org.apache.spark.examples.ml.MinMaxScalerExample.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.MinMaxScaler
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object MinMaxScalerExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("MinMaxScalerExample")
      .getOrCreate()

    // $example on$
    val dataFrame = spark.createDataFrame(Seq(
      (0, Vectors.dense(1.0, 0.1, -1.0)),
      (1, Vectors.dense(2.0, 1.1, 1.0)),
      (2, Vectors.dense(3.0, 10.1, 3.0))
    )).toDF("id", "features")

    val scaler = new MinMaxScaler()
      .setInputCol("features")
      .setOutputCol("scaledFeatures")

    // Compute summary statistics and generate MinMaxScalerModel
    val scalerModel = scaler.fit(dataFrame)

    // rescale each feature to range [min, max].
    val scaledData = scalerModel.transform(dataFrame)
    println(s"Features scaled to range: [${scaler.getMin}, ${scaler.getMax}]")
    scaledData.select("features", "scaledFeatures").show()
    // $example off$

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