0001
0002
0003
0004
0005
0006
0007
0008
0009
0010
0011
0012
0013
0014
0015
0016
0017
0018 package org.apache.spark.examples.ml;
0019
0020
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.classification.GBTClassificationModel;
0025 import org.apache.spark.ml.classification.GBTClassifier;
0026 import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator;
0027 import org.apache.spark.ml.feature.*;
0028 import org.apache.spark.sql.Dataset;
0029 import org.apache.spark.sql.Row;
0030 import org.apache.spark.sql.SparkSession;
0031
0032
0033 public class JavaGradientBoostedTreeClassifierExample {
0034 public static void main(String[] args) {
0035 SparkSession spark = SparkSession
0036 .builder()
0037 .appName("JavaGradientBoostedTreeClassifierExample")
0038 .getOrCreate();
0039
0040
0041
0042 Dataset<Row> data = spark
0043 .read()
0044 .format("libsvm")
0045 .load("data/mllib/sample_libsvm_data.txt");
0046
0047
0048
0049 StringIndexerModel labelIndexer = new StringIndexer()
0050 .setInputCol("label")
0051 .setOutputCol("indexedLabel")
0052 .fit(data);
0053
0054
0055 VectorIndexerModel featureIndexer = new VectorIndexer()
0056 .setInputCol("features")
0057 .setOutputCol("indexedFeatures")
0058 .setMaxCategories(4)
0059 .fit(data);
0060
0061
0062 Dataset<Row>[] splits = data.randomSplit(new double[] {0.7, 0.3});
0063 Dataset<Row> trainingData = splits[0];
0064 Dataset<Row> testData = splits[1];
0065
0066
0067 GBTClassifier gbt = new GBTClassifier()
0068 .setLabelCol("indexedLabel")
0069 .setFeaturesCol("indexedFeatures")
0070 .setMaxIter(10);
0071
0072
0073 IndexToString labelConverter = new IndexToString()
0074 .setInputCol("prediction")
0075 .setOutputCol("predictedLabel")
0076 .setLabels(labelIndexer.labelsArray()[0]);
0077
0078
0079 Pipeline pipeline = new Pipeline()
0080 .setStages(new PipelineStage[] {labelIndexer, featureIndexer, gbt, labelConverter});
0081
0082
0083 PipelineModel model = pipeline.fit(trainingData);
0084
0085
0086 Dataset<Row> predictions = model.transform(testData);
0087
0088
0089 predictions.select("predictedLabel", "label", "features").show(5);
0090
0091
0092 MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
0093 .setLabelCol("indexedLabel")
0094 .setPredictionCol("prediction")
0095 .setMetricName("accuracy");
0096 double accuracy = evaluator.evaluate(predictions);
0097 System.out.println("Test Error = " + (1.0 - accuracy));
0098
0099 GBTClassificationModel gbtModel = (GBTClassificationModel)(model.stages()[2]);
0100 System.out.println("Learned classification GBT model:\n" + gbtModel.toDebugString());
0101
0102
0103 spark.stop();
0104 }
0105 }