diff options
author | Yanbo Liang <ybliang8@gmail.com> | 2015-05-08 15:48:39 -0700 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2015-05-08 15:48:50 -0700 |
commit | ab48df3918c6009cc268abfb74056d86363435d7 (patch) | |
tree | 9b06cdce06ab898e57ed4efc167ee0ca0ddd87f6 /mllib/src/main | |
parent | 21bd7222e55b9cf684c072141998a0623a69f514 (diff) | |
download | spark-ab48df3918c6009cc268abfb74056d86363435d7.tar.gz spark-ab48df3918c6009cc268abfb74056d86363435d7.tar.bz2 spark-ab48df3918c6009cc268abfb74056d86363435d7.zip |
[SPARK-5913] [MLLIB] Python API for ChiSqSelector
Add a Python API for mllib.feature.ChiSqSelector
https://issues.apache.org/jira/browse/SPARK-5913
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #5939 from yanboliang/spark-5913 and squashes the following commits:
cdaac99 [Yanbo Liang] Python API for ChiSqSelector
(cherry picked from commit 35c9599b94de759204ed33cdd46d8ee108bccd86)
Signed-off-by: Joseph K. Bradley <joseph@databricks.com>
Diffstat (limited to 'mllib/src/main')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala index 426306d78c..8c30ad4b39 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala @@ -495,6 +495,16 @@ private[python] class PythonMLLibAPI extends Serializable { } /** + * Java stub for ChiSqSelector.fit(). This stub returns a + * handle to the Java object instead of the content of the Java object. + * Extra care needs to be taken in the Python code to ensure it gets freed on + * exit; see the Py4J documentation. + */ + def fitChiSqSelector(numTopFeatures: Int, data: JavaRDD[LabeledPoint]): ChiSqSelectorModel = { + new ChiSqSelector(numTopFeatures).fit(data.rdd) + } + + /** * Java stub for IDF.fit(). This stub returns a * handle to the Java object instead of the content of the Java object. * Extra care needs to be taken in the Python code to ensure it gets freed on |