diff options
Diffstat (limited to 'examples/src/main/python/mllib/latent_dirichlet_allocation_example.py')
-rw-r--r-- | examples/src/main/python/mllib/latent_dirichlet_allocation_example.py | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/latent_dirichlet_allocation_example.py b/examples/src/main/python/mllib/latent_dirichlet_allocation_example.py new file mode 100644 index 0000000000..2a1bef5f20 --- /dev/null +++ b/examples/src/main/python/mllib/latent_dirichlet_allocation_example.py @@ -0,0 +1,54 @@ +# +# 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 + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.clustering import LDA, LDAModel +from pyspark.mllib.linalg import Vectors +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="LatentDirichletAllocationExample") # SparkContext + + # $example on$ + # Load and parse the data + data = sc.textFile("data/mllib/sample_lda_data.txt") + parsedData = data.map(lambda line: Vectors.dense([float(x) for x in line.strip().split(' ')])) + # Index documents with unique IDs + corpus = parsedData.zipWithIndex().map(lambda x: [x[1], x[0]]).cache() + + # Cluster the documents into three topics using LDA + ldaModel = LDA.train(corpus, k=3) + + # Output topics. Each is a distribution over words (matching word count vectors) + print("Learned topics (as distributions over vocab of " + str(ldaModel.vocabSize()) + + " words):") + topics = ldaModel.topicsMatrix() + for topic in range(3): + print("Topic " + str(topic) + ":") + for word in range(0, ldaModel.vocabSize()): + print(" " + str(topics[word][topic])) + + # Save and load model + ldaModel.save(sc, "target/org/apache/spark/PythonLatentDirichletAllocationExample/LDAModel") + sameModel = LDAModel\ + .load(sc, "target/org/apache/spark/PythonLatentDirichletAllocationExample/LDAModel") + # $example off$ + + sc.stop() |