examples/ml/JavaVectorSlicerExample.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 java.util.Arrays;
0024 import java.util.List;
0025
0026 import org.apache.spark.ml.attribute.Attribute;
0027 import org.apache.spark.ml.attribute.AttributeGroup;
0028 import org.apache.spark.ml.attribute.NumericAttribute;
0029 import org.apache.spark.ml.feature.VectorSlicer;
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.*;
0035 // $example off$
0036
0037 public class JavaVectorSlicerExample {
0038   public static void main(String[] args) {
0039     SparkSession spark = SparkSession
0040       .builder()
0041       .appName("JavaVectorSlicerExample")
0042       .getOrCreate();
0043
0044     // $example on$
0045     Attribute[] attrs = {
0046       NumericAttribute.defaultAttr().withName("f1"),
0047       NumericAttribute.defaultAttr().withName("f2"),
0048       NumericAttribute.defaultAttr().withName("f3")
0049     };
0050     AttributeGroup group = new AttributeGroup("userFeatures", attrs);
0051
0052     List<Row> data = Arrays.asList(
0053       RowFactory.create(Vectors.sparse(3, new int[]{0, 1}, new double[]{-2.0, 2.3})),
0054       RowFactory.create(Vectors.dense(-2.0, 2.3, 0.0))
0055     );
0056
0057     Dataset<Row> dataset =
0058       spark.createDataFrame(data, (new StructType()).add(group.toStructField()));
0059
0060     VectorSlicer vectorSlicer = new VectorSlicer()
0061       .setInputCol("userFeatures").setOutputCol("features");
0062
0063     vectorSlicer.setIndices(new int[]{1}).setNames(new String[]{"f3"});
0064     // or slicer.setIndices(new int[]{1, 2}), or slicer.setNames(new String[]{"f2", "f3"})
0065
0066     Dataset<Row> output = vectorSlicer.transform(dataset);
0067     output.show(false);
0068     // $example off$
0069
0070     spark.stop();
0071   }
0072 }
0073