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

Go to download

Show more of this group Show more artifacts with this name
Show all versions of spark-examples_2.12 Show documentation

The 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.
 */

package org.apache.spark.examples.ml

// scalastyle:off println

// $example on$
import org.apache.spark.ml.clustering.GaussianMixture
// $example off$
import org.apache.spark.sql.SparkSession

/**
 * An example demonstrating Gaussian Mixture Model (GMM).
 * Run with
 * {{{
 * bin/run-example ml.GaussianMixtureExample
 * }}}
 */
object GaussianMixtureExample {
  def main(args: Array[String]): Unit = {
    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(s"Gaussian $i:\nweight=${model.weights(i)}\n" +
          s"mu=${model.gaussians(i).mean}\nsigma=\n${model.gaussians(i).cov}\n")
    }
    // $example off$

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