamMap
c7f6921 [Xiangrui Meng] move ParamGridBuilder test to ParamGridBuilderSuite
e246f29 [Xiangrui Meng] re-org:
7772430 [Xiangrui Meng] remove modelParams add a simple text classification pipeline
b95c408 [Xiangrui Meng] remove implicits add unit tests to params
bab3e5b [Xiangrui Meng] update params
fe0ee92 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-3530
6e86d98 [Xiangrui Meng] some code clean-up
2d040b3 [Xiangrui Meng] implement setters inside each class, add Params.copyValues [ci skip]
fd751fc [Xiangrui Meng] add java-friendly versions of fit and tranform
3f810cd [Xiangrui Meng] use multi-model training api in cv
5b8f413 [Xiangrui Meng] rename model to modelParams
9d2d35d [Xiangrui Meng] test varargs and chain model params
f46e927 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-3530
1ef26e0 [Xiangrui Meng] specialize methods/types for Java
df293ed [Xiangrui Meng] switch to setter/getter
376db0a [Xiangrui Meng] pipeline and parameters
See inline comment about the bug. I also did some code clean-up. dbtsai I moved `update` to a private method of `MultivariateOnlineSummarizer`. I don't think it will cause performance regression, but it would be great if you have some time to test.
Author: Xiangrui Meng <meng@databricks.com>
Closes#3220 from mengxr/SPARK-4355 and squashes the following commits:
5ef601f [Xiangrui Meng] fix OnlineSummarizer.merge when other.mean is zero and some code clean-up
SPARK-1553 added alternating nonnegative least squares to MLLib, however it's not possible to access it via the python API. This pull request resolves that.
Author: Michelangelo D'Agostino <mdagostino@civisanalytics.com>
Closes#3095 from mdagost/python_nmf and squashes the following commits:
a6743ad [Michelangelo D'Agostino] Use setters instead of static methods in PythonMLLibAPI. Remove the new static methods I added. Set seed in tests. Change ratings to ratingsRDD in both train and trainImplicit for consistency.
7cffd39 [Michelangelo D'Agostino] Swapped nonnegative and seed in a few more places.
3fdc851 [Michelangelo D'Agostino] Moved seed to the end of the python parameter list.
bdcc154 [Michelangelo D'Agostino] Change seed type to java.lang.Long so that it can handle null.
cedf043 [Michelangelo D'Agostino] Added in ability to set the seed from python and made that play nice with the nonnegative changes. Also made the python ALS tests more exact.
a72fdc9 [Michelangelo D'Agostino] Expose nonnegative ALS in the python API.
### Summary
* Made it easier to construct default Strategy and BoostingStrategy and to set parameters using simple types.
* Added Scala and Java examples for GradientBoostedTrees
* small cleanups and fixes
### Details
GradientBoosting bug fixes (“bug” = bad default options)
* Force boostingStrategy.weakLearnerParams.algo = Regression
* Force boostingStrategy.weakLearnerParams.impurity = impurity.Variance
* Only persist data if not yet persisted (since it causes an error if persisted twice)
BoostingStrategy
* numEstimators: renamed to numIterations
* removed subsamplingRate (duplicated by Strategy)
* removed categoricalFeaturesInfo since it belongs with the weak learner params (since boosting can be oblivious to feature type)
* Changed algo to var (not val) and added BeanProperty, with overload taking String argument
* Added assertValid() method
* Updated defaultParams() method and eliminated defaultWeakLearnerParams() since that belongs in Strategy
Strategy (for DecisionTree)
* Changed algo to var (not val) and added BeanProperty, with overload taking String argument
* Added setCategoricalFeaturesInfo method taking Java Map.
* Cleaned up assertValid
* Changed val’s to def’s since parameters can now be changed.
CC: manishamde mengxr codedeft
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#3094 from jkbradley/gbt-api and squashes the following commits:
7a27e22 [Joseph K. Bradley] scalastyle fix
52013d5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into gbt-api
e9b8410 [Joseph K. Bradley] Summary of changes
```
pyspark.mllib.stat.StatisticschiSqTest(observed, expected=None)
:: Experimental ::
If `observed` is Vector, conduct Pearson's chi-squared goodness
of fit test of the observed data against the expected distribution,
or againt the uniform distribution (by default), with each category
having an expected frequency of `1 / len(observed)`.
(Note: `observed` cannot contain negative values)
If `observed` is matrix, conduct Pearson's independence test on the
input contingency matrix, which cannot contain negative entries or
columns or rows that sum up to 0.
If `observed` is an RDD of LabeledPoint, conduct Pearson's independence
test for every feature against the label across the input RDD.
For each feature, the (feature, label) pairs are converted into a
contingency matrix for which the chi-squared statistic is computed.
All label and feature values must be categorical.
:param observed: it could be a vector containing the observed categorical
counts/relative frequencies, or the contingency matrix
(containing either counts or relative frequencies),
or an RDD of LabeledPoint containing the labeled dataset
with categorical features. Real-valued features will be
treated as categorical for each distinct value.
:param expected: Vector containing the expected categorical counts/relative
frequencies. `expected` is rescaled if the `expected` sum
differs from the `observed` sum.
:return: ChiSquaredTest object containing the test statistic, degrees
of freedom, p-value, the method used, and the null hypothesis.
```
Author: Davies Liu <davies@databricks.com>
Closes#3091 from davies/his and squashes the following commits:
145d16c [Davies Liu] address comments
0ab0764 [Davies Liu] fix float
5097d54 [Davies Liu] add Hypothesis test Python API
Author: Niklas Wilcke <1wilcke@informatik.uni-hamburg.de>
Closes#2907 from numbnut/master and squashes the following commits:
7f7c767 [Niklas Wilcke] [Spark-4060] [MLlib] exposing special rdd functions to the public, #2907
This PR simplify serializer, always use batched serializer (AutoBatchedSerializer as default), even batch size is 1.
Author: Davies Liu <davies@databricks.com>
This patch had conflicts when merged, resolved by
Committer: Josh Rosen <joshrosen@databricks.com>
Closes#2920 from davies/fix_autobatch and squashes the following commits:
e544ef9 [Davies Liu] revert unrelated change
6880b14 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
1d557fc [Davies Liu] fix tests
8180907 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
76abdce [Davies Liu] clean up
53fa60b [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
d7ac751 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
2cc2497 [Davies Liu] Merge branch 'master' of github.com:apache/spark into fix_autobatch
b4292ce [Davies Liu] fix bug in master
d79744c [Davies Liu] recover hive tests
be37ece [Davies Liu] refactor
eb3938d [Davies Liu] refactor serializer in scala
8d77ef2 [Davies Liu] simplify serializer, use AutoBatchedSerializer by default.
Register MLlib's Vector as a SQL user-defined type (UDT) in both Scala and Python. With this PR, we can easily map a RDD[LabeledPoint] to a SchemaRDD, and then select columns or save to a Parquet file. Examples in Scala/Python are attached. The Scala code was copied from jkbradley.
~~This PR contains the changes from #3068 . I will rebase after #3068 is merged.~~
marmbrus jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#3070 from mengxr/SPARK-3573 and squashes the following commits:
3a0b6e5 [Xiangrui Meng] organize imports
236f0a0 [Xiangrui Meng] register vector as UDT and provide dataset examples
Saw Jenkins test failures due to random seeds.
jkbradley manishamde
Author: Xiangrui Meng <meng@databricks.com>
Closes#3084 from mengxr/fix-baggedpoint-suite and squashes the following commits:
f735a43 [Xiangrui Meng] fix seed in BaggedPointSuite
...sion trees. jkbradley mengxr chouqin Please review this.
Author: Sung Chung <schung@alpinenow.com>
Closes#2868 from codedeft/SPARK-3161 and squashes the following commits:
5f5a156 [Sung Chung] [SPARK-3161][MLLIB] Adding a node Id caching mechanism for training decision trees.
In #2928 , we shade commons-math3 to prevent future conflicts with hadoop. It caused problems with our Jenkins master build with maven. Some tests used local-cluster mode, where the assembly jar contains relocated math3 classes, while mllib test code still compiles with core and the untouched math3 classes.
This PR sets commons-math3 version based on hadoop profiles.
pwendell JoshRosen srowen
Author: Xiangrui Meng <meng@databricks.com>
Closes#3023 from mengxr/SPARK-4121-alt and squashes the following commits:
580f6d9 [Xiangrui Meng] replace tab by spaces
7f71f08 [Xiangrui Meng] revert changes to PoissonSampler to avoid conflicts
d3353d9 [Xiangrui Meng] do not shade commons-math3
b4180dc [Xiangrui Meng] temp work
This adds a Streaming KMeans algorithm to MLlib. It uses an update rule that generalizes the mini-batch KMeans update to incorporate a decay factor, which allows past data to be forgotten. The decay factor can be specified explicitly, or via a more intuitive "fractional decay" setting, in units of either data points or batches.
The PR includes:
- StreamingKMeans algorithm with decay factor settings
- Usage example
- Additions to documentation clustering page
- Unit tests of basic behavior and decay behaviors
tdas mengxr rezazadeh
Author: freeman <the.freeman.lab@gmail.com>
Author: Jeremy Freeman <the.freeman.lab@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#2942 from freeman-lab/streaming-kmeans and squashes the following commits:
b2e5b4a [freeman] Fixes to docs / examples
078617c [Jeremy Freeman] Merge pull request #1 from mengxr/SPARK-3254
2e682c0 [Xiangrui Meng] take discount on previous weights; use BLAS; detect dying clusters
0411bf5 [freeman] Change decay parameterization
9f7aea9 [freeman] Style fixes
374a706 [freeman] Formatting
ad9bdc2 [freeman] Use labeled points and predictOnValues in examples
77dbd3f [freeman] Make initialization check an assertion
9cfc301 [freeman] Make random seed an argument
44050a9 [freeman] Simpler constructor
c7050d5 [freeman] Fix spacing
2899623 [freeman] Use pattern matching for clarity
a4a316b [freeman] Use collect
1472ec5 [freeman] Doc formatting
ea22ec8 [freeman] Fix imports
2086bdc [freeman] Log cluster center updates
ea9877c [freeman] More documentation
9facbe3 [freeman] Bug fix
5db7074 [freeman] Example usage for StreamingKMeans
f33684b [freeman] Add explanation and example to docs
b5b5f8d [freeman] Add better documentation
a0fd790 [freeman] Merge remote-tracking branch 'upstream/master' into streaming-kmeans
9fd9c15 [freeman] Merge remote-tracking branch 'upstream/master' into streaming-kmeans
b93350f [freeman] Streaming KMeans with decay
Given the popular demand for gradient boosting and AdaBoost in MLlib, I am creating a WIP branch for early feedback on gradient boosting with AdaBoost to follow soon after this PR is accepted. This is based on work done along with hirakendu that was pending due to decision tree optimizations and random forests work.
Ideally, boosting algorithms should work with any base learners. This will soon be possible once the MLlib API is finalized -- we want to ensure we use a consistent interface for the underlying base learners. In the meantime, this PR uses decision trees as base learners for the gradient boosting algorithm. The current PR allows "pluggable" loss functions and provides least squares error and least absolute error by default.
Here is the task list:
- [x] Gradient boosting support
- [x] Pluggable loss functions
- [x] Stochastic gradient boosting support – Re-use the BaggedPoint approach used for RandomForest.
- [x] Binary classification support
- [x] Support configurable checkpointing – This approach will avoid long lineage chains.
- [x] Create classification and regression APIs
- [x] Weighted Ensemble Model -- created a WeightedEnsembleModel class that can be used by ensemble algorithms such as random forests and boosting.
- [x] Unit Tests
Future work:
+ Multi-class classification is currently not supported by this PR since it requires discussion on the best way to support "deviance" as a loss function.
+ BaggedRDD caching -- Avoid repeating feature to bin mapping for each tree estimator after standard API work is completed.
cc: jkbradley hirakendu mengxr etrain atalwalkar chouqin
Author: Manish Amde <manish9ue@gmail.com>
Author: manishamde <manish9ue@gmail.com>
Closes#2607 from manishamde/gbt and squashes the following commits:
991c7b5 [Manish Amde] public api
ff2a796 [Manish Amde] addressing comments
b4c1318 [Manish Amde] removing spaces
8476b6b [Manish Amde] fixing line length
0183cb9 [Manish Amde] fixed naming and formatting issues
1c40c33 [Manish Amde] add newline, removed spaces
e33ab61 [Manish Amde] minor comment
eadbf09 [Manish Amde] parameter renaming
035a2ed [Manish Amde] jkbradley formatting suggestions
9f7359d [Manish Amde] simplified gbt logic and added more tests
49ba107 [Manish Amde] merged from master
eff21fe [Manish Amde] Added gradient boosting tests
3fd0528 [Manish Amde] moved helper methods to new class
a32a5ab [Manish Amde] added test for subsampling without replacement
781542a [Manish Amde] added support for fractional subsampling with replacement
3a18cc1 [Manish Amde] cleaned up api for conversion to bagged point and moved tests to it's own test suite
0e81906 [Manish Amde] improving caching unpersisting logic
d971f73 [Manish Amde] moved RF code to use WeightedEnsembleModel class
fee06d3 [Manish Amde] added weighted ensemble model
1b01943 [Manish Amde] add weights for base learners
9bc6e74 [Manish Amde] adding random seed as parameter
d2c8323 [Manish Amde] Merge branch 'master' into gbt
2ae97b7 [Manish Amde] added documentation for the loss classes
9366b8f [Manish Amde] minor: using numTrees instead of trees.size
3b43896 [Manish Amde] added learning rate for prediction
9b2e35e [Manish Amde] Merge branch 'master' into gbt
6a11c02 [manishamde] fixing formatting
823691b [Manish Amde] fixing RF test
1f47941 [Manish Amde] changing access modifier
5b67102 [Manish Amde] shortened parameter list
5ab3796 [Manish Amde] minor reformatting
9155a9d [Manish Amde] consolidated boosting configuration and added public API
631baea [Manish Amde] Merge branch 'master' into gbt
2cb1258 [Manish Amde] public API support
3b8ffc0 [Manish Amde] added documentation
8e10c63 [Manish Amde] modified unpersist strategy
f62bc48 [Manish Amde] added unpersist
bdca43a [Manish Amde] added timing parameters
2fbc9c7 [Manish Amde] fixing binomial classification prediction
6dd4dd8 [Manish Amde] added support for log loss
9af0231 [Manish Amde] classification attempt
62cc000 [Manish Amde] basic checkpointing
4784091 [Manish Amde] formatting
78ed452 [Manish Amde] added newline and fixed if statement
3973dd1 [Manish Amde] minor indicating subsample is double during comparison
aa8fae7 [Manish Amde] minor refactoring
1a8031c [Manish Amde] sampling with replacement
f1c9ef7 [Manish Amde] Merge branch 'master' into gbt
cdceeef [Manish Amde] added documentation
6251fd5 [Manish Amde] modified method name
5538521 [Manish Amde] disable checkpointing for now
0ae1c0a [Manish Amde] basic gradient boosting code from earlier branches
Implementation of various multi-label classification measures, including: Hamming-loss, strict and default Accuracy, macro-averaged Precision, Recall and F1-measure based on documents and labels, micro-averaged measures: https://issues.apache.org/jira/browse/SPARK-2329
Multi-class measures are currently in the following pull request: https://github.com/apache/spark/pull/1155
Author: Alexander Ulanov <nashb@yandex.ru>
Author: avulanov <nashb@yandex.ru>
Closes#1270 from avulanov/multilabelmetrics and squashes the following commits:
fc8175e [Alexander Ulanov] Merge with previous updates
43a613e [Alexander Ulanov] Addressing reviewers comments: change Set to Array
517a594 [avulanov] Addressing reviewers comments: Scala style
cf4222bc [avulanov] Addressing reviewers comments: renaming. Added label method that returns the list of labels
1843f73 [Alexander Ulanov] Scala style fix
79e8476 [Alexander Ulanov] Replacing fold(_ + _) with sum as suggested by srowen
ca46765 [Alexander Ulanov] Cosmetic changes: Apache header and parameter explanation
40593f5 [Alexander Ulanov] Multi-label metrics: Hamming-loss, strict and normal accuracy, fix to macro measures, bunch of tests
ad62df0 [Alexander Ulanov] Comments and scala style check
154164b [Alexander Ulanov] Multilabel evaluation metics and tests: macro precision and recall averaged by docs, micro and per-class precision and recall averaged by class
More efficient sampling, based on Gap Sampling optimization:
http://erikerlandson.github.io/blog/2014/09/11/faster-random-samples-with-gap-sampling/
Author: Erik Erlandson <eerlands@redhat.com>
Closes#2455 from erikerlandson/spark-3250-pr and squashes the following commits:
72496bc [Erik Erlandson] [SPARK-3250] Implement Gap Sampling optimization for random sampling
Create several helper functions to call MLlib Java API, convert the arguments to Java type and convert return value to Python object automatically, this simplify serialization in MLlib Python API very much.
After this, the MLlib Python API does not need to deal with serialization details anymore, it's easier to add new API.
cc mengxr
Author: Davies Liu <davies@databricks.com>
Closes#2995 from davies/cleanup and squashes the following commits:
8fa6ec6 [Davies Liu] address comments
16b85a0 [Davies Liu] Merge branch 'master' of github.com:apache/spark into cleanup
43743e5 [Davies Liu] bugfix
731331f [Davies Liu] simplify serialization in MLlib Python API
Add RegressionMetrics.scala as regression metrics used for evaluation and corresponding test case RegressionMetricsSuite.scala.
Author: Yanbo Liang <yanbohappy@gmail.com>
Author: liangyanbo <liangyanbo@meituan.com>
Closes#2978 from yanbohappy/regression_metrics and squashes the following commits:
730d0a9 [Yanbo Liang] more clearly annotation
3d0bec1 [Yanbo Liang] rename and keep code style
a8ad3e3 [Yanbo Liang] simplify code for keeping style
d454909 [Yanbo Liang] rename parameter and function names, delete unused columns, add reference
2e56282 [liangyanbo] rename r2_score() and remove unused column
43bb12b [liangyanbo] add regression metrics
This simple patch filters out extra whitespace entries.
Author: Joseph E. Gonzalez <joseph.e.gonzalez@gmail.com>
Author: Joey <joseph.e.gonzalez@gmail.com>
Closes#2996 from jegonzal/loadLibSVM and squashes the following commits:
e0227ab [Joey] improving readability
e028e84 [Joseph E. Gonzalez] fixing whitespace bug in loadLibSVMFile when parsing libSVM files
In MultivariateOnlineSummarizer, breeze's activeIterator is used
to loop through the nonZero elements in the vector. However,
activeIterator doesn't perform well due to lots of overhead.
In this PR, native while loop is used for both DenseVector and SparseVector.
The benchmark result with 20 executors using mnist8m dataset:
Before:
DenseVector: 48.2 seconds
SparseVector: 16.3 seconds
After:
DenseVector: 17.8 seconds
SparseVector: 11.2 seconds
Since MultivariateOnlineSummarizer is used in several places,
the overall performance gain in mllib library will be significant with this PR.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#2992 from dbtsai/SPARK-4129 and squashes the following commits:
b99db6c [DB Tsai] fixed java.lang.ArrayIndexOutOfBoundsException
2b5e882 [DB Tsai] small refactoring
ebe3e74 [DB Tsai] First commit
Also update step parameter to pass the proposed test
Author: coderxiang <shuoxiangpub@gmail.com>
Closes#2965 from coderxiang/nnls-test and squashes the following commits:
24b06f9 [coderxiang] add test case on objective value for NNLS; update step parameter to pass the test
This change replaces usages of colt with commons-math3 equivalents, and makes some minor necessary adjustments to related code and tests to match.
Author: Sean Owen <sowen@cloudera.com>
Closes#2928 from srowen/SPARK-4022 and squashes the following commits:
61a232f [Sean Owen] Fix failure due to different sampling in JavaAPISuite.sample()
16d66b8 [Sean Owen] Simplify seeding with call to reseedRandomGenerator
a1a78e0 [Sean Owen] Use Well19937c
31c7641 [Sean Owen] Fix Python Poisson test by choosing a different seed; about 88% of seeds should work but 1 didn't, it seems
5c9c67f [Sean Owen] Additional test fixes from review
d8f88e0 [Sean Owen] Replace colt with commons-math3. Some tests do not pass yet.
This follows https://github.com/apache/spark/pull/2893 , but does not completely fix SPARK-3359 either. This fixes minor scaladoc/javadoc issues that Javadoc 8 will treat as errors.
Author: Sean Owen <sowen@cloudera.com>
Closes#2909 from srowen/SPARK-3359 and squashes the following commits:
f62c347 [Sean Owen] Fix some javadoc issues that javadoc 8 considers errors. This is not all of the errors turned up when javadoc 8 runs on output of genjavadoc.
Thare are some inconsistent spellings 'MLlib' and 'MLLib' in some documents and source codes.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#2903 from sarutak/SPARK-4055 and squashes the following commits:
b031640 [Kousuke Saruta] Fixed inconsistent spelling "MLlib and MLLib"
Add common metrics for ranking algorithms (http://www-nlp.stanford.edu/IR-book/), including:
- Mean Average Precision
- Precisionn: top-n precision
- Discounted cumulative gain (DCG) and NDCG
The following methods and the corresponding tests are implemented:
```
class RankingMetrics[T](predictionAndLabels: RDD[(Array[T], Array[T])]) {
/* Returns the precsionk for each query */
lazy val precAtK: RDD[Array[Double]]
/**
* param k the position to compute the truncated precision
* return the average precision at the first k ranking positions
*/
def precision(k: Int): Double
/* Returns the average precision for each query */
lazy val avePrec: RDD[Double]
/*Returns the mean average precision (MAP) of all the queries*/
lazy val meanAvePrec: Double
/*Returns the normalized discounted cumulative gain for each query */
lazy val ndcgAtK: RDD[Array[Double]]
/**
* param k the position to compute the truncated ndcg
* return the average ndcg at the first k ranking positions
*/
def ndcg(k: Int): Double
}
```
Author: coderxiang <shuoxiangpub@gmail.com>
Closes#2667 from coderxiang/rankingmetrics and squashes the following commits:
d881097 [coderxiang] update doc
14d9cd9 [coderxiang] remove unexpected files
d7fb93f [coderxiang] style change and remove ignored files
f113ee1 [coderxiang] modify doc for displaying superscript and subscript
f626896 [coderxiang] improve doc and remove unnecessary computation while labSet is empty
be6645e [coderxiang] set the precision of empty labset to 0.0
d64c120 [coderxiang] add logWarning for empty ground truth set
dfae292 [coderxiang] handle empty labSet for map. add test
62047c4 [coderxiang] style change and add documentation
f66612d [coderxiang] add additional test of precisionAt
b794cb2 [coderxiang] move private members precAtK, ndcgAtK into public methods. style change
77c9e5d [coderxiang] set precAtK and ndcgAtK as private member. Improve documentation
5f87bce [coderxiang] add API to calculate precision and ndcg at each ranking position
b7851cc [coderxiang] Use generic type to represent IDs
e443fee [coderxiang] change style and use alternative builtin methods
3a5a6ff [coderxiang] add ranking metrics
https://issues.apache.org/jira/browse/SPARK-3770
We need access to the underlying latent user features from python. However, the userFeatures RDD from the MatrixFactorizationModel isn't accessible from the python bindings. I've added a method to the underlying scala class to turn the RDD[(Int, Array[Double])] to an RDD[String]. This is then accessed from the python recommendation.py
Author: Michelangelo D'Agostino <mdagostino@civisanalytics.com>
Closes#2636 from mdagost/mf_user_features and squashes the following commits:
c98f9e2 [Michelangelo D'Agostino] Added unit tests for userFeatures and productFeatures and merged master.
d5eadf8 [Michelangelo D'Agostino] Merge branch 'master' into mf_user_features
2481a2a [Michelangelo D'Agostino] Merged master and resolved conflict.
a6ffb96 [Michelangelo D'Agostino] Eliminated a function from our first approach to this problem that is no longer needed now that we added the fromTuple2RDD function.
2aa1bf8 [Michelangelo D'Agostino] Implemented a function called fromTuple2RDD in PythonMLLibAPI and used it to expose the MF userFeatures and productFeatures in python.
34cb2a2 [Michelangelo D'Agostino] A couple of lint cleanups and a comment.
cdd98e3 [Michelangelo D'Agostino] It's working now.
e1fbe5e [Michelangelo D'Agostino] Added scala function to stringify userFeatures for access in python.
DecisionTree splits on continuous features by choosing an array of values from a subsample of the data.
Currently, it does not check for identical values in the subsample, so it could end up having multiple copies of the same split. In this PR, we choose splits for a continuous feature in 3 steps:
1. Sort sample values for this feature
2. Get number of occurrence of each distinct value
3. Iterate the value count array computed in step 2 to choose splits.
After find splits, `numSplits` and `numBins` in metadata will be updated.
CC: mengxr manishamde jkbradley, please help me review this, thanks.
Author: Qiping Li <liqiping1991@gmail.com>
Author: chouqin <liqiping1991@gmail.com>
Author: liqi <liqiping1991@gmail.com>
Author: qiping.lqp <qiping.lqp@alibaba-inc.com>
Closes#2780 from chouqin/dt-findsplits and squashes the following commits:
18d0301 [Qiping Li] check explicitly findsplits return distinct splits
8dc28ab [chouqin] remove blank lines
ffc920f [chouqin] adjust code based on comments and add more test cases
9857039 [chouqin] Merge branch 'master' of https://github.com/apache/spark into dt-findsplits
d353596 [qiping.lqp] fix pyspark doc test
9e64699 [Qiping Li] fix random forest unit test
3c72913 [Qiping Li] fix random forest unit test
092efcb [Qiping Li] fix bug
f69f47f [Qiping Li] fix bug
ab303a4 [Qiping Li] fix bug
af6dc97 [Qiping Li] fix bug
2a8267a [Qiping Li] fix bug
c339a61 [Qiping Li] fix bug
369f812 [Qiping Li] fix style
8f46af6 [Qiping Li] add comments and unit test
9e7138e [Qiping Li] Merge branch 'dt-findsplits' of https://github.com/chouqin/spark into dt-findsplits
1b25a35 [Qiping Li] Merge branch 'master' of https://github.com/apache/spark into dt-findsplits
0cd744a [liqi] fix bug
3652823 [Qiping Li] fix bug
af7cb79 [Qiping Li] Choose splits for continuous features in DecisionTree more adaptively
SPARK-3934: When run with a mix of unordered categorical and continuous features, on multiclass classification, RandomForest fails. The bug is in the sanity checks in getFeatureOffset and getLeftRightFeatureOffsets, which use the wrong indices for checking whether features are unordered.
Fix: Remove the sanity checks since they are not really needed, and since they would require DTStatsAggregator to keep track of an extra set of indices (for the feature subset).
Added test to RandomForestSuite which failed with old version but now works.
SPARK-3918: Added baggedInput.unpersist at end of training.
Also:
* I removed DTStatsAggregator.isUnordered since it is no longer used.
* DecisionTreeMetadata: Added logWarning when maxBins is automatically reduced.
* Updated DecisionTreeRunner to explicitly fix the test data to have the same number of features as the training data. This is a temporary fix which should eventually be replaced by pre-indexing both datasets.
* RandomForestModel: Updated toString to print total number of nodes in forest.
* Changed Predict class to be public DeveloperApi. This was necessary to allow users to create their own trees by hand (for testing).
CC: mengxr manishamde chouqin codedeft Just notifying you of these small bug fixes.
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#2785 from jkbradley/dtrunner-update and squashes the following commits:
9132321 [Joseph K. Bradley] merged with master, fixed imports
9dbd000 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dtrunner-update
e116473 [Joseph K. Bradley] Changed Predict class to be public DeveloperApi.
f502e65 [Joseph K. Bradley] bug fix for SPARK-3934
7f3d60f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dtrunner-update
ba567ab [Joseph K. Bradley] Changed DTRunner to load test data using same number of features as in training data.
4e88c1f [Joseph K. Bradley] changed RF toString to print total number of nodes
Customized pickler should be registered before unpickling, but in executor, there is no way to register the picklers before run the tasks.
So, we need to register the picklers in the tasks itself, duplicate the javaToPython() and pythonToJava() in MLlib, call SerDe.initialize() before pickling or unpickling.
Author: Davies Liu <davies.liu@gmail.com>
Closes#2830 from davies/fix_pickle and squashes the following commits:
0c85fb9 [Davies Liu] revert the privacy change
6b94e15 [Davies Liu] use JavaConverters instead of JavaConversions
0f02050 [Davies Liu] hotfix: Customized pickler does not work in cluster
Avoid overflow in computing n*(n+1)/2 as much as possible; throw explicit error when Gramian computation will fail due to negative array size; warn about large result when computing Gramian too
Author: Sean Owen <sowen@cloudera.com>
Closes#2801 from srowen/SPARK-3803 and squashes the following commits:
b4e6d92 [Sean Owen] Avoid overflow in computing n*(n+1)/2 as much as possible; throw explicit error when Gramian computation will fail due to negative array size; warn about large result when computing Gramian too
During trainning Gradient Boosting Decision Tree on large-scale sparse data, spark spill hundreds of data onto disk. And find the bug below:
In version 1.1.0 DecisionTree.scala, train Method, treeInput has been persisted in Memory, but without unpersist. It caused heavy DISK usage.
In github version(1.2.0 maybe), RandomForest.scala, train Method, baggedInput has been persisted but without unpersisted too.
After added unpersist, it works right.
https://issues.apache.org/jira/browse/SPARK-3918
Author: omgteam <Kimlong.Liu@gmail.com>
Closes#2775 from omgteam/master and squashes the following commits:
815d543 [omgteam] adjust tab to spaces
1a36f83 [omgteam] Bug: fix without unpersist baggedInput in RandomForest.scala
I noticed a few issues with how temp directories are created and deleted:
*Minor*
* Guava's `Files.createTempDir()` plus `File.deleteOnExit()` is used in many tests to make a temp dir, but `Utils.createTempDir()` seems to be the standard Spark mechanism
* Call to `File.deleteOnExit()` could be pushed into `Utils.createTempDir()` as well, along with this replacement
* _I messed up the message in an exception in `Utils` in SPARK-3794; fixed here_
*Bit Less Minor*
* `Utils.deleteRecursively()` fails immediately if any `IOException` occurs, instead of trying to delete any remaining files and subdirectories. I've observed this leave temp dirs around. I suggest changing it to continue in the face of an exception and throw one of the possibly several exceptions that occur at the end.
* `Utils.createTempDir()` will add a JVM shutdown hook every time the method is called. Even if the subdir is the parent of another parent dir, since this check is inside the hook. However `Utils` manages a set of all dirs to delete on shutdown already, called `shutdownDeletePaths`. A single hook can be registered to delete all of these on exit. This is how Tachyon temp paths are cleaned up in `TachyonBlockManager`.
I noticed a few other things that might be changed but wanted to ask first:
* Shouldn't the set of dirs to delete be `File`, not just `String` paths?
* `Utils` manages the set of `TachyonFile` that have been registered for deletion, but the shutdown hook is managed in `TachyonBlockManager`. Should this logic not live together, and not in `Utils`? it's more specific to Tachyon, and looks a slight bit odd to import in such a generic place.
Author: Sean Owen <sowen@cloudera.com>
Closes#2670 from srowen/SPARK-3811 and squashes the following commits:
071ae60 [Sean Owen] Update per @vanzin's review
da0146d [Sean Owen] Make Utils.deleteRecursively try to delete all paths even when an exception occurs; use one shutdown hook instead of one per method call to delete temp dirs
3a0faa4 [Sean Owen] Standardize on Utils.createTempDir instead of Files.createTempDir
cc mengxr
Author: GuoQiang Li <witgo@qq.com>
Closes#2730 from witgo/SPARK-3856 and squashes the following commits:
2cffce1 [GuoQiang Li] use norm operator after breeze 0.10 upgrade
Currently, the implementation does one unnecessary aggregation step. The aggregation step for level L (to choose splits) gives enough information to set the predictions of any leaf nodes at level L+1. We can use that info and skip the aggregation step for the last level of the tree (which only has leaf nodes).
### Implementation Details
Each node now has a `impurity` field and the `predict` is changed from type `Double` to type `Predict`(this can be used to compute predict probability in the future) When compute best splits for each node, we also compute impurity and predict for the child nodes, which is used to constructed newly allocated child nodes. So at level L, we have set impurity and predict for nodes at level L +1.
If level L+1 is the last level, then we can avoid aggregation. What's more, calculation of parent impurity in
Top nodes for each tree needs to be treated differently because we have to compute impurity and predict for them first. In `binsToBestSplit`, if current node is top node(level == 0), we calculate impurity and predict first.
after finding best split, top node's predict and impurity is set to the calculated value. Non-top nodes's impurity and predict are already calculated and don't need to be recalculated again. I have considered to add a initialization step to set top nodes' impurity and predict and then we can treat all nodes in the same way, but this will need a lot of duplication of code(all the code to do seq operation(BinSeqOp) needs to be duplicated), so I choose the current way.
CC mengxr manishamde jkbradley, please help me review this, thanks.
Author: Qiping Li <liqiping1991@gmail.com>
Closes#2708 from chouqin/avoid-agg and squashes the following commits:
8e269ea [Qiping Li] adjust code and comments
eefeef1 [Qiping Li] adjust comments and check child nodes' impurity
c41b1b6 [Qiping Li] fix pyspark unit test
7ad7a71 [Qiping Li] fix unit test
822c912 [Qiping Li] add comments and unit test
e41d715 [Qiping Li] fix bug in test suite
6cc0333 [Qiping Li] SPARK-3158: Avoid 1 extra aggregation for DecisionTree training
Got warning msg:
~~~
[warn] /Users/meng/src/spark/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala:50: method norm in trait NumericOps is deprecated: Use norm(XXX) instead of XXX.norm
[warn] var norm = vector.toBreeze.norm(p)
~~~
dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#2718 from mengxr/SPARK-3856 and squashes the following commits:
4f38169 [Xiangrui Meng] use norm operator
In Breeze 0.10, the L1regParam can be configured through anonymous function in OWLQN, and each component can be penalized differently. This is required for GLMNET in MLlib with L1/L2 regularization.
2570911026
Author: DB Tsai <dbtsai@dbtsai.com>
Closes#2693 from dbtsai/breeze0.10 and squashes the following commits:
7a0c45c [DB Tsai] In Breeze 0.10, the L1regParam can be configured through anonymous function in OWLQN, and each component can be penalized differently. This is required for GLMNET in MLlib with L1/L2 regularization. 2570911026
mengxr
Added PySpark support for Word2Vec
Change list
(1) PySpark support for Word2Vec
(2) SerDe support of string sequence both on python side and JVM side
(3) Test for SerDe of string sequence on JVM side
Author: Liquan Pei <liquanpei@gmail.com>
Closes#2356 from Ishiihara/Word2Vec-python and squashes the following commits:
476ea34 [Liquan Pei] style fixes
b13a0b9 [Liquan Pei] resolve merge conflicts and minor fixes
8671eba [Liquan Pei] Merge remote-tracking branch 'upstream/master' into Word2Vec-python
daf88a6 [Liquan Pei] modification according to feedback
a73fa19 [Liquan Pei] clean up
3d8007b [Liquan Pei] fix findSynonyms for vector
1bdcd2e [Liquan Pei] minor fixes
cdef9f4 [Liquan Pei] add missing comments
b7447eb [Liquan Pei] modify according to feedback
b9a7383 [Liquan Pei] cache words RDD in fit
89490bf [Liquan Pei] add tests and Word2VecModelWrapper
78bbb53 [Liquan Pei] use pickle for seq string SerDe
a264b08 [Liquan Pei] Merge remote-tracking branch 'upstream/master' into Word2Vec-python
ca1e5ff [Liquan Pei] fix test
68e7276 [Liquan Pei] minor style fixes
48d5e72 [Liquan Pei] Functionality improvement
0ad3ac1 [Liquan Pei] minor fix
c867fdf [Liquan Pei] add Word2Vec to pyspark
Add a toString method to GeneralizedLinearModel, also change `__str__` to `__repr__` for some classes, to provide better message in repr.
This PR is based on #1388, thanks to sryza!
closes#1388
Author: Sandy Ryza <sandy@cloudera.com>
Author: Davies Liu <davies.liu@gmail.com>
Closes#2625 from davies/string and squashes the following commits:
3544aad [Davies Liu] fix LinearModel
0bcd642 [Davies Liu] Merge branch 'sandy-spark-2461' of github.com:sryza/spark
1ce5c2d [Sandy Ryza] __repr__ back to __str__ in a couple places
aa9e962 [Sandy Ryza] Switch __str__ to __repr__
a0c5041 [Sandy Ryza] Add labels back in
1aa17f5 [Sandy Ryza] Match existing conventions
fac1bc4 [Sandy Ryza] Fix PEP8 error
f7b58ed [Sandy Ryza] SPARK-2461. Add a toString method to GeneralizedLinearModel
Currently, all best splits are computed on the driver, which makes the driver a bottleneck for both communication and computation. This PR fix this problem by computed best splits on executors.
Instead of send all aggregate stats to the driver node, we can send aggregate stats for a node to a particular executor, using `reduceByKey` operation, then we can compute best split for this node there.
Implementation details:
Each node now has a nodeStatsAggregator, which save aggregate stats for all features and bins.
First use mapPartition to compute node aggregate stats for all nodes in each partition.
Then transform node aggregate stats to (nodeIndex, nodeStatsAggregator) pairs and use to `reduceByKey` operation to combine nodeStatsAggregator for the same node.
After all stats have been combined, best splits can be computed for each node based on the node aggregate stats. Best split result is collected to driver to construct the decision tree.
CC: mengxr manishamde jkbradley, please help me review this, thanks.
Author: qiping.lqp <qiping.lqp@alibaba-inc.com>
Author: chouqin <liqiping1991@gmail.com>
Closes#2595 from chouqin/dt-dist-agg and squashes the following commits:
db0d24a [chouqin] fix a minor bug and adjust code
a0d9de3 [chouqin] adjust code based on comments
9f201a6 [chouqin] fix bug: statsSize -> allStatsSize
a8a7ed0 [chouqin] Merge branch 'master' of https://github.com/apache/spark into dt-dist-agg
f13b346 [chouqin] adjust randomforest comments
c32636e [chouqin] adjust code based on comments
ac6a505 [chouqin] adjust code based on comments
7bbb787 [chouqin] add comments
bdd2a63 [qiping.lqp] fix test suite
a75df27 [qiping.lqp] fix test suite
b5b0bc2 [qiping.lqp] fix style
e76414f [qiping.lqp] fix testsuite
748bd45 [qiping.lqp] fix type-mismatch bug
24eacd8 [qiping.lqp] fix type-mismatch bug
5f63d6c [qiping.lqp] add multiclassification using One-Vs-All strategy
4f56496 [qiping.lqp] fix bug
f00fc22 [qiping.lqp] fix bug
532993a [qiping.lqp] Compute best splits distributively in decision tree
Thread names are useful for correlating failures.
Author: Reynold Xin <rxin@apache.org>
Closes#2600 from rxin/log4j and squashes the following commits:
83ffe88 [Reynold Xin] [SPARK-3748] Log thread name in unit test logs
DecisionTreeRunner functionality additions:
* Allow user to pass in a test dataset
* Do not print full model if the model is too large.
As part of this, modify DecisionTreeModel and RandomForestModel to allow printing less info. Proposed updates:
* toString: prints model summary
* toDebugString: prints full model (named after RDD.toDebugString)
Similar update to Python API:
* __repr__() now prints a model summary
* toDebugString() now prints the full model
CC: mengxr chouqin manishamde codedeft Small update (whomever can take a look). Thanks!
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#2604 from jkbradley/dtrunner-update and squashes the following commits:
b2b3c60 [Joseph K. Bradley] re-added python sql doc test, temporarily removed before
07b1fae [Joseph K. Bradley] repr() now prints a model summary toDebugString() now prints the full model
1d0d93d [Joseph K. Bradley] Updated DT and RF to print less when toString is called. Added toDebugString for verbose printing.
22eac8c [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dtrunner-update
e007a95 [Joseph K. Bradley] Updated DecisionTreeRunner to accept a test dataset.
1. doc updates
2. simple checks on vector dimensions
3. use column major for matrices
davies jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#2548 from mengxr/mllib-py-clean and squashes the following commits:
6dce2df [Xiangrui Meng] address comments
116b5db [Xiangrui Meng] use np.dot instead of array.dot
75f2fcc [Xiangrui Meng] fix python style
fefce00 [Xiangrui Meng] better check of vector size with more tests
067ef71 [Xiangrui Meng] majored -> major
ef853f9 [Xiangrui Meng] update python linalg api and small fixes
# All-pairs similarity via DIMSUM
Compute all pairs of similar vectors using brute force approach, and also DIMSUM sampling approach.
Laying down some notation: we are looking for all pairs of similar columns in an m x n RowMatrix whose entries are denoted a_ij, with the i’th row denoted r_i and the j’th column denoted c_j. There is an oversampling parameter labeled ɣ that should be set to 4 log(n)/s to get provably correct results (with high probability), where s is the similarity threshold.
The algorithm is stated with a Map and Reduce, with proofs of correctness and efficiency in published papers [1] [2]. The reducer is simply the summation reducer. The mapper is more interesting, and is also the heart of the scheme. As an exercise, you should try to see why in expectation, the map-reduce below outputs cosine similarities.
[1] Bosagh-Zadeh, Reza and Carlsson, Gunnar (2013), Dimension Independent Matrix Square using MapReduce, arXiv:1304.1467 http://arxiv.org/abs/1304.1467
[2] Bosagh-Zadeh, Reza and Goel, Ashish (2012), Dimension Independent Similarity Computation, arXiv:1206.2082 http://arxiv.org/abs/1206.2082
# Testing
Tests for all invocations included.
Added L1 and L2 norm computation to MultivariateStatisticalSummary since it was needed. Added tests for both of them.
Author: Reza Zadeh <rizlar@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#1778 from rezazadeh/dimsumv2 and squashes the following commits:
404c64c [Reza Zadeh] Merge remote-tracking branch 'upstream/master' into dimsumv2
4eb71c6 [Reza Zadeh] Add excludes for normL1 and normL2
ee8bd65 [Reza Zadeh] Merge remote-tracking branch 'upstream/master' into dimsumv2
976ddd4 [Reza Zadeh] Broadcast colMags. Avoid div by zero.
3467cff [Reza Zadeh] Merge remote-tracking branch 'upstream/master' into dimsumv2
aea0247 [Reza Zadeh] Allow large thresholds to promote sparsity
9fe17c0 [Xiangrui Meng] organize imports
2196ba5 [Xiangrui Meng] Merge branch 'rezazadeh-dimsumv2' into dimsumv2
254ca08 [Reza Zadeh] Merge remote-tracking branch 'upstream/master' into dimsumv2
f2947e4 [Xiangrui Meng] some optimization
3c4cf41 [Xiangrui Meng] Merge branch 'master' into rezazadeh-dimsumv2
0e4eda4 [Reza Zadeh] Use partition index for RNG
251bb9c [Reza Zadeh] Documentation
25e9d0d [Reza Zadeh] Line length for style
fb296f6 [Reza Zadeh] renamed to normL1 and normL2
3764983 [Reza Zadeh] Documentation
e9c6791 [Reza Zadeh] New interface and documentation
613f261 [Reza Zadeh] Column magnitude summary
75a0b51 [Reza Zadeh] Use Ints instead of Longs in the shuffle
0f12ade [Reza Zadeh] Style changes
eb1dc20 [Reza Zadeh] Use Double.PositiveInfinity instead of Double.Max
f56a882 [Reza Zadeh] Remove changes to MultivariateOnlineSummarizer
dbc55ba [Reza Zadeh] Make colMagnitudes a method in RowMatrix
41e8ece [Reza Zadeh] style changes
139c8e1 [Reza Zadeh] Syntax changes
029aa9c [Reza Zadeh] javadoc and new test
75edb25 [Reza Zadeh] All tests passing!
05e59b8 [Reza Zadeh] Add test
502ce52 [Reza Zadeh] new interface
654c4fb [Reza Zadeh] default methods
3726ca9 [Reza Zadeh] Remove MatrixAlgebra
6bebabb [Reza Zadeh] remove changes to MatrixSuite
5b8cd7d [Reza Zadeh] Initial files
This PR adds RandomForest to MLlib. The implementation is basic, and future performance optimizations will be important. (Note: RFs = Random Forests.)
# Overview
## RandomForest
* trains multiple trees at once to reduce the number of passes over the data
* allows feature subsets at each node
* uses a queue of nodes instead of fixed groups for each level
This implementation is based an implementation by manishamde and the [Alpine Labs Sequoia Forest](https://github.com/AlpineNow/SparkML2) by codedeft (in particular, the TreePoint, BaggedPoint, and node queue implementations). Thank you for your inputs!
## Testing
Correctness: This has been tested for correctness with the test suites and with DecisionTreeRunner on example datasets.
Performance: This has been performance tested using [this branch of spark-perf](https://github.com/jkbradley/spark-perf/tree/rfs). Results below.
### Regression tests for DecisionTree
Summary: For training 1 tree, there are small regressions, especially from feature subsampling.
In the table below, each row is a single (random) dataset. The 2 different sets of result columns are for 2 different RF implementations:
* (numTrees): This is from an earlier commit, after implementing RandomForest to train multiple trees at once. It does not include any code for feature subsampling.
* (feature subsets): This is from this current PR's code, after implementing feature subsampling.
These tests were to identify regressions in DecisionTree, so they are training 1 tree with all of the features (i.e., no feature subsampling).
These were run on an EC2 cluster with 15 workers, training 1 tree with maxDepth = 5 (= 6 levels). Speedup values < 1 indicate slowdowns from the old DecisionTree implementation.
numInstances | numFeatures | runtime (sec) | speedup | runtime (sec) | speedup
---- | ---- | ---- | ---- | ---- | ----
| | (numTrees) | (numTrees) | (feature subsets) | (feature subsets)
20000 | 100 | 4.051 | 1.044433473 | 4.478 | 0.9448414471
20000 | 500 | 8.472 | 1.104461756 | 9.315 | 1.004508857
20000 | 1500 | 19.354 | 1.05854087 | 20.863 | 0.9819776638
20000 | 3500 | 43.674 | 1.072033704 | 45.887 | 1.020332556
200000 | 100 | 4.196 | 1.171830315 | 4.848 | 1.014232673
200000 | 500 | 8.926 | 1.082791844 | 9.771 | 0.989151571
200000 | 1500 | 20.58 | 1.068415938 | 22.134 | 0.9934038131
200000 | 3500 | 48.043 | 1.075203464 | 52.249 | 0.9886505005
2000000 | 100 | 4.944 | 1.01355178 | 5.796 | 0.8645617667
2000000 | 500 | 11.11 | 1.016831683 | 12.482 | 0.9050632911
2000000 | 1500 | 31.144 | 1.017852556 | 35.274 | 0.8986789136
2000000 | 3500 | 79.981 | 1.085382778 | 101.105 | 0.8586123337
20000000 | 100 | 8.304 | 0.9270231214 | 9.073 | 0.8484514494
20000000 | 500 | 28.174 | 1.083268262 | 34.236 | 0.8914592826
20000000 | 1500 | 143.97 | 0.9579634646 | 159.275 | 0.8659111599
### Tests for forests
I have run other tests with numTrees=10 and with sqrt(numFeatures), and those indicate that multi-model training and feature subsets can speed up training for forests, especially when training deeper trees.
# Details on specific classes
## Changes to DecisionTree
* Main train() method is now in RandomForest.
* findBestSplits() is no longer needed. (It split levels into groups, but we now use a queue of nodes.)
* Many small changes to support RFs. (Note: These methods should be moved to RandomForest.scala in a later PR, but are in DecisionTree.scala to make code comparison easier.)
## RandomForest
* Main train() method is from old DecisionTree.
* selectNodesToSplit: Note that it selects nodes and feature subsets jointly to track memory usage.
## RandomForestModel
* Stores an Array[DecisionTreeModel]
* Prediction:
* For classification, most common label. For regression, mean.
* We could support other methods later.
## examples/.../DecisionTreeRunner
* This now takes numTrees and featureSubsetStrategy, to support RFs.
## DTStatsAggregator
* 2 types of functionality (w/ and w/o subsampling features): These require different indexing methods. (We could treat both as subsampling, but this is less efficient
DTStatsAggregator is now abstract, and 2 child classes implement these 2 types of functionality.
## impurities
* These now take instance weights.
## Node
* Some vals changed to vars.
* This is unfortunately a public API change (DeveloperApi). This could be avoided by creating a LearningNode struct, but would be awkward.
## RandomForestSuite
Please let me know if there are missing tests!
## BaggedPoint
This wraps TreePoint and holds bootstrap weights/counts.
# Design decisions
* BaggedPoint: BaggedPoint is separate from TreePoint since it may be useful for other bagging algorithms later on.
* RandomForest public API: What options should be easily supported by the train* methods? Should ALL options be in the Java-friendly constructors? Should there be a constructor taking Strategy?
* Feature subsampling options: What options should be supported? scikit-learn supports the same options, except for "onethird." One option would be to allow users to specific fractions ("0.1"): the current options could be supported, and any unrecognized values would be parsed as Doubles in [0,1].
* Splits and bins are computed before bootstrapping, so all trees use the same discretization.
* One queue, instead of one queue per tree.
CC: mengxr manishamde codedeft chouqin Please let me know if you have suggestions---thanks!
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Author: qiping.lqp <qiping.lqp@alibaba-inc.com>
Author: chouqin <liqiping1991@gmail.com>
Closes#2435 from jkbradley/rfs-new and squashes the following commits:
c694174 [Joseph K. Bradley] Fixed typo
cc59d78 [Joseph K. Bradley] fixed imports
e25909f [Joseph K. Bradley] Simplified node group maps. Specifically, created NodeIndexInfo to store node index in agg and feature subsets, and no longer create extra maps in findBestSplits
fbe9a1e [Joseph K. Bradley] Changed default featureSubsetStrategy to be sqrt for classification, onethird for regression. Updated docs with references.
ef7c293 [Joseph K. Bradley] Updates based on code review. Most substantial changes: * Simplified DTStatsAggregator * Made RandomForestModel.trees public * Added test for regression to RandomForestSuite
593b13c [Joseph K. Bradley] Fixed bug in metadata for computing log2(num features). Now it checks >= 1.
a1a08df [Joseph K. Bradley] Removed old comments
866e766 [Joseph K. Bradley] Changed RandomForestSuite randomized tests to use multiple fixed random seeds.
ff8bb96 [Joseph K. Bradley] removed usage of null from RandomForest and replaced with Option
bf1a4c5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into rfs-new
6b79c07 [Joseph K. Bradley] Added RandomForestSuite, and fixed small bugs, style issues.
d7753d4 [Joseph K. Bradley] Added numTrees and featureSubsetStrategy to DecisionTreeRunner (to support RandomForest). Fixed bugs so that RandomForest now runs.
746d43c [Joseph K. Bradley] Implemented feature subsampling. Tested DecisionTree but not RandomForest.
6309d1d [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into rfs-new. Added RandomForestModel.toString
b7ae594 [Joseph K. Bradley] Updated docs. Small fix for bug which does not cause errors: No longer allocate unused child nodes for leaf nodes.
121c74e [Joseph K. Bradley] Basic random forests are implemented. Random features per node not yet implemented. Test suite not implemented.
325d18a [Joseph K. Bradley] Merge branch 'chouqin-dt-preprune' into rfs-new
4ef9bf1 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into rfs-new
61b2e72 [Joseph K. Bradley] Added max of 10GB for maxMemoryInMB in Strategy.
a95e7c8 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into chouqin-dt-preprune
6da8571 [Joseph K. Bradley] RFs partly implemented, not done yet
eddd1eb [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into rfs-new
5c4ac33 [Joseph K. Bradley] Added check in Strategy to make sure minInstancesPerNode >= 1
0dd4d87 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-spark-3160
95c479d [Joseph K. Bradley] * Fixed typo in tree suite test "do not choose split that does not satisfy min instance per node requirements" * small style fixes
e2628b6 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into chouqin-dt-preprune
19b01af [Joseph K. Bradley] Merge remote-tracking branch 'chouqin/dt-preprune' into chouqin-dt-preprune
f1d11d1 [chouqin] fix typo
c7ebaf1 [chouqin] fix typo
39f9b60 [chouqin] change edge `minInstancesPerNode` to 2 and add one more test
c6e2dfc [Joseph K. Bradley] Added minInstancesPerNode and minInfoGain parameters to DecisionTreeRunner.scala and to Python API in tree.py
306120f [Joseph K. Bradley] Fixed typo in DecisionTreeModel.scala doc
eaa1dcf [Joseph K. Bradley] Added topNode doc in DecisionTree and scalastyle fix
d4d7864 [Joseph K. Bradley] Marked Node.build as deprecated
d4dbb99 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-spark-3160
1a8f0ad [Joseph K. Bradley] Eliminated pre-allocated nodes array in main train() method. * Nodes are constructed and added to the tree structure as needed during training.
0278a11 [chouqin] remove `noSplit` and set `Predict` private to tree
d593ec7 [chouqin] fix docs and change minInstancesPerNode to 1
2ab763b [Joseph K. Bradley] Simplifications to DecisionTree code:
efcc736 [qiping.lqp] fix bug
10b8012 [qiping.lqp] fix style
6728fad [qiping.lqp] minor fix: remove empty lines
bb465ca [qiping.lqp] Merge branch 'master' of https://github.com/apache/spark into dt-preprune
cadd569 [qiping.lqp] add api docs
46b891f [qiping.lqp] fix bug
e72c7e4 [qiping.lqp] add comments
845c6fa [qiping.lqp] fix style
f195e83 [qiping.lqp] fix style
987cbf4 [qiping.lqp] fix bug
ff34845 [qiping.lqp] separate calculation of predict of node from calculation of info gain
ac42378 [qiping.lqp] add min info gain and min instances per node parameters in decision tree
This PR for [SPARK-3614](https://issues.apache.org/jira/browse/SPARK-3614) adds functionality for filtering out terms which do not appear in at least a minimum number of documents.
This is implemented using a minimumOccurence parameter (default 0). When terms' document frequencies are less than minimumOccurence, their IDFs are set to 0, just like when the DF is 0. As a result, the TF-IDFs for the terms are found to be 0, as if the terms were not present in the documents.
This PR makes the following changes:
* Add a minimumOccurence parameter to the IDF and DocumentFrequencyAggregator classes.
* Create a parameter-less constructor for IDF with a default minimumOccurence value of 0 to remain backwards-compatibility with the original IDF API.
* Sets the IDFs to 0 for terms which DFs are less than minimumOccurence
* Add tests to the Spark IDFSuite and Java JavaTfIdfSuite test suites
* Updated the MLLib Feature Extraction programming guide to describe the new feature
Author: RJ Nowling <rnowling@gmail.com>
Closes#2494 from rnowling/spark-3614-idf-filter and squashes the following commits:
0aa3c63 [RJ Nowling] Fix identation
e6523a8 [RJ Nowling] Remove unnecessary toDouble's from IDFSuite
bfa82ec [RJ Nowling] Add space after if
30d20b3 [RJ Nowling] Add spaces around equals signs
9013447 [RJ Nowling] Add space before division operator
79978fc [RJ Nowling] Remove unnecessary semi-colon
40fd70c [RJ Nowling] Change minimumOccurence to minDocFreq in code and docs
47850ab [RJ Nowling] Changed minimumOccurence to Int from Long
9fb4093 [RJ Nowling] Remove unnecessary lines from IDF class docs
1fc09d8 [RJ Nowling] Add backwards-compatible constructor to DocumentFrequencyAggregator
1801fd2 [RJ Nowling] Fix style errors in IDF.scala
6897252 [RJ Nowling] Preface minimumOccurence members with val to make them final and immutable
a200bab [RJ Nowling] Remove unnecessary else statement
4b974f5 [RJ Nowling] Remove accidentally-added import from testing
c0cc643 [RJ Nowling] Add minimumOccurence filtering to IDF
Add warnings to KMeans, GeneralizedLinearAlgorithm, and computeSVD when called with input data that is not cached. KMeans is implemented iteratively, and I believe that GeneralizedLinearAlgorithm’s current optimizers are iterative and its future optimizers are also likely to be iterative. RowMatrix’s computeSVD is iterative against an RDD when run in DistARPACK mode. ALS and DecisionTree are iterative as well, but they implement RDD caching internally so do not require a warning.
I added a warning to GeneralizedLinearAlgorithm rather than inside its optimizers, where the iteration actually occurs, because internally GeneralizedLinearAlgorithm maps its input data to an uncached RDD before passing it to an optimizer. (In other words, the warning would be printed for every GeneralizedLinearAlgorithm run, regardless of whether its input is cached, if the warning were in GradientDescent or other optimizer.) I assume that use of an uncached RDD by GeneralizedLinearAlgorithm is intentional, and that the mapping there (adding label, intercepts and scaling) is a lightweight operation. Arguably a user calling an optimizer such as GradientDescent will be knowledgable enough to cache their data without needing a log warning, so lack of a warning in the optimizers may be ok.
Some of the documentation examples making use of these iterative algorithms did not cache their training RDDs (while others did). I updated the examples to always cache. I also fixed some (unrelated) minor errors in the documentation examples.
Author: Aaron Staple <aaron.staple@gmail.com>
Closes#2347 from staple/SPARK-1484 and squashes the following commits:
bd49701 [Aaron Staple] Address review comments.
ab2d4a4 [Aaron Staple] Disable warnings on python code path.
a7a0f99 [Aaron Staple] Change code comments per review comments.
7cca1dc [Aaron Staple] Change warning message text.
c77e939 [Aaron Staple] [SPARK-1484][MLLIB] Warn when running an iterative algorithm on uncached data.
3b6c511 [Aaron Staple] Minor doc example fixes.
Currently, we serialize the data between JVM and Python case by case manually, this cannot scale to support so many APIs in MLlib.
This patch will try to address this problem by serialize the data using pickle protocol, using Pyrolite library to serialize/deserialize in JVM. Pickle protocol can be easily extended to support customized class.
All the modules are refactored to use this protocol.
Known issues: There will be some performance regression (both CPU and memory, the serialized data increased)
Author: Davies Liu <davies.liu@gmail.com>
Closes#2378 from davies/pickle_mllib and squashes the following commits:
dffbba2 [Davies Liu] Merge branch 'master' of github.com:apache/spark into pickle_mllib
810f97f [Davies Liu] fix equal of matrix
032cd62 [Davies Liu] add more type check and conversion for user_product
bd738ab [Davies Liu] address comments
e431377 [Davies Liu] fix cache of rdd, refactor
19d0967 [Davies Liu] refactor Picklers
2511e76 [Davies Liu] cleanup
1fccf1a [Davies Liu] address comments
a2cc855 [Davies Liu] fix tests
9ceff73 [Davies Liu] test size of serialized Rating
44e0551 [Davies Liu] fix cache
a379a81 [Davies Liu] fix pickle array in python2.7
df625c7 [Davies Liu] Merge commit '154d141' into pickle_mllib
154d141 [Davies Liu] fix autobatchedpickler
44736d7 [Davies Liu] speed up pickling array in Python 2.7
e1d1bfc [Davies Liu] refactor
708dc02 [Davies Liu] fix tests
9dcfb63 [Davies Liu] fix style
88034f0 [Davies Liu] rafactor, address comments
46a501e [Davies Liu] choose batch size automatically
df19464 [Davies Liu] memorize the module and class name during pickleing
f3506c5 [Davies Liu] Merge branch 'master' into pickle_mllib
722dd96 [Davies Liu] cleanup _common.py
0ee1525 [Davies Liu] remove outdated tests
b02e34f [Davies Liu] remove _common.py
84c721d [Davies Liu] Merge branch 'master' into pickle_mllib
4d7963e [Davies Liu] remove muanlly serialization
6d26b03 [Davies Liu] fix tests
c383544 [Davies Liu] classification
f2a0856 [Davies Liu] mllib/regression
d9f691f [Davies Liu] mllib/util
cccb8b1 [Davies Liu] mllib/tree
8fe166a [Davies Liu] Merge branch 'pickle' into pickle_mllib
aa2287e [Davies Liu] random
f1544c4 [Davies Liu] refactor clustering
52d1350 [Davies Liu] use new protocol in mllib/stat
b30ef35 [Davies Liu] use pickle to serialize data for mllib/recommendation
f44f771 [Davies Liu] enable tests about array
3908f5c [Davies Liu] Merge branch 'master' into pickle
c77c87b [Davies Liu] cleanup debugging code
60e4e2f [Davies Liu] support unpickle array.array for Python 2.6
Local `SparseMatrix` support added in Compressed Column Storage (CCS) format in addition to Level-2 and Level-3 BLAS operations such as dgemv and dgemm respectively.
BLAS doesn't support sparse matrix operations, therefore support for `SparseMatrix`-`DenseMatrix` multiplication and `SparseMatrix`-`DenseVector` implementations have been added. I will post performance comparisons in the comments momentarily.
Author: Burak <brkyvz@gmail.com>
Closes#2294 from brkyvz/SPARK-3418 and squashes the following commits:
88814ed [Burak] Hopefully fixed MiMa this time
47e49d5 [Burak] really fixed MiMa issue
f0bae57 [Burak] [SPARK-3418] Fixed MiMa compatibility issues (excluded from check)
4b7dbec [Burak] 9/17 comments addressed
7af2f83 [Burak] sealed traits Vector and Matrix
d3a8a16 [Burak] [SPARK-3418] Squashed missing alpha bug.
421045f [Burak] [SPARK-3418] New code review comments addressed
f35a161 [Burak] [SPARK-3418] Code review comments addressed and multiplication further optimized
2508577 [Burak] [SPARK-3418] Fixed one more style issue
d16e8a0 [Burak] [SPARK-3418] Fixed style issues and added documentation for methods
204a3f7 [Burak] [SPARK-3418] Fixed failing Matrix unit test
6025297 [Burak] [SPARK-3418] Fixed Scala-style errors
dc7be71 [Burak] [SPARK-3418][MLlib] Matrix unit tests expanded with indexing and updating
d2d5851 [Burak] [SPARK-3418][MLlib] Sparse Matrix support and additional native BLAS operations added
Added minInstancesPerNode, minInfoGain params to:
* DecisionTreeRunner.scala example
* Python API (tree.py)
Also:
* Fixed typo in tree suite test "do not choose split that does not satisfy min instance per node requirements"
* small style fixes
CC: mengxr
Author: qiping.lqp <qiping.lqp@alibaba-inc.com>
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Author: chouqin <liqiping1991@gmail.com>
Closes#2349 from jkbradley/chouqin-dt-preprune and squashes the following commits:
61b2e72 [Joseph K. Bradley] Added max of 10GB for maxMemoryInMB in Strategy.
a95e7c8 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into chouqin-dt-preprune
95c479d [Joseph K. Bradley] * Fixed typo in tree suite test "do not choose split that does not satisfy min instance per node requirements" * small style fixes
e2628b6 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into chouqin-dt-preprune
19b01af [Joseph K. Bradley] Merge remote-tracking branch 'chouqin/dt-preprune' into chouqin-dt-preprune
f1d11d1 [chouqin] fix typo
c7ebaf1 [chouqin] fix typo
39f9b60 [chouqin] change edge `minInstancesPerNode` to 2 and add one more test
c6e2dfc [Joseph K. Bradley] Added minInstancesPerNode and minInfoGain parameters to DecisionTreeRunner.scala and to Python API in tree.py
0278a11 [chouqin] remove `noSplit` and set `Predict` private to tree
d593ec7 [chouqin] fix docs and change minInstancesPerNode to 1
efcc736 [qiping.lqp] fix bug
10b8012 [qiping.lqp] fix style
6728fad [qiping.lqp] minor fix: remove empty lines
bb465ca [qiping.lqp] Merge branch 'master' of https://github.com/apache/spark into dt-preprune
cadd569 [qiping.lqp] add api docs
46b891f [qiping.lqp] fix bug
e72c7e4 [qiping.lqp] add comments
845c6fa [qiping.lqp] fix style
f195e83 [qiping.lqp] fix style
987cbf4 [qiping.lqp] fix bug
ff34845 [qiping.lqp] separate calculation of predict of node from calculation of info gain
ac42378 [qiping.lqp] add min info gain and min instances per node parameters in decision tree
Updating this to reflect the newest SVD via ARPACK
Author: Reza Zadeh <rizlar@gmail.com>
Closes#2389 from rezazadeh/irmdocs and squashes the following commits:
7fa1313 [Reza Zadeh] Update svd docs
715da25 [Reza Zadeh] Updated computeSVD documentation IndexedRowMatrix
SimpleUpdater ignores the regularizer, which leads to an unregularized
LogReg. To enable the common L2 regularizer (and the corresponding
regularization parameter) for logistic regression the SquaredL2Updater
has to be used in SGD (see, e.g., [SVMWithSGD])
Author: Christoph Sawade <christoph@sawade.me>
Closes#2398 from BigCrunsh/fix-regparam-logreg and squashes the following commits:
0820c04 [Christoph Sawade] Use SquaredL2Updater in LogisticRegressionWithSGD
This PR includes some code simplifications and re-organization which will be helpful for implementing random forests. The main changes are that the nodes and parentImpurities arrays are no longer pre-allocated in the main train() method.
Also added 2 bug fixes:
* maxMemoryUsage calculation
* over-allocation of space for bins in DTStatsAggregator for unordered features.
Relation to RFs:
* Since RFs will be deeper and will therefore be more likely sparse (not full trees), it could be a cost savings to avoid pre-allocating a full tree.
* The associated re-organization also reduces bookkeeping, which will make RFs easier to implement.
* The return code doneTraining may be generalized to include cases such as nodes ready for local training.
Details:
No longer pre-allocate parentImpurities array in main train() method.
* parentImpurities values are now stored in individual nodes (in Node.stats.impurity).
* These were not really needed. They were used in calculateGainForSplit(), but they can be calculated anyways using parentNodeAgg.
No longer using Node.build since tree structure is constructed on-the-fly.
* Did not eliminate since it is public (Developer) API. Marked as deprecated.
Eliminated pre-allocated nodes array in main train() method.
* Nodes are constructed and added to the tree structure as needed during training.
* Moved tree construction from main train() method into findBestSplitsPerGroup() since there is no need to keep the (split, gain) array for an entire level of nodes. Only one element of that array is needed at a time, so we do not the array.
findBestSplits() now returns 2 items:
* rootNode (newly created root node on first iteration, same root node on later iterations)
* doneTraining (indicating if all nodes at that level were leafs)
Updated DecisionTreeSuite. Notes:
* Improved test "Second level node building with vs. without groups"
** generateOrderedLabeledPoints() modified so that it really does require 2 levels of internal nodes.
* Related update: Added Node.deepCopy (private[tree]), used for test suite
CC: mengxr
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#2341 from jkbradley/dt-spark-3160 and squashes the following commits:
07dd1ee [Joseph K. Bradley] Fixed overflow bug with computing maxMemoryUsage in DecisionTree. Also fixed bug with over-allocating space in DTStatsAggregator for unordered features.
debe072 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-spark-3160
5c4ac33 [Joseph K. Bradley] Added check in Strategy to make sure minInstancesPerNode >= 1
0dd4d87 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-spark-3160
306120f [Joseph K. Bradley] Fixed typo in DecisionTreeModel.scala doc
eaa1dcf [Joseph K. Bradley] Added topNode doc in DecisionTree and scalastyle fix
d4d7864 [Joseph K. Bradley] Marked Node.build as deprecated
d4dbb99 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-spark-3160
1a8f0ad [Joseph K. Bradley] Eliminated pre-allocated nodes array in main train() method. * Nodes are constructed and added to the tree structure as needed during training.
2ab763b [Joseph K. Bradley] Simplifications to DecisionTree code:
These two parameters can act as early stop rules to do pre-pruning. When a split cause cause left or right child to have less than `minInstancesPerNode` or has less information gain than `minInfoGain`, current node will not be split by this split.
When there is no possible splits that satisfy requirements, there is no useful information gain stats, but we still need to calculate the predict value for current node. So I separated calculation of predict from calculation of information gain, which can also save computation when the number of possible splits is large. Please see [SPARK-3272](https://issues.apache.org/jira/browse/SPARK-3272) for more details.
CC: mengxr manishamde jkbradley, please help me review this, thanks.
Author: qiping.lqp <qiping.lqp@alibaba-inc.com>
Author: chouqin <liqiping1991@gmail.com>
Closes#2332 from chouqin/dt-preprune and squashes the following commits:
f1d11d1 [chouqin] fix typo
c7ebaf1 [chouqin] fix typo
39f9b60 [chouqin] change edge `minInstancesPerNode` to 2 and add one more test
0278a11 [chouqin] remove `noSplit` and set `Predict` private to tree
d593ec7 [chouqin] fix docs and change minInstancesPerNode to 1
efcc736 [qiping.lqp] fix bug
10b8012 [qiping.lqp] fix style
6728fad [qiping.lqp] minor fix: remove empty lines
bb465ca [qiping.lqp] Merge branch 'master' of https://github.com/apache/spark into dt-preprune
cadd569 [qiping.lqp] add api docs
46b891f [qiping.lqp] fix bug
e72c7e4 [qiping.lqp] add comments
845c6fa [qiping.lqp] fix style
f195e83 [qiping.lqp] fix style
987cbf4 [qiping.lqp] fix bug
ff34845 [qiping.lqp] separate calculation of predict of node from calculation of info gain
ac42378 [qiping.lqp] add min info gain and min instances per node parameters in decision tree
Adjust the default values of decision tree, based on the memory requirement discussed in https://github.com/apache/spark/pull/2125 :
1. maxMemoryInMB: 128 -> 256
2. maxBins: 100 -> 32
3. maxDepth: 4 -> 5 (in some example code)
jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#2322 from mengxr/tree-defaults and squashes the following commits:
cda453a [Xiangrui Meng] fix tests
5900445 [Xiangrui Meng] update comments
8c81831 [Xiangrui Meng] update default values of tree:
Summary:
1. Variable numBins for each feature [SPARK-3043]
2. Reduced data reshaping in aggregation [SPARK-3043]
3. Choose ordering for ordered categorical features adaptively [SPARK-3156]
4. Changed nodes to use 1-indexing [SPARK-3086]
5. Small clean-ups
Note: This PR looks bigger than it is since I moved several functions from inside findBestSplitsPerGroup to outside of it (to make it clear what was being serialized in the aggregation).
Speedups: This update helps most when many features use few bins but a few features use many bins. Some example results on speedups with 2M examples, 3.5K features (15-worker EC2 cluster):
* Example where old code was reasonably efficient (1/2 continuous, 1/4 binary, 1/4 20-category): 164.813 --> 116.491 sec
* Example where old code wasted many bins (1/10 continuous, 81/100 binary, 9/100 20-category): 128.701 --> 39.334 sec
Details:
(1) Variable numBins for each feature [SPARK-3043]
DecisionTreeMetadata now computes a variable numBins for each feature. It also tracks numSplits.
(2) Reduced data reshaping in aggregation [SPARK-3043]
Added DTStatsAggregator, a wrapper around the aggregate statistics array for easy but efficient indexing.
* Added ImpurityAggregator and ImpurityCalculator classes, to make DecisionTree code more oblivious to the type of impurity.
* Design note: I originally tried creating Impurity classes which stored data and storing the aggregates in an Array[Array[Array[Impurity]]]. However, this led to significant slowdowns, perhaps because of overhead in creating so many objects.
The aggregate statistics are never reshaped, and cumulative sums are computed in-place.
Updated the layout of aggregation functions. The update simplifies things by (1) dividing features into ordered/unordered (instead of ordered/unordered/continuous) and (2) making use of the DTStatsAggregator for indexing.
For this update, the following functions were refactored:
* updateBinForOrderedFeature
* updateBinForUnorderedFeature
* binaryOrNotCategoricalBinSeqOp
* multiclassWithCategoricalBinSeqOp
* regressionBinSeqOp
The above 5 functions were replaced with:
* orderedBinSeqOp
* someUnorderedBinSeqOp
Other changes:
* calculateGainForSplit now treats all feature types the same way.
* Eliminated extractLeftRightNodeAggregates.
(3) Choose ordering for ordered categorical features adaptively [SPARK-3156]
Updated binsToBestSplit():
* This now computes cumulative sums of stats for ordered features.
* For ordered categorical features, it chooses an ordering for categories. (This uses to be done by findSplitsBins.)
* Uses iterators to shorten code and avoid building an Array[Array[InformationGainStats]].
Side effects:
* In findSplitsBins: A sample of the data is only taken for data with continuous features. It is not needed for data with only categorical features.
* In findSplitsBins: splits and bins are no longer pre-computed for ordered categorical features since they are not needed.
* TreePoint binning is simpler for categorical features.
(4) Changed nodes to use 1-indexing [SPARK-3086]
Nodes used to be indexed from 0. Now they are indexed from 1.
Node indexing functions are now collected in object Node (Node.scala).
(5) Small clean-ups
Eliminated functions extractNodeInfo() and extractInfoForLowerLevels() to reduce duplicate code.
Eliminated InvalidBinIndex since it is no longer used.
CC: mengxr manishamde Please let me know if you have thoughts on this—thanks!
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#2125 from jkbradley/dt-opt3alt and squashes the following commits:
42c192a [Joseph K. Bradley] Merge branch 'rfs' into dt-opt3alt
d3cc46b [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3alt
00e4404 [Joseph K. Bradley] optimization for TreePoint construction (pre-computing featureArity and isUnordered as arrays)
425716c [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into rfs
a2acea5 [Joseph K. Bradley] Small optimizations based on profiling
aa4e4df [Joseph K. Bradley] Updated DTStatsAggregator with bug fix (nodeString should not be multiplied by statsSize)
4651154 [Joseph K. Bradley] Changed numBins semantics for unordered features. * Before: numBins = numSplits = (1 << k - 1) - 1 * Now: numBins = 2 * numSplits = 2 * [(1 << k - 1) - 1] * This also involved changing the semantics of: ** DecisionTreeMetadata.numUnorderedBins()
1e3b1c7 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3alt
1485fcc [Joseph K. Bradley] Made some DecisionTree methods private.
92f934f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3alt
e676da1 [Joseph K. Bradley] Updated documentation for DecisionTree
37ca845 [Joseph K. Bradley] Fixed problem with how DecisionTree handles ordered categorical features.
105f8ab [Joseph K. Bradley] Removed commented-out getEmptyBinAggregates from DecisionTree
062c31d [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3alt
6d32ccd [Joseph K. Bradley] In DecisionTree.binsToBestSplit, changed loops to iterators to shorten code.
807cd00 [Joseph K. Bradley] Finished DTStatsAggregator, a wrapper around the aggregate statistics for easy but hopefully efficient indexing. Modified old ImpurityAggregator classes and renamed them ImpurityCalculator; added ImpurityAggregator classes which work with DTStatsAggregator but do not store data. Unit tests all succeed.
f2166fd [Joseph K. Bradley] still working on DTStatsAggregator
92f7118 [Joseph K. Bradley] Added partly written DTStatsAggregator
fd8df30 [Joseph K. Bradley] Moved some aggregation helpers outside of findBestSplitsPerGroup
d7c53ee [Joseph K. Bradley] Added more doc for ImpurityAggregator
a40f8f1 [Joseph K. Bradley] Changed nodes to be indexed from 1. Tests work.
95cad7c [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3
5f94342 [Joseph K. Bradley] Added treeAggregate since not yet merged from master. Moved node indexing functions to Node.
61c4509 [Joseph K. Bradley] Fixed bugs from merge: missing DT timer call, and numBins setting. Cleaned up DT Suite some.
3ba7166 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3
b314659 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt3
9c83363 [Joseph K. Bradley] partial merge but not done yet
45f7ea7 [Joseph K. Bradley] partial merge, not yet done
5fce635 [Joseph K. Bradley] Merge branch 'dt-opt2' into dt-opt3
26d10dd [Joseph K. Bradley] Removed tree/model/Filter.scala since no longer used. Removed debugging println calls in DecisionTree.scala.
356daba [Joseph K. Bradley] Merge branch 'dt-opt1' into dt-opt2
430d782 [Joseph K. Bradley] Added more debug info on binning error. Added some docs.
d036089 [Joseph K. Bradley] Print timing info to logDebug.
e66f1b1 [Joseph K. Bradley] TreePoint * Updated doc * Made some methods private
8464a6e [Joseph K. Bradley] Moved TimeTracker to tree/impl/ in its own file, and cleaned it up. Removed debugging println calls from DecisionTree. Made TreePoint extend Serialiable
a87e08f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
dd4d3aa [Joseph K. Bradley] Mid-process in bug fix: bug for binary classification with categorical features * Bug: Categorical features were all treated as ordered for binary classification. This is possible but would require the bin ordering to be determined on-the-fly after the aggregation. Currently, the ordering is determined a priori and fixed for all splits. * (Temp) Fix: Treat low-arity categorical features as unordered for binary classification. * Related change: I removed most tests for isMulticlass in the code. I instead test metadata for whether there are unordered features. * Status: The bug may be fixed, but more testing needs to be done.
438a660 [Joseph K. Bradley] removed subsampling for mnist8m from DT
86e217f [Joseph K. Bradley] added cache to DT input
e3c84cc [Joseph K. Bradley] Added stuff fro mnist8m to D T Runner
51ef781 [Joseph K. Bradley] Fixed bug introduced by last commit: Variance impurity calculation was incorrect since counts were swapped accidentally
fd65372 [Joseph K. Bradley] Major changes: * Created ImpurityAggregator classes, rather than old aggregates. * Feature split/bin semantics are based on ordered vs. unordered ** E.g.: numSplits = numBins for all unordered features, and numSplits = numBins - 1 for all ordered features. * numBins can differ for each feature
c1565a5 [Joseph K. Bradley] Small DecisionTree updates: * Simplification: Updated calculateGainForSplit to take aggregates for a single (feature, split) pair. * Internal doc: findAggForOrderedFeatureClassification
b914f3b [Joseph K. Bradley] DecisionTree optimization: eliminated filters + small changes
b2ed1f3 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt
0f676e2 [Joseph K. Bradley] Optimizations + Bug fix for DecisionTree
3211f02 [Joseph K. Bradley] Optimizing DecisionTree * Added TreePoint representation to avoid calling findBin multiple times. * (not working yet, but debugging)
f61e9d2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
bcf874a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
511ec85 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
a95bc22 [Joseph K. Bradley] timing for DecisionTree internals
Author: GuoQiang Li <witgo@qq.com>
Closes#2268 from witgo/SPARK-3397 and squashes the following commits:
eaf913f [GuoQiang Li] Bump pom.xml version number of master branch to 1.2.0-SNAPSHOT
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#2248 from sarutak/SPARK-3372 and squashes the following commits:
73a28b8 [Kousuke Saruta] Replaced UTF-8 hyphen with ascii hyphen
Kill this bug fast before it does damage.
Author: Reza Zadeh <rizlar@gmail.com>
Closes#2224 from rezazadeh/indexrmbug and squashes the following commits:
53386d6 [Reza Zadeh] Squash bug in IndexedRowMatrix
to re-construct k-means models freeman-lab
Author: Xiangrui Meng <meng@databricks.com>
Closes#2112 from mengxr/public-constructors and squashes the following commits:
18d53a9 [Xiangrui Meng] make KMeans constructor public
Sorry I didn't realize this in #2043. Ishiihara
Author: Xiangrui Meng <meng@databricks.com>
Closes#2049 from mengxr/more-w2v and squashes the following commits:
050b1c5 [Xiangrui Meng] output shuffle data directly
or Jenkins will complain about no Apache header in checkpoint files. tdas rxin
Author: Xiangrui Meng <meng@databricks.com>
Closes#2046 from mengxr/tmp-checkpoint and squashes the following commits:
0d3ec73 [Xiangrui Meng] remove ssc.stop
9797843 [Xiangrui Meng] change checkpointDir to lazy val
89964ab [Xiangrui Meng] use temp folder for checkpoint
because NB treats feature values as term frequencies. jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes#2038 from mengxr/nb-neg and squashes the following commits:
52c37c3 [Xiangrui Meng] address comments
65f892d [Xiangrui Meng] detect negative values in nb
very minor update Ishiihara
Author: Xiangrui Meng <meng@databricks.com>
Closes#2043 from mengxr/minor-w2v and squashes the following commits:
be649fd [Xiangrui Meng] remove map because we only need append
eccefcc [Xiangrui Meng] minor updates to word2vec
Though we don't use default argument for methods in RandomRDDs, it is still not easy for Java users to use because the output type is either `RDD[Double]` or `RDD[Vector]`. Java users should expect `JavaDoubleRDD` and `JavaRDD[Vector]`, respectively. We should create dedicated methods for Java users, and allow default arguments in Scala methods in RandomRDDs, to make life easier for both Java and Scala users. This PR also contains documentation for random data generation. brkyvz
Author: Xiangrui Meng <meng@databricks.com>
Closes#2041 from mengxr/stat-doc and squashes the following commits:
fc5eedf [Xiangrui Meng] add missing comma
ffde810 [Xiangrui Meng] address comments
aef6d07 [Xiangrui Meng] add doc for random data generation
b99d94b [Xiangrui Meng] add java-friendly methods to RandomRDDs
Refactored tests for streaming linear regression to use existing streaming test utilities. Summary of changes:
- Made ``mllib`` depend on tests from ``streaming``
- Rewrote accuracy and convergence tests to use ``setupStreams`` and ``runStreams``
- Added new test for the accuracy of predictions generated by ``predictOnValue``
These tests should run faster, be easier to extend/maintain, and provide a reference for new tests.
mengxr tdas
Author: freeman <the.freeman.lab@gmail.com>
Closes#2037 from freeman-lab/streamingLR-predict-tests and squashes the following commits:
e851ca7 [freeman] Fixed long lines
50eb0bf [freeman] Refactored tests to use streaming test tools
32c43c2 [freeman] Added test for prediction
It is useful in streaming to allow users to carry extra data with the prediction, for monitoring the prediction error for example. freeman-lab
Author: Xiangrui Meng <meng@databricks.com>
Closes#2023 from mengxr/predict-on-values and squashes the following commits:
cac47b8 [Xiangrui Meng] add classtag
2821b3b [Xiangrui Meng] use mapValues
0925efa [Xiangrui Meng] add predictOnValues to StreamingLR and fix predictOn
Added examples for statistical summarization:
* Scala: StatisticalSummary.scala
** Tests: correlation, MultivariateOnlineSummarizer
* python: statistical_summary.py
** Tests: correlation (since MultivariateOnlineSummarizer has no Python API)
Added examples for random and sampled RDDs:
* Scala: RandomAndSampledRDDs.scala
* python: random_and_sampled_rdds.py
* Both test:
** RandomRDDGenerators.normalRDD, normalVectorRDD
** RDD.sample, takeSample, sampleByKey
Added sc.stop() to all examples.
CorrelationSuite.scala
* Added 1 test for RDDs with only 1 value
RowMatrix.scala
* numCols(): Added check for numRows = 0, with error message.
* computeCovariance(): Added check for numRows <= 1, with error message.
Python SparseVector (pyspark/mllib/linalg.py)
* Added toDense() function
python/run-tests script
* Added stat.py (doc test)
CC: mengxr dorx Main changes were examples to show usage across APIs.
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#1878 from jkbradley/mllib-stats-api-check and squashes the following commits:
ea5c047 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
dafebe2 [Joseph K. Bradley] Bug fixes for examples SampledRDDs.scala and sampled_rdds.py: Check for division by 0 and for missing key in maps.
8d1e555 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
60c72d9 [Joseph K. Bradley] Fixed stat.py doc test to work for Python versions printing nan or NaN.
b20d90a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
4e5d15e [Joseph K. Bradley] Changed pyspark/mllib/stat.py doc tests to use NaN instead of nan.
32173b7 [Joseph K. Bradley] Stats examples update.
c8c20dc [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
cf70b07 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
0b7cec3 [Joseph K. Bradley] Small updates based on code review. Renamed statistical_summary.py to correlations.py
ab48f6e [Joseph K. Bradley] RowMatrix.scala * numCols(): Added check for numRows = 0, with error message. * computeCovariance(): Added check for numRows <= 1, with error message.
65e4ebc [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
8195c78 [Joseph K. Bradley] Added examples for random and sampled RDDs: * Scala: RandomAndSampledRDDs.scala * python: random_and_sampled_rdds.py * Both test: ** RandomRDDGenerators.normalRDD, normalVectorRDD ** RDD.sample, takeSample, sampleByKey
064985b [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into mllib-stats-api-check
ee918e9 [Joseph K. Bradley] Added examples for statistical summarization: * Scala: StatisticalSummary.scala ** Tests: correlation, MultivariateOnlineSummarizer * python: statistical_summary.py ** Tests: correlation (since MultivariateOnlineSummarizer has no Python API)
Small DecisionTree updates:
* Changed main DecisionTree aggregate to treeAggregate.
* Fixed bug in python example decision_tree_runner.py with missing argument (since categoricalFeaturesInfo is no longer an optional argument for trainClassifier).
* Fixed same bug in python doc tests, and added tree.py to doc tests.
CC: mengxr
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#2015 from jkbradley/dt-opt2 and squashes the following commits:
b5114fa [Joseph K. Bradley] Fixed python tree.py doc test (extra newline)
8e4665d [Joseph K. Bradley] Added tree.py to python doc tests. Fixed bug from missing categoricalFeaturesInfo argument.
b7b2922 [Joseph K. Bradley] Fixed bug in python example decision_tree_runner.py with missing argument. Changed main DecisionTree aggregate to treeAggregate.
85bbc1f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt2
66d076f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt2
a0ed0da [Joseph K. Bradley] Renamed DTMetadata to DecisionTreeMetadata. Small doc updates.
3726d20 [Joseph K. Bradley] Small code improvements based on code review.
ac0b9f8 [Joseph K. Bradley] Small updates based on code review. Main change: Now using << instead of math.pow.
db0d773 [Joseph K. Bradley] scala style fix
6a38f48 [Joseph K. Bradley] Added DTMetadata class for cleaner code
931a3a7 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt2
797f68a [Joseph K. Bradley] Fixed DecisionTreeSuite bug for training second level. Needed to update treePointToNodeIndex with groupShift.
f40381c [Joseph K. Bradley] Merge branch 'dt-opt1' into dt-opt2
5f2dec2 [Joseph K. Bradley] Fixed scalastyle issue in TreePoint
6b5651e [Joseph K. Bradley] Updates based on code review. 1 major change: persisting to memory + disk, not just memory.
2d2aaaf [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
26d10dd [Joseph K. Bradley] Removed tree/model/Filter.scala since no longer used. Removed debugging println calls in DecisionTree.scala.
356daba [Joseph K. Bradley] Merge branch 'dt-opt1' into dt-opt2
430d782 [Joseph K. Bradley] Added more debug info on binning error. Added some docs.
d036089 [Joseph K. Bradley] Print timing info to logDebug.
e66f1b1 [Joseph K. Bradley] TreePoint * Updated doc * Made some methods private
8464a6e [Joseph K. Bradley] Moved TimeTracker to tree/impl/ in its own file, and cleaned it up. Removed debugging println calls from DecisionTree. Made TreePoint extend Serialiable
a87e08f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
c1565a5 [Joseph K. Bradley] Small DecisionTree updates: * Simplification: Updated calculateGainForSplit to take aggregates for a single (feature, split) pair. * Internal doc: findAggForOrderedFeatureClassification
b914f3b [Joseph K. Bradley] DecisionTree optimization: eliminated filters + small changes
b2ed1f3 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt
0f676e2 [Joseph K. Bradley] Optimizations + Bug fix for DecisionTree
3211f02 [Joseph K. Bradley] Optimizing DecisionTree * Added TreePoint representation to avoid calling findBin multiple times. * (not working yet, but debugging)
f61e9d2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
bcf874a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
511ec85 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
a95bc22 [Joseph K. Bradley] timing for DecisionTree internals
mengxr
Remove transform(dataset: RDD[String]) from public API.
Author: Liquan Pei <liquanpei@gmail.com>
Closes#2010 from Ishiihara/Word2Vec-api and squashes the following commits:
17b1031 [Liquan Pei] remove transform(dataset: RDD[String]) from public API
mengxr Please review the code. Adding weights in reduceByKey soon.
Only output model entry for words appeared in the partition before merging and use reduceByKey to combine model. In general, this implementation is 30s or so faster than implementation using big array.
Author: Liquan Pei <liquanpei@gmail.com>
Closes#1932 from Ishiihara/Word2Vec-improve2 and squashes the following commits:
d5377a9 [Liquan Pei] use syn0Global and syn1Global to represent model
cad2011 [Liquan Pei] bug fix for synModify array out of bound
083aa66 [Liquan Pei] update synGlobal in place and reduce synOut size
9075e1c [Liquan Pei] combine syn0Global and syn1Global to synGlobal
aa2ab36 [Liquan Pei] use reduceByKey to combine models
There is a bug determining the column index. dorx
Author: Xiangrui Meng <meng@databricks.com>
Closes#1997 from mengxr/chisq-index and squashes the following commits:
8fc2ab2 [Xiangrui Meng] fix col indexing bug and add a check for number of distinct values
DecisionTree needs to match each example to a node at each iteration. It currently does this with a set of filters very inefficiently: For each example, it examines each node at the current level and traces up to the root to see if that example should be handled by that node.
Fix: Filter top-down using the partly built tree itself.
Major changes:
* Eliminated Filter class, findBinsForLevel() method.
* Set up node parent links in main loop over levels in train().
* Added predictNodeIndex() for filtering top-down.
* Added DTMetadata class
Other changes:
* Pre-compute set of unorderedFeatures.
Notes for following expected PR based on [https://issues.apache.org/jira/browse/SPARK-3043]:
* The unorderedFeatures set will next be stored in a metadata structure to simplify function calls (to store other items such as the data in strategy).
I've done initial tests indicating that this speeds things up, but am only now running large-scale ones.
CC: mengxr manishamde chouqin Any comments are welcome---thanks!
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#1975 from jkbradley/dt-opt2 and squashes the following commits:
a0ed0da [Joseph K. Bradley] Renamed DTMetadata to DecisionTreeMetadata. Small doc updates.
3726d20 [Joseph K. Bradley] Small code improvements based on code review.
ac0b9f8 [Joseph K. Bradley] Small updates based on code review. Main change: Now using << instead of math.pow.
db0d773 [Joseph K. Bradley] scala style fix
6a38f48 [Joseph K. Bradley] Added DTMetadata class for cleaner code
931a3a7 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt2
797f68a [Joseph K. Bradley] Fixed DecisionTreeSuite bug for training second level. Needed to update treePointToNodeIndex with groupShift.
f40381c [Joseph K. Bradley] Merge branch 'dt-opt1' into dt-opt2
5f2dec2 [Joseph K. Bradley] Fixed scalastyle issue in TreePoint
6b5651e [Joseph K. Bradley] Updates based on code review. 1 major change: persisting to memory + disk, not just memory.
2d2aaaf [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
26d10dd [Joseph K. Bradley] Removed tree/model/Filter.scala since no longer used. Removed debugging println calls in DecisionTree.scala.
356daba [Joseph K. Bradley] Merge branch 'dt-opt1' into dt-opt2
430d782 [Joseph K. Bradley] Added more debug info on binning error. Added some docs.
d036089 [Joseph K. Bradley] Print timing info to logDebug.
e66f1b1 [Joseph K. Bradley] TreePoint * Updated doc * Made some methods private
8464a6e [Joseph K. Bradley] Moved TimeTracker to tree/impl/ in its own file, and cleaned it up. Removed debugging println calls from DecisionTree. Made TreePoint extend Serialiable
a87e08f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
c1565a5 [Joseph K. Bradley] Small DecisionTree updates: * Simplification: Updated calculateGainForSplit to take aggregates for a single (feature, split) pair. * Internal doc: findAggForOrderedFeatureClassification
b914f3b [Joseph K. Bradley] DecisionTree optimization: eliminated filters + small changes
b2ed1f3 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt
0f676e2 [Joseph K. Bradley] Optimizations + Bug fix for DecisionTree
3211f02 [Joseph K. Bradley] Optimizing DecisionTree * Added TreePoint representation to avoid calling findBin multiple times. * (not working yet, but debugging)
f61e9d2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
bcf874a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
511ec85 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
a95bc22 [Joseph K. Bradley] timing for DecisionTree internals
- promote nullHypothesis field in ChiSqTestResult to TestResult. Every test should have a null hypothesis
- correct null hypothesis statement for independence test
- p-value: 0.01 -> 0.1
Author: Xiangrui Meng <meng@databricks.com>
Closes#1982 from mengxr/fix-chisq and squashes the following commits:
5f0de02 [Xiangrui Meng] make ChiSqTestResult constructor package private
bc74ea1 [Xiangrui Meng] update chisq-test
`RandomRDDGenerators` means factory for `RandomRDDGenerator`. However, its methods return RDDs but not RDDGenerators. So a more proper (and shorter) name would be `RandomRDDs`.
dorx brkyvz
Author: Xiangrui Meng <meng@databricks.com>
Closes#1979 from mengxr/randomrdds and squashes the following commits:
b161a2d [Xiangrui Meng] rename RandomRDDGenerators to RandomRDDs
Move `parse()` from `LabeledPointParser` to `LabeledPoint` and make it public. This breaks binary compatibility only when a user uses synthesized methods like `tupled` and `curried`, which is rare.
`LabeledPoint.parse` is more consistent with `Vectors.parse`, which is why `LabeledPointParser` is not preferred.
freeman-lab tdas
Author: Xiangrui Meng <meng@databricks.com>
Closes#1952 from mengxr/labelparser and squashes the following commits:
c818fb2 [Xiangrui Meng] merge master
ce20e6f [Xiangrui Meng] update mima excludes
b386b8d [Xiangrui Meng] fix tests
2436b3d [Xiangrui Meng] add parse() to LabeledPoint
The current implementation requires sorting individual columns, which could be done with a global sort.
result on a 32-node cluster:
m | n | prev | this
---|---|-------|-----
1000000 | 50 | 55s | 9s
10000000 | 50 | 97s | 76s
1000000 | 100 | 119s | 15s
Author: Xiangrui Meng <meng@databricks.com>
Closes#1917 from mengxr/spearman and squashes the following commits:
4d5d262 [Xiangrui Meng] remove unused import
85c48de [Xiangrui Meng] minor updates
a048d0c [Xiangrui Meng] remove cache and set a limit to cachedIds
b98bb18 [Xiangrui Meng] add comments
0846e07 [Xiangrui Meng] first version
Should ask users to set parameters through the optimizer. dbtsai
Author: Xiangrui Meng <meng@databricks.com>
Closes#1973 from mengxr/lr-lbfgs and squashes the following commits:
e3efbb1 [Xiangrui Meng] fix tests
21b3579 [Xiangrui Meng] fix method name
641eea4 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into lr-lbfgs
456ab7c [Xiangrui Meng] update LRWithLBFGS
DecisionTree improvements:
(1) TreePoint representation to avoid binning multiple times
(2) Bug fix: isSampleValid indexed bins incorrectly for unordered categorical features
(3) Timing for DecisionTree internals
Details:
(1) TreePoint representation to avoid binning multiple times
[https://issues.apache.org/jira/browse/SPARK-3022]
Added private[tree] TreePoint class for representing binned feature values.
The input RDD of LabeledPoint is converted to the TreePoint representation initially and then cached. This avoids the previous problem of re-computing bins multiple times.
(2) Bug fix: isSampleValid indexed bins incorrectly for unordered categorical features
[https://issues.apache.org/jira/browse/SPARK-3041]
isSampleValid used to treat unordered categorical features incorrectly: It treated the bins as if indexed by featured values, rather than by subsets of values/categories.
* exhibited for unordered features (multi-class classification with categorical features of low arity)
* Fix: Index bins correctly for unordered categorical features.
(3) Timing for DecisionTree internals
Added tree/impl/TimeTracker.scala class which is private[tree] for now, for timing key parts of DT code.
Prints timing info via logDebug.
CC: mengxr manishamde chouqin Very similar update, with one bug fix. Many apologies for the conflicting update, but I hope that a few more optimizations I have on the way (which depend on this update) will prove valuable to you: SPARK-3042 and SPARK-3043
Author: Joseph K. Bradley <joseph.kurata.bradley@gmail.com>
Closes#1950 from jkbradley/dt-opt1 and squashes the following commits:
5f2dec2 [Joseph K. Bradley] Fixed scalastyle issue in TreePoint
6b5651e [Joseph K. Bradley] Updates based on code review. 1 major change: persisting to memory + disk, not just memory.
2d2aaaf [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
430d782 [Joseph K. Bradley] Added more debug info on binning error. Added some docs.
d036089 [Joseph K. Bradley] Print timing info to logDebug.
e66f1b1 [Joseph K. Bradley] TreePoint * Updated doc * Made some methods private
8464a6e [Joseph K. Bradley] Moved TimeTracker to tree/impl/ in its own file, and cleaned it up. Removed debugging println calls from DecisionTree. Made TreePoint extend Serialiable
a87e08f [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-opt1
0f676e2 [Joseph K. Bradley] Optimizations + Bug fix for DecisionTree
3211f02 [Joseph K. Bradley] Optimizing DecisionTree * Added TreePoint representation to avoid calling findBin multiple times. * (not working yet, but debugging)
f61e9d2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
bcf874a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
511ec85 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into dt-timing
a95bc22 [Joseph K. Bradley] timing for DecisionTree internals
In theory, the scale of your inputs are irrelevant to logistic regression.
You can "theoretically" multiply X1 by 1E6 and the estimate for β1 will
adjust accordingly. It will be 1E-6 times smaller than the original β1, due
to the invariance property of MLEs.
However, during the optimization process, the convergence (rate)
depends on the condition number of the training dataset. Scaling
the variables often reduces this condition number, thus improving
the convergence rate.
Without reducing the condition number, some training datasets
mixing the columns with different scales may not be able to converge.
GLMNET and LIBSVM packages perform the scaling to reduce
the condition number, and return the weights in the original scale.
See page 9 in http://cran.r-project.org/web/packages/glmnet/glmnet.pdf
Here, if useFeatureScaling is enabled, we will standardize the training
features by dividing the variance of each column (without subtracting
the mean to densify the sparse vector), and train the model in the
scaled space. Then we transform the coefficients from the scaled space
to the original scale as GLMNET and LIBSVM do.
Currently, it's only enabled in LogisticRegressionWithLBFGS.
Author: DB Tsai <dbtsai@alpinenow.com>
Closes#1897 from dbtsai/dbtsai-feature-scaling and squashes the following commits:
f19fc02 [DB Tsai] Added more comments
1d85289 [DB Tsai] Improve the convergence rate by minimize the condition number in LOR with LBFGS
As mentioned in SPARK-2465, using `MEMORY_AND_DISK_SER` for user/product in/out links together with `spark.rdd.compress=true` can help reduce the space requirement by a lot, at the cost of speed. It might be useful to add this option so people can run ALS on much bigger datasets.
Another option for the method name is `setIntermediateRDDStorageLevel`.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1913 from mengxr/als-storagelevel and squashes the following commits:
d942017 [Xiangrui Meng] rename to setIntermediateRDDStorageLevel
7550029 [Xiangrui Meng] add ALS.setIntermediateDataStorageLevel
Iterator.fill uses less memory
Author: Xiangrui Meng <meng@databricks.com>
Closes#1930 from mengxr/rand-gen-iter and squashes the following commits:
24178ca [Xiangrui Meng] use Iterator.fill instead of Array.fill
For both Scala and Python.
The ser/de util functions were moved out of `PythonMLLibAPI` and into their own object to avoid creating the `PythonMLLibAPI` object inside of `MultivariateStatisticalSummarySerialized`, which is then referenced inside of a method in `PythonMLLibAPI`.
`MultivariateStatisticalSummarySerialized` was created to serialize the `Vector` fields in `MultivariateStatisticalSummary`.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1911 from dorx/colStats and squashes the following commits:
77b9924 [Doris Xin] developerAPI tag
de9cbbe [Doris Xin] reviewer comments and moved more ser/de
459faba [Doris Xin] colStats in Statistics for both Scala and Python
