spark-instrumented-optimizer/python/docs/source/reference/pyspark.mllib.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

254 lines
4.5 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.
MLlib
=====
Classification
--------------
.. currentmodule:: pyspark.mllib.classification
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
LogisticRegressionModel
LogisticRegressionWithSGD
LogisticRegressionWithLBFGS
SVMModel
SVMWithSGD
NaiveBayesModel
NaiveBayes
StreamingLogisticRegressionWithSGD
Clustering
----------
.. currentmodule:: pyspark.mllib.clustering
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
BisectingKMeansModel
BisectingKMeans
KMeansModel
KMeans
GaussianMixtureModel
GaussianMixture
PowerIterationClusteringModel
PowerIterationClustering
StreamingKMeans
StreamingKMeansModel
LDA
LDAModel
Evaluation
----------
.. currentmodule:: pyspark.mllib.evaluation
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
BinaryClassificationMetrics
RegressionMetrics
MulticlassMetrics
RankingMetrics
Feature
-------
.. currentmodule:: pyspark.mllib.feature
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Normalizer
StandardScalerModel
StandardScaler
HashingTF
IDFModel
IDF
Word2Vec
Word2VecModel
ChiSqSelector
ChiSqSelectorModel
ElementwiseProduct
Frequency Pattern Mining
------------------------
.. currentmodule:: pyspark.mllib.fpm
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
FPGrowth
FPGrowthModel
PrefixSpan
PrefixSpanModel
Vector and Matrix
-----------------
.. currentmodule:: pyspark.mllib.linalg
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Vector
DenseVector
SparseVector
Vectors
Matrix
DenseMatrix
SparseMatrix
Matrices
QRDecomposition
Distributed Representation
~~~~~~~~~~~~~~~~~~~~~~~~~~
.. currentmodule:: pyspark.mllib.linalg.distributed
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
BlockMatrix
CoordinateMatrix
DistributedMatrix
IndexedRow
IndexedRowMatrix
MatrixEntry
RowMatrix
SingularValueDecomposition
Random
------
.. currentmodule:: pyspark.mllib.random
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
RandomRDDs
Recommendation
--------------
.. currentmodule:: pyspark.mllib.recommendation
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
MatrixFactorizationModel
ALS
Rating
Regression
----------
.. currentmodule:: pyspark.mllib.regression
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
LabeledPoint
LinearModel
LinearRegressionModel
LinearRegressionWithSGD
RidgeRegressionModel
RidgeRegressionWithSGD
LassoModel
LassoWithSGD
IsotonicRegressionModel
IsotonicRegression
StreamingLinearAlgorithm
StreamingLinearRegressionWithSGD
Statistics
----------
.. currentmodule:: pyspark.mllib.stat
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
Statistics
MultivariateStatisticalSummary
ChiSqTestResult
MultivariateGaussian
KernelDensity
Tree
----
.. currentmodule:: pyspark.mllib.tree
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
DecisionTreeModel
DecisionTree
RandomForestModel
RandomForest
GradientBoostedTreesModel
GradientBoostedTrees
Utilities
---------
.. currentmodule:: pyspark.mllib.util
.. autosummary::
:template: autosummary/class_with_docs.rst
:toctree: api/
JavaLoader
JavaSaveable
LinearDataGenerator
Loader
MLUtils
Saveable