Java Auc类代码示例

import org.apache.mahout.classifier.evaluation.Auc; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
 showAuc = true;
     showConfusion = true;
     Auc collector = new Auc();
     LogisticModelParameters lmp = LogisticModelParameters.loadFrom(new File(modelFile));
     CsvRecordFactory csv = lmp.getCsvRecordFactory();
     OnlineLogisticRegression lr = lmp.createRegression();
     BufferedReader in = OnlineLogisticRegressionTest.open(inputFile);
     String line = in.readLine();
     csv.firstLine(line);
     line = in.readLine();
     PrintWriter output=new PrintWriter(new OutputStreamWriter(System.out, Charsets.UTF_8), true);
     output.println("\"target\",\"model-output\",\"log-likelihood\"");
     while (line != null) {
     	System.out.println("-----" + line);
         Vector v = new SequentialAccessSparseVector(lmp.getNumFeatures());
         int target = csv.processLine(line, v);
         double score = lr.classifyScalarNoLink(v);
         output.printf(Locale.ENGLISH, "%d,%.3f,%.6f%n", target, score, lr.logLikelihood(target, v));
        collector.add(target, score);
         line = in.readLine();
         System.out.println("I am here");
       }
     output.printf(Locale.ENGLISH, "AUC = %.2f%n", collector.auc());
     Matrix m = collector.confusion();
     output.printf(Locale.ENGLISH, "confusion: [[%.1f, %.1f], [%.1f, %.1f]]%n",
       m.get(0, 0), m.get(1, 0), m.get(0, 1), m.get(1, 1));
     m = collector.entropy();
     output.printf(Locale.ENGLISH, "entropy: [[%.1f, %.1f], [%.1f, %.1f]]%n",
       m.get(0, 0), m.get(1, 0), m.get(0, 1), m.get(1, 1));
}
 

import org.apache.mahout.classifier.evaluation.Auc; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
  List<TelephoneCall> calls = Lists.newArrayList(new TelephoneCallParser("bank-full.csv"));

  double heldOutPercentage = 0.10;


  for (int run = 0; run < 20; run++) {
    Collections.shuffle(calls);
    int cutoff = (int) (heldOutPercentage * calls.size());
    List<TelephoneCall> test = calls.subList(0, cutoff);
    List<TelephoneCall> train = calls.subList(cutoff, calls.size());

    OnlineLogisticRegression lr = new OnlineLogisticRegression(NUM_CATEGORIES, TelephoneCall.FEATURES, new L1())
      .learningRate(1)
      .alpha(1)
      .lambda(0.000001)
      .stepOffset(10000)
      .decayExponent(0.2);
    for (int pass = 0; pass < 20; pass++) {
      for (TelephoneCall observation : train) {
        lr.train(observation.getTarget(), observation.asVector());
      }
      if (pass % 5 == 0) {
        Auc eval = new Auc(0.5);
        for (TelephoneCall testCall : test) {
          eval.add(testCall.getTarget(), lr.classifyScalar(testCall.asVector()));
        }
        System.out.printf("%d, %.4f, %.4f\n", pass, lr.currentLearningRate(), eval.auc());
      }
    }

  }
}