org.apache.spark.examples.mllib.GaussianMixtureExample.scala Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 2.1.3.2

Show newest version

/*
 * 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.
 */

// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.clustering.{GaussianMixture, GaussianMixtureModel}
import org.apache.spark.mllib.linalg.Vectors
// $example off$

object GaussianMixtureExample {

  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("GaussianMixtureExample")
    val sc = new SparkContext(conf)

    // $example on$
    // Load and parse the data
    val data = sc.textFile("data/mllib/gmm_data.txt")
    val parsedData = data.map(s => Vectors.dense(s.trim.split(' ').map(_.toDouble))).cache()

    // Cluster the data into two classes using GaussianMixture
    val gmm = new GaussianMixture().setK(2).run(parsedData)

    // Save and load model
    gmm.save(sc, "target/org/apache/spark/GaussianMixtureExample/GaussianMixtureModel")
    val sameModel = GaussianMixtureModel.load(sc,
      "target/org/apache/spark/GaussianMixtureExample/GaussianMixtureModel")

    // output parameters of max-likelihood model
    for (i <- 0 until gmm.k) {
      println("weight=%f\nmu=%s\nsigma=\n%s\n" format
        (gmm.weights(i), gmm.gaussians(i).mu, gmm.gaussians(i).sigma))
    }
    // $example off$

    sc.stop()
  }
}
// scalastyle:on println