Java PearsonsCorrelation.getCorrelationMatrix方法代码示例

import org.apache.commons.math3.stat.correlation.PearsonsCorrelation; //导入方法依赖的package包/类
/**
 * Calculates pearson correlation between pair of columns in the in the matrix, assuming that there is a strict
 * one to one relationship between the matrix columns and the field specifications in the list.
 *
 * Writes the correlation, pValue and standard error to a file using JSON format.
 *
 * @param matrix the input matrix where fields are represented by as columns and subjects by rows
 * @param fields a list of field specifications for which the correlations are to be calculated
 * @param correlationAnalysisOutputPath is the file to which the results are written
 * @throws Exception
 */
public static void calculateAndOutputCorrelations(RealMatrix matrix, List<FieldRecipe> fields,
                                                   String correlationAnalysisOutputPath) throws Exception {
    PearsonsCorrelation correlation = new PearsonsCorrelation(matrix);
    RealMatrix correlationMatrix = correlation.getCorrelationMatrix();
    RealMatrix pValueMatrix = correlation.getCorrelationPValues();
    RealMatrix standardErrorMatrix = correlation.getCorrelationStandardErrors();

    // Output the correlation analysis
    JSONArray correlationArray = new JSONArray();
    for (int i=0; i<correlationMatrix.getRowDimension(); i++){
        for (int j=0; j<correlationMatrix.getColumnDimension(); j++){
            JSONObject correlationObject = new JSONObject();
            correlationObject.put("xFieldLabel", fields.get(i).toField().getLabel());
            correlationObject.put("yFieldLabel", fields.get(j).toField().getLabel());
            correlationObject.put("correlationCoefficient", correlationMatrix.getEntry(i,j));
            correlationObject.put("pValue", pValueMatrix.getEntry(i,j));
            correlationObject.put("standardError", standardErrorMatrix.getEntry(i,j));
            correlationArray.add(correlationObject);
        }
    }
    Writer writer = new OutputStreamWriter(new FileOutputStream(correlationAnalysisOutputPath), "UTF-8");
    writer.write(correlationArray.toJSONString());
    writer.flush();
    writer.close();
}
 

import org.apache.commons.math3.stat.correlation.PearsonsCorrelation; //导入方法依赖的package包/类
/**
 *  creates the correlation of Samples useing Pearson's,Kendall's and Spearman's correlation coefficient
 * @param samples
 * @param rank
 * @param type
 */
public static void createCorrelationOfSamples(List<Sample> samples, String rank, String type) {
    //We need the unified map to make sure the counts are properly aligned
    LinkedList<TaxonNode> taxonNodeList = getUnifiedTaxonList(samples, rank);

    //The matrix data needs to be double, since PearsonsCorrelation only takes double arrays
    double[][] taxaCounts = new double[samples.size()][taxonNodeList.size()];
    for (int sampleIndex = 0; sampleIndex < samples.size(); sampleIndex++) {
        double[] currentSampleCounts = new double[taxonNodeList.size()];
        for (int taxonIndex = 0; taxonIndex < currentSampleCounts.length; taxonIndex++) {
            currentSampleCounts[taxonIndex] = samples.get(sampleIndex).getTaxonCountRecursive(taxonNodeList.get(taxonIndex));
        }
        taxaCounts[sampleIndex] = currentSampleCounts;
    }


    switch (type) {
        case "pearson":
            pearsonsCorrelation = new PearsonsCorrelation(taxaCounts);
            correlationMatrix = pearsonsCorrelation.getCorrelationMatrix();
            pValueMatrix = pearsonsCorrelation.getCorrelationPValues();
            break;
        case "spearman":
            spearmansCorrelation = new SpearmansCorrelation(new BlockRealMatrix(taxaCounts));
            correlationMatrix = spearmansCorrelation.getCorrelationMatrix();
            pValueMatrix = spearmansCorrelation.getRankCorrelation().getCorrelationPValues();
            break;
        case "kendall":
            kendallsCorrelation = new KendallsCorrelation(taxaCounts);
            correlationMatrix = kendallsCorrelation.getCorrelationMatrix();
            pValueMatrix = new PearsonsCorrelation(taxaCounts).getCorrelationPValues(); //No p-values available for kendall's correlation!
            break;
    }

    //Correct the NaNs to 0.0s
    for (int i = 0; i < correlationMatrix.getRowDimension(); i++) {
        for (int j = 0; j < correlationMatrix.getColumnDimension(); j++) {
            if (Double.isNaN(correlationMatrix.getEntry(i, j)))
                correlationMatrix.setEntry(i, j, 0.0);

        }
    }

    for (int i = 0; i < pValueMatrix.getRowDimension(); i++) {
        for (int j = 0; j < pValueMatrix.getColumnDimension(); j++) {
            if (Double.isNaN(pValueMatrix.getEntry(i, j)))
                pValueMatrix.setEntry(i, j, 1.0);
        }
    }


}
 

import org.apache.commons.math3.stat.correlation.PearsonsCorrelation; //导入方法依赖的package包/类
@Test
public void testPCorr() {
    MillerUpdatingRegression instance = new MillerUpdatingRegression(4, false);
    double[][] x = new double[airdata[0].length][];
    double[] y = new double[airdata[0].length];
    double[] cp = new double[10];
    double[] yxcorr = new double[4];
    double[] diag = new double[4];
    double sumysq = 0.0;
    int off = 0;
    for (int i = 0; i < airdata[0].length; i++) {
        x[i] = new double[4];
        x[i][0] = 1.0;
        x[i][1] = FastMath.log(airdata[3][i]);
        x[i][2] = FastMath.log(airdata[4][i]);
        x[i][3] = airdata[5][i];
        y[i] = FastMath.log(airdata[2][i]);
        off = 0;
        for (int j = 0; j < 4; j++) {
            double tmp = x[i][j];
            for (int k = 0; k <= j; k++, off++) {
                cp[off] += tmp * x[i][k];
            }
            yxcorr[j] += tmp * y[i];
        }
        sumysq += y[i] * y[i];
    }
    PearsonsCorrelation pearson = new PearsonsCorrelation(x);
    RealMatrix corr = pearson.getCorrelationMatrix();
    off = 0;
    for (int i = 0; i < 4; i++, off += (i + 1)) {
        diag[i] = FastMath.sqrt(cp[off]);
    }

    instance.addObservations(x, y);
    double[] pc = instance.getPartialCorrelations(0);
    int idx = 0;
    off = 0;
    int off2 = 6;
    for (int i = 0; i < 4; i++) {
        for (int j = 0; j < i; j++) {
            if (FastMath.abs(pc[idx] - cp[off] / (diag[i] * diag[j])) > 1.0e-8) {
                Assert.fail("Failed cross products... i = " + i + " j = " + j);
            }
            ++idx;
            ++off;
        }
        ++off;
        if (FastMath.abs(pc[i+off2] - yxcorr[ i] / (FastMath.sqrt(sumysq) * diag[i])) > 1.0e-8) {
            Assert.fail("Assert.failed cross product i = " + i + " y");
        }
    }
    double[] pc2 = instance.getPartialCorrelations(1);

    idx = 0;

    for (int i = 1; i < 4; i++) {
        for (int j = 1; j < i; j++) {
            if (FastMath.abs(pc2[idx] - corr.getEntry(j, i)) > 1.0e-8) {
                Assert.fail("Failed cross products... i = " + i + " j = " + j);
            }
            ++idx;
        }
    }
    double[] pc3 = instance.getPartialCorrelations(2);
    if (pc3 == null) {
        Assert.fail("Should not be null");
    }
    return;
}
 

import org.apache.commons.math3.stat.correlation.PearsonsCorrelation; //导入方法依赖的package包/类
@Test
public void testPCorr() {
    MillerUpdatingRegression instance = new MillerUpdatingRegression(4, false);
    double[][] x = new double[airdata[0].length][];
    double[] y = new double[airdata[0].length];
    double[] cp = new double[10];
    double[] yxcorr = new double[4];
    double[] diag = new double[4];
    double sumysq = 0.0;
    int off = 0;
    for (int i = 0; i < airdata[0].length; i++) {
        x[i] = new double[4];
        x[i][0] = 1.0;
        x[i][1] = Math.log(airdata[3][i]);
        x[i][2] = Math.log(airdata[4][i]);
        x[i][3] = airdata[5][i];
        y[i] = Math.log(airdata[2][i]);
        off = 0;
        for (int j = 0; j < 4; j++) {
            double tmp = x[i][j];
            for (int k = 0; k <= j; k++, off++) {
                cp[off] += tmp * x[i][k];
            }
            yxcorr[j] += tmp * y[i];
        }
        sumysq += y[i] * y[i];
    }
    PearsonsCorrelation pearson = new PearsonsCorrelation(x);
    RealMatrix corr = pearson.getCorrelationMatrix();
    off = 0;
    for (int i = 0; i < 4; i++, off += (i + 1)) {
        diag[i] = FastMath.sqrt(cp[off]);
    }

    instance.addObservations(x, y);
    double[] pc = instance.getPartialCorrelations(0);
    int idx = 0;
    off = 0;
    int off2 = 6;
    for (int i = 0; i < 4; i++) {
        for (int j = 0; j < i; j++) {
            if (Math.abs(pc[idx] - cp[off] / (diag[i] * diag[j])) > 1.0e-8) {
                Assert.fail("Failed cross products... i = " + i + " j = " + j);
            }
            ++idx;
            ++off;
        }
        ++off;
        if (Math.abs(pc[i+off2] - yxcorr[ i] / (FastMath.sqrt(sumysq) * diag[i])) > 1.0e-8) {
            Assert.fail("Assert.failed cross product i = " + i + " y");
        }
    }
    double[] pc2 = instance.getPartialCorrelations(1);

    idx = 0;

    for (int i = 1; i < 4; i++) {
        for (int j = 1; j < i; j++) {
            if (Math.abs(pc2[idx] - corr.getEntry(j, i)) > 1.0e-8) {
                Assert.fail("Failed cross products... i = " + i + " j = " + j);
            }
            ++idx;
        }
    }
    double[] pc3 = instance.getPartialCorrelations(2);
    if (pc3 == null) {
        Assert.fail("Should not be null");
    }
    return;
}