/
githubmirror
/
spark
Обзор
Документация
Войти
/
githubmirror
/
spark
Код
Запросы
0
Пакеты
0
Релизы
0
Аналитика
Безопасность
master
examples/src/main/python/ml/bucketizer_example.py
44 строки
2 KB
Hyukjin Kwon
[SPARK-37836][PYTHON][INFRA] Enable F841, E722, E305 and E226 for PEP 8 compliance
07 янв 2022, 17:43
07 янв 2022, 17:43
9000339
Код
Авторство
О чём код?
# # 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 pyspark.sql import SparkSession # $example on$ from pyspark.ml.feature import Bucketizer # $example off$ if __name__ == "__main__": spark = SparkSession\ .builder\ .appName("BucketizerExample")\ .getOrCreate() # $example on$ splits = [-float("inf"), -0.5, 0.0, 0.5, float("inf")] data = [(-999.9,), (-0.5,), (-0.3,), (0.0,), (0.2,), (999.9,)] dataFrame = spark.createDataFrame(data, ["features"]) bucketizer = Bucketizer(splits=splits, inputCol="features", outputCol="bucketedFeatures") # Transform original data into its bucket index. bucketedData = bucketizer.transform(dataFrame) print("Bucketizer output with %d buckets" % (len(bucketizer.getSplits()) - 1)) bucketedData.show() # $example off$ spark.stop()