org.apache.spark.examples.ml.BucketizerExample.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.ml

// $example on$
import org.apache.spark.ml.feature.Bucketizer
// $example off$
import org.apache.spark.sql.SparkSession
/**
 * An example for Bucketizer.
 * Run with
 * {{{
 * bin/run-example ml.BucketizerExample
 * }}}
 */
object BucketizerExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("BucketizerExample")
      .getOrCreate()

    // $example on$
    val splits = Array(Double.NegativeInfinity, -0.5, 0.0, 0.5, Double.PositiveInfinity)

    val data = Array(-999.9, -0.5, -0.3, 0.0, 0.2, 999.9)
    val dataFrame = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")

    val bucketizer = new Bucketizer()
      .setInputCol("features")
      .setOutputCol("bucketedFeatures")
      .setSplits(splits)

    // Transform original data into its bucket index.
    val bucketedData = bucketizer.transform(dataFrame)

    println(s"Bucketizer output with ${bucketizer.getSplits.length-1} buckets")
    bucketedData.show()
    // $example off$

    // $example on$
    val splitsArray = Array(
      Array(Double.NegativeInfinity, -0.5, 0.0, 0.5, Double.PositiveInfinity),
      Array(Double.NegativeInfinity, -0.3, 0.0, 0.3, Double.PositiveInfinity))

    val data2 = Array(
      (-999.9, -999.9),
      (-0.5, -0.2),
      (-0.3, -0.1),
      (0.0, 0.0),
      (0.2, 0.4),
      (999.9, 999.9))
    val dataFrame2 = spark.createDataFrame(data2).toDF("features1", "features2")

    val bucketizer2 = new Bucketizer()
      .setInputCols(Array("features1", "features2"))
      .setOutputCols(Array("bucketedFeatures1", "bucketedFeatures2"))
      .setSplitsArray(splitsArray)

    // Transform original data into its bucket index.
    val bucketedData2 = bucketizer2.transform(dataFrame2)

    println(s"Bucketizer output with [" +
      s"${bucketizer2.getSplitsArray(0).length-1}, " +
      s"${bucketizer2.getSplitsArray(1).length-1}] buckets for each input column")
    bucketedData2.show()
    // $example off$

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