add cv to tf doc

Author: hhbyyh

docs/ml-features.md

@@ -22,10 +22,19 @@ This section covers algorithms for working with features, roughly divided into t
 
 [Term Frequency-Inverse Document Frequency (TF-IDF)](http://en.wikipedia.org/wiki/Tf%E2%80%93idf) is a common text pre-processing step.  In Spark ML, TF-IDF is separate into two parts: TF (+hashing) and IDF.
 
-**TF**: `HashingTF` is a `Transformer` which takes sets of terms and converts those sets into fixed-length feature vectors.  In text processing, a "set of terms" might be a bag of words.
-The algorithm combines Term Frequency (TF) counts with the [hashing trick](http://en.wikipedia.org/wiki/Feature_hashing) for dimensionality reduction.
+**TF**: Both `HashingTF` and `CountVectorizer` can be used to get the term frequency. 
 
-**IDF**: `IDF` is an `Estimator` which fits on a dataset and produces an `IDFModel`.  The `IDFModel` takes feature vectors (generally created from `HashingTF`) and scales each column.  Intuitively, it down-weights columns which appear frequently in a corpus.
+`HashingTF` is a `Transformer` which takes sets of terms and converts those sets into 
+fixed-length feature vectors.  In text processing, a "set of terms" might be a bag of words.
+The algorithm combines Term Frequency (TF) counts with the 
+[hashing trick](http://en.wikipedia.org/wiki/Feature_hashing) for dimensionality reduction.
+
+`CountVectorizer` converts text documents to vectors of token counts. Refer to [CountVectorizer
+](ml-features.html#countvectorizer) for more details.
+
+**IDF**: `IDF` is an `Estimator` which fits on a dataset and produces an `IDFModel`.  The 
+`IDFModel` takes feature vectors (generally created from `HashingTF` or `CountVectorizer`) and scales each column.  
+Intuitively, it down-weights columns which appear frequently in a corpus.
 
 Please refer to the [MLlib user guide on TF-IDF](mllib-feature-extraction.html#tf-idf) for more details on Term Frequency and Inverse Document Frequency.
 

examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java

@@ -63,6 +63,8 @@ public static void main(String[] args) {
       .setOutputCol("rawFeatures")
       .setNumFeatures(numFeatures);
     Dataset<Row> featurizedData = hashingTF.transform(wordsData);
+    // alternatively, CountVectorizer can also be used to get term frequency vectors
+
     IDF idf = new IDF().setInputCol("rawFeatures").setOutputCol("features");
     IDFModel idfModel = idf.fit(featurizedData);
     Dataset<Row> rescaledData = idfModel.transform(featurizedData);

examples/src/main/python/ml/tf_idf_example.py

@@ -37,6 +37,8 @@
     wordsData = tokenizer.transform(sentenceData)
     hashingTF = HashingTF(inputCol="words", outputCol="rawFeatures", numFeatures=20)
     featurizedData = hashingTF.transform(wordsData)
+    # alternatively, CountVectorizer can also be used to get term frequency vectors
+
     idf = IDF(inputCol="rawFeatures", outputCol="features")
     idfModel = idf.fit(featurizedData)
     rescaledData = idfModel.transform(featurizedData)

examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala

@@ -20,7 +20,7 @@ package org.apache.spark.examples.ml
 
 import org.apache.spark.{SparkConf, SparkContext}
 // $example on$
-import org.apache.spark.ml.feature.{HashingTF, IDF, Tokenizer}
+import org.apache.spark.ml.feature.{CountVectorizer, HashingTF, IDF, Tokenizer}
 // $example off$
 import org.apache.spark.sql.SQLContext
 
@@ -43,6 +43,8 @@ object TfIdfExample {
     val hashingTF = new HashingTF()
       .setInputCol("words").setOutputCol("rawFeatures").setNumFeatures(20)
     val featurizedData = hashingTF.transform(wordsData)
+    // alternatively, CountVectorizer can also be used to get term frequency vectors
+
     val idf = new IDF().setInputCol("rawFeatures").setOutputCol("features")
     val idfModel = idf.fit(featurizedData)
     val rescaledData = idfModel.transform(featurizedData)