[SPARK-3773][PySpark][Doc] Sphinx build warning

When building Sphinx documents for PySpark, we have 12 warnings.
Their causes are almost docstrings in broken ReST format.

To reproduce this issue, we should run following commands on the commit: 6e27cb630de69fa5acb510b4e2f6b980742b1957.

```bash
$ cd ./python/docs
$ make clean html
...
/Users/<user>/MyRepos/Scala/spark/python/pyspark/__init__.py:docstring of pyspark.SparkContext.sequenceFile:4: ERROR: Unexpected indentation.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/__init__.py:docstring of pyspark.RDD.saveAsSequenceFile:4: ERROR: Unexpected indentation.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.LogisticRegressionWithSGD.train:14: ERROR: Unexpected indentation.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.LogisticRegressionWithSGD.train:16: WARNING: Definition list ends without a blank line; unexpected unindent.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.LogisticRegressionWithSGD.train:17: WARNING: Block quote ends without a blank line; unexpected unindent.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.SVMWithSGD.train:14: ERROR: Unexpected indentation.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.SVMWithSGD.train:16: WARNING: Definition list ends without a blank line; unexpected unindent.
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/classification.py:docstring of pyspark.mllib.classification.SVMWithSGD.train:17: WARNING: Block quote ends without a blank line; unexpected unindent.
/Users/<user>/MyRepos/Scala/spark/python/docs/pyspark.mllib.rst:50: WARNING: missing attribute mentioned in :members: or __all__: module pyspark.mllib.regression, attribute RidgeRegressionModelLinearRegressionWithSGD
/Users/<user>/MyRepos/Scala/spark/python/pyspark/mllib/tree.py:docstring of pyspark.mllib.tree.DecisionTreeModel.predict:3: ERROR: Unexpected indentation.
...
checking consistency... /Users/<user>/MyRepos/Scala/spark/python/docs/modules.rst:: WARNING: document isn't included in any toctree
...
copying static files... WARNING: html_static_path entry u'/Users/<user>/MyRepos/Scala/spark/python/docs/_static' does not exist
...
build succeeded, 12 warnings.
```

Author: cocoatomo <cocoatomo77@gmail.com>

Closes #2653 from cocoatomo/issues/3773-sphinx-build-warnings and squashes the following commits:

6f65661 [cocoatomo] [SPARK-3773][PySpark][Doc] Sphinx build warning

1 files changed, 9 insertions, 6 deletions

diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py
index 8fe8c6db2a..54f34a9833 100644
--- a/python/pyspark/mllib/regression.py
+++ b/python/pyspark/mllib/regression.py
@@ -22,7 +22,7 @@ from pyspark import SparkContext
 from pyspark.mllib.linalg import SparseVector, _convert_to_vector
 from pyspark.serializers import PickleSerializer, AutoBatchedSerializer
 
-__all__ = ['LabeledPoint', 'LinearModel', 'LinearRegressionModel', 'RidgeRegressionModel'
+__all__ = ['LabeledPoint', 'LinearModel', 'LinearRegressionModel', 'RidgeRegressionModel',
            'LinearRegressionWithSGD', 'LassoWithSGD', 'RidgeRegressionWithSGD']
 
 
@@ -155,11 +155,14 @@ class LinearRegressionWithSGD(object):
         @param regParam:          The regularizer parameter (default: 1.0).
         @param regType:           The type of regularizer used for training
                                   our model.
-                                  Allowed values: "l1" for using L1Updater,
-                                                  "l2" for using
-                                                       SquaredL2Updater,
-                                                  "none" for no regularizer.
-                                  (default: "none")
+
+                                  :Allowed values:
+                                     - "l1" for using L1Updater,
+                                     - "l2" for using SquaredL2Updater,
+                                     - "none" for no regularizer.
+
+                                     (default: "none")
+
         @param intercept:         Boolean parameter which indicates the use
                                   or not of the augmented representation for
                                   training data (i.e. whether bias features