examples/ml/JavaTfIdfExample.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 // $example on$
0021 import java.util.Arrays;
0022 import java.util.List;
0023
0024 import org.apache.spark.ml.feature.HashingTF;
0025 import org.apache.spark.ml.feature.IDF;
0026 import org.apache.spark.ml.feature.IDFModel;
0027 import org.apache.spark.ml.feature.Tokenizer;
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.SparkSession;
0032 import org.apache.spark.sql.types.DataTypes;
0033 import org.apache.spark.sql.types.Metadata;
0034 import org.apache.spark.sql.types.StructField;
0035 import org.apache.spark.sql.types.StructType;
0036 // $example off$
0037
0038 public class JavaTfIdfExample {
0039   public static void main(String[] args) {
0040     SparkSession spark = SparkSession
0041       .builder()
0042       .appName("JavaTfIdfExample")
0043       .getOrCreate();
0044
0045     // $example on$
0046     List<Row> data = Arrays.asList(
0047       RowFactory.create(0.0, "Hi I heard about Spark"),
0048       RowFactory.create(0.0, "I wish Java could use case classes"),
0049       RowFactory.create(1.0, "Logistic regression models are neat")
0050     );
0051     StructType schema = new StructType(new StructField[]{
0052       new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
0053       new StructField("sentence", DataTypes.StringType, false, Metadata.empty())
0054     });
0055     Dataset<Row> sentenceData = spark.createDataFrame(data, schema);
0056
0057     Tokenizer tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words");
0058     Dataset<Row> wordsData = tokenizer.transform(sentenceData);
0059
0060     int numFeatures = 20;
0061     HashingTF hashingTF = new HashingTF()
0062       .setInputCol("words")
0063       .setOutputCol("rawFeatures")
0064       .setNumFeatures(numFeatures);
0065
0066     Dataset<Row> featurizedData = hashingTF.transform(wordsData);
0067     // alternatively, CountVectorizer can also be used to get term frequency vectors
0068
0069     IDF idf = new IDF().setInputCol("rawFeatures").setOutputCol("features");
0070     IDFModel idfModel = idf.fit(featurizedData);
0071
0072     Dataset<Row> rescaledData = idfModel.transform(featurizedData);
0073     rescaledData.select("label", "features").show();
0074     // $example off$
0075
0076     spark.stop();
0077   }
0078 }