examples/ml/JavaRandomForestRegressorExample.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 org.apache.spark.ml.Pipeline;
0022 import org.apache.spark.ml.PipelineModel;
0023 import org.apache.spark.ml.PipelineStage;
0024 import org.apache.spark.ml.evaluation.RegressionEvaluator;
0025 import org.apache.spark.ml.feature.VectorIndexer;
0026 import org.apache.spark.ml.feature.VectorIndexerModel;
0027 import org.apache.spark.ml.regression.RandomForestRegressionModel;
0028 import org.apache.spark.ml.regression.RandomForestRegressor;
0029 import org.apache.spark.sql.Dataset;
0030 import org.apache.spark.sql.Row;
0031 import org.apache.spark.sql.SparkSession;
0032 // $example off$
0033
0034 public class JavaRandomForestRegressorExample {
0035   public static void main(String[] args) {
0036     SparkSession spark = SparkSession
0037       .builder()
0038       .appName("JavaRandomForestRegressorExample")
0039       .getOrCreate();
0040
0041     // $example on$
0042     // Load and parse the data file, converting it to a DataFrame.
0043     Dataset<Row> data = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
0044
0045     // Automatically identify categorical features, and index them.
0046     // Set maxCategories so features with > 4 distinct values are treated as continuous.
0047     VectorIndexerModel featureIndexer = new VectorIndexer()
0048       .setInputCol("features")
0049       .setOutputCol("indexedFeatures")
0050       .setMaxCategories(4)
0051       .fit(data);
0052
0053     // Split the data into training and test sets (30% held out for testing)
0054     Dataset<Row>[] splits = data.randomSplit(new double[] {0.7, 0.3});
0055     Dataset<Row> trainingData = splits[0];
0056     Dataset<Row> testData = splits[1];
0057
0058     // Train a RandomForest model.
0059     RandomForestRegressor rf = new RandomForestRegressor()
0060       .setLabelCol("label")
0061       .setFeaturesCol("indexedFeatures");
0062
0063     // Chain indexer and forest in a Pipeline
0064     Pipeline pipeline = new Pipeline()
0065       .setStages(new PipelineStage[] {featureIndexer, rf});
0066
0067     // Train model. This also runs the indexer.
0068     PipelineModel model = pipeline.fit(trainingData);
0069
0070     // Make predictions.
0071     Dataset<Row> predictions = model.transform(testData);
0072
0073     // Select example rows to display.
0074     predictions.select("prediction", "label", "features").show(5);
0075
0076     // Select (prediction, true label) and compute test error
0077     RegressionEvaluator evaluator = new RegressionEvaluator()
0078       .setLabelCol("label")
0079       .setPredictionCol("prediction")
0080       .setMetricName("rmse");
0081     double rmse = evaluator.evaluate(predictions);
0082     System.out.println("Root Mean Squared Error (RMSE) on test data = " + rmse);
0083
0084     RandomForestRegressionModel rfModel = (RandomForestRegressionModel)(model.stages()[1]);
0085     System.out.println("Learned regression forest model:\n" + rfModel.toDebugString());
0086     // $example off$
0087
0088     spark.stop();
0089   }
0090 }