examples/ml/JavaStringIndexerExample.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.StringIndexer;
0027 import org.apache.spark.sql.Dataset;
0028 import org.apache.spark.sql.Row;
0029 import org.apache.spark.sql.RowFactory;
0030 import org.apache.spark.sql.types.StructField;
0031 import org.apache.spark.sql.types.StructType;
0032
0033 import static org.apache.spark.sql.types.DataTypes.*;
0034 // $example off$
0035
0036 public class JavaStringIndexerExample {
0037   public static void main(String[] args) {
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaStringIndexerExample")
0041       .getOrCreate();
0042
0043     // $example on$
0044     List<Row> data = Arrays.asList(
0045       RowFactory.create(0, "a"),
0046       RowFactory.create(1, "b"),
0047       RowFactory.create(2, "c"),
0048       RowFactory.create(3, "a"),
0049       RowFactory.create(4, "a"),
0050       RowFactory.create(5, "c")
0051     );
0052     StructType schema = new StructType(new StructField[]{
0053       createStructField("id", IntegerType, false),
0054       createStructField("category", StringType, false)
0055     });
0056     Dataset<Row> df = spark.createDataFrame(data, schema);
0057
0058     StringIndexer indexer = new StringIndexer()
0059       .setInputCol("category")
0060       .setOutputCol("categoryIndex");
0061
0062     Dataset<Row> indexed = indexer.fit(df).transform(df);
0063     indexed.show();
0064     // $example off$
0065
0066     spark.stop();
0067   }
0068 }