org.apache.spark.examples.ml.JavaStringIndexerExample Maven / Gradle / Ivy
The newest version!
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.examples.ml;
import org.apache.spark.sql.SparkSession;
// $example on$
import java.util.Arrays;
import java.util.List;
import org.apache.spark.ml.feature.StringIndexer;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import static org.apache.spark.sql.types.DataTypes.*;
// $example off$
public class JavaStringIndexerExample {
public static void main(String[] args) {
SparkSession spark = SparkSession
.builder()
.appName("JavaStringIndexerExample")
.getOrCreate();
// $example on$
List data = Arrays.asList(
RowFactory.create(0, "a"),
RowFactory.create(1, "b"),
RowFactory.create(2, "c"),
RowFactory.create(3, "a"),
RowFactory.create(4, "a"),
RowFactory.create(5, "c")
);
StructType schema = new StructType(new StructField[]{
createStructField("id", IntegerType, false),
createStructField("category", StringType, false)
});
Dataset df = spark.createDataFrame(data, schema);
StringIndexer indexer = new StringIndexer()
.setInputCol("category")
.setOutputCol("categoryIndex");
Dataset indexed = indexer.fit(df).transform(df);
indexed.show();
// $example off$
spark.stop();
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy