org.apache.commons.math3.stat.correlation.Covariance Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of virtdata-lib-realer Show documentation
Show all versions of virtdata-lib-realer Show documentation
With inspiration from other libraries
/*
* 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.commons.math3.stat.correlation;
import org.apache.commons.math3.exception.MathIllegalArgumentException;
import org.apache.commons.math3.exception.NotStrictlyPositiveException;
import org.apache.commons.math3.exception.util.LocalizedFormats;
import org.apache.commons.math3.linear.RealMatrix;
import org.apache.commons.math3.linear.BlockRealMatrix;
import org.apache.commons.math3.stat.descriptive.moment.Mean;
import org.apache.commons.math3.stat.descriptive.moment.Variance;
/**
* Computes covariances for pairs of arrays or columns of a matrix.
*
* The constructors that take RealMatrix or
* double[][] arguments generate covariance matrices. The
* columns of the input matrices are assumed to represent variable values.
*
* The constructor argument biasCorrected determines whether or
* not computed covariances are bias-corrected.
*
* Unbiased covariances are given by the formula
* cov(X, Y) = Σ[(xi - E(X))(yi - E(Y))] / (n - 1)
* where E(X) is the mean of X and E(Y)
* is the mean of the Y values.
*
* Non-bias-corrected estimates use n in place of n - 1
*
* @since 2.0
*/
public class Covariance {
/** covariance matrix */
private final RealMatrix covarianceMatrix;
/**
* Create an empty covariance matrix.
*/
/** Number of observations (length of covariate vectors) */
private final int n;
/**
* Create a Covariance with no data
*/
public Covariance() {
super();
covarianceMatrix = null;
n = 0;
}
/**
* Create a Covariance matrix from a rectangular array
* whose columns represent covariates.
*
*
The biasCorrected parameter determines whether or not
* covariance estimates are bias-corrected.
*
* The input array must be rectangular with at least one column
* and two rows.
*
* @param data rectangular array with columns representing covariates
* @param biasCorrected true means covariances are bias-corrected
* @throws MathIllegalArgumentException if the input data array is not
* rectangular with at least two rows and one column.
* @throws NotStrictlyPositiveException if the input data array is not
* rectangular with at least one row and one column.
*/
public Covariance(double[][] data, boolean biasCorrected)
throws MathIllegalArgumentException, NotStrictlyPositiveException {
this(new BlockRealMatrix(data), biasCorrected);
}
/**
* Create a Covariance matrix from a rectangular array
* whose columns represent covariates.
*
* The input array must be rectangular with at least one column
* and two rows
*
* @param data rectangular array with columns representing covariates
* @throws MathIllegalArgumentException if the input data array is not
* rectangular with at least two rows and one column.
* @throws NotStrictlyPositiveException if the input data array is not
* rectangular with at least one row and one column.
*/
public Covariance(double[][] data)
throws MathIllegalArgumentException, NotStrictlyPositiveException {
this(data, true);
}
/**
* Create a covariance matrix from a matrix whose columns
* represent covariates.
*
* The biasCorrected parameter determines whether or not
* covariance estimates are bias-corrected.
*
* The matrix must have at least one column and two rows
*
* @param matrix matrix with columns representing covariates
* @param biasCorrected true means covariances are bias-corrected
* @throws MathIllegalArgumentException if the input matrix does not have
* at least two rows and one column
*/
public Covariance(RealMatrix matrix, boolean biasCorrected)
throws MathIllegalArgumentException {
checkSufficientData(matrix);
n = matrix.getRowDimension();
covarianceMatrix = computeCovarianceMatrix(matrix, biasCorrected);
}
/**
* Create a covariance matrix from a matrix whose columns
* represent covariates.
*
* The matrix must have at least one column and two rows
*
* @param matrix matrix with columns representing covariates
* @throws MathIllegalArgumentException if the input matrix does not have
* at least two rows and one column
*/
public Covariance(RealMatrix matrix) throws MathIllegalArgumentException {
this(matrix, true);
}
/**
* Returns the covariance matrix
*
* @return covariance matrix
*/
public RealMatrix getCovarianceMatrix() {
return covarianceMatrix;
}
/**
* Returns the number of observations (length of covariate vectors)
*
* @return number of observations
*/
public int getN() {
return n;
}
/**
* Compute a covariance matrix from a matrix whose columns represent
* covariates.
* @param matrix input matrix (must have at least one column and two rows)
* @param biasCorrected determines whether or not covariance estimates are bias-corrected
* @return covariance matrix
* @throws MathIllegalArgumentException if the matrix does not contain sufficient data
*/
protected RealMatrix computeCovarianceMatrix(RealMatrix matrix, boolean biasCorrected)
throws MathIllegalArgumentException {
int dimension = matrix.getColumnDimension();
Variance variance = new Variance(biasCorrected);
RealMatrix outMatrix = new BlockRealMatrix(dimension, dimension);
for (int i = 0; i < dimension; i++) {
for (int j = 0; j < i; j++) {
double cov = covariance(matrix.getColumn(i), matrix.getColumn(j), biasCorrected);
outMatrix.setEntry(i, j, cov);
outMatrix.setEntry(j, i, cov);
}
outMatrix.setEntry(i, i, variance.evaluate(matrix.getColumn(i)));
}
return outMatrix;
}
/**
* Create a covariance matrix from a matrix whose columns represent
* covariates. Covariances are computed using the bias-corrected formula.
* @param matrix input matrix (must have at least one column and two rows)
* @return covariance matrix
* @throws MathIllegalArgumentException if matrix does not contain sufficient data
* @see #Covariance
*/
protected RealMatrix computeCovarianceMatrix(RealMatrix matrix)
throws MathIllegalArgumentException {
return computeCovarianceMatrix(matrix, true);
}
/**
* Compute a covariance matrix from a rectangular array whose columns represent
* covariates.
* @param data input array (must have at least one column and two rows)
* @param biasCorrected determines whether or not covariance estimates are bias-corrected
* @return covariance matrix
* @throws MathIllegalArgumentException if the data array does not contain sufficient
* data
* @throws NotStrictlyPositiveException if the input data array is not
* rectangular with at least one row and one column.
*/
protected RealMatrix computeCovarianceMatrix(double[][] data, boolean biasCorrected)
throws MathIllegalArgumentException, NotStrictlyPositiveException {
return computeCovarianceMatrix(new BlockRealMatrix(data), biasCorrected);
}
/**
* Create a covariance matrix from a rectangular array whose columns represent
* covariates. Covariances are computed using the bias-corrected formula.
* @param data input array (must have at least one column and two rows)
* @return covariance matrix
* @throws MathIllegalArgumentException if the data array does not contain sufficient data
* @throws NotStrictlyPositiveException if the input data array is not
* rectangular with at least one row and one column.
* @see #Covariance
*/
protected RealMatrix computeCovarianceMatrix(double[][] data)
throws MathIllegalArgumentException, NotStrictlyPositiveException {
return computeCovarianceMatrix(data, true);
}
/**
* Computes the covariance between the two arrays.
*
* Array lengths must match and the common length must be at least 2.
*
* @param xArray first data array
* @param yArray second data array
* @param biasCorrected if true, returned value will be bias-corrected
* @return returns the covariance for the two arrays
* @throws MathIllegalArgumentException if the arrays lengths do not match or
* there is insufficient data
*/
public double covariance(final double[] xArray, final double[] yArray, boolean biasCorrected)
throws MathIllegalArgumentException {
Mean mean = new Mean();
double result = 0d;
int length = xArray.length;
if (length != yArray.length) {
throw new MathIllegalArgumentException(
LocalizedFormats.DIMENSIONS_MISMATCH_SIMPLE, length, yArray.length);
} else if (length < 2) {
throw new MathIllegalArgumentException(
LocalizedFormats.INSUFFICIENT_OBSERVED_POINTS_IN_SAMPLE, length, 2);
} else {
double xMean = mean.evaluate(xArray);
double yMean = mean.evaluate(yArray);
for (int i = 0; i < length; i++) {
double xDev = xArray[i] - xMean;
double yDev = yArray[i] - yMean;
result += (xDev * yDev - result) / (i + 1);
}
}
return biasCorrected ? result * ((double) length / (double)(length - 1)) : result;
}
/**
* Computes the covariance between the two arrays, using the bias-corrected
* formula.
*
* Array lengths must match and the common length must be at least 2.
*
* @param xArray first data array
* @param yArray second data array
* @return returns the covariance for the two arrays
* @throws MathIllegalArgumentException if the arrays lengths do not match or
* there is insufficient data
*/
public double covariance(final double[] xArray, final double[] yArray)
throws MathIllegalArgumentException {
return covariance(xArray, yArray, true);
}
/**
* Throws MathIllegalArgumentException if the matrix does not have at least
* one column and two rows.
* @param matrix matrix to check
* @throws MathIllegalArgumentException if the matrix does not contain sufficient data
* to compute covariance
*/
private void checkSufficientData(final RealMatrix matrix) throws MathIllegalArgumentException {
int nRows = matrix.getRowDimension();
int nCols = matrix.getColumnDimension();
if (nRows < 2 || nCols < 1) {
throw new MathIllegalArgumentException(
LocalizedFormats.INSUFFICIENT_ROWS_AND_COLUMNS,
nRows, nCols);
}
}
}