examples/ml/JavaDecisionTreeRegressionExample.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 // scalastyle:off println
0018 package org.apache.spark.examples.ml;
0019 // $example on$
0020 import org.apache.spark.ml.Pipeline;
0021 import org.apache.spark.ml.PipelineModel;
0022 import org.apache.spark.ml.PipelineStage;
0023 import org.apache.spark.ml.evaluation.RegressionEvaluator;
0024 import org.apache.spark.ml.feature.VectorIndexer;
0025 import org.apache.spark.ml.feature.VectorIndexerModel;
0026 import org.apache.spark.ml.regression.DecisionTreeRegressionModel;
0027 import org.apache.spark.ml.regression.DecisionTreeRegressor;
0028 import org.apache.spark.sql.Dataset;
0029 import org.apache.spark.sql.Row;
0030 import org.apache.spark.sql.SparkSession;
0031 // $example off$
0032
0033 public class JavaDecisionTreeRegressionExample {
0034   public static void main(String[] args) {
0035     SparkSession spark = SparkSession
0036       .builder()
0037       .appName("JavaDecisionTreeRegressionExample")
0038       .getOrCreate();
0039     // $example on$
0040     // Load the data stored in LIBSVM format as a DataFrame.
0041     Dataset<Row> data = spark.read().format("libsvm")
0042       .load("data/mllib/sample_libsvm_data.txt");
0043
0044     // Automatically identify categorical features, and index them.
0045     // Set maxCategories so features with > 4 distinct values are treated as continuous.
0046     VectorIndexerModel featureIndexer = new VectorIndexer()
0047       .setInputCol("features")
0048       .setOutputCol("indexedFeatures")
0049       .setMaxCategories(4)
0050       .fit(data);
0051
0052     // Split the data into training and test sets (30% held out for testing).
0053     Dataset<Row>[] splits = data.randomSplit(new double[]{0.7, 0.3});
0054     Dataset<Row> trainingData = splits[0];
0055     Dataset<Row> testData = splits[1];
0056
0057     // Train a DecisionTree model.
0058     DecisionTreeRegressor dt = new DecisionTreeRegressor()
0059       .setFeaturesCol("indexedFeatures");
0060
0061     // Chain indexer and tree in a Pipeline.
0062     Pipeline pipeline = new Pipeline()
0063       .setStages(new PipelineStage[]{featureIndexer, dt});
0064
0065     // Train model. This also runs the indexer.
0066     PipelineModel model = pipeline.fit(trainingData);
0067
0068     // Make predictions.
0069     Dataset<Row> predictions = model.transform(testData);
0070
0071     // Select example rows to display.
0072     predictions.select("label", "features").show(5);
0073
0074     // Select (prediction, true label) and compute test error.
0075     RegressionEvaluator evaluator = new RegressionEvaluator()
0076       .setLabelCol("label")
0077       .setPredictionCol("prediction")
0078       .setMetricName("rmse");
0079     double rmse = evaluator.evaluate(predictions);
0080     System.out.println("Root Mean Squared Error (RMSE) on test data = " + rmse);
0081
0082     DecisionTreeRegressionModel treeModel =
0083       (DecisionTreeRegressionModel) (model.stages()[1]);
0084     System.out.println("Learned regression tree model:\n" + treeModel.toDebugString());
0085     // $example off$
0086
0087     spark.stop();
0088   }
0089 }