org.apache.spark.examples.mllib.HypothesisTestingKolmogorovSmirnovTestExample.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.
 */

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

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.stat.Statistics
import org.apache.spark.rdd.RDD
// $example off$

object HypothesisTestingKolmogorovSmirnovTestExample {

  def main(args: Array[String]): Unit = {

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

    // $example on$
    val data: RDD[Double] = sc.parallelize(Seq(0.1, 0.15, 0.2, 0.3, 0.25))  // an RDD of sample data

    // run a KS test for the sample versus a standard normal distribution
    val testResult = Statistics.kolmogorovSmirnovTest(data, "norm", 0, 1)
    // summary of the test including the p-value, test statistic, and null hypothesis if our p-value
    // indicates significance, we can reject the null hypothesis.
    println(testResult)
    println()

    // perform a KS test using a cumulative distribution function of our making
    val myCDF = Map(0.1 -> 0.2, 0.15 -> 0.6, 0.2 -> 0.05, 0.3 -> 0.05, 0.25 -> 0.1)
    val testResult2 = Statistics.kolmogorovSmirnovTest(data, myCDF)
    println(testResult2)
    // $example off$

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