[SPARK-3309] [PySpark] Put all public API in __all__

Put all public API in __all__, also put them all in pyspark.__init__.py, then we can got all the documents for public API by `pydoc pyspark`. It also can be used by other programs (such as Sphinx or Epydoc) to generate only documents for public APIs.

Author: Davies Liu <davies.liu@gmail.com>

Closes #2205 from davies/public and squashes the following commits:

c6c5567 [Davies Liu] fix message
f7b35be [Davies Liu] put SchemeRDD, Row in pyspark.sql module
7e3016a [Davies Liu] add __all__ in mllib
6281b48 [Davies Liu] fix doc for SchemaRDD
6caab21 [Davies Liu] add public interfaces into pyspark.__init__.py

8 files changed, 27 insertions, 7 deletions

diff --git a/python/pyspark/mllib/classification.py b/python/pyspark/mllib/classification.py
index ffdda7ee19..71ab46b61d 100644
--- a/python/pyspark/mllib/classification.py
+++ b/python/pyspark/mllib/classification.py
@@ -30,6 +30,10 @@ from pyspark.mllib.regression import LabeledPoint, LinearModel
 from math import exp, log
 
 
+__all__ = ['LogisticRegressionModel', 'LogisticRegressionWithSGD', 'SVMModel',
+           'SVMWithSGD', 'NaiveBayesModel', 'NaiveBayes']
+
+
 class LogisticRegressionModel(LinearModel):
 
     """A linear binary classification model derived from logistic regression.
diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py
index a0630d1d5c..f3e952a1d8 100644
--- a/python/pyspark/mllib/clustering.py
+++ b/python/pyspark/mllib/clustering.py
@@ -25,6 +25,8 @@ from pyspark.mllib._common import \
     _get_initial_weights, _serialize_rating, _regression_train_wrapper
 from pyspark.mllib.linalg import SparseVector
 
+__all__ = ['KMeansModel', 'KMeans']
+
 
 class KMeansModel(object):
 
diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py
index f485a69db1..e69051c104 100644
--- a/python/pyspark/mllib/linalg.py
+++ b/python/pyspark/mllib/linalg.py
@@ -27,6 +27,9 @@ import numpy
 from numpy import array, array_equal, ndarray, float64, int32
 
 
+__all__ = ['SparseVector', 'Vectors']
+
+
 class SparseVector(object):
 
     """
diff --git a/python/pyspark/mllib/random.py b/python/pyspark/mllib/random.py
index 4dc1a4a912..3e59c73db8 100644
--- a/python/pyspark/mllib/random.py
+++ b/python/pyspark/mllib/random.py
@@ -25,6 +25,9 @@ from pyspark.mllib._common import _deserialize_double, _deserialize_double_vecto
 from pyspark.serializers import NoOpSerializer
 
 
+__all__ = ['RandomRDDs', ]
+
+
 class RandomRDDs:
     """
     Generator methods for creating RDDs comprised of i.i.d samples from
diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py
index e863fc249e..2df23394da 100644
--- a/python/pyspark/mllib/recommendation.py
+++ b/python/pyspark/mllib/recommendation.py
@@ -24,6 +24,8 @@ from pyspark.mllib._common import \
     _serialize_tuple, RatingDeserializer
 from pyspark.rdd import RDD
 
+__all__ = ['MatrixFactorizationModel', 'ALS']
+
 
 class MatrixFactorizationModel(object):
 
diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index d8792cf448..f572dcfb84 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -17,15 +17,15 @@
 
 from numpy import array, ndarray
 from pyspark import SparkContext
-from pyspark.mllib._common import \
-    _dot, _get_unmangled_rdd, _get_unmangled_double_vector_rdd, \
-    _serialize_double_matrix, _deserialize_double_matrix, \
-    _serialize_double_vector, _deserialize_double_vector, \
-    _get_initial_weights, _serialize_rating, _regression_train_wrapper, \
+from pyspark.mllib._common import _dot, _regression_train_wrapper, \
     _linear_predictor_typecheck, _have_scipy, _scipy_issparse
 from pyspark.mllib.linalg import SparseVector, Vectors
 
 
+__all__ = ['LabeledPoint', 'LinearModel', 'LinearRegressionModel', 'RidgeRegressionModel'
+           'LinearRegressionWithSGD', 'LassoWithSGD', 'RidgeRegressionWithSGD']
+
+
 class LabeledPoint(object):
 
     """
diff --git a/python/pyspark/mllib/stat.py b/python/pyspark/mllib/stat.py
index feef0d16cd..8c726f171c 100644
--- a/python/pyspark/mllib/stat.py
+++ b/python/pyspark/mllib/stat.py
@@ -21,8 +21,10 @@ Python package for statistical functions in MLlib.
 
 from pyspark.mllib._common import \
     _get_unmangled_double_vector_rdd, _get_unmangled_rdd, \
-    _serialize_double, _serialize_double_vector, \
-    _deserialize_double, _deserialize_double_matrix, _deserialize_double_vector
+    _serialize_double, _deserialize_double_matrix, _deserialize_double_vector
+
+
+__all__ = ['MultivariateStatisticalSummary', 'Statistics']
 
 
 class MultivariateStatisticalSummary(object):
diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py
index e9d778df5a..a2fade61e9 100644
--- a/python/pyspark/mllib/tree.py
+++ b/python/pyspark/mllib/tree.py
@@ -26,6 +26,9 @@ from pyspark.mllib.regression import LabeledPoint
 from pyspark.serializers import NoOpSerializer
 
 
+__all__ = ['DecisionTreeModel', 'DecisionTree']
+
+
 class DecisionTreeModel(object):
 
     """
@@ -88,6 +91,7 @@ class DecisionTree(object):
                   It will probably be modified for Spark v1.2.
 
     Example usage:
+
     >>> from numpy import array
     >>> import sys
     >>> from pyspark.mllib.regression import LabeledPoint