covariance.java,v

包含了模式识别中常用的一些分类器设计算法

head	1.3;
access;
symbols;
locks; strict;
comment	@# @;


1.3
date	2005.05.23.21.05.54;	author rirwin;	state Exp;
branches;
next	1.2;

1.2
date	2005.03.09.21.21.11;	author patil;	state Exp;
branches;
next	1.1;

1.1
date	2004.12.28.00.04.32;	author patil;	state Exp;
branches;
next	;


desc
@@


1.3
log
@Fixed javadoc syntax.
@
text
@/** 
 * file: Covariance.java
 *
 * Last editted: Ryan Irwin
 *
 */

// import necessary java libraries
//


//These imports are not needed - Phil T. 6-23-03
//import java.awt.*;
//import java.applet.*;
//import javax.swing.*;

/**
 * Covariance as the name sggests computes the covariance matrix given 
 * two random vectors i.e., the X = (x1, x2, x3 ...) and Y = (y1, y2, y3 ...)
 */
public class Covariance 
{

    // *********************************************************************
    //
    // declare class methods
    //
    // *********************************************************************
    
    /**
     * The method normalizes the covariance matrix based on the the range of 
     * the values within the covariance matrix
     *
     * @@param   M covariance matrix
     */
    public void normalizeCovariance(double[][] M) 
    {
	
	// declare local variables
	//
	double min = Double.MAX_VALUE;
	double max = -Double.MAX_VALUE;
	
	// obtain the minimum and maximum value from the covariance matrix
	//
	for(int i=0; i < M.length; i++) 
	{
	    for(int j=0; j < M.length; j++) 
	    {
		if (M[i][j] < min) 
		{
		    min = M[i][j];
		}
		if (M[i][j] > max) 
		{
		    max = M[i][j];
		}
	    }
	}
	
	// normalize the covariance matrix
	//
	for(int i=0; i < M.length; i++) 
	{
	    for(int j=0; j < M.length; j++) 
	    {
		M[i][j] = (M[i][j] - min) / (max - min);
	    }
	}
    }
    
    /**
     * computes the covariance matrix given two discrete random variables
     *
     * @@param   x random vector X = (x1, x2, x3 ...)
     * @@param   y random vector Y = (y1, y2, y3 ...)
     *
     * @@return  covariance matrix
     */
    public double[][] computeCovariance(double[] x, double[] y) 
    {
	
	// declare local variables
	//
	double sum11 = 0.0;
	double sum12 = 0.0;
	double sum21 = 0.0;
	double sum22 = 0.0;
	
	double sum1 = 0.0;
	double mean1 = 0.0;
	double sum2 = 0.0;
	double mean2 = 0.0;
	
	// declare the covariance matrix
	//
	double[][] cov = new double[2][2];
	
	// compute the mean of the first random variable
	//
	for(int i = 0; i < x.length; i++) 
	{ 
	    sum1 += x[i]; 
	}
	mean1 = sum1 / x.length;

	// compute the mean of the second random variable
	//
	for(int i = 0; i < y.length; i++) 
	{ 
	    sum2 += y[i]; 
	}
	mean2 = sum2 / y.length;
	
	// compute the c11 component of the covariance matrix
	//
	for(int i = 0; i < x.length; i++) 
	{
	    sum11 += (x[i] - mean1) * (x[i] - mean1);
	}
	cov[0][0] = sum11 / (x.length - 1);

	// compute the c12 component of the covariance matrix
	//
	for(int i = 0; i < x.length; i++) 
	{
	    sum12 += (x[i] - mean1) * (y[i] - mean2);
	}
	cov[0][1] = sum12 / (x.length - 1);

	// compute the c21 component of the covariance matrix
	//
	for(int i = 0; i < x.length; i++) 
	{    
	    sum21 += (y[i] - mean2) * (x[i] - mean1);
	}
	cov[1][0] = sum21 / (x.length - 1);

	// compute the c22 component of the covariance matrix
	//
	for(int i = 0; i < x.length; i++) 
	{
	    sum22 += (y[i] - mean2) * (y[i] - mean2);
	}
	cov[1][1] = sum22 / (x.length - 1);

	// return the covariance matrix
	//
	return cov;
    }
}
@


1.2
log
@Comments changed to suit the Java Documentation Style.
corrected a spelling mistake.
@
text
@d3 3
a17 2
 * class: Covariance
 *
a30 6
     * method:  normalizeCovariance
     *
     * @@param   double[][] M: covariance matrix
     *
     * @@return  none
     *
d34 1
d73 1
a73 1
     * method: computeCovariance
d75 2
a76 2
     * @@param   double[] x: random vector X = (x1, x2, x3 ...)
     * @@param   double[] y: random vector Y = (y1, y2, y3 ...)
a78 3
     *
     * computes the covariance matrix given two discrete random variables
     *
@


1.1
log
@Initial revision
@
text
@d1 3
a3 2
// file: Covariance.java
//
d14 8
a21 6
// class: Covariance
//
// Covariance as the name sggests computes the covariance matrix given 
// two random vectors i.e., the X = (x1, x2, x3 ...) and Y = (y1, y2, y3 ...)
//
public class Covariance {
d29 14
a42 11
    // method:  normalizeCovariance
    //
    // arguments:
    //    double[][] M: conariance matrix
    //
    // returns  : none
    //
    // computes the covariance matrix given two discrete random variables
    //
    public void normalizeCovariance(double[][] M) {

d47 1
a47 1

d50 6
a55 3
	for(int i=0; i < M.length; i++) {
	    for(int j=0; j < M.length; j++) {
		if (M[i][j] < min) {
d58 2
a59 1
		if (M[i][j] > max) {
d67 4
a70 2
	for(int i=0; i < M.length; i++) {
	    for(int j=0; j < M.length; j++) {
d76 14
a89 12
    // method: computeCovariance
    //
    // arguments:
    //    double[] x: random vector X = (x1, x2, x3 ...)
    //    double[] y: random vector Y = (y1, y2, y3 ...)
    //
    // returns  : covariance matrix
    //
    // computes the covariance matrix given two discrete random variables
    //
    public double[][] computeCovariance(double[] x, double[] y) {

d96 1
a96 1

d101 1
a101 1

d105 1
a105 1

d108 2
a109 1
	for(int i=0; i < x.length; i++) { 
d116 2
a117 1
	for(int i=0; i < y.length; i++) { 
d124 2
a125 1
	for(int i=0; i < x.length; i++) {
d132 2
a133 1
	for(int i=0; i < x.length; i++) {
d140 2
a141 1
	for(int i=0; i < x.length; i++) {
d148 2
a149 1
	for(int i=0; i < x.length; i++) {
a158 3

//
// end of file
@