diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/src/main/python/ml/quantile_discretizer_example.py | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/quantile_discretizer_example.py b/examples/src/main/python/ml/quantile_discretizer_example.py new file mode 100644 index 0000000000..6ae7bb18f8 --- /dev/null +++ b/examples/src/main/python/ml/quantile_discretizer_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 + +# $example on$ +from pyspark.ml.feature import QuantileDiscretizer +# $example off$ +from pyspark.sql import SparkSession + + +if __name__ == "__main__": + spark = SparkSession.builder.appName("PythonQuantileDiscretizerExample").getOrCreate() + + # $example on$ + data = [(0, 18.0,), (1, 19.0,), (2, 8.0,), (3, 5.0,), (4, 2.2,)] + dataFrame = spark.createDataFrame(data, ["id", "hour"]) + + discretizer = QuantileDiscretizer(numBuckets=3, inputCol="hour", outputCol="result") + + result = discretizer.fit(dataFrame).transform(dataFrame) + result.show() + # $example off$ + + spark.stop() |