ml/stat/JavaSummarizerSuite.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.stat;
0019
0020 import java.io.IOException;
0021 import java.util.ArrayList;
0022 import java.util.List;
0023
0024 import org.junit.Test;
0025 import static org.junit.Assert.assertEquals;
0026 import static org.junit.Assert.assertArrayEquals;
0027
0028 import org.apache.spark.SharedSparkSession;
0029 import org.apache.spark.sql.Row;
0030 import org.apache.spark.sql.Dataset;
0031 import static org.apache.spark.sql.functions.col;
0032 import org.apache.spark.ml.feature.LabeledPoint;
0033 import org.apache.spark.ml.linalg.Vector;
0034 import org.apache.spark.ml.linalg.Vectors;
0035
0036 public class JavaSummarizerSuite extends SharedSparkSession {
0037
0038   private transient Dataset<Row> dataset;
0039
0040   @Override
0041   public void setUp() throws IOException {
0042     super.setUp();
0043     List<LabeledPoint> points = new ArrayList<>();
0044     points.add(new LabeledPoint(0.0, Vectors.dense(1.0, 2.0)));
0045     points.add(new LabeledPoint(0.0, Vectors.dense(3.0, 4.0)));
0046
0047     dataset = spark.createDataFrame(jsc.parallelize(points, 2), LabeledPoint.class);
0048   }
0049
0050   @Test
0051   public void testSummarizer() {
0052     dataset.select(col("features"));
0053     Row result = dataset
0054       .select(Summarizer.metrics("mean", "max", "count").summary(col("features")))
0055       .first().getStruct(0);
0056     Vector meanVec = result.getAs("mean");
0057     Vector maxVec = result.getAs("max");
0058     long count = result.getAs("count");
0059
0060     assertEquals(2L, count);
0061     assertArrayEquals(new double[]{2.0, 3.0}, meanVec.toArray(), 0.0);
0062     assertArrayEquals(new double[]{3.0, 4.0}, maxVec.toArray(), 0.0);
0063   }
0064 }