Java TTest类代码示例

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
@Test
public void acceptSignificantBenefitWith10Threads() throws Exception {
    // given
    final int nThreads = 10;

    // when
    final Tuple2<DescriptiveStatistics, DescriptiveStatistics> results =
            measure(nThreads, generatorSupplier, nMeasurements, taskFactory);

    // then
    assertThat(results.second().getMean(), is(lessThan(results.first().getMean())));

    double p = new TTest().tTest(results.first(), results.second());
    System.out.println("t-Test: p=" + p);
    assertThat(p, is(lessThanOrEqualTo(HIGHLY_SIGNIFICANT.getAlpha())));
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
private boolean checkTimeSeriesSimularityTtest(double[] r_generated, double[] java_generated) {
    TTest t_test_obj = new TTest();
    // Performs a paired t-test evaluating the null hypothesis that the mean of the paired
    // differences between sample1
    // and sample2 is 0 in favor of the two-sided alternative that the mean paired difference is not
    // equal to 0,
    // with significance level 0.05.
    double p_value = t_test_obj.tTest(r_generated, java_generated);
    boolean reject_null_hyphothesis = (p_value < 0.05);
    return reject_null_hyphothesis;
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
@Override
public double evaluate(double[] baseline, double[] treatment) {

  double[] boostedBaseline = multiply(baseline, boost);

  /*
  double sampleSum = 0;
  double sampleSumSquares = 0;
  int n = boostedBaseline.length;

  for (int i = 0; i < baseline.length; i++) {
    double delta = treatment[i] - boostedBaseline[i];
    sampleSum += delta;
    sampleSumSquares += delta * delta;
  }

  double sampleVariance = sampleSumSquares / (n - 1);
  double sampleMean = sampleSum / baseline.length;

  double sampleDeviation = Math.sqrt(sampleVariance);
  double meanDeviation = sampleDeviation / Math.sqrt(n);
  double t = sampleMean / meanDeviation;

  return 1.0 - Stat.studentTProb(t, n - 1);
  */

  //- Use Apache Commons Math3 directly for t-test p-value calculation
  TTest tt = new TTest();
  double pval = tt.tTest (boostedBaseline, treatment);

  return 1.0 - pval;
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
private boolean checkTimeSeriesSimularityTtest(double[] r_generated, double[] java_generated) {
    TTest t_test_obj = new TTest();
    // Performs a paired t-test evaluating the null hypothesis that the mean of the paired differences between sample1
    // and sample2 is 0 in favor of the two-sided alternative that the mean paired difference is not equal to 0,
    // with significance level 0.05.
    double p_value = t_test_obj.tTest(r_generated, java_generated);
    boolean reject_null_hyphothesis = (p_value < 0.05);
    return reject_null_hyphothesis;
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
/**
 * T-test on a given pair of ArrayOfDoublesSketches
 * @param serializedSketchA ArrayOfDoublesSketch in as serialized binary
 * @param serializedSketchB ArrayOfDoublesSketch in as serialized binary
 * @return list of p-values
 */
public List<Double> evaluate(final BytesWritable serializedSketchA, final BytesWritable serializedSketchB) {
  if (serializedSketchA == null || serializedSketchB == null) { return null; }
  final ArrayOfDoublesSketch sketchA =
      ArrayOfDoublesSketches.wrapSketch(Memory.wrap(serializedSketchA.getBytes()));
  final ArrayOfDoublesSketch sketchB =
      ArrayOfDoublesSketches.wrapSketch(Memory.wrap(serializedSketchB.getBytes()));

  if (sketchA.getNumValues() != sketchB.getNumValues()) {
    throw new IllegalArgumentException("Both sketches must have the same number of values");
  }

  // If the sketches contain fewer than 2 values, the p-value can't be calculated
  if (sketchA.getRetainedEntries() < 2 || sketchB.getRetainedEntries() < 2) {
    return null;
  }

  final SummaryStatistics[] summariesA = ArrayOfDoublesSketchStats.sketchToSummaryStatistics(sketchA);
  final SummaryStatistics[] summariesB = ArrayOfDoublesSketchStats.sketchToSummaryStatistics(sketchB);

  final TTest tTest = new TTest();
  final List<Double> pValues = new ArrayList<Double>(sketchA.getNumValues());
  for (int i = 0; i < sketchA.getNumValues(); i++) {
    pValues.add(tTest.tTest(summariesA[i], summariesB[i]));
  }
  return pValues;
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
@Override
public Tuple exec(final Tuple input) throws IOException {
  if ((input == null) || (input.size() != 2)) {
    return null;
  }

  // Get the two sketches
  final DataByteArray dbaA = (DataByteArray) input.get(0);
  final DataByteArray dbaB = (DataByteArray) input.get(1);
  final ArrayOfDoublesSketch sketchA = ArrayOfDoublesSketches.wrapSketch(Memory.wrap(dbaA.get()));
  final ArrayOfDoublesSketch sketchB = ArrayOfDoublesSketches.wrapSketch(Memory.wrap(dbaB.get()));

  // Check that the size of the arrays in the sketches are the same
  if (sketchA.getNumValues() != sketchB.getNumValues()) {
    throw new IllegalArgumentException("Both sketches must have the same number of values");
  }

  // Store the number of metrics
  final int numMetrics = sketchA.getNumValues();

  // If the sketches contain fewer than 2 values, the p-value can't be calculated
  if (sketchA.getRetainedEntries() < 2 || sketchB.getRetainedEntries() < 2) {
    return null;
  }

  // Get the statistical summary from each sketch
  final SummaryStatistics[] summariesA = ArrayOfDoublesSketchStats.sketchToSummaryStatistics(sketchA);
  final SummaryStatistics[] summariesB = ArrayOfDoublesSketchStats.sketchToSummaryStatistics(sketchB);

  // Calculate the p-values
  final TTest tTest = new TTest();
  final Tuple pValues = TupleFactory.getInstance().newTuple(numMetrics);
  for (int i = 0; i < numMetrics; i++) {
    // Pass the sampled values for each metric
    pValues.set(i, tTest.tTest(summariesA[i], summariesB[i]));
  }

  return pValues;
}
 

import org.apache.commons.math3.stat.inference.TTest; //导入依赖的package包/类
public boolean predictLabelsForColumn(Map<String, ArrayList<Double>> trainingLabelToExamplesMap,
			ArrayList<Double> testExamples, int numPred, ArrayList<String> predictions, ArrayList<Double> confidenceScores) {

		List<Prediction> sortedPredictions = new ArrayList<Prediction>();	// descending order of p-Value
		
    TTest test = new TTest();  		
		double pValue;
    
  	double[] sample1 = new double[testExamples.size()];
  	for(int i = 0; i < testExamples.size(); i++){
      sample1[i] = testExamples.get(i);
  	}
    
    for (Entry<String, ArrayList<Double>> entry : trainingLabelToExamplesMap.entrySet()) {
    	
    	String label = entry.getKey();
    	ArrayList<Double> trainExamples = entry.getValue();
    	
    	double[] sample2 = new double[trainExamples.size()];
    	for(int i = 0; i < trainExamples.size(); i++){
        sample2[i] = trainExamples.get(i);
    	}
    	
    	pValue = test.tTest(sample1, sample2);
    	
    	Prediction pred = new Prediction(label, pValue);
    	
//    	double tValue = Math.abs(test.t(sample1, sample2));
//    	Prediction pred = new Prediction(label, tValue);

    	sortedPredictions.add(pred);
   
    }
   
		// sorting based on p-Value
		Collections.sort(sortedPredictions, new PredictionComparator());
    
		for(int j=0; j<numPred && j<sortedPredictions.size(); j++)
		{
			predictions.add(sortedPredictions.get(j).predictionLabel);
			confidenceScores.add(sortedPredictions.get(j).confidenceScore);
		}
		
		return true;
	}