ml/feature/JavaVectorAssemblerSuite.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
0022 import static org.apache.spark.sql.types.DataTypes.*;
0023
0024 import org.junit.Assert;
0025 import org.junit.Test;
0026
0027 import org.apache.spark.SharedSparkSession;
0028 import org.apache.spark.ml.linalg.Vector;
0029 import org.apache.spark.ml.linalg.VectorUDT;
0030 import org.apache.spark.ml.linalg.Vectors;
0031 import org.apache.spark.sql.Dataset;
0032 import org.apache.spark.sql.Row;
0033 import org.apache.spark.sql.RowFactory;
0034 import org.apache.spark.sql.types.StructField;
0035 import org.apache.spark.sql.types.StructType;
0036
0037 public class JavaVectorAssemblerSuite extends SharedSparkSession {
0038
0039   @Test
0040   public void testVectorAssembler() {
0041     StructType schema = createStructType(new StructField[]{
0042       createStructField("id", IntegerType, false),
0043       createStructField("x", DoubleType, false),
0044       createStructField("y", new VectorUDT(), false),
0045       createStructField("name", StringType, false),
0046       createStructField("z", new VectorUDT(), false),
0047       createStructField("n", LongType, false)
0048     });
0049     Row row = RowFactory.create(
0050       0, 0.0, Vectors.dense(1.0, 2.0), "a",
0051       Vectors.sparse(2, new int[]{1}, new double[]{3.0}), 10L);
0052     Dataset<Row> dataset = spark.createDataFrame(Arrays.asList(row), schema);
0053     VectorAssembler assembler = new VectorAssembler()
0054       .setInputCols(new String[]{"x", "y", "z", "n"})
0055       .setOutputCol("features");
0056     Dataset<Row> output = assembler.transform(dataset);
0057     Assert.assertEquals(
0058       Vectors.sparse(6, new int[]{1, 2, 4, 5}, new double[]{1.0, 2.0, 3.0, 10.0}),
0059       output.select("features").first().<Vector>getAs(0));
0060   }
0061 }