org.apache.commons.math3.stat.inference.MannWhitneyUTest Java Examples

The following examples show how to use org.apache.commons.math3.stat.inference.MannWhitneyUTest. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: MannWhitneyUEvaluator.java    From lucene-solr with Apache License 2.0 6 votes vote down vote up 
@Override
public Object doWork(Object... values) throws IOException {
  @SuppressWarnings({"unchecked"})
  List<double[]> mannWhitneyUInput = Arrays.stream(values)
      .map(value -> ((List<Number>) value).stream().mapToDouble(Number::doubleValue).toArray())
      .collect(Collectors.toList());
  if(mannWhitneyUInput.size() == 2) {
    MannWhitneyUTest mannwhitneyutest = new MannWhitneyUTest();
    double u = mannwhitneyutest.mannWhitneyU(mannWhitneyUInput.get(0), mannWhitneyUInput.get(1));
    double p = mannwhitneyutest.mannWhitneyUTest(mannWhitneyUInput.get(0), mannWhitneyUInput.get(1));
    Tuple tuple = new Tuple();
    tuple.put("u-statistic", u);
    tuple.put(StreamParams.P_VALUE, p);
    return tuple;
  }else{
    throw new IOException(String.format(Locale.ROOT,"%s(...) only works with a list of 2 arrays but a list of %d array(s) was provided.", constructingFactory.getFunctionName(getClass()), mannWhitneyUInput.size()));
  }
}
Example #2
Source File: ComputeMannWhitneyUCommand.java    From megan-ce with GNU General Public License v3.0 5 votes vote down vote up 
public void apply(NexusStreamParser np) throws Exception {
    np.matchIgnoreCase(getSyntax());

    final Document doc = getDir().getDocument();
    int numberSelectedNodes = ((ViewerBase) getViewer()).getNumberSelectedNodes();

    MannWhitneyUTest mannWhitneyUTest = new MannWhitneyUTest();

    double[] x = new double[numberSelectedNodes];
    double[] y = new double[numberSelectedNodes];

    ViewerBase viewer = (ViewerBase) getViewer();
    int count = 0;
    for (Node v : viewer.getSelectedNodes()) {
        if (v.getOutDegree() > 0) {
            x[count] = ((NodeData) v.getData()).getAssigned(0);
            y[count] = ((NodeData) v.getData()).getAssigned(1);
        } else {
            x[count] = ((NodeData) v.getData()).getSummarized(0);
            y[count] = ((NodeData) v.getData()).getSummarized(1);
        }
    }
    double p = mannWhitneyUTest.mannWhitneyUTest(x, y);
    final String message = "Mann Whitney U Test for " + doc.getNumberOfSamples() + " samples based on " + numberSelectedNodes + " selected nodes:\n"
            + "U value=" + mannWhitneyUTest.mannWhitneyU(x, y) + "\n"
            + "p-value=" + (float) p + "\n";
    //System.err.println(message);
    NotificationsInSwing.showInformation(getViewer().getFrame(), message);
}
Example #3
Source File: StatisticsUtil.java    From AILibs with GNU Affero General Public License v3.0 2 votes vote down vote up 
/**
 * Computes the p-value according to the MannWhitneyU test for iid. samples A and B.
 *
 * @param sampleA The first sample.
 * @param sampleB The second sample.
 * @return The p-value of the test for the given two samples.
 */
public static double mannWhitneyTwoSidedSignificanceP(final double[] sampleA, final double[] sampleB) {
	return new MannWhitneyUTest().mannWhitneyUTest(sampleA, sampleB);
}