[SPARK-14238][ML][MLLIB][PYSPARK] Add binary toggle Param to PySpark HashingTF in ML & MLlib

## What changes were proposed in this pull request?

This fix tries to add binary toggle Param to PySpark HashingTF in ML & MLlib. If this toggle is set, then all non-zero counts will be set to 1.

Note: This fix (SPARK-14238) is extended from SPARK-13963 where Scala implementation was done.

## How was this patch tested?

This fix adds two tests to cover the code changes. One for HashingTF in PySpark's ML and one for HashingTF in PySpark's MLLib.

Author: Yong Tang <yong.tang.github@outlook.com>

Closes #12079 from yongtang/SPARK-14238.

4 files changed, 69 insertions, 3 deletions

diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 0b0c573eea..809a513316 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -536,14 +536,19 @@ class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures, Java
     .. versionadded:: 1.3.0
     """
 
+    binary = Param(Params._dummy(), "binary", "If True, all non zero counts are set to 1. " +
+                   "This is useful for discrete probabilistic models that model binary events " +
+                   "rather than integer counts. Default False.",
+                   typeConverter=TypeConverters.toBoolean)
+
     @keyword_only
-    def __init__(self, numFeatures=1 << 18, inputCol=None, outputCol=None):
+    def __init__(self, numFeatures=1 << 18, binary=False, inputCol=None, outputCol=None):
         """
         __init__(self, numFeatures=1 << 18, inputCol=None, outputCol=None)
         """
         super(HashingTF, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.HashingTF", self.uid)
-        self._setDefault(numFeatures=1 << 18)
+        self._setDefault(numFeatures=1 << 18, binary=False)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)
 
@@ -557,6 +562,21 @@ class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures, Java
         kwargs = self.setParams._input_kwargs
         return self._set(**kwargs)
 
+    @since("2.0.0")
+    def setBinary(self, value):
+        """
+        Sets the value of :py:attr:`binary`.
+        """
+        self._paramMap[self.binary] = value
+        return self
+
+    @since("2.0.0")
+    def getBinary(self):
+        """
+        Gets the value of binary or its default value.
+        """
+        return self.getOrDefault(self.binary)
+
 
 @inherit_doc
 class IDF(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWritable):
diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py
index 0b0ad2377f..86c0254a2b 100644
--- a/python/pyspark/ml/tests.py
+++ b/python/pyspark/ml/tests.py
@@ -847,6 +847,25 @@ class TrainingSummaryTest(PySparkTestCase):
         self.assertAlmostEqual(sameSummary.areaUnderROC, s.areaUnderROC)
 
 
+class HashingTFTest(PySparkTestCase):
+
+    def test_apply_binary_term_freqs(self):
+        sqlContext = SQLContext(self.sc)
+
+        df = sqlContext.createDataFrame([(0, ["a", "a", "b", "c", "c", "c"])], ["id", "words"])
+        n = 100
+        hashingTF = HashingTF()
+        hashingTF.setInputCol("words").setOutputCol("features").setNumFeatures(n).setBinary(True)
+        output = hashingTF.transform(df)
+        features = output.select("features").first().features.toArray()
+        expected = Vectors.sparse(n, {(ord("a") % n): 1.0,
+                                      (ord("b") % n): 1.0,
+                                      (ord("c") % n): 1.0}).toArray()
+        for i in range(0, n):
+            self.assertAlmostEqual(features[i], expected[i], 14, "Error at " + str(i) +
+                                   ": expected " + str(expected[i]) + ", got " + str(features[i]))
+
+
 if __name__ == "__main__":
     from pyspark.ml.tests import *
     if xmlrunner:
diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py
index 6129353525..b3dd2f63a5 100644
--- a/python/pyspark/mllib/feature.py
+++ b/python/pyspark/mllib/feature.py
@@ -379,6 +379,17 @@ class HashingTF(object):
     """
     def __init__(self, numFeatures=1 << 20):
         self.numFeatures = numFeatures
+        self.binary = False
+
+    @since("2.0.0")
+    def setBinary(self, value):
+        """
+        If True, term frequency vector will be binary such that non-zero
+        term counts will be set to 1
+        (default: False)
+        """
+        self.binary = value
+        return self
 
     @since('1.2.0')
     def indexOf(self, term):
@@ -398,7 +409,7 @@ class HashingTF(object):
         freq = {}
         for term in document:
             i = self.indexOf(term)
-            freq[i] = freq.get(i, 0) + 1.0
+            freq[i] = 1.0 if self.binary else freq.get(i, 0) + 1.0
         return Vectors.sparse(self.numFeatures, freq.items())
 
 
diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index 5f515b666c..ac55fbf798 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -58,6 +58,7 @@ from pyspark.mllib.recommendation import Rating
 from pyspark.mllib.regression import LabeledPoint, StreamingLinearRegressionWithSGD
 from pyspark.mllib.random import RandomRDDs
 from pyspark.mllib.stat import Statistics
+from pyspark.mllib.feature import HashingTF
 from pyspark.mllib.feature import Word2Vec
 from pyspark.mllib.feature import IDF
 from pyspark.mllib.feature import StandardScaler, ElementwiseProduct
@@ -1583,6 +1584,21 @@ class ALSTests(MLlibTestCase):
         self.assertRaises(Py4JJavaError, self.sc._jvm.SerDe.loads, bytearray(ser.dumps(r)))
 
 
+class HashingTFTest(MLlibTestCase):
+
+    def test_binary_term_freqs(self):
+        hashingTF = HashingTF(100).setBinary(True)
+        doc = "a a b c c c".split(" ")
+        n = hashingTF.numFeatures
+        output = hashingTF.transform(doc).toArray()
+        expected = Vectors.sparse(n, {hashingTF.indexOf("a"): 1.0,
+                                      hashingTF.indexOf("b"): 1.0,
+                                      hashingTF.indexOf("c"): 1.0}).toArray()
+        for i in range(0, n):
+            self.assertAlmostEqual(output[i], expected[i], 14, "Error at " + str(i) +
+                                   ": expected " + str(expected[i]) + ", got " + str(output[i]))
+
+
 if __name__ == "__main__":
     from pyspark.mllib.tests import *
     if not _have_scipy: