examples/ml/JavaFeatureHasherExample.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.FeatureHasher;
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 JavaFeatureHasherExample {
0037   public static void main(String[] args) {
0038     SparkSession spark = SparkSession
0039       .builder()
0040       .appName("JavaFeatureHasherExample")
0041       .getOrCreate();
0042
0043     // $example on$
0044     List<Row> data = Arrays.asList(
0045       RowFactory.create(2.2, true, "1", "foo"),
0046       RowFactory.create(3.3, false, "2", "bar"),
0047       RowFactory.create(4.4, false, "3", "baz"),
0048       RowFactory.create(5.5, false, "4", "foo")
0049     );
0050     StructType schema = new StructType(new StructField[]{
0051       new StructField("real", DataTypes.DoubleType, false, Metadata.empty()),
0052       new StructField("bool", DataTypes.BooleanType, false, Metadata.empty()),
0053       new StructField("stringNum", DataTypes.StringType, false, Metadata.empty()),
0054       new StructField("string", DataTypes.StringType, false, Metadata.empty())
0055     });
0056     Dataset<Row> dataset = spark.createDataFrame(data, schema);
0057
0058     FeatureHasher hasher = new FeatureHasher()
0059       .setInputCols(new String[]{"real", "bool", "stringNum", "string"})
0060       .setOutputCol("features");
0061
0062     Dataset<Row> featurized = hasher.transform(dataset);
0063
0064     featurized.show(false);
0065     // $example off$
0066
0067     spark.stop();
0068   }
0069 }