examples/ml/JavaVectorIndexerExample.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.Map;
0024
0025 import org.apache.spark.ml.feature.VectorIndexer;
0026 import org.apache.spark.ml.feature.VectorIndexerModel;
0027 import org.apache.spark.sql.Dataset;
0028 import org.apache.spark.sql.Row;
0029 // $example off$
0030
0031 public class JavaVectorIndexerExample {
0032   public static void main(String[] args) {
0033     SparkSession spark = SparkSession
0034       .builder()
0035       .appName("JavaVectorIndexerExample")
0036       .getOrCreate();
0037
0038     // $example on$
0039     Dataset<Row> data = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
0040
0041     VectorIndexer indexer = new VectorIndexer()
0042       .setInputCol("features")
0043       .setOutputCol("indexed")
0044       .setMaxCategories(10);
0045     VectorIndexerModel indexerModel = indexer.fit(data);
0046
0047     Map<Integer, Map<Double, Integer>> categoryMaps = indexerModel.javaCategoryMaps();
0048     System.out.print("Chose " + categoryMaps.size() + " categorical features:");
0049
0050     for (Integer feature : categoryMaps.keySet()) {
0051       System.out.print(" " + feature);
0052     }
0053     System.out.println();
0054
0055     // Create new column "indexed" with categorical values transformed to indices
0056     Dataset<Row> indexedData = indexerModel.transform(data);
0057     indexedData.show();
0058     // $example off$
0059     spark.stop();
0060   }
0061 }