dbx.compute.spark.jobs.ml.JavaStopWordsRemoverExample.java Source code

Introduction

Here is the source code for dbx.compute.spark.jobs.ml.JavaStopWordsRemoverExample.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 dbx.compute.spark.jobs.ml;

import org.apache.spark.sql.SparkSession;

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

import org.apache.spark.ml.feature.StopWordsRemover;
import org.apache.spark.sql.Dataset;
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 JavaStopWordsRemoverExample {

    public static void main(String[] args) {
        SparkSession spark = SparkSession.builder().appName("JavaStopWordsRemoverExample").getOrCreate();

        // $example on$
        StopWordsRemover remover = new StopWordsRemover().setInputCol("raw").setOutputCol("filtered");

        List<Row> data = Arrays.asList(RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")),
                RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb")));

        StructType schema = new StructType(new StructField[] {
                new StructField("raw", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty()) });

        Dataset<Row> dataset = spark.createDataFrame(data, schema);
        remover.transform(dataset).show();
        // $example off$
        spark.stop();
    }
}