spark JavaBinaryClassificationMetricsExample 源码

spark JavaBinaryClassificationMetricsExample 代码

文件路径：/examples/src/main/java/org/apache/spark/examples/mllib/JavaBinaryClassificationMetricsExample.java

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spark.examples.mllib;

// $example on$
import scala.Tuple2;

import org.apache.spark.api.java.*;
import org.apache.spark.mllib.classification.LogisticRegressionModel;
import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS;
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;
// $example off$
import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;

public class JavaBinaryClassificationMetricsExample {
  public static void main(String[] args) {
    SparkConf conf = new SparkConf().setAppName("Java Binary Classification Metrics Example");
    SparkContext sc = new SparkContext(conf);
    // $example on$
    String path = "data/mllib/sample_binary_classification_data.txt";
    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc, path).toJavaRDD();

    // Split initial RDD into two... [60% training data, 40% testing data].
    JavaRDD<LabeledPoint>[] splits =
      data.randomSplit(new double[]{0.6, 0.4}, 11L);
    JavaRDD<LabeledPoint> training = splits[0].cache();
    JavaRDD<LabeledPoint> test = splits[1];

    // Run training algorithm to build the model.
    LogisticRegressionModel model = new LogisticRegressionWithLBFGS()
      .setNumClasses(2)
      .run(training.rdd());

    // Clear the prediction threshold so the model will return probabilities
    model.clearThreshold();

    // Compute raw scores on the test set.
    JavaPairRDD<Object, Object> predictionAndLabels = test.mapToPair(p ->
      new Tuple2<>(model.predict(p.features()), p.label()));

    // Get evaluation metrics.
    BinaryClassificationMetrics metrics =
      new BinaryClassificationMetrics(predictionAndLabels.rdd());

    // Precision by threshold
    JavaRDD<Tuple2<Object, Object>> precision = metrics.precisionByThreshold().toJavaRDD();
    System.out.println("Precision by threshold: " + precision.collect());

    // Recall by threshold
    JavaRDD<?> recall = metrics.recallByThreshold().toJavaRDD();
    System.out.println("Recall by threshold: " + recall.collect());

    // F Score by threshold
    JavaRDD<?> f1Score = metrics.fMeasureByThreshold().toJavaRDD();
    System.out.println("F1 Score by threshold: " + f1Score.collect());

    JavaRDD<?> f2Score = metrics.fMeasureByThreshold(2.0).toJavaRDD();
    System.out.println("F2 Score by threshold: " + f2Score.collect());

    // Precision-recall curve
    JavaRDD<?> prc = metrics.pr().toJavaRDD();
    System.out.println("Precision-recall curve: " + prc.collect());

    // Thresholds
    JavaRDD<Double> thresholds = precision.map(t -> Double.parseDouble(t._1().toString()));

    // ROC Curve
    JavaRDD<?> roc = metrics.roc().toJavaRDD();
    System.out.println("ROC curve: " + roc.collect());

    // AUPRC
    System.out.println("Area under precision-recall curve = " + metrics.areaUnderPR());

    // AUROC
    System.out.println("Area under ROC = " + metrics.areaUnderROC());

    // Save and load model
    model.save(sc, "target/tmp/LogisticRegressionModel");
    LogisticRegressionModel.load(sc, "target/tmp/LogisticRegressionModel");
    // $example off$

    sc.stop();
  }
}

相关信息

spark 源码目录

相关文章

spark JavaALS 源码

spark JavaAssociationRulesExample 源码

spark JavaBisectingKMeansExample 源码

spark JavaChiSqSelectorExample 源码

spark JavaCorrelationsExample 源码

spark JavaDecisionTreeClassificationExample 源码

spark JavaDecisionTreeRegressionExample 源码

spark JavaElementwiseProductExample 源码

spark JavaGaussianMixtureExample 源码

spark JavaGradientBoostingClassificationExample 源码