ml/feature/JavaStopWordsRemoverSuite.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.ml.feature;
0019
0020 import java.util.Arrays;
0021 import java.util.List;
0022
0023 import org.junit.Test;
0024
0025 import org.apache.spark.SharedSparkSession;
0026 import org.apache.spark.sql.Dataset;
0027 import org.apache.spark.sql.Row;
0028 import org.apache.spark.sql.RowFactory;
0029 import org.apache.spark.sql.types.DataTypes;
0030 import org.apache.spark.sql.types.Metadata;
0031 import org.apache.spark.sql.types.StructField;
0032 import org.apache.spark.sql.types.StructType;
0033
0034
0035 public class JavaStopWordsRemoverSuite extends SharedSparkSession {
0036
0037   @Test
0038   public void javaCompatibilityTest() {
0039     StopWordsRemover remover = new StopWordsRemover()
0040       .setInputCol("raw")
0041       .setOutputCol("filtered");
0042
0043     List<Row> data = Arrays.asList(
0044       RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")),
0045       RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb"))
0046     );
0047     StructType schema = new StructType(new StructField[]{
0048       new StructField("raw", DataTypes.createArrayType(DataTypes.StringType), false,
0049         Metadata.empty())
0050     });
0051     Dataset<Row> dataset = spark.createDataFrame(data, schema);
0052
0053     remover.transform(dataset).collect();
0054   }
0055 }