From 943d4fa204a827ca8ecc39d9cf04e86890ee9840 Mon Sep 17 00:00:00 2001
From: Xusen Yin <yinxusen@gmail.com>
Date: Mon, 26 Oct 2015 21:17:53 -0700
Subject: [SPARK-11289][DOC] Substitute code examples in ML features extractors
 with include_example

mengxr https://issues.apache.org/jira/browse/SPARK-11289

I make some changes in ML feature extractors. I.e. TF-IDF, Word2Vec, and CountVectorizer. I add new example code in spark/examples, hope it is the right place to add those examples.

Author: Xusen Yin <yinxusen@gmail.com>

Closes #9266 from yinxusen/SPARK-11289.
---
 examples/src/main/python/ml/word2vec_example.py | 45 +++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 examples/src/main/python/ml/word2vec_example.py

(limited to 'examples/src/main/python/ml/word2vec_example.py')

diff --git a/examples/src/main/python/ml/word2vec_example.py b/examples/src/main/python/ml/word2vec_example.py
new file mode 100644
index 0000000000..53c77feb10
--- /dev/null
+++ b/examples/src/main/python/ml/word2vec_example.py
@@ -0,0 +1,45 @@
+#
+# 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 Word2Vec
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="Word2VecExample")
+    sqlContext = SQLContext(sc)
+
+    # $example on$
+    # Input data: Each row is a bag of words from a sentence or document.
+    documentDF = sqlContext.createDataFrame([
+        ("Hi I heard about Spark".split(" "), ),
+        ("I wish Java could use case classes".split(" "), ),
+        ("Logistic regression models are neat".split(" "), )
+    ], ["text"])
+    # Learn a mapping from words to Vectors.
+    word2Vec = Word2Vec(vectorSize=3, minCount=0, inputCol="text", outputCol="result")
+    model = word2Vec.fit(documentDF)
+    result = model.transform(documentDF)
+    for feature in result.select("result").take(3):
+        print(feature)
+    # $example off$
+
+    sc.stop()
-- 
cgit v1.2.3