examples/src/main/python/ml/lda_example.py

#
# 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.
#

"""
An example demonstrating LDA.
Run with:
  bin/spark-submit examples/src/main/python/ml/lda_example.py
"""
# $example on$
from pyspark.ml.clustering import LDA
# $example off$
from pyspark.sql import SparkSession

if __name__ == "__main__":
    spark = SparkSession \
        .builder \
        .appName("LDAExample") \
        .getOrCreate()

    # $example on$
    # Loads data.
    dataset = spark.read.format("libsvm").load("data/mllib/sample_lda_libsvm_data.txt")

    # Trains a LDA model.
    lda = LDA(k=10, maxIter=10)
    model = lda.fit(dataset)

    ll = model.logLikelihood(dataset)
    lp = model.logPerplexity(dataset)
    print("The lower bound on the log likelihood of the entire corpus: " + str(ll))
    print("The upper bound on perplexity: " + str(lp))

    # Describe topics.
    topics = model.describeTopics(3)
    print("The topics described by their top-weighted terms:")
    topics.show(truncate=False)

    # Shows the result
    transformed = model.transform(dataset)
    transformed.show(truncate=False)
    # $example off$

    spark.stop()