diff options
Diffstat (limited to 'examples/src/main/scala')
| -rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala index 28115f9390..396f073e6b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/TfIdfExample.scala @@ -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) |