examples/ml/JavaStopWordsRemoverExample.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.StopWordsRemover;
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.DataTypes;
0031 import org.apache.spark.sql.types.Metadata;
0032 import org.apache.spark.sql.types.StructField;
0033 import org.apache.spark.sql.types.StructType;
0034 // $example off$
0035
0036 public class JavaStopWordsRemoverExample {
0037
0038   public static void main(String[] args) {
0039     SparkSession spark = SparkSession
0040       .builder()
0041       .appName("JavaStopWordsRemoverExample")
0042       .getOrCreate();
0043
0044     // $example on$
0045     StopWordsRemover remover = new StopWordsRemover()
0046       .setInputCol("raw")
0047       .setOutputCol("filtered");
0048
0049     List<Row> data = Arrays.asList(
0050       RowFactory.create(Arrays.asList("I", "saw", "the", "red", "balloon")),
0051       RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb"))
0052     );
0053
0054     StructType schema = new StructType(new StructField[]{
0055       new StructField(
0056         "raw", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty())
0057     });
0058
0059     Dataset<Row> dataset = spark.createDataFrame(data, schema);
0060     remover.transform(dataset).show(false);
0061     // $example off$
0062     spark.stop();
0063   }
0064 }