python/ml/vector_slicer_example.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 from __future__ import print_function
0019
0020 # $example on$
0021 from pyspark.ml.feature import VectorSlicer
0022 from pyspark.ml.linalg import Vectors
0023 from pyspark.sql.types import Row
0024 # $example off$
0025 from pyspark.sql import SparkSession
0026
0027 if __name__ == "__main__":
0028     spark = SparkSession\
0029         .builder\
0030         .appName("VectorSlicerExample")\
0031         .getOrCreate()
0032
0033     # $example on$
0034     df = spark.createDataFrame([
0035         Row(userFeatures=Vectors.sparse(3, {0: -2.0, 1: 2.3})),
0036         Row(userFeatures=Vectors.dense([-2.0, 2.3, 0.0]))])
0037
0038     slicer = VectorSlicer(inputCol="userFeatures", outputCol="features", indices=[1])
0039
0040     output = slicer.transform(df)
0041
0042     output.select("userFeatures", "features").show()
0043     # $example off$
0044
0045     spark.stop()