python/ml/lda_example.py

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 """
0019 An example demonstrating LDA.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/lda_example.py
0022 """
0023 from __future__ import print_function
0024
0025 # $example on$
0026 from pyspark.ml.clustering import LDA
0027 # $example off$
0028 from pyspark.sql import SparkSession
0029
0030 if __name__ == "__main__":
0031     spark = SparkSession \
0032         .builder \
0033         .appName("LDAExample") \
0034         .getOrCreate()
0035
0036     # $example on$
0037     # Loads data.
0038     dataset = spark.read.format("libsvm").load("data/mllib/sample_lda_libsvm_data.txt")
0039
0040     # Trains a LDA model.
0041     lda = LDA(k=10, maxIter=10)
0042     model = lda.fit(dataset)
0043
0044     ll = model.logLikelihood(dataset)
0045     lp = model.logPerplexity(dataset)
0046     print("The lower bound on the log likelihood of the entire corpus: " + str(ll))
0047     print("The upper bound on perplexity: " + str(lp))
0048
0049     # Describe topics.
0050     topics = model.describeTopics(3)
0051     print("The topics described by their top-weighted terms:")
0052     topics.show(truncate=False)
0053
0054     # Shows the result
0055     transformed = model.transform(dataset)
0056     transformed.show(truncate=False)
0057     # $example off$
0058
0059     spark.stop()