📄 algorithmlda2.java,v
字号:
d67 4a70 4 point_means_d = new Vector();
decision_regions_d = new Vector();
support_vectors_d = new Vector();
description_d = new Vector();
d113 9a121 4 set1_d = (Vector)data_points_d.dset1.clone();
set2_d = (Vector)data_points_d.dset2.clone();
set3_d = (Vector)data_points_d.dset3.clone();
set4_d = (Vector)data_points_d.dset4.clone();
@1.6log@java documentation comments style.@text@d55 1a55 1 * @@return boolean
d132 1a132 1 * @@return boolean
d166 2d237 2d306 4a309 4 * @@param M1 : covariance matrix of the first class
* @@param M2 : covariance matrix of the second class
* @@param M3 : covariance matrix of the third class
* @@param M4 : covariance matrix of the fourth class
d634 1a634 1 * @@param M : Matrix storing within class scatter matrix
d1048 4a1051 4 * @@param M1: between class scatter matrix for the first class
* @@param M2: between class scatter matrix for the second class
* @@param M3: between class scatter matrix for the third class
* @@param M4: between class scatter matrix for the fourth class
@1.5log@minor changesclear@text@d1 12a12 5/*
* AlgorithmLDA2.java v6.0 03/15/2005
* Author Phil Trasatti Created on Jul 15, 2003
*/
d16 3d50 7a56 3 /* (non-Javadoc)
* @@see IFAlgorithm#initialize()
*/
d72 10a81 10 W = new Matrix();
B1 = new Matrix();
B2 = new Matrix();
B3 = new Matrix();
B4 = new Matrix();
S1 = new Matrix();
S2 = new Matrix();
S3 = new Matrix();
S4 = new Matrix();
CLDA = new Matrix();
d86 1a86 1 invW = new Matrix();
a108 1
d129 5d162 5d232 4d264 4a298 1 *
d302 5a306 5 * @@param Matrix M1: covariance matrix of the first class
* @@param Matrix M2: covariance matrix of the second class
* @@param Matrix M3: covariance matrix of the third class
* @@param Matrix M4: covariance matrix of the forth class
*
a627 1 *
d630 2a631 2 * @@param Matrix M: within class scatter matrix
*
a856 1 *
a857 1 *
d888 2a889 2 double incrementY = (scale.ymax-scale.ymin)/outputHeight;
double incrementX = (scale.xmax-scale.xmin)/outputWidth;
a1040 1 *
d1044 4a1047 5 * @@param Matrix M1: between class scatter matrix for the first class
* @@param Matrix M2: between class scatter matrix for the second class
* @@param Matrix M3: between class scatter matrix for the third class
* @@param Matrix M4: between class scatter matrix for the forth class
*
d1331 1a1331 1 // compute the between class scatter contribution of the forth set
d1352 5d1558 4@1.4log@minor changes.@text@d268 10a277 10 *
* Transforms a given set of points to a new space
* using the class dependent linear discrimination analysis algorithm
*
* @@param Matrix M1: covariance matrix of the first class
* @@param Matrix M2: covariance matrix of the second class
* @@param Matrix M3: covariance matrix of the third class
* @@param Matrix M4: covariance matrix of the forth class
*
*/
d541 1a541 1 // compute the transformation matrix for the forth data set
d1346 1d1348 1d1435 1a1435 2 {
d1450 1a1450 2 {
d1472 1a1472 2 {
d1487 1a1487 2 {
@1.3log@nothing major. Changes made to suit Java Documentation Style. and IFC style of coding.@text@d1 5a7 3/*
* Created on Jul 15, 2003
*/
a8 4/**
* @@author Phil Trasatti
*
*/
d47 3a49 2 // Debug
//System.out.println(algo_id + ": initialize()");
d75 1d92 1d97 1d104 1d108 1d112 1d119 2a120 1 //System.out.println(algo_id + ": step1()");
d127 1d136 1d138 1d147 2a148 1 //System.out.println(algo_id + ": step2()");
d164 3a166 3 // determine the ratio of the between class scatter matrix
// to the within class scatter matrix
//
d193 3a195 2 //----
output_panel_d.addOutput(point_means_d, Classify.PTYPE_OUTPUT_LARGE, Color.black);
d198 3a200 2 //----
output_panel_d.addOutput(support_vectors_d, Classify.PTYPE_INPUT, Color.cyan);
d219 1a219 1 //----
d222 2a223 2 // compute errors
//
d227 4a230 1 output_panel_d.addOutput( decision_regions_d, Classify.PTYPE_INPUT, new Color(255, 200, 0));
a231 1 //Color.black);
d240 2a241 1 //System.out.println(algo_id + " run()");
d266 1d268 3a270 1 * method transformLDA1
a271 1 * @@param Data d: input data point
a276 4 * @@return none
*
* this method transforms a given set of points to a new space
* using the class dependent linear discrimination analysis algorithm
d312 1a312 1 // declare arrays for the eigenvalues
d318 2a319 2 // declare an array to store the eigen vectors
//
d324 2a325 1 double maxsamples = set1_d.size() + set2_d.size() + set3_d.size() + set4_d.size();
a339 1
a348 1
d405 1a405 2 {
d414 1a414 2 {
d430 1a430 1 W.col = 2;
d432 22a453 19 // reset the matrices
//
W.resetMatrix();
// initialize the matrix needed to compute the eigenvalues
//
T.initMatrix(S2.Elem, 2, 2);
// make a copy of the original matrix
//
M.copyMatrix(T);
// compute the eigen values
//
eigVal2 = Eigen.compEigenVal(T);
// compute the eigen vectors
//
for (int i = 0; i < 2; i++)
d455 1a455 5 Eigen.calcEigVec(M, eigVal2[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
a456 4
// save the transformation matrix
//
LDA2 = W;
d458 6a463 1
d470 1a470 2 {
d479 29a507 1 {
d509 12a520 42 // declare matrix objects
//
Matrix T = new Matrix();
Matrix M = new Matrix();
Matrix W = new Matrix();
// allocate memory for the matrix elements
//
T.Elem = new double[2][2];
M.Elem = new double[2][2];
W.Elem = new double[2][2];
// initialize the transformation matrix dimensions
//
W.row = 2;
W.col = 2;
// reset the matrices
//
W.resetMatrix();
// initialize the matrix needed to compute the eigenvalues
//
T.initMatrix(S3.Elem, 2, 2);
// make a copy of the original matrix
//
M.copyMatrix(T);
// compute the eigen values
//
eigVal3 = Eigen.compEigenVal(T);
// compute the eigen vectors
//
for (int i = 0; i < 2; i++)
{
Eigen.calcEigVec(M, eigVal3[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
d522 5a526 4
// save the transformation matrix
//
LDA3 = W;
d535 1a535 2 {
d598 2a599 1 * method: withinClass
a600 1 * @@param Data d: input data points
a602 4 * @@return none
*
* this method determines the within class scatter matrix
*
d620 2a621 1 double maxsamples = set1_d.size() + set2_d.size() + set3_d.size() + set4_d.size();
a826 10 // method computeMeans
//
// param:
// Data d: input data point
//
// return : none
//
// display two matrices
//
a827 4 * method: computeDecisionRegions
*
* @@param none
* @@return none
d835 2a836 1 //System.out.println(algo_id + ": computeDecisionRegions()");
d839 1a862 1 //compute the line of discrimination for class dependent LDA
a869 1
a907 1
d980 2a981 1 dist = MathUtil.distance(C.Elem[0][0], C.Elem[0][1], D.Elem[0][0], D.Elem[0][1]);
d1003 2a1004 1 if (associated != output_canvas_d[i][j - 1] || associated != output_canvas_d[i - 1][j])
a1013 1 * method: betweenClass1
d1015 3a1017 1 * @@param Data d: input data points
a1022 5 * @@return none
*
* this method determines the between class scatter matrix for
* the class dependent linear discrimination algorithm
*
d1059 2a1060 1 double maxsamples = set1_d.size() + set2_d.size() + set3_d.size() + set4_d.size();
a1133 1
a1169 1
a1175 1
a1181 1
a1190 1
a1197 1
a1203 1
a1209 1
d1218 1a1218 2 {
d1249 1a1249 2 {
d1269 1a1269 2 {
d1289 1a1289 2 {
d1309 1a1309 2 {
a1328 1
d1350 2a1351 2 double incrementY = (scale.ymax-scale.ymin)/outputHeight;
double incrementX = (scale.xmax-scale.xmin)/outputWidth;
d1363 2a1364 1 if (output_canvas_d[(int)((point.x-scale.xmin)/incrementX)][(int)((point.y-scale.ymin)/incrementY)] != 0)
a1372 1
d1401 2a1402 1 if (output_canvas_d[(int)((point.x-scale.xmin)/incrementX)][(int)((point.y-scale.ymin)/incrementY)] != 1)
d1440 2a1441 1 if (output_canvas_d[(int)((point.x-scale.xmin)/incrementX)][(int)((point.y-scale.ymin)/incrementY)] != 2)
d1479 2a1480 1 if (output_canvas_d[(int)((point.x-scale.xmin)/incrementX)][(int)((point.y-scale.ymin)/incrementY)] != 3)
a1527 1
a1643 1
a1644 1
@1.2log@"Algorithm Complete" added and debug statements commented.@text@d13 35a47 35
Vector decision_regions_d;
Vector support_vectors_d;
int output_canvas_d[][];
// declare local matrix objects
Matrix W;
Matrix B1;
Matrix B2;
Matrix B3;
Matrix B4;
Matrix S1;
Matrix S2;
Matrix S3;
Matrix S4;
Matrix invW;
Matrix LDA1;
Matrix LDA2;
Matrix LDA3;
Matrix LDA4;
Matrix CLDA1; // covariance matrix for CLDA1
Matrix CLDA2; // covariance matrix for CLDA2
Matrix CLDA3; // covariance matrix for CLDA3
Matrix CLDA4; // covariance matrix for CLDA4
Matrix CLDA; // covariance matrix for CLDA
/* (non-Javadoc)
* @@see IFAlgorithm#initialize()
*/
public boolean initialize()
{
algo_id = "AlgorithmLDA2";
d51 29a79 23 step_count = 3;
point_means_d = new Vector();
decision_regions_d = new Vector();
support_vectors_d = new Vector();
description_d = new Vector();
// create local matrix objects
//
W = new Matrix();
B1 = new Matrix();
B2 = new Matrix();
B3 = new Matrix();
B4 = new Matrix();
S1 = new Matrix();
S2 = new Matrix();
S3 = new Matrix();
S4 = new Matrix();
CLDA = new Matrix();
CLDA1 = new Matrix();
CLDA2 = new Matrix();
CLDA3 = new Matrix();
CLDA4 = new Matrix();
invW = new Matrix();
d81 5a85 15 // Add the process description for the LDA algorithm
if (description_d.size() == 0)
{
String str = new String(" 0. Initialize the original data.");
description_d.addElement(str);
str = new String(" 1. Displaying the original data.");
description_d.addElement(str);
str = new String(" 2. Computing the means and covariance.");
description_d.addElement(str);
str = new String(" 3. Computing the decision regions based on the class dependent LDA algorithm.");
description_d.addElement(str);
}
d87 6a92 2 // append message to process box
pro_box_d.appendMessage("Class Dependent LDA Analysis:" + "\n");
d95 5a99 5 // set the data points for this algorithm
set1_d = (Vector)data_points_d.dset1.clone();
set2_d = (Vector)data_points_d.dset2.clone();
set3_d = (Vector)data_points_d.dset3.clone();
set4_d = (Vector)data_points_d.dset4.clone();
d101 2a102 2 // set the step index
step_index_d = 0;
d104 2a105 2⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -