diff options
author | Xusen Yin <yinxusen@gmail.com> | 2015-12-09 12:00:48 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-12-09 12:00:48 -0800 |
commit | 051c6a066f7b5fcc7472412144c15b50a5319bd5 (patch) | |
tree | 810e743d0bd63ec07818e57d51469238e0998564 /examples/src/main/python/ml/string_indexer_example.py | |
parent | 1eb7c22ce72a1b82ed194a51bbcf0da9c771605a (diff) | |
download | spark-051c6a066f7b5fcc7472412144c15b50a5319bd5.tar.gz spark-051c6a066f7b5fcc7472412144c15b50a5319bd5.tar.bz2 spark-051c6a066f7b5fcc7472412144c15b50a5319bd5.zip |
[SPARK-11551][DOC] Replace example code in ml-features.md using include_example
PR on behalf of somideshmukh, thanks!
Author: Xusen Yin <yinxusen@gmail.com>
Author: somideshmukh <somilde@us.ibm.com>
Closes #10219 from yinxusen/SPARK-11551.
Diffstat (limited to 'examples/src/main/python/ml/string_indexer_example.py')
-rw-r--r-- | examples/src/main/python/ml/string_indexer_example.py | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/string_indexer_example.py b/examples/src/main/python/ml/string_indexer_example.py new file mode 100644 index 0000000000..58a8cb5d56 --- /dev/null +++ b/examples/src/main/python/ml/string_indexer_example.py @@ -0,0 +1,39 @@ +# +# 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 StringIndexer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="StringIndexerExample") + sqlContext = SQLContext(sc) + + # $example on$ + df = sqlContext.createDataFrame( + [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")], + ["id", "category"]) + indexer = StringIndexer(inputCol="category", outputCol="categoryIndex") + indexed = indexer.fit(df).transform(df) + indexed.show() + # $example off$ + + sc.stop() |