python/ml/bisecting_k_means_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 bisecting k-means clustering.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/bisecting_k_means_example.py
0022 """
0023 from __future__ import print_function
0024
0025 # $example on$
0026 from pyspark.ml.clustering import BisectingKMeans
0027 from pyspark.ml.evaluation import ClusteringEvaluator
0028 # $example off$
0029 from pyspark.sql import SparkSession
0030
0031 if __name__ == "__main__":
0032     spark = SparkSession\
0033         .builder\
0034         .appName("BisectingKMeansExample")\
0035         .getOrCreate()
0036
0037     # $example on$
0038     # Loads data.
0039     dataset = spark.read.format("libsvm").load("data/mllib/sample_kmeans_data.txt")
0040
0041     # Trains a bisecting k-means model.
0042     bkm = BisectingKMeans().setK(2).setSeed(1)
0043     model = bkm.fit(dataset)
0044
0045     # Make predictions
0046     predictions = model.transform(dataset)
0047
0048     # Evaluate clustering by computing Silhouette score
0049     evaluator = ClusteringEvaluator()
0050
0051     silhouette = evaluator.evaluate(predictions)
0052     print("Silhouette with squared euclidean distance = " + str(silhouette))
0053
0054     # Shows the result.
0055     print("Cluster Centers: ")
0056     centers = model.clusterCenters()
0057     for center in centers:
0058         print(center)
0059     # $example off$
0060
0061     spark.stop()