python/ml/quantile_discretizer_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 QuantileDiscretizer
0022 # $example off$
0023 from pyspark.sql import SparkSession
0024
0025 if __name__ == "__main__":
0026     spark = SparkSession\
0027         .builder\
0028         .appName("QuantileDiscretizerExample")\
0029         .getOrCreate()
0030
0031     # $example on$
0032     data = [(0, 18.0), (1, 19.0), (2, 8.0), (3, 5.0), (4, 2.2)]
0033     df = spark.createDataFrame(data, ["id", "hour"])
0034     # $example off$
0035
0036     # Output of QuantileDiscretizer for such small datasets can depend on the number of
0037     # partitions. Here we force a single partition to ensure consistent results.
0038     # Note this is not necessary for normal use cases
0039     df = df.repartition(1)
0040
0041     # $example on$
0042     discretizer = QuantileDiscretizer(numBuckets=3, inputCol="hour", outputCol="result")
0043
0044     result = discretizer.fit(df).transform(df)
0045     result.show()
0046     # $example off$
0047
0048     spark.stop()