examples/ml/JavaOneHotEncoderExample.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.feature.OneHotEncoder;
0027 import org.apache.spark.ml.feature.OneHotEncoderModel;
0028 import org.apache.spark.sql.Dataset;
0029 import org.apache.spark.sql.Row;
0030 import org.apache.spark.sql.RowFactory;
0031 import org.apache.spark.sql.types.DataTypes;
0032 import org.apache.spark.sql.types.Metadata;
0033 import org.apache.spark.sql.types.StructField;
0034 import org.apache.spark.sql.types.StructType;
0035 // $example off$
0036
0037 public class JavaOneHotEncoderExample {
0038   public static void main(String[] args) {
0039     SparkSession spark = SparkSession
0040       .builder()
0041       .appName("JavaOneHotEncoderExample")
0042       .getOrCreate();
0043
0044     // Note: categorical features are usually first encoded with StringIndexer
0045     // $example on$
0046     List<Row> data = Arrays.asList(
0047       RowFactory.create(0.0, 1.0),
0048       RowFactory.create(1.0, 0.0),
0049       RowFactory.create(2.0, 1.0),
0050       RowFactory.create(0.0, 2.0),
0051       RowFactory.create(0.0, 1.0),
0052       RowFactory.create(2.0, 0.0)
0053     );
0054
0055     StructType schema = new StructType(new StructField[]{
0056       new StructField("categoryIndex1", DataTypes.DoubleType, false, Metadata.empty()),
0057       new StructField("categoryIndex2", DataTypes.DoubleType, false, Metadata.empty())
0058     });
0059
0060     Dataset<Row> df = spark.createDataFrame(data, schema);
0061
0062     OneHotEncoder encoder = new OneHotEncoder()
0063       .setInputCols(new String[] {"categoryIndex1", "categoryIndex2"})
0064       .setOutputCols(new String[] {"categoryVec1", "categoryVec2"});
0065
0066     OneHotEncoderModel model = encoder.fit(df);
0067     Dataset<Row> encoded = model.transform(df);
0068     encoded.show();
0069     // $example off$
0070
0071     spark.stop();
0072   }
0073 }
0074