spark git commit: [SPARK-14509][DOC] Add python CountVectorizerExample

[jk...@apache.org]

Repository: spark
Updated Branches:
  refs/heads/master a91aaf5a8 -> fcdd69260


[SPARK-14509][DOC] Add python CountVectorizerExample

## What changes were proposed in this pull request?
Add python CountVectorizerExample

## How was this patch tested?
manual tests

Author: Zheng RuiFeng <ru...@foxmail.com>

Closes #11917 from zhengruifeng/cv_pe.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/fcdd6926
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/fcdd6926
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/fcdd6926

Branch: refs/heads/master
Commit: fcdd69260ec75c180f4d727ff2625ca9bf0bdad7
Parents: a91aaf5
Author: Zheng RuiFeng <ru...@foxmail.com>
Authored: Wed Apr 13 13:56:23 2016 -0700
Committer: Joseph K. Bradley <jo...@databricks.com>
Committed: Wed Apr 13 13:56:23 2016 -0700

----------------------------------------------------------------------
 docs/ml-features.md                             |  9 ++++
 .../main/python/ml/count_vectorizer_example.py  | 44 ++++++++++++++++++++
 2 files changed, 53 insertions(+)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/fcdd6926/docs/ml-features.md
----------------------------------------------------------------------
diff --git a/docs/ml-features.md b/docs/ml-features.md
index 5cc27d3..70812eb 100644
--- a/docs/ml-features.md
+++ b/docs/ml-features.md
@@ -149,6 +149,15 @@ for more details on the API.
 
 {% include_example java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java %}
 </div>
+
+<div data-lang="python" markdown="1">
+
+Refer to the [CountVectorizer Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.CountVectorizer)
+and the [CountVectorizerModel Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.CountVectorizerModel)
+for more details on the API.
+
+{% include_example python/ml/count_vectorizer_example.py %}
+</div>
 </div>
 
 # Feature Transformers

http://git-wip-us.apache.org/repos/asf/spark/blob/fcdd6926/examples/src/main/python/ml/count_vectorizer_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/count_vectorizer_example.py b/examples/src/main/python/ml/count_vectorizer_example.py
new file mode 100644
index 0000000..e839f64
--- /dev/null
+++ b/examples/src/main/python/ml/count_vectorizer_example.py
@@ -0,0 +1,44 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from __future__ import print_function
+
+from pyspark import SparkContext
+from pyspark.sql import SQLContext
+# $example on$
+from pyspark.ml.feature import CountVectorizer
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="CountVectorizerExample")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Input data: Each row is a bag of words with a ID.
+    df = sqlContext.createDataFrame([
+        (0, "a b c".split(" ")),
+        (1, "a b b c a".split(" "))
+    ], ["id", "words"])
+
+    # fit a CountVectorizerModel from the corpus.
+    cv = CountVectorizer(inputCol="words", outputCol="features", vocabSize=3, minDF=2.0)
+    model = cv.fit(df)
+    result = model.transform(df)
+    result.show()
+    # $example off$
+
+    sc.stop()


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org