/
githubmirror
/
spark
Обзор
Документация
Войти
/
githubmirror
/
spark
Код
Запросы
0
Пакеты
0
Релизы
0
Аналитика
Безопасность
master
examples/src/main/python/ml/count_vectorizer_example.py
45 строк
1 KB
HyukjinKwon
[SPARK-32138] Drop Python 2.7, 3.4 and 3.5
14 июл 2020, 05:22
14 июл 2020, 05:22
4ad9bfd
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 CountVectorizer # $example off$ if __name__ == "__main__": spark = SparkSession\ .builder\ .appName("CountVectorizerExample")\ .getOrCreate() # $example on$ # Input data: Each row is a bag of words with a ID. df = spark.createDataFrame([ (0, "a b c".split(" ")), (1, "a b b c a".split(" ")) ], ["id", "words"]) # fit a CountVectorizerModel from the corpus. cv = CountVectorizer(inputCol="words", outputCol="features", vocabSize=3, minDF=2.0) model = cv.fit(df) result = model.transform(df) result.show(truncate=False) # $example off$ spark.stop()