|
||||
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 from pyspark import SparkContext 0021 # $example on$ 0022 from pyspark.mllib.feature import Word2Vec 0023 # $example off$ 0024 0025 if __name__ == "__main__": 0026 sc = SparkContext(appName="Word2VecExample") # SparkContext 0027 0028 # $example on$ 0029 inp = sc.textFile("data/mllib/sample_lda_data.txt").map(lambda row: row.split(" ")) 0030 0031 word2vec = Word2Vec() 0032 model = word2vec.fit(inp) 0033 0034 synonyms = model.findSynonyms('1', 5) 0035 0036 for word, cosine_distance in synonyms: 0037 print("{}: {}".format(word, cosine_distance)) 0038 # $example off$ 0039 0040 sc.stop()
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.1.0 LXR engine. The LXR team |