diff options
Diffstat (limited to 'examples')
3 files changed, 170 insertions, 0 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaGaussianMixtureExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaGaussianMixtureExample.java new file mode 100644 index 0000000000..79b9909581 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaGaussianMixtureExample.java @@ -0,0 +1,64 @@ +/* + * 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. + */ + +package org.apache.spark.examples.ml; + +// $example on$ +import org.apache.spark.ml.clustering.GaussianMixture; +import org.apache.spark.ml.clustering.GaussianMixtureModel; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +// $example off$ +import org.apache.spark.sql.SparkSession; + + +/** + * An example demonstrating Gaussian Mixture Model. + * Run with + * <pre> + * bin/run-example ml.JavaGaussianMixtureExample + * </pre> + */ +public class JavaGaussianMixtureExample { + + public static void main(String[] args) { + + // Creates a SparkSession + SparkSession spark = SparkSession + .builder() + .appName("JavaGaussianMixtureExample") + .getOrCreate(); + + // $example on$ + // Loads data + Dataset<Row> dataset = spark.read().format("libsvm").load("data/mllib/sample_kmeans_data.txt"); + + // Trains a GaussianMixture model + GaussianMixture gmm = new GaussianMixture() + .setK(2); + GaussianMixtureModel model = gmm.fit(dataset); + + // Output the parameters of the mixture model + for (int i = 0; i < model.getK(); i++) { + System.out.printf("weight=%f\nmu=%s\nsigma=\n%s\n", + model.weights()[i], model.gaussians()[i].mean(), model.gaussians()[i].cov()); + } + // $example off$ + + spark.stop(); + } +} diff --git a/examples/src/main/python/ml/gaussian_mixture_example.py b/examples/src/main/python/ml/gaussian_mixture_example.py new file mode 100644 index 0000000000..2ca13d68f6 --- /dev/null +++ b/examples/src/main/python/ml/gaussian_mixture_example.py @@ -0,0 +1,48 @@ +# +# 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 pyspark.ml.clustering import GaussianMixture +# $example off$ +from pyspark.sql import SparkSession + +""" +A simple example demonstrating Gaussian Mixture Model (GMM). +Run with: + bin/spark-submit examples/src/main/python/ml/gaussian_mixture_example.py +""" + +if __name__ == "__main__": + spark = SparkSession\ + .builder\ + .appName("PythonGuassianMixtureExample")\ + .getOrCreate() + + # $example on$ + # loads data + dataset = spark.read.format("libsvm").load("data/mllib/sample_kmeans_data.txt") + + gmm = GaussianMixture().setK(2) + model = gmm.fit(dataset) + + print("Gaussians: ") + model.gaussiansDF.show() + # $example off$ + + spark.stop() diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/GaussianMixtureExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/GaussianMixtureExample.scala new file mode 100644 index 0000000000..c484ee5556 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/GaussianMixtureExample.scala @@ -0,0 +1,58 @@ +/* + * 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. + */ + +package org.apache.spark.examples.ml + +// scalastyle:off println + +// $example on$ +import org.apache.spark.ml.clustering.GaussianMixture +import org.apache.spark.sql.SparkSession +// $example off$ + +/** + * An example demonstrating Gaussian Mixture Model (GMM). + * Run with + * {{{ + * bin/run-example ml.GaussianMixtureExample + * }}} + */ +object GaussianMixtureExample { + def main(args: Array[String]): Unit = { + // Creates a SparkSession + val spark = SparkSession.builder.appName(s"${this.getClass.getSimpleName}").getOrCreate() + + // $example on$ + // Loads data + val dataset = spark.read.format("libsvm").load("data/mllib/sample_kmeans_data.txt") + + // Trains Gaussian Mixture Model + val gmm = new GaussianMixture() + .setK(2) + val model = gmm.fit(dataset) + + // output parameters of mixture model model + for (i <- 0 until model.getK) { + println("weight=%f\nmu=%s\nsigma=\n%s\n" format + (model.weights(i), model.gaussians(i).mean, model.gaussians(i).cov)) + } + // $example off$ + + spark.stop() + } +} +// scalastyle:on println |