ml/feature/JavaStandardScalerSuite.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.ml.feature;
0019
0020 import java.util.Arrays;
0021 import java.util.List;
0022
0023 import org.junit.Test;
0024
0025 import org.apache.spark.SharedSparkSession;
0026 import org.apache.spark.ml.linalg.Vectors;
0027 import org.apache.spark.sql.Dataset;
0028 import org.apache.spark.sql.Row;
0029
0030 public class JavaStandardScalerSuite extends SharedSparkSession {
0031
0032   @Test
0033   public void standardScaler() {
0034     // The tests are to check Java compatibility.
0035     List<VectorIndexerSuite.FeatureData> points = Arrays.asList(
0036       new VectorIndexerSuite.FeatureData(Vectors.dense(0.0, -2.0)),
0037       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 3.0)),
0038       new VectorIndexerSuite.FeatureData(Vectors.dense(1.0, 4.0))
0039     );
0040     Dataset<Row> dataFrame = spark.createDataFrame(jsc.parallelize(points, 2),
0041       VectorIndexerSuite.FeatureData.class);
0042     StandardScaler scaler = new StandardScaler()
0043       .setInputCol("features")
0044       .setOutputCol("scaledFeatures")
0045       .setWithStd(true)
0046       .setWithMean(false);
0047
0048     // Compute summary statistics by fitting the StandardScaler
0049     StandardScalerModel scalerModel = scaler.fit(dataFrame);
0050
0051     // Normalize each feature to have unit standard deviation.
0052     Dataset<Row> scaledData = scalerModel.transform(dataFrame);
0053     scaledData.count();
0054   }
0055 }