Skip to content

[SPARK-15837][ML][PySpark]Word2vec python add maxsentence parameter #13578

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
WeichenXu123 wants to merge 1 commit into from
Closed

[SPARK-15837][ML][PySpark]Word2vec python add maxsentence parameter #13578

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 24 additions & 5 deletions python/pyspark/ml/feature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2234,28 +2234,33 @@ class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, Has
windowSize = Param(Params._dummy(), "windowSize",
"the window size (context words from [-window, window]). Default value is 5",
typeConverter=TypeConverters.toInt)
maxSentenceLength = Param(Params._dummy(), "maxSentenceLength",
"Maximum length (in words) of each sentence in the input data. " +
"Any sentence longer than this threshold will " +
"be divided into chunks up to the size.",
typeConverter=TypeConverters.toInt)

@keyword_only
def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=None, inputCol=None, outputCol=None, windowSize=5):
seed=None, inputCol=None, outputCol=None, windowSize=5, maxSentenceLength=1000):
"""
__init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, \
seed=None, inputCol=None, outputCol=None, windowSize=5)
seed=None, inputCol=None, outputCol=None, windowSize=5, maxSentenceLength=1000)
"""
super(Word2Vec, self).__init__()
self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.Word2Vec", self.uid)
self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=None, windowSize=5)
seed=None, windowSize=5, maxSentenceLength=1000)
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)

@keyword_only
@since("1.4.0")
def setParams(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=None, inputCol=None, outputCol=None, windowSize=5):
seed=None, inputCol=None, outputCol=None, windowSize=5, maxSentenceLength=1000):
"""
setParams(self, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, seed=None, \
inputCol=None, outputCol=None, windowSize=5)
inputCol=None, outputCol=None, windowSize=5, maxSentenceLength=1000)
Sets params for this Word2Vec.
"""
kwargs = self.setParams._input_kwargs
Expand Down Expand Up @@ -2317,6 +2322,20 @@ def getWindowSize(self):
"""
return self.getOrDefault(self.windowSize)

@since("2.0.0")
def setMaxSentenceLength(self, value):
"""
Sets the value of :py:attr:`maxSentenceLength`.
"""
return self._set(maxSentenceLength=value)

@since("2.0.0")
def getMaxSentenceLength(self):
"""
Gets the value of maxSentenceLength or its default value.
"""
return self.getOrDefault(self.maxSentenceLength)

def _create_model(self, java_model):
return Word2VecModel(java_model)

Expand Down