spark-instrumented-optimizer/python/docs/source/reference/pyspark.ml.rst
HyukjinKwon 9818f079aa [SPARK-33243][PYTHON][BUILD] Add numpydoc into documentation dependency
### What changes were proposed in this pull request?

This PR proposes to initiate the migration to NumPy documentation style (from reST style) in PySpark docstrings.
This PR also adds one migration example of `SparkContext`.

- **Before:**
    ...
    ![Screen Shot 2020-10-26 at 7 02 05 PM](https://user-images.githubusercontent.com/6477701/97161090-a8ea0200-17c0-11eb-8204-0e70d18fc571.png)
    ...
    ![Screen Shot 2020-10-26 at 7 02 09 PM](https://user-images.githubusercontent.com/6477701/97161100-aab3c580-17c0-11eb-92ad-f5ad4441ce16.png)
    ...

- **After:**

    ...
    ![Screen Shot 2020-10-26 at 7 24 08 PM](https://user-images.githubusercontent.com/6477701/97161219-d636b000-17c0-11eb-80ab-d17a570ecb4b.png)
    ...

See also https://numpydoc.readthedocs.io/en/latest/format.html

### Why are the changes needed?

There are many reasons for switching to NumPy documentation style.

1. Arguably reST style doesn't fit well when the docstring grows large because it provides (arguably) less structures and syntax.

2. NumPy documentation style provides a better human readable docstring format. For example, notebook users often just do `help(...)` by `pydoc`.

3. NumPy documentation style is pretty commonly used in data science libraries, for example, pandas, numpy, Dask, Koalas,
matplotlib, ... Using NumPy documentation style can give users a consistent documentation style.

### Does this PR introduce _any_ user-facing change?

The dependency itself doesn't change anything user-facing.
The documentation change in `SparkContext` does, as shown above.

### How was this patch tested?

Manually tested via running `cd python` and `make clean html`.

Closes #30149 from HyukjinKwon/SPARK-33243.

Authored-by: HyukjinKwon <gurwls223@apache.org>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2020-10-27 14:03:57 +09:00

367 lines
6.9 KiB
ReStructuredText

.. Licensed to the Apache Software Foundation (ASF) under one
or more contributor license agreements. See the NOTICE file
distributed with this work for additional information
regarding copyright ownership. The ASF licenses this file
to you under the Apache License, Version 2.0 (the
"License"); you may not use this file except in compliance
with the License. You may obtain a copy of the License at
.. http://www.apache.org/licenses/LICENSE-2.0
.. Unless required by applicable law or agreed to in writing,
software distributed under the License is distributed on an
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
KIND, either express or implied. See the License for the
specific language governing permissions and limitations
under the License.
ML
==
ML Pipeline APIs
----------------
.. currentmodule:: pyspark.ml
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Transformer
UnaryTransformer
Estimator
Model
Predictor
PredictionModel
Pipeline
PipelineModel
Parameters
----------
.. currentmodule:: pyspark.ml.param
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Param
Params
TypeConverters
Feature
-------
.. currentmodule:: pyspark.ml.feature
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
ANOVASelector
ANOVASelectorModel
Binarizer
BucketedRandomProjectionLSH
BucketedRandomProjectionLSHModel
Bucketizer
ChiSqSelector
ChiSqSelectorModel
CountVectorizer
CountVectorizerModel
DCT
ElementwiseProduct
FeatureHasher
FValueSelector
FValueSelectorModel
HashingTF
IDF
IDFModel
Imputer
ImputerModel
IndexToString
Interaction
MaxAbsScaler
MaxAbsScalerModel
MinHashLSH
MinHashLSHModel
MinMaxScaler
MinMaxScalerModel
NGram
Normalizer
OneHotEncoder
OneHotEncoderModel
PCA
PCAModel
PolynomialExpansion
QuantileDiscretizer
RobustScaler
RobustScalerModel
RegexTokenizer
RFormula
RFormulaModel
SQLTransformer
StandardScaler
StandardScalerModel
StopWordsRemover
StringIndexer
StringIndexerModel
Tokenizer
VarianceThresholdSelector
VarianceThresholdSelectorModel
VectorAssembler
VectorIndexer
VectorIndexerModel
VectorSizeHint
VectorSlicer
Word2Vec
Word2VecModel
Classification
--------------
.. currentmodule:: pyspark.ml.classification
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
LinearSVC
LinearSVCModel
LinearSVCSummary
LinearSVCTrainingSummary
LogisticRegression
LogisticRegressionModel
LogisticRegressionSummary
LogisticRegressionTrainingSummary
BinaryLogisticRegressionSummary
BinaryLogisticRegressionTrainingSummary
DecisionTreeClassifier
DecisionTreeClassificationModel
GBTClassifier
GBTClassificationModel
RandomForestClassifier
RandomForestClassificationModel
RandomForestClassificationSummary
RandomForestClassificationTrainingSummary
BinaryRandomForestClassificationSummary
BinaryRandomForestClassificationTrainingSummary
NaiveBayes
NaiveBayesModel
MultilayerPerceptronClassifier
MultilayerPerceptronClassificationModel
MultilayerPerceptronClassificationSummary
MultilayerPerceptronClassificationTrainingSummary
OneVsRest
OneVsRestModel
FMClassifier
FMClassificationModel
FMClassificationSummary
FMClassificationTrainingSummary
Clustering
----------
.. currentmodule:: pyspark.ml.clustering
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
BisectingKMeans
BisectingKMeansModel
BisectingKMeansSummary
KMeans
KMeansModel
KMeansSummary
GaussianMixture
GaussianMixtureModel
GaussianMixtureSummary
LDA
LDAModel
LocalLDAModel
DistributedLDAModel
PowerIterationClustering
ML Functions
----------------------------
.. currentmodule:: pyspark.ml.functions
.. autosummary::
:toctree: api/
vector_to_array
Vector and Matrix
-----------------
.. currentmodule:: pyspark.ml.linalg
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Vector
DenseVector
SparseVector
Vectors
Matrix
DenseMatrix
SparseMatrix
Matrices
Recommendation
--------------
.. currentmodule:: pyspark.ml.recommendation
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
ALS
ALSModel
Regression
----------
.. currentmodule:: pyspark.ml.regression
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
AFTSurvivalRegression
AFTSurvivalRegressionModel
DecisionTreeRegressor
DecisionTreeRegressionModel
GBTRegressor
GBTRegressionModel
GeneralizedLinearRegression
GeneralizedLinearRegressionModel
GeneralizedLinearRegressionSummary
GeneralizedLinearRegressionTrainingSummary
IsotonicRegression
IsotonicRegressionModel
LinearRegression
LinearRegressionModel
LinearRegressionSummary
LinearRegressionTrainingSummary
RandomForestRegressor
RandomForestRegressionModel
FMRegressor
FMRegressionModel
Statistics
----------
.. currentmodule:: pyspark.ml.stat
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
ANOVATest
ChiSquareTest
Correlation
FValueTest
KolmogorovSmirnovTest
MultivariateGaussian
Summarizer
SummaryBuilder
Tuning
------
.. currentmodule:: pyspark.ml.tuning
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
ParamGridBuilder
CrossValidator
CrossValidatorModel
TrainValidationSplit
TrainValidationSplitModel
Evaluation
----------
.. currentmodule:: pyspark.ml.evaluation
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Evaluator
BinaryClassificationEvaluator
RegressionEvaluator
MulticlassClassificationEvaluator
MultilabelClassificationEvaluator
ClusteringEvaluator
RankingEvaluator
Frequency Pattern Mining
----------------------------
.. currentmodule:: pyspark.ml.fpm
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
FPGrowth
FPGrowthModel
PrefixSpan
Image
-----
.. currentmodule:: pyspark.ml.image
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
ImageSchema
_ImageSchema
Utilities
---------
.. currentmodule:: pyspark.ml.util
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
BaseReadWrite
DefaultParamsReadable
DefaultParamsReader
DefaultParamsWritable
DefaultParamsWriter
GeneralMLWriter
HasTrainingSummary
Identifiable
MLReadable
MLReader
MLWritable
MLWriter