examples/ml/JavaRobustScalerExample.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.ml;
0019
0020 import org.apache.spark.sql.SparkSession;
0021
0022 // $example on$
0023 import org.apache.spark.ml.feature.RobustScaler;
0024 import org.apache.spark.ml.feature.RobustScalerModel;
0025 import org.apache.spark.sql.Dataset;
0026 import org.apache.spark.sql.Row;
0027 // $example off$
0028
0029 public class JavaRobustScalerExample {
0030   public static void main(String[] args) {
0031     SparkSession spark = SparkSession
0032       .builder()
0033       .appName("JavaRobustScalerExample")
0034       .getOrCreate();
0035
0036     // $example on$
0037     Dataset<Row> dataFrame =
0038       spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
0039
0040     RobustScaler scaler = new RobustScaler()
0041       .setInputCol("features")
0042       .setOutputCol("scaledFeatures")
0043       .setWithScaling(true)
0044       .setWithCentering(false)
0045       .setLower(0.25)
0046       .setUpper(0.75);
0047
0048     // Compute summary statistics by fitting the RobustScaler
0049     RobustScalerModel scalerModel = scaler.fit(dataFrame);
0050
0051     // Transform each feature to have unit quantile range.
0052     Dataset<Row> scaledData = scalerModel.transform(dataFrame);
0053     scaledData.show();
0054     // $example off$
0055     spark.stop();
0056   }
0057 }