examples/ml/JavaNGramExample.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 import org.apache.spark.sql.Dataset;
0021 import org.apache.spark.sql.SparkSession;
0022
0023 // $example on$
0024 import java.util.Arrays;
0025 import java.util.List;
0026
0027 import org.apache.spark.ml.feature.NGram;
0028 import org.apache.spark.sql.Row;
0029 import org.apache.spark.sql.RowFactory;
0030 import org.apache.spark.sql.types.DataTypes;
0031 import org.apache.spark.sql.types.Metadata;
0032 import org.apache.spark.sql.types.StructField;
0033 import org.apache.spark.sql.types.StructType;
0034 // $example off$
0035
0036 public class JavaNGramExample {
0037   public static void main(String[] args) {
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaNGramExample")
0041       .getOrCreate();
0042
0043     // $example on$
0044     List<Row> data = Arrays.asList(
0045       RowFactory.create(0, Arrays.asList("Hi", "I", "heard", "about", "Spark")),
0046       RowFactory.create(1, Arrays.asList("I", "wish", "Java", "could", "use", "case", "classes")),
0047       RowFactory.create(2, Arrays.asList("Logistic", "regression", "models", "are", "neat"))
0048     );
0049
0050     StructType schema = new StructType(new StructField[]{
0051       new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
0052       new StructField(
0053         "words", DataTypes.createArrayType(DataTypes.StringType), false, Metadata.empty())
0054     });
0055
0056     Dataset<Row> wordDataFrame = spark.createDataFrame(data, schema);
0057
0058     NGram ngramTransformer = new NGram().setN(2).setInputCol("words").setOutputCol("ngrams");
0059
0060     Dataset<Row> ngramDataFrame = ngramTransformer.transform(wordDataFrame);
0061     ngramDataFrame.select("ngrams").show(false);
0062     // $example off$
0063
0064     spark.stop();
0065   }
0066 }