diff options
author | BenFradet <benjamin.fradet@gmail.com> | 2015-12-08 12:45:34 -0800 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2015-12-08 12:45:34 -0800 |
commit | 06746b3005e5e9892d0314bee3bfdfaebc36d3d4 (patch) | |
tree | d0bdd5af1a56b07fe00c6c5c44a0da3f276338e6 /examples/src/main/python/ml | |
parent | 5cb4695051e3dac847b1ea14d62e54dcf672c31c (diff) | |
download | spark-06746b3005e5e9892d0314bee3bfdfaebc36d3d4.tar.gz spark-06746b3005e5e9892d0314bee3bfdfaebc36d3d4.tar.bz2 spark-06746b3005e5e9892d0314bee3bfdfaebc36d3d4.zip |
[SPARK-12159][ML] Add user guide section for IndexToString transformer
Documentation regarding the `IndexToString` label transformer with code snippets in Scala/Java/Python.
Author: BenFradet <benjamin.fradet@gmail.com>
Closes #10166 from BenFradet/SPARK-12159.
Diffstat (limited to 'examples/src/main/python/ml')
-rw-r--r-- | examples/src/main/python/ml/index_to_string_example.py | 45 |
1 files changed, 45 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/index_to_string_example.py b/examples/src/main/python/ml/index_to_string_example.py new file mode 100644 index 0000000000..fb0ba2950b --- /dev/null +++ b/examples/src/main/python/ml/index_to_string_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 +# $example on$ +from pyspark.ml.feature import IndexToString, StringIndexer +# $example off$ +from pyspark.sql import SQLContext + +if __name__ == "__main__": + sc = SparkContext(appName="IndexToStringExample") + sqlContext = SQLContext(sc) + + # $example on$ + df = sqlContext.createDataFrame( + [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")], + ["id", "category"]) + + stringIndexer = StringIndexer(inputCol="category", outputCol="categoryIndex") + model = stringIndexer.fit(df) + indexed = model.transform(df) + + converter = IndexToString(inputCol="categoryIndex", outputCol="originalCategory") + converted = converter.transform(indexed) + + converted.select("id", "originalCategory").show() + # $example off$ + + sc.stop() |