diff options
Diffstat (limited to 'examples/src/main/python/ml/vector_indexer_example.py')
| -rw-r--r-- | examples/src/main/python/ml/vector_indexer_example.py | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/vector_indexer_example.py b/examples/src/main/python/ml/vector_indexer_example.py new file mode 100644 index 0000000000..146f41c1dd --- /dev/null +++ b/examples/src/main/python/ml/vector_indexer_example.py @@ -0,0 +1,40 @@ +# +# 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 VectorIndexer +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="VectorIndexerExample") + sqlContext = SQLContext(sc) + + # $example on$ + data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") + indexer = VectorIndexer(inputCol="features", outputCol="indexed", maxCategories=10) + indexerModel = indexer.fit(data) + + # Create new column "indexed" with categorical values transformed to indices + indexedData = indexerModel.transform(data) + indexedData.show() + # $example off$ + + sc.stop() |