examples/ml/JavaWord2VecExample.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.Word2Vec;
0025 import org.apache.spark.ml.feature.Word2VecModel;
0026 import org.apache.spark.ml.linalg.Vector;
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.SparkSession;
0031 import org.apache.spark.sql.types.*;
0032 // $example off$
0033
0034 public class JavaWord2VecExample {
0035   public static void main(String[] args) {
0036     SparkSession spark = SparkSession
0037       .builder()
0038       .appName("JavaWord2VecExample")
0039       .getOrCreate();
0040
0041     // $example on$
0042     // Input data: Each row is a bag of words from a sentence or document.
0043     List<Row> data = Arrays.asList(
0044       RowFactory.create(Arrays.asList("Hi I heard about Spark".split(" "))),
0045       RowFactory.create(Arrays.asList("I wish Java could use case classes".split(" "))),
0046       RowFactory.create(Arrays.asList("Logistic regression models are neat".split(" ")))
0047     );
0048     StructType schema = new StructType(new StructField[]{
0049       new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())
0050     });
0051     Dataset<Row> documentDF = spark.createDataFrame(data, schema);
0052
0053     // Learn a mapping from words to Vectors.
0054     Word2Vec word2Vec = new Word2Vec()
0055       .setInputCol("text")
0056       .setOutputCol("result")
0057       .setVectorSize(3)
0058       .setMinCount(0);
0059
0060     Word2VecModel model = word2Vec.fit(documentDF);
0061     Dataset<Row> result = model.transform(documentDF);
0062
0063     for (Row row : result.collectAsList()) {
0064       List<String> text = row.getList(0);
0065       Vector vector = (Vector) row.get(1);
0066       System.out.println("Text: " + text + " => \nVector: " + vector + "\n");
0067     }
0068     // $example off$
0069
0070     spark.stop();
0071   }
0072 }