examples/ml/JavaQuantileDiscretizerExample.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.SparkSession;
0021 // $example on$
0022 import java.util.Arrays;
0023 import java.util.List;
0024
0025 import org.apache.spark.ml.feature.QuantileDiscretizer;
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.types.DataTypes;
0030 import org.apache.spark.sql.types.Metadata;
0031 import org.apache.spark.sql.types.StructField;
0032 import org.apache.spark.sql.types.StructType;
0033 // $example off$
0034
0035 public class JavaQuantileDiscretizerExample {
0036   public static void main(String[] args) {
0037     SparkSession spark = SparkSession
0038       .builder()
0039       .appName("JavaQuantileDiscretizerExample")
0040       .getOrCreate();
0041
0042     // $example on$
0043     List<Row> data = Arrays.asList(
0044       RowFactory.create(0, 18.0),
0045       RowFactory.create(1, 19.0),
0046       RowFactory.create(2, 8.0),
0047       RowFactory.create(3, 5.0),
0048       RowFactory.create(4, 2.2)
0049     );
0050
0051     StructType schema = new StructType(new StructField[]{
0052       new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
0053       new StructField("hour", DataTypes.DoubleType, false, Metadata.empty())
0054     });
0055
0056     Dataset<Row> df = spark.createDataFrame(data, schema);
0057     // $example off$
0058     // Output of QuantileDiscretizer for such small datasets can depend on the number of
0059     // partitions. Here we force a single partition to ensure consistent results.
0060     // Note this is not necessary for normal use cases
0061     df = df.repartition(1);
0062     // $example on$
0063     QuantileDiscretizer discretizer = new QuantileDiscretizer()
0064       .setInputCol("hour")
0065       .setOutputCol("result")
0066       .setNumBuckets(3);
0067
0068     Dataset<Row> result = discretizer.fit(df).transform(df);
0069     result.show(false);
0070     // $example off$
0071     spark.stop();
0072   }
0073 }