From cde592a29c21f752cb977934ee56809fdbb5f8b8 Mon Sep 17 00:00:00 2001
From: noelsmith <mail@noelsmith.com>
Date: Sun, 6 Sep 2015 22:18:25 +0100
Subject: [PATCH 1/4] Added @since to mllib.feature

---
 python/pyspark/__init__.py      | 20 ++++++++++++
 python/pyspark/mllib/feature.py | 58 ++++++++++++++++++++++++++++++++-
 2 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py
index 8475dfb1c6ad0..76ee3b1895e9f 100644
--- a/python/pyspark/__init__.py
+++ b/python/pyspark/__init__.py
@@ -67,6 +67,26 @@ def deco(f):
 # for back compatibility
 from pyspark.sql import SQLContext, HiveContext, SchemaRDD, Row
 
+
+def since(version):
+    """
+    A decorator that annotates a function to append the version of Spark the function was added.
+    """
+    import re
+    indent_p = re.compile(r'\n( +)')
+
+    def deco(f):
+        if f.__doc__ is None:
+            f.__doc__ = ".. versionadded:: {}".format(version)
+            return f
+        else:
+            indents = indent_p.findall(f.__doc__)
+            indent = ' ' * (min(len(m) for m in indents) if indents else 0)
+            f.__doc__ = "{}\n\n{}.. versionadded:: {}".format(f.__doc__.rstrip(), indent, version)
+            return f
+    return deco
+
+
 __all__ = [
     "SparkConf", "SparkContext", "SparkFiles", "RDD", "StorageLevel", "Broadcast",
     "Accumulator", "AccumulatorParam", "MarshalSerializer", "PickleSerializer",
diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py
index f921e3ad1a314..7b077b058c3fd 100644
--- a/python/pyspark/mllib/feature.py
+++ b/python/pyspark/mllib/feature.py
@@ -30,7 +30,7 @@
 
 from py4j.protocol import Py4JJavaError
 
-from pyspark import SparkContext
+from pyspark import SparkContext, since
 from pyspark.rdd import RDD, ignore_unicode_prefix
 from pyspark.mllib.common import callMLlibFunc, JavaModelWrapper
 from pyspark.mllib.linalg import (
@@ -84,11 +84,14 @@ class Normalizer(VectorTransformer):
     >>> nor2 = Normalizer(float("inf"))
     >>> nor2.transform(v)
     DenseVector([0.0, 0.5, 1.0])
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, p=2.0):
         assert p >= 1.0, "p should be greater than 1.0"
         self.p = float(p)
 
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies unit length normalization on a vector.
@@ -133,7 +136,11 @@ class StandardScalerModel(JavaVectorTransformer):
     .. note:: Experimental
 
     Represents a StandardScaler model that can transform vectors.
+
+    .. versionadded:: 1.2.0
     """
+
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies standardization transformation on a vector.
@@ -149,6 +156,7 @@ def transform(self, vector):
         """
         return JavaVectorTransformer.transform(self, vector)
 
+    @since('1.4.0')
     def setWithMean(self, withMean):
         """
         Setter of the boolean which decides
@@ -157,6 +165,7 @@ def setWithMean(self, withMean):
         self.call("setWithMean", withMean)
         return self
 
+    @since('1.4.0')
     def setWithStd(self, withStd):
         """
         Setter of the boolean which decides
@@ -189,6 +198,8 @@ class StandardScaler(object):
     >>> for r in result.collect(): r
     DenseVector([-0.7071, 0.7071, -0.7071])
     DenseVector([0.7071, -0.7071, 0.7071])
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, withMean=False, withStd=True):
         if not (withMean or withStd):
@@ -196,6 +207,7 @@ def __init__(self, withMean=False, withStd=True):
         self.withMean = withMean
         self.withStd = withStd
 
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the mean and variance and stores as a model to be used
@@ -215,7 +227,11 @@ class ChiSqSelectorModel(JavaVectorTransformer):
     .. note:: Experimental
 
     Represents a Chi Squared selector model.
+
+    .. versionadded:: 1.4.0
     """
+
+    @since('1.4.0')
     def transform(self, vector):
         """
         Applies transformation on a vector.
@@ -245,10 +261,13 @@ class ChiSqSelector(object):
     SparseVector(1, {0: 6.0})
     >>> model.transform(DenseVector([8.0, 9.0, 5.0]))
     DenseVector([5.0])
+
+    .. versionadded:: 1.4.0
     """
     def __init__(self, numTopFeatures):
         self.numTopFeatures = int(numTopFeatures)
 
+    @since('1.4.0')
     def fit(self, data):
         """
         Returns a ChiSquared feature selector.
@@ -265,6 +284,8 @@ def fit(self, data):
 class PCAModel(JavaVectorTransformer):
     """
     Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.
+
+    .. versionadded:: 1.5.0
     """
 
 
@@ -281,6 +302,8 @@ class PCA(object):
     1.648...
     >>> pcArray[1]
     -4.013...
+
+    .. versionadded:: 1.5.0
     """
     def __init__(self, k):
         """
@@ -288,6 +311,7 @@ def __init__(self, k):
         """
         self.k = int(k)
 
+    @since('1.5.0')
     def fit(self, data):
         """
         Computes a [[PCAModel]] that contains the principal components of the input vectors.
@@ -312,14 +336,18 @@ class HashingTF(object):
     >>> doc = "a a b b c d".split(" ")
     >>> htf.transform(doc)
     SparseVector(100, {...})
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, numFeatures=1 << 20):
         self.numFeatures = numFeatures
 
+    @since('1.2.0')
     def indexOf(self, term):
         """ Returns the index of the input term. """
         return hash(term) % self.numFeatures
 
+    @since('1.2.0')
     def transform(self, document):
         """
         Transforms the input document (list of terms) to term frequency
@@ -339,7 +367,10 @@ def transform(self, document):
 class IDFModel(JavaVectorTransformer):
     """
     Represents an IDF model that can transform term frequency vectors.
+
+    .. versionadded:: 1.2.0
     """
+    @since('1.2.0')
     def transform(self, x):
         """
         Transforms term frequency (TF) vectors to TF-IDF vectors.
@@ -358,6 +389,7 @@ def transform(self, x):
         """
         return JavaVectorTransformer.transform(self, x)
 
+    @since('1.4.0')
     def idf(self):
         """
         Returns the current IDF vector.
@@ -401,10 +433,13 @@ class IDF(object):
     DenseVector([0.0, 0.0, 1.3863, 0.863])
     >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))
     SparseVector(4, {1: 0.0, 3: 0.5754})
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self, minDocFreq=0):
         self.minDocFreq = minDocFreq
 
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the inverse document frequency.
@@ -420,7 +455,10 @@ def fit(self, dataset):
 class Word2VecModel(JavaVectorTransformer, JavaSaveable, JavaLoader):
     """
     class for Word2Vec model
+
+    .. versionadded:: 1.2.0
     """
+    @since('1.2.0')
     def transform(self, word):
         """
         Transforms a word to its vector representation
@@ -435,6 +473,7 @@ def transform(self, word):
         except Py4JJavaError:
             raise ValueError("%s not found" % word)
 
+    @since('1.2.0')
     def findSynonyms(self, word, num):
         """
         Find synonyms of a word
@@ -450,6 +489,7 @@ def findSynonyms(self, word, num):
         words, similarity = self.call("findSynonyms", word, num)
         return zip(words, similarity)
 
+    @since('1.4.0')
     def getVectors(self):
         """
         Returns a map of words to their vector representations.
@@ -457,7 +497,11 @@ def getVectors(self):
         return self.call("getVectors")
 
     @classmethod
+    @since('1.5.0')
     def load(cls, sc, path):
+        """
+        Load a model from the given path.
+        """
         jmodel = sc._jvm.org.apache.spark.mllib.feature \
             .Word2VecModel.load(sc._jsc.sc(), path)
         return Word2VecModel(jmodel)
@@ -507,6 +551,8 @@ class Word2Vec(object):
     ...     rmtree(path)
     ... except OSError:
     ...     pass
+
+    .. versionadded:: 1.2.0
     """
     def __init__(self):
         """
@@ -519,6 +565,7 @@ def __init__(self):
         self.seed = random.randint(0, sys.maxsize)
         self.minCount = 5
 
+    @since('1.2.0')
     def setVectorSize(self, vectorSize):
         """
         Sets vector size (default: 100).
@@ -526,6 +573,7 @@ def setVectorSize(self, vectorSize):
         self.vectorSize = vectorSize
         return self
 
+    @since('1.2.0')
     def setLearningRate(self, learningRate):
         """
         Sets initial learning rate (default: 0.025).
@@ -533,6 +581,7 @@ def setLearningRate(self, learningRate):
         self.learningRate = learningRate
         return self
 
+    @since('1.2.0')
     def setNumPartitions(self, numPartitions):
         """
         Sets number of partitions (default: 1). Use a small number for
@@ -541,6 +590,7 @@ def setNumPartitions(self, numPartitions):
         self.numPartitions = numPartitions
         return self
 
+    @since('1.2.0')
     def setNumIterations(self, numIterations):
         """
         Sets number of iterations (default: 1), which should be smaller
@@ -549,6 +599,7 @@ def setNumIterations(self, numIterations):
         self.numIterations = numIterations
         return self
 
+    @since('1.2.0')
     def setSeed(self, seed):
         """
         Sets random seed.
@@ -556,6 +607,7 @@ def setSeed(self, seed):
         self.seed = seed
         return self
 
+    @since('1.4.0')
     def setMinCount(self, minCount):
         """
         Sets minCount, the minimum number of times a token must appear
@@ -564,6 +616,7 @@ def setMinCount(self, minCount):
         self.minCount = minCount
         return self
 
+    @since('1.2.0')
     def fit(self, data):
         """
         Computes the vector representation of each word in vocabulary.
@@ -596,10 +649,13 @@ class ElementwiseProduct(VectorTransformer):
     >>> rdd = sc.parallelize([a, b])
     >>> eprod.transform(rdd).collect()
     [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]
+
+    .. versionadded:: 1.5.0
     """
     def __init__(self, scalingVector):
         self.scalingVector = _convert_to_vector(scalingVector)
 
+    @since('1.5.0')
     def transform(self, vector):
         """
         Computes the Hadamard product of the vector.

From e6a4c471e8ec90a5da66d0c5e21176fac6df485c Mon Sep 17 00:00:00 2001
From: noelsmith <mail@noelsmith.com>
Date: Wed, 9 Sep 2015 20:51:15 +0100
Subject: [PATCH 2/4] Removed duplicate since decorator

---
 python/pyspark/__init__.py | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/python/pyspark/__init__.py b/python/pyspark/__init__.py
index 76ee3b1895e9f..8475dfb1c6ad0 100644
--- a/python/pyspark/__init__.py
+++ b/python/pyspark/__init__.py
@@ -67,26 +67,6 @@ def deco(f):
 # for back compatibility
 from pyspark.sql import SQLContext, HiveContext, SchemaRDD, Row
 
-
-def since(version):
-    """
-    A decorator that annotates a function to append the version of Spark the function was added.
-    """
-    import re
-    indent_p = re.compile(r'\n( +)')
-
-    def deco(f):
-        if f.__doc__ is None:
-            f.__doc__ = ".. versionadded:: {}".format(version)
-            return f
-        else:
-            indents = indent_p.findall(f.__doc__)
-            indent = ' ' * (min(len(m) for m in indents) if indents else 0)
-            f.__doc__ = "{}\n\n{}.. versionadded:: {}".format(f.__doc__.rstrip(), indent, version)
-            return f
-    return deco
-
-
 __all__ = [
     "SparkConf", "SparkContext", "SparkFiles", "RDD", "StorageLevel", "Broadcast",
     "Accumulator", "AccumulatorParam", "MarshalSerializer", "PickleSerializer",

From bcf77a3a59b489c743ebcac2639170278f36162a Mon Sep 17 00:00:00 2001
From: noelsmith <mail@noelsmith.com>
Date: Thu, 10 Sep 2015 21:28:21 +0100
Subject: [PATCH 3/4] Removed maintenance number from versions

---
 python/pyspark/mllib/feature.py | 76 ++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 38 deletions(-)

diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py
index 7b077b058c3fd..8c82cf6b90e61 100644
--- a/python/pyspark/mllib/feature.py
+++ b/python/pyspark/mllib/feature.py
@@ -85,13 +85,13 @@ class Normalizer(VectorTransformer):
     >>> nor2.transform(v)
     DenseVector([0.0, 0.5, 1.0])
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
     def __init__(self, p=2.0):
         assert p >= 1.0, "p should be greater than 1.0"
         self.p = float(p)
 
-    @since('1.2.0')
+    @since(1.2)
     def transform(self, vector):
         """
         Applies unit length normalization on a vector.
@@ -137,10 +137,10 @@ class StandardScalerModel(JavaVectorTransformer):
 
     Represents a StandardScaler model that can transform vectors.
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
 
-    @since('1.2.0')
+    @since(1.2)
     def transform(self, vector):
         """
         Applies standardization transformation on a vector.
@@ -156,7 +156,7 @@ def transform(self, vector):
         """
         return JavaVectorTransformer.transform(self, vector)
 
-    @since('1.4.0')
+    @since(1.4)
     def setWithMean(self, withMean):
         """
         Setter of the boolean which decides
@@ -165,7 +165,7 @@ def setWithMean(self, withMean):
         self.call("setWithMean", withMean)
         return self
 
-    @since('1.4.0')
+    @since(1.4)
     def setWithStd(self, withStd):
         """
         Setter of the boolean which decides
@@ -199,7 +199,7 @@ class StandardScaler(object):
     DenseVector([-0.7071, 0.7071, -0.7071])
     DenseVector([0.7071, -0.7071, 0.7071])
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
     def __init__(self, withMean=False, withStd=True):
         if not (withMean or withStd):
@@ -207,7 +207,7 @@ def __init__(self, withMean=False, withStd=True):
         self.withMean = withMean
         self.withStd = withStd
 
-    @since('1.2.0')
+    @since(1.2)
     def fit(self, dataset):
         """
         Computes the mean and variance and stores as a model to be used
@@ -228,10 +228,10 @@ class ChiSqSelectorModel(JavaVectorTransformer):
 
     Represents a Chi Squared selector model.
 
-    .. versionadded:: 1.4.0
+    .. versionadded:: 1.4
     """
 
-    @since('1.4.0')
+    @since(1.4)
     def transform(self, vector):
         """
         Applies transformation on a vector.
@@ -262,12 +262,12 @@ class ChiSqSelector(object):
     >>> model.transform(DenseVector([8.0, 9.0, 5.0]))
     DenseVector([5.0])
 
-    .. versionadded:: 1.4.0
+    .. versionadded:: 1.4
     """
     def __init__(self, numTopFeatures):
         self.numTopFeatures = int(numTopFeatures)
 
-    @since('1.4.0')
+    @since(1.4)
     def fit(self, data):
         """
         Returns a ChiSquared feature selector.
@@ -285,7 +285,7 @@ class PCAModel(JavaVectorTransformer):
     """
     Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.
 
-    .. versionadded:: 1.5.0
+    .. versionadded:: 1.5
     """
 
 
@@ -303,7 +303,7 @@ class PCA(object):
     >>> pcArray[1]
     -4.013...
 
-    .. versionadded:: 1.5.0
+    .. versionadded:: 1.5
     """
     def __init__(self, k):
         """
@@ -311,7 +311,7 @@ def __init__(self, k):
         """
         self.k = int(k)
 
-    @since('1.5.0')
+    @since(1.5)
     def fit(self, data):
         """
         Computes a [[PCAModel]] that contains the principal components of the input vectors.
@@ -337,17 +337,17 @@ class HashingTF(object):
     >>> htf.transform(doc)
     SparseVector(100, {...})
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
     def __init__(self, numFeatures=1 << 20):
         self.numFeatures = numFeatures
 
-    @since('1.2.0')
+    @since(1.2)
     def indexOf(self, term):
         """ Returns the index of the input term. """
         return hash(term) % self.numFeatures
 
-    @since('1.2.0')
+    @since(1.2)
     def transform(self, document):
         """
         Transforms the input document (list of terms) to term frequency
@@ -368,9 +368,9 @@ class IDFModel(JavaVectorTransformer):
     """
     Represents an IDF model that can transform term frequency vectors.
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
-    @since('1.2.0')
+    @since(1.2)
     def transform(self, x):
         """
         Transforms term frequency (TF) vectors to TF-IDF vectors.
@@ -389,7 +389,7 @@ def transform(self, x):
         """
         return JavaVectorTransformer.transform(self, x)
 
-    @since('1.4.0')
+    @since(1.4)
     def idf(self):
         """
         Returns the current IDF vector.
@@ -434,12 +434,12 @@ class IDF(object):
     >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))
     SparseVector(4, {1: 0.0, 3: 0.5754})
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
     def __init__(self, minDocFreq=0):
         self.minDocFreq = minDocFreq
 
-    @since('1.2.0')
+    @since(1.2)
     def fit(self, dataset):
         """
         Computes the inverse document frequency.
@@ -456,9 +456,9 @@ class Word2VecModel(JavaVectorTransformer, JavaSaveable, JavaLoader):
     """
     class for Word2Vec model
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
-    @since('1.2.0')
+    @since(1.2)
     def transform(self, word):
         """
         Transforms a word to its vector representation
@@ -473,7 +473,7 @@ def transform(self, word):
         except Py4JJavaError:
             raise ValueError("%s not found" % word)
 
-    @since('1.2.0')
+    @since(1.2)
     def findSynonyms(self, word, num):
         """
         Find synonyms of a word
@@ -489,7 +489,7 @@ def findSynonyms(self, word, num):
         words, similarity = self.call("findSynonyms", word, num)
         return zip(words, similarity)
 
-    @since('1.4.0')
+    @since(1.4)
     def getVectors(self):
         """
         Returns a map of words to their vector representations.
@@ -497,7 +497,7 @@ def getVectors(self):
         return self.call("getVectors")
 
     @classmethod
-    @since('1.5.0')
+    @since(1.5)
     def load(cls, sc, path):
         """
         Load a model from the given path.
@@ -552,7 +552,7 @@ class Word2Vec(object):
     ... except OSError:
     ...     pass
 
-    .. versionadded:: 1.2.0
+    .. versionadded:: 1.2
     """
     def __init__(self):
         """
@@ -565,7 +565,7 @@ def __init__(self):
         self.seed = random.randint(0, sys.maxsize)
         self.minCount = 5
 
-    @since('1.2.0')
+    @since(1.2)
     def setVectorSize(self, vectorSize):
         """
         Sets vector size (default: 100).
@@ -573,7 +573,7 @@ def setVectorSize(self, vectorSize):
         self.vectorSize = vectorSize
         return self
 
-    @since('1.2.0')
+    @since(1.2)
     def setLearningRate(self, learningRate):
         """
         Sets initial learning rate (default: 0.025).
@@ -581,7 +581,7 @@ def setLearningRate(self, learningRate):
         self.learningRate = learningRate
         return self
 
-    @since('1.2.0')
+    @since(1.2)
     def setNumPartitions(self, numPartitions):
         """
         Sets number of partitions (default: 1). Use a small number for
@@ -590,7 +590,7 @@ def setNumPartitions(self, numPartitions):
         self.numPartitions = numPartitions
         return self
 
-    @since('1.2.0')
+    @since(1.2)
     def setNumIterations(self, numIterations):
         """
         Sets number of iterations (default: 1), which should be smaller
@@ -599,7 +599,7 @@ def setNumIterations(self, numIterations):
         self.numIterations = numIterations
         return self
 
-    @since('1.2.0')
+    @since(1.2)
     def setSeed(self, seed):
         """
         Sets random seed.
@@ -607,7 +607,7 @@ def setSeed(self, seed):
         self.seed = seed
         return self
 
-    @since('1.4.0')
+    @since(1.4)
     def setMinCount(self, minCount):
         """
         Sets minCount, the minimum number of times a token must appear
@@ -616,7 +616,7 @@ def setMinCount(self, minCount):
         self.minCount = minCount
         return self
 
-    @since('1.2.0')
+    @since(1.2)
     def fit(self, data):
         """
         Computes the vector representation of each word in vocabulary.
@@ -650,12 +650,12 @@ class ElementwiseProduct(VectorTransformer):
     >>> eprod.transform(rdd).collect()
     [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]
 
-    .. versionadded:: 1.5.0
+    .. versionadded:: 1.5
     """
     def __init__(self, scalingVector):
         self.scalingVector = _convert_to_vector(scalingVector)
 
-    @since('1.5.0')
+    @since(1.5)
     def transform(self, vector):
         """
         Computes the Hadamard product of the vector.

From 7853215a80a06fd1d1deb45e8f3340fa9bb54129 Mon Sep 17 00:00:00 2001
From: noelsmith <mail@noelsmith.com>
Date: Mon, 14 Sep 2015 22:08:41 +0100
Subject: [PATCH 4/4] Reinstated 3-part version numbers

---
 python/pyspark/mllib/feature.py | 76 ++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 38 deletions(-)

diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py
index 8c82cf6b90e61..7b077b058c3fd 100644
--- a/python/pyspark/mllib/feature.py
+++ b/python/pyspark/mllib/feature.py
@@ -85,13 +85,13 @@ class Normalizer(VectorTransformer):
     >>> nor2.transform(v)
     DenseVector([0.0, 0.5, 1.0])
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
     def __init__(self, p=2.0):
         assert p >= 1.0, "p should be greater than 1.0"
         self.p = float(p)
 
-    @since(1.2)
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies unit length normalization on a vector.
@@ -137,10 +137,10 @@ class StandardScalerModel(JavaVectorTransformer):
 
     Represents a StandardScaler model that can transform vectors.
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
 
-    @since(1.2)
+    @since('1.2.0')
     def transform(self, vector):
         """
         Applies standardization transformation on a vector.
@@ -156,7 +156,7 @@ def transform(self, vector):
         """
         return JavaVectorTransformer.transform(self, vector)
 
-    @since(1.4)
+    @since('1.4.0')
     def setWithMean(self, withMean):
         """
         Setter of the boolean which decides
@@ -165,7 +165,7 @@ def setWithMean(self, withMean):
         self.call("setWithMean", withMean)
         return self
 
-    @since(1.4)
+    @since('1.4.0')
     def setWithStd(self, withStd):
         """
         Setter of the boolean which decides
@@ -199,7 +199,7 @@ class StandardScaler(object):
     DenseVector([-0.7071, 0.7071, -0.7071])
     DenseVector([0.7071, -0.7071, 0.7071])
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
     def __init__(self, withMean=False, withStd=True):
         if not (withMean or withStd):
@@ -207,7 +207,7 @@ def __init__(self, withMean=False, withStd=True):
         self.withMean = withMean
         self.withStd = withStd
 
-    @since(1.2)
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the mean and variance and stores as a model to be used
@@ -228,10 +228,10 @@ class ChiSqSelectorModel(JavaVectorTransformer):
 
     Represents a Chi Squared selector model.
 
-    .. versionadded:: 1.4
+    .. versionadded:: 1.4.0
     """
 
-    @since(1.4)
+    @since('1.4.0')
     def transform(self, vector):
         """
         Applies transformation on a vector.
@@ -262,12 +262,12 @@ class ChiSqSelector(object):
     >>> model.transform(DenseVector([8.0, 9.0, 5.0]))
     DenseVector([5.0])
 
-    .. versionadded:: 1.4
+    .. versionadded:: 1.4.0
     """
     def __init__(self, numTopFeatures):
         self.numTopFeatures = int(numTopFeatures)
 
-    @since(1.4)
+    @since('1.4.0')
     def fit(self, data):
         """
         Returns a ChiSquared feature selector.
@@ -285,7 +285,7 @@ class PCAModel(JavaVectorTransformer):
     """
     Model fitted by [[PCA]] that can project vectors to a low-dimensional space using PCA.
 
-    .. versionadded:: 1.5
+    .. versionadded:: 1.5.0
     """
 
 
@@ -303,7 +303,7 @@ class PCA(object):
     >>> pcArray[1]
     -4.013...
 
-    .. versionadded:: 1.5
+    .. versionadded:: 1.5.0
     """
     def __init__(self, k):
         """
@@ -311,7 +311,7 @@ def __init__(self, k):
         """
         self.k = int(k)
 
-    @since(1.5)
+    @since('1.5.0')
     def fit(self, data):
         """
         Computes a [[PCAModel]] that contains the principal components of the input vectors.
@@ -337,17 +337,17 @@ class HashingTF(object):
     >>> htf.transform(doc)
     SparseVector(100, {...})
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
     def __init__(self, numFeatures=1 << 20):
         self.numFeatures = numFeatures
 
-    @since(1.2)
+    @since('1.2.0')
     def indexOf(self, term):
         """ Returns the index of the input term. """
         return hash(term) % self.numFeatures
 
-    @since(1.2)
+    @since('1.2.0')
     def transform(self, document):
         """
         Transforms the input document (list of terms) to term frequency
@@ -368,9 +368,9 @@ class IDFModel(JavaVectorTransformer):
     """
     Represents an IDF model that can transform term frequency vectors.
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
-    @since(1.2)
+    @since('1.2.0')
     def transform(self, x):
         """
         Transforms term frequency (TF) vectors to TF-IDF vectors.
@@ -389,7 +389,7 @@ def transform(self, x):
         """
         return JavaVectorTransformer.transform(self, x)
 
-    @since(1.4)
+    @since('1.4.0')
     def idf(self):
         """
         Returns the current IDF vector.
@@ -434,12 +434,12 @@ class IDF(object):
     >>> model.transform(Vectors.sparse(n, (1, 3), (1.0, 2.0)))
     SparseVector(4, {1: 0.0, 3: 0.5754})
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
     def __init__(self, minDocFreq=0):
         self.minDocFreq = minDocFreq
 
-    @since(1.2)
+    @since('1.2.0')
     def fit(self, dataset):
         """
         Computes the inverse document frequency.
@@ -456,9 +456,9 @@ class Word2VecModel(JavaVectorTransformer, JavaSaveable, JavaLoader):
     """
     class for Word2Vec model
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
-    @since(1.2)
+    @since('1.2.0')
     def transform(self, word):
         """
         Transforms a word to its vector representation
@@ -473,7 +473,7 @@ def transform(self, word):
         except Py4JJavaError:
             raise ValueError("%s not found" % word)
 
-    @since(1.2)
+    @since('1.2.0')
     def findSynonyms(self, word, num):
         """
         Find synonyms of a word
@@ -489,7 +489,7 @@ def findSynonyms(self, word, num):
         words, similarity = self.call("findSynonyms", word, num)
         return zip(words, similarity)
 
-    @since(1.4)
+    @since('1.4.0')
     def getVectors(self):
         """
         Returns a map of words to their vector representations.
@@ -497,7 +497,7 @@ def getVectors(self):
         return self.call("getVectors")
 
     @classmethod
-    @since(1.5)
+    @since('1.5.0')
     def load(cls, sc, path):
         """
         Load a model from the given path.
@@ -552,7 +552,7 @@ class Word2Vec(object):
     ... except OSError:
     ...     pass
 
-    .. versionadded:: 1.2
+    .. versionadded:: 1.2.0
     """
     def __init__(self):
         """
@@ -565,7 +565,7 @@ def __init__(self):
         self.seed = random.randint(0, sys.maxsize)
         self.minCount = 5
 
-    @since(1.2)
+    @since('1.2.0')
     def setVectorSize(self, vectorSize):
         """
         Sets vector size (default: 100).
@@ -573,7 +573,7 @@ def setVectorSize(self, vectorSize):
         self.vectorSize = vectorSize
         return self
 
-    @since(1.2)
+    @since('1.2.0')
     def setLearningRate(self, learningRate):
         """
         Sets initial learning rate (default: 0.025).
@@ -581,7 +581,7 @@ def setLearningRate(self, learningRate):
         self.learningRate = learningRate
         return self
 
-    @since(1.2)
+    @since('1.2.0')
     def setNumPartitions(self, numPartitions):
         """
         Sets number of partitions (default: 1). Use a small number for
@@ -590,7 +590,7 @@ def setNumPartitions(self, numPartitions):
         self.numPartitions = numPartitions
         return self
 
-    @since(1.2)
+    @since('1.2.0')
     def setNumIterations(self, numIterations):
         """
         Sets number of iterations (default: 1), which should be smaller
@@ -599,7 +599,7 @@ def setNumIterations(self, numIterations):
         self.numIterations = numIterations
         return self
 
-    @since(1.2)
+    @since('1.2.0')
     def setSeed(self, seed):
         """
         Sets random seed.
@@ -607,7 +607,7 @@ def setSeed(self, seed):
         self.seed = seed
         return self
 
-    @since(1.4)
+    @since('1.4.0')
     def setMinCount(self, minCount):
         """
         Sets minCount, the minimum number of times a token must appear
@@ -616,7 +616,7 @@ def setMinCount(self, minCount):
         self.minCount = minCount
         return self
 
-    @since(1.2)
+    @since('1.2.0')
     def fit(self, data):
         """
         Computes the vector representation of each word in vocabulary.
@@ -650,12 +650,12 @@ class ElementwiseProduct(VectorTransformer):
     >>> eprod.transform(rdd).collect()
     [DenseVector([2.0, 2.0, 9.0]), DenseVector([9.0, 6.0, 12.0])]
 
-    .. versionadded:: 1.5
+    .. versionadded:: 1.5.0
     """
     def __init__(self, scalingVector):
         self.scalingVector = _convert_to_vector(scalingVector)
 
-    @since(1.5)
+    @since('1.5.0')
     def transform(self, vector):
         """
         Computes the Hadamard product of the vector.