examples/ml/JavaCountVectorizerExample.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.CountVectorizer;
0025 import org.apache.spark.ml.feature.CountVectorizerModel;
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.SparkSession;
0030 import org.apache.spark.sql.types.*;
0031 // $example off$
0032
0033 public class JavaCountVectorizerExample {
0034   public static void main(String[] args) {
0035     SparkSession spark = SparkSession
0036       .builder()
0037       .appName("JavaCountVectorizerExample")
0038       .getOrCreate();
0039
0040     // $example on$
0041     // Input data: Each row is a bag of words from a sentence or document.
0042     List<Row> data = Arrays.asList(
0043       RowFactory.create(Arrays.asList("a", "b", "c")),
0044       RowFactory.create(Arrays.asList("a", "b", "b", "c", "a"))
0045     );
0046     StructType schema = new StructType(new StructField [] {
0047       new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())
0048     });
0049     Dataset<Row> df = spark.createDataFrame(data, schema);
0050
0051     // fit a CountVectorizerModel from the corpus
0052     CountVectorizerModel cvModel = new CountVectorizer()
0053       .setInputCol("text")
0054       .setOutputCol("feature")
0055       .setVocabSize(3)
0056       .setMinDF(2)
0057       .fit(df);
0058
0059     // alternatively, define CountVectorizerModel with a-priori vocabulary
0060     CountVectorizerModel cvm = new CountVectorizerModel(new String[]{"a", "b", "c"})
0061       .setInputCol("text")
0062       .setOutputCol("feature");
0063
0064     cvModel.transform(df).show(false);
0065     // $example off$
0066
0067     spark.stop();
0068   }
0069 }