org.apache.spark.examples.ml.NormalizerExample.scala Maven / Gradle / Ivy
/*
* 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.Normalizer
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession
object NormalizerExample {
def main(args: Array[String]): Unit = {
val spark = SparkSession
.builder
.appName("NormalizerExample")
.getOrCreate()
// $example on$
val dataFrame = spark.createDataFrame(Seq(
(0, Vectors.dense(1.0, 0.5, -1.0)),
(1, Vectors.dense(2.0, 1.0, 1.0)),
(2, Vectors.dense(4.0, 10.0, 2.0))
)).toDF("id", "features")
// Normalize each Vector using $L^1$ norm.
val normalizer = new Normalizer()
.setInputCol("features")
.setOutputCol("normFeatures")
.setP(1.0)
val l1NormData = normalizer.transform(dataFrame)
println("Normalized using L^1 norm")
l1NormData.show()
// Normalize each Vector using $L^\infty$ norm.
val lInfNormData = normalizer.transform(dataFrame, normalizer.p -> Double.PositiveInfinity)
println("Normalized using L^inf norm")
lInfNormData.show()
// $example off$
spark.stop()
}
}
// scalastyle:on println
© 2015 - 2025 Weber Informatics LLC | Privacy Policy