com.sdw.dream.spark.examples.ml.JavaBucketizerExample.java Source code

Introduction

Here is the source code for com.sdw.dream.spark.examples.ml.JavaBucketizerExample.java

Source

/*
 * 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 com.sdw.dream.spark.examples.ml;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.SQLContext;

// $example on$
import java.util.Arrays;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.ml.feature.Bucketizer;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
// $example off$

public class JavaBucketizerExample {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("JavaBucketizerExample");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        SQLContext jsql = new SQLContext(jsc);

        // $example on$
        double[] splits = { Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY };

        JavaRDD<Row> data = jsc.parallelize(Arrays.asList(RowFactory.create(-0.5), RowFactory.create(-0.3),
                RowFactory.create(0.0), RowFactory.create(0.2)));
        StructType schema = new StructType(
                new StructField[] { new StructField("features", DataTypes.DoubleType, false, Metadata.empty()) });
        DataFrame dataFrame = jsql.createDataFrame(data, schema);

        Bucketizer bucketizer = new Bucketizer().setInputCol("features").setOutputCol("bucketedFeatures")
                .setSplits(splits);

        // Transform original data into its bucket index.
        DataFrame bucketedData = bucketizer.transform(dataFrame);
        bucketedData.show();
        // $example off$
        jsc.stop();
    }
}