ml/feature/JavaHashingTFSuite.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.Assert;
0024 import org.junit.Test;
0025
0026 import org.apache.spark.SharedSparkSession;
0027 import org.apache.spark.ml.linalg.Vector;
0028 import org.apache.spark.sql.Dataset;
0029 import org.apache.spark.sql.Row;
0030 import org.apache.spark.sql.RowFactory;
0031 import org.apache.spark.sql.types.DataTypes;
0032 import org.apache.spark.sql.types.Metadata;
0033 import org.apache.spark.sql.types.StructField;
0034 import org.apache.spark.sql.types.StructType;
0035
0036
0037 public class JavaHashingTFSuite extends SharedSparkSession {
0038
0039   @Test
0040   public void hashingTF() {
0041     List<Row> data = Arrays.asList(
0042       RowFactory.create(0.0, "Hi I heard about Spark"),
0043       RowFactory.create(0.0, "I wish Java could use case classes"),
0044       RowFactory.create(1.0, "Logistic regression models are neat")
0045     );
0046     StructType schema = new StructType(new StructField[]{
0047       new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
0048       new StructField("sentence", DataTypes.StringType, false, Metadata.empty())
0049     });
0050
0051     Dataset<Row> sentenceData = spark.createDataFrame(data, schema);
0052     Tokenizer tokenizer = new Tokenizer()
0053       .setInputCol("sentence")
0054       .setOutputCol("words");
0055     Dataset<Row> wordsData = tokenizer.transform(sentenceData);
0056     int numFeatures = 20;
0057     HashingTF hashingTF = new HashingTF()
0058       .setInputCol("words")
0059       .setOutputCol("rawFeatures")
0060       .setNumFeatures(numFeatures);
0061     Dataset<Row> featurizedData = hashingTF.transform(wordsData);
0062     IDF idf = new IDF().setInputCol("rawFeatures").setOutputCol("features");
0063     IDFModel idfModel = idf.fit(featurizedData);
0064     Dataset<Row> rescaledData = idfModel.transform(featurizedData);
0065     for (Row r : rescaledData.select("features", "label").takeAsList(3)) {
0066       Vector features = r.getAs(0);
0067       Assert.assertEquals(numFeatures, features.size());
0068     }
0069   }
0070 }