[DOC] [PYSPARK] [MLLIB] Added newlines to docstrings to fix parameter…

… formatting

Added newlines before `:param ...:` and `:return:` markup. Without these, parameter lists aren't formatted correctly in the API docs. I.e:

![screen shot 2015-09-21 at 21 49 26](https://cloud.githubusercontent.com/assets/11915197/10004686/de3c41d4-60aa-11e5-9c50-a46dcb51243f.png)

.. looks like this once newline is added:

![screen shot 2015-09-21 at 21 50 14](https://cloud.githubusercontent.com/assets/11915197/10004706/f86bfb08-60aa-11e5-8524-ae4436713502.png)

Author: noelsmith <[email protected]>

Closes apache#8851 from noel-smith/docstring-missing-newline-fix.

python/pyspark/ml/param/__init__.py

@@ -164,6 +164,7 @@ def extractParamMap(self, extra=None):
         a flat param map, where the latter value is used if there exist
         conflicts, i.e., with ordering: default param values <
         user-supplied values < extra.
+
         :param extra: extra param values
         :return: merged param map
         """
@@ -182,6 +183,7 @@ def copy(self, extra=None):
         embedded and extra parameters over and returns the copy.
         Subclasses should override this method if the default approach
         is not sufficient.
+
         :param extra: Extra parameters to copy to the new instance
         :return: Copy of this instance
         """
@@ -201,6 +203,7 @@ def _shouldOwn(self, param):
     def _resolveParam(self, param):
         """
         Resolves a param and validates the ownership.
+
         :param param: param name or the param instance, which must
                       belong to this Params instance
         :return: resolved param instance
@@ -243,6 +246,7 @@ def _copyValues(self, to, extra=None):
         """
         Copies param values from this instance to another instance for
         params shared by them.
+
         :param to: the target instance
         :param extra: extra params to be copied
         :return: the target instance with param values copied

python/pyspark/ml/pipeline.py

@@ -154,6 +154,7 @@ def __init__(self, stages=None):
     def setStages(self, value):
         """
         Set pipeline stages.
+
         :param value: a list of transformers or estimators
         :return: the pipeline instance
         """

python/pyspark/ml/tuning.py

@@ -254,6 +254,7 @@ def copy(self, extra=None):
         Creates a copy of this instance with a randomly generated uid
         and some extra params. This copies creates a deep copy of
         the embedded paramMap, and copies the embedded and extra parameters over.
+
         :param extra: Extra parameters to copy to the new instance
         :return: Copy of this instance
         """
@@ -290,6 +291,7 @@ def copy(self, extra=None):
         and some extra params. This copies the underlying bestModel,
         creates a deep copy of the embedded paramMap, and
         copies the embedded and extra parameters over.
+
         :param extra: Extra parameters to copy to the new instance
         :return: Copy of this instance
         """

python/pyspark/ml/wrapper.py

@@ -119,6 +119,7 @@ def _create_model(self, java_model):
     def _fit_java(self, dataset):
         """
         Fits a Java model to the input dataset.
+
         :param dataset: input dataset, which is an instance of
                         :py:class:`pyspark.sql.DataFrame`
         :param params: additional params (overwriting embedded values)
@@ -173,6 +174,7 @@ def copy(self, extra=None):
         extra params. This implementation first calls Params.copy and
         then make a copy of the companion Java model with extra params.
         So both the Python wrapper and the Java model get copied.
+
         :param extra: Extra parameters to copy to the new instance
         :return: Copy of this instance
         """

python/pyspark/mllib/evaluation.py

@@ -147,7 +147,7 @@ class MulticlassMetrics(JavaModelWrapper):
     """
     Evaluator for multiclass classification.
 
-    :param predictionAndLabels an RDD of (prediction, label) pairs.
+    :param predictionAndLabels: an RDD of (prediction, label) pairs.
 
     >>> predictionAndLabels = sc.parallelize([(0.0, 0.0), (0.0, 1.0), (0.0, 0.0),
     ...     (1.0, 0.0), (1.0, 1.0), (1.0, 1.0), (1.0, 1.0), (2.0, 2.0), (2.0, 0.0)])

python/pyspark/mllib/linalg/__init__.py

@@ -240,6 +240,7 @@ class Vector(object):
     def toArray(self):
         """
         Convert the vector into an numpy.ndarray
+
         :return: numpy.ndarray
         """
         raise NotImplementedError

python/pyspark/streaming/context.py

@@ -240,6 +240,7 @@ def start(self):
     def awaitTermination(self, timeout=None):
         """
         Wait for the execution to stop.
+
         @param timeout: time to wait in seconds
         """
         if timeout is None:
@@ -252,6 +253,7 @@ def awaitTerminationOrTimeout(self, timeout):
         Wait for the execution to stop. Return `true` if it's stopped; or
         throw the reported error during the execution; or `false` if the
         waiting time elapsed before returning from the method.
+
         @param timeout: time to wait in seconds
         """
         self._jssc.awaitTerminationOrTimeout(int(timeout * 1000))

python/pyspark/streaming/mqtt.py

@@ -31,6 +31,7 @@ def createStream(ssc, brokerUrl, topic,
                      storageLevel=StorageLevel.MEMORY_AND_DISK_SER_2):
         """
         Create an input stream that pulls messages from a Mqtt Broker.
+
         :param ssc:  StreamingContext object
         :param brokerUrl:  Url of remote mqtt publisher
         :param topic:  topic name to subscribe to