From d18276cb1d82790a402960835e112aebd0c55513 Mon Sep 17 00:00:00 2001 From: Zheng RuiFeng Date: Fri, 11 Mar 2016 09:21:12 +0200 Subject: [SPARK-13672][ML] Add python examples of BisectingKMeans in ML and MLLIB JIRA: https://issues.apache.org/jira/browse/SPARK-13672 ## What changes were proposed in this pull request? add two python examples of BisectingKMeans for ml and mllib ## How was this patch tested? manual tests Author: Zheng RuiFeng Closes #11515 from zhengruifeng/mllib_bkm_pe. --- docs/mllib-clustering.md | 6 +++ .../main/python/ml/bisecting_k_means_example.py | 57 ++++++++++++++++++++++ .../main/python/mllib/bisecting_k_means_example.py | 50 +++++++++++++++++++ python/pyspark/mllib/clustering.py | 1 + 4 files changed, 114 insertions(+) create mode 100644 examples/src/main/python/ml/bisecting_k_means_example.py create mode 100644 examples/src/main/python/mllib/bisecting_k_means_example.py diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md index 44720147be..6897ba4a5d 100644 --- a/docs/mllib-clustering.md +++ b/docs/mllib-clustering.md @@ -399,6 +399,12 @@ Refer to the [`BisectingKMeans` Java docs](api/java/org/apache/spark/mllib/clust {% include_example java/org/apache/spark/examples/mllib/JavaBisectingKMeansExample.java %} + +
+Refer to the [`BisectingKMeans` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.clustering.BisectingKMeans) and [`BisectingKMeansModel` Python docs](api/python/pyspark.mllib.html#pyspark.mllib.clustering.BisectingKMeansModel) for more details on the API. + +{% include_example python/mllib/bisecting_k_means_example.py %} +
## Streaming k-means diff --git a/examples/src/main/python/ml/bisecting_k_means_example.py b/examples/src/main/python/ml/bisecting_k_means_example.py new file mode 100644 index 0000000000..e6f6bfd7e8 --- /dev/null +++ b/examples/src/main/python/ml/bisecting_k_means_example.py @@ -0,0 +1,57 @@ +# +# 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.ml.clustering import BisectingKMeans, BisectingKMeansModel +from pyspark.mllib.linalg import VectorUDT, _convert_to_vector, Vectors +from pyspark.mllib.linalg import Vectors +from pyspark.sql.types import Row +# $example off$ +from pyspark.sql import SQLContext + +""" +A simple example demonstrating a bisecting k-means clustering. +""" + +if __name__ == "__main__": + + sc = SparkContext(appName="PythonBisectingKMeansExample") + sqlContext = SQLContext(sc) + + # $example on$ + data = sc.textFile("data/mllib/kmeans_data.txt") + parsed = data.map(lambda l: Row(features=Vectors.dense([float(x) for x in l.split(' ')]))) + training = sqlContext.createDataFrame(parsed) + + kmeans = BisectingKMeans().setK(2).setSeed(1).setFeaturesCol("features") + + model = kmeans.fit(training) + + # Evaluate clustering + cost = model.computeCost(training) + print("Bisecting K-means Cost = " + str(cost)) + + centers = model.clusterCenters() + print("Cluster Centers: ") + for center in centers: + print(center) + # $example off$ + + sc.stop() diff --git a/examples/src/main/python/mllib/bisecting_k_means_example.py b/examples/src/main/python/mllib/bisecting_k_means_example.py new file mode 100644 index 0000000000..7f4d0402d6 --- /dev/null +++ b/examples/src/main/python/mllib/bisecting_k_means_example.py @@ -0,0 +1,50 @@ +# +# 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 + +# $example on$ +from numpy import array +# $example off$ + +from pyspark import SparkContext +# $example on$ +from pyspark.mllib.clustering import BisectingKMeans, BisectingKMeansModel +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonBisectingKMeansExample") # SparkContext + + # $example on$ + # Load and parse the data + data = sc.textFile("data/mllib/kmeans_data.txt") + parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')])) + + # Build the model (cluster the data) + model = BisectingKMeans.train(parsedData, 2, maxIterations=5) + + # Evaluate clustering + cost = model.computeCost(parsedData) + print("Bisecting K-means Cost = " + str(cost)) + + # Save and load model + path = "target/org/apache/spark/PythonBisectingKMeansExample/BisectingKMeansModel" + model.save(sc, path) + sameModel = BisectingKMeansModel.load(sc, path) + # $example off$ + + sc.stop() diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py index 5a5bf59dd5..23d118bd40 100644 --- a/python/pyspark/mllib/clustering.py +++ b/python/pyspark/mllib/clustering.py @@ -142,6 +142,7 @@ class BisectingKMeans(object): .. versionadded:: 2.0.0 """ + @classmethod @since('2.0.0') def train(self, rdd, k=4, maxIterations=20, minDivisibleClusterSize=1.0, seed=-1888008604): """ -- cgit v1.2.3