diff --git a/python/pyspark/ml/param/__init__.py b/python/pyspark/ml/param/__init__.py
index eeeac49b2198085047052c286eb1cbd69cd48153..2e0c63cb47b17400fbef39abfc7fd614f0ce999b 100644
--- a/python/pyspark/ml/param/__init__.py
+++ b/python/pyspark/ml/param/__init__.py
@@ -164,6 +164,7 @@ class Params(Identifiable):
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 @@ class Params(Identifiable):
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 @@ class Params(Identifiable):
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 @@ class Params(Identifiable):
"""
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
diff --git a/python/pyspark/ml/pipeline.py b/python/pyspark/ml/pipeline.py
index 13cf2b0f7bbd9cf21091fa591d56e0bc001355b7..312a8502b3a2c5b58765bbaa5184544c5edddf1a 100644
--- a/python/pyspark/ml/pipeline.py
+++ b/python/pyspark/ml/pipeline.py
@@ -154,6 +154,7 @@ class Pipeline(Estimator):
def setStages(self, value):
"""
Set pipeline stages.
+
:param value: a list of transformers or estimators
:return: the pipeline instance
"""
diff --git a/python/pyspark/ml/tuning.py b/python/pyspark/ml/tuning.py
index ab5621f45c72c0107de55bc804f0c45a57ebc058..705ee53685752ce5fb5ab7f1887f1d4f428f4370 100644
--- a/python/pyspark/ml/tuning.py
+++ b/python/pyspark/ml/tuning.py
@@ -254,6 +254,7 @@ class CrossValidator(Estimator):
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 @@ class CrossValidatorModel(Model):
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
"""
diff --git a/python/pyspark/ml/wrapper.py b/python/pyspark/ml/wrapper.py
index 8218c7c5f801c302079d2e96c7e2195b06c1173d..4bcb4aaec89de0605ae3df8ebba07131eebfdb5f 100644
--- a/python/pyspark/ml/wrapper.py
+++ b/python/pyspark/ml/wrapper.py
@@ -119,6 +119,7 @@ class JavaEstimator(Estimator, JavaWrapper):
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 @@ class JavaModel(Model, JavaTransformer):
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
"""
diff --git a/python/pyspark/mllib/evaluation.py b/python/pyspark/mllib/evaluation.py
index 4398ca86f2ec2c4d92cae6c93ccae6855221890b..a90e5c50e54b945e67aa9db0edd24e833245ed9d 100644
--- a/python/pyspark/mllib/evaluation.py
+++ b/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)])
diff --git a/python/pyspark/mllib/linalg/__init__.py b/python/pyspark/mllib/linalg/__init__.py
index f929e3e96fbe25953c6107a0e6fe4b9ecf1ace72..ea42127f1651f1c8938f58cb3c2d82a624b376f7 100644
--- a/python/pyspark/mllib/linalg/__init__.py
+++ b/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
diff --git a/python/pyspark/streaming/context.py b/python/pyspark/streaming/context.py
index 4069d7a1499862aa30eb13d3163e02628da1fa84..a8c9ffc235b9e13c1876c27586a2e70043cd9e83 100644
--- a/python/pyspark/streaming/context.py
+++ b/python/pyspark/streaming/context.py
@@ -240,6 +240,7 @@ class StreamingContext(object):
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 @@ class StreamingContext(object):
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))
diff --git a/python/pyspark/streaming/mqtt.py b/python/pyspark/streaming/mqtt.py
index f06598971c5480db44027c6c7d79c445e1f2a832..fa83006c36db6ab80b78723081462820e0bbcdb1 100644
--- a/python/pyspark/streaming/mqtt.py
+++ b/python/pyspark/streaming/mqtt.py
@@ -31,6 +31,7 @@ class MQTTUtils(object):
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