📄 algorithmlda2.java,v
字号:
// append message to process box
pro_box_d.appendMessage((String)description_d.get(step_index_d));
d107 3a109 3 // exit gracefully
return true;
}
d111 4a114 4 boolean step1()
{
// Debug
//System.out.println(algo_id + ": step1()");
d116 18a133 18 pro_box_d.setProgressMin(0);
pro_box_d.setProgressMax(20);
pro_box_d.setProgressCurr(0);
// append message to process box
output_panel_d.addOutput(set1_d, Classify.PTYPE_INPUT,
data_points_d.color_dset1);
output_panel_d.addOutput(set2_d, Classify.PTYPE_INPUT,
data_points_d.color_dset2);
output_panel_d.addOutput(set3_d, Classify.PTYPE_INPUT,
data_points_d.color_dset3);
output_panel_d.addOutput(set4_d, Classify.PTYPE_INPUT,
data_points_d.color_dset4);
// step 1 completed
pro_box_d.setProgressCurr(20);
output_panel_d.repaint();
return true;
}
d135 4a138 4 boolean step2()
{
// Debug
//System.out.println(algo_id + ": step2()");
d140 3a142 3 pro_box_d.setProgressMin(0);
pro_box_d.setProgressMax(20);
pro_box_d.setProgressCurr(0);
d144 1a144 1 computeMeans();
d146 3a148 3 // determine the within class scatter matrix
//
withinClass(W);
d150 3a152 3 // determine the between class scatter matrix
//
betweenClass1(B1, B2, B3, B4);
d157 1a157 1 W.invertMatrix(invW);
d159 16a174 16 if (set1_d.size() > 0)
{
invW.multMatrix(B1, S1);
}
if (set2_d.size() > 0)
{
invW.multMatrix(B2, S2);
}
if (set3_d.size() > 0)
{
invW.multMatrix(B3, S3);
}
if (set4_d.size() > 0)
{
invW.multMatrix(B4, S4);
}
d176 3a178 3 // transform the samples from all data sets
//
transformLDA1(S1, S2, S3, S4);
d180 1a180 1 printMatrices();
d182 3a184 3 // display means
//----
output_panel_d.addOutput(point_means_d, Classify.PTYPE_OUTPUT_LARGE, Color.black);
d186 3a188 3 // display support vectors
//----
output_panel_d.addOutput(support_vectors_d, Classify.PTYPE_INPUT, Color.cyan);
d190 6a195 6 // display support vectors
//
pro_box_d.setProgressCurr(20);
output_panel_d.repaint();
return true;
}
d197 4a200 4 boolean step3()
{
// Debug
//System.out.println(algo_id + ": step3()");
d202 7a208 7 pro_box_d.setProgressMin(0);
pro_box_d.setProgressMax(20);
pro_box_d.setProgressCurr(0);
// compute the decision regisions
//----
computeDecisionRegions();
d212 1a212 1 computeErrors();
d214 2a215 2 // display support vectors
output_panel_d.addOutput( decision_regions_d, Classify.PTYPE_INPUT, new Color(255, 200, 0));
d217 2a218 2 //Color.black);
output_panel_d.repaint();
d220 13a232 1 return true;
d234 2a235 2
public void run()
d237 4a240 2 // Debug
//System.out.println(algo_id + " run()");
d242 6a247 22 if (step_index_d == 1)
{
disableControl();
step1();
enableControl();
}
else if (step_index_d == 2)
{
disableControl();
step2();
enableControl();
}
else if (step_index_d == 3)
{
disableControl();
step3();
pro_box_d.appendMessage(" Algorithm Complete");
enableControl();
}
return;
d249 46d296 2a297 47 // method transformLDA1
//
// arguments:
// Data d: input data point
// Matrix M1: covariance matrix of the first class
// Matrix M2: covariance matrix of the second class
// Matrix M3: covariance matrix of the third class
// Matrix M4: covariance matrix of the forth class
//
// return : none
//
// this method transforms a given set of points to a new space
// using the class dependent linear discrimination analysis algorithm
//
public void transformLDA1(Matrix S1, Matrix S2, Matrix S3, Matrix S4)
{
// declare local variables
int size = 0;
int xsize1 = 0;
int ysize1 = 0;
int xsize2 = 0;
int ysize2 = 0;
int xsize3 = 0;
int ysize3 = 0;
int xsize4 = 0;
int ysize4 = 0;
double xval1 = 0.0;
double yval1 = 0.0;
double xval2 = 0.0;
double yval2 = 0.0;
double xval3 = 0.0;
double yval3 = 0.0;
double xval4 = 0.0;
double yval4 = 0.0;
double xmean1 = 0.0;
double ymean1 = 0.0;
double xmean2 = 0.0;
double ymean2 = 0.0;
double xmean3 = 0.0;
double ymean3 = 0.0;
double xmean4 = 0.0;
double ymean4 = 0.0;
double xval = 0.0;
double yval = 0.0;
d300 4a303 4 double eigVal1[] = null;
double eigVal2[] = null;
double eigVal3[] = null;
double eigVal4[] = null;
d307 1a307 1 double eigVec[] = new double[2];
d309 3a311 3 // compute the propabilities of each data set
//
double maxsamples = set1_d.size() + set2_d.size() + set3_d.size() + set4_d.size();
d313 4a316 4 double p1 = set1_d.size() / maxsamples;
double p2 = set2_d.size() / maxsamples;
double p3 = set3_d.size() / maxsamples;
double p4 = set4_d.size() / maxsamples;
d319 4a322 1 size = set1_d.size();
d324 7a330 2 xsize1 += size;
ysize1 += size;
d332 44a375 1 for (int i = 0; i < size; i++)
d377 1a377 4
MyPoint p = (MyPoint)set1_d.elementAt(i);
xval1 += p.x;
yval1 += p.y;
d379 20d400 23a422 1 // compute the transformation matrix for the first data set
d424 1a424 8 if (size > 0)
{
// declare matrix objects
//
Matrix T = new Matrix();
Matrix M = new Matrix();
Matrix W = new Matrix();
d426 3a428 5 // allocate memory for the matrix elements
//
T.Elem = new double[2][2];
M.Elem = new double[2][2];
W.Elem = new double[2][2];
d430 3a432 12 // 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(S1.Elem, 2, 2);
d434 1a434 39 // make a copy of the original matrix
//
M.copyMatrix(T);
// compute the eigen values
//
eigVal1 = Eigen.compEigenVal(T);
// compute the eigen vectors
//
for (int i = 0; i < 2; i++)
{
Eigen.calcEigVec(M, eigVal1[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
}
// save the transformation matrix
//
LDA1 = W;
}
size = set2_d.size();
xsize2 += size;
ysize2 += size;
for (int i = 0; i < size; i++)
{
MyPoint p = (MyPoint)set2_d.elementAt(i);
xval2 += p.x;
yval2 += p.y;
}
// compute the transformation matrix for the second data set
d436 1a436 31 if (size > 0)
{
// 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(S2.Elem, 2, 2);
// make a copy of the original matrix
//
M.copyMatrix(T);
d438 1a438 34 // compute the eigen values
//
eigVal2 = Eigen.compEigenVal(T);
// compute the eigen vectors
//
for (int i = 0; i < 2; i++)
{
Eigen.calcEigVec(M, eigVal2[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
}
// save the transformation matrix
//
LDA2 = W;
}
size = set3_d.size();
xsize3 += size;
ysize3 += size;
for (int i = 0; i < size; i++)
{
MyPoint p = (MyPoint)set3_d.elementAt(i);
xval3 += p.x;
yval3 += p.y;
}
// compute the transformation matrix for the third data set
d440 1a440 1 if (size > 0)
d442 2a443 37
// 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++)
d445 1a445 5 Eigen.calcEigVec(M, eigVal3[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
a446 4
// save the transformation matrix
//
LDA3 = W;
d449 6a454 1 size = set4_d.size();
d456 2a457 2 xsize4 += size;
ysize4 += size;
d459 7a465 2 for (int i = 0; i < size; i++)
{
d467 6a472 6 MyPoint p = (MyPoint)set4_d.elementAt(i);
xval4 += p.x;
yval4 += p.y;
}
// compute the transformation matrix for the forth data set
d474 3a476 2 if (size > 0)
{
d478 5a482 5 // declare matrix objects
//
Matrix T = new Matrix();
Matrix M = new Matrix();
Matrix W = new Matrix();
d484 4a487 5 // allocate memory for the matrix elements
//
T.Elem = new double[2][2];
M.Elem = new double[2][2];
W.Elem = new double[2][2];
d489 3a491 4 // initialize the transformation matrix dimensions
//
W.row = 2;
W.col = 2;
d493 3a495 3 // reset the matrices
//
W.resetMatrix();
d497 3a499 3 // initialize the matrix needed to compute the eigenvalues
//
T.initMatrix(S4.Elem, 2, 2);
d501 3a503 3 // make a copy of the original matrix
//
M.copyMatrix(T);
d505 6a510 7 // compute the eigen values
//
eigVal4 = Eigen.compEigenVal(T);
// compute the eigen vectors
//
for (int i = 0; i < 2; i++)
d512 2a513 10 Eigen.calcEigVec(M, eigVal4[i], eigVec);
for (int j = 0; j < 2; j++)
{
W.Elem[j][i] = eigVec[j];
}
}
// save the transformation matrix
//
LDA4 = W;
d515 17a531 1
d533 2a534 8
// method: withinClass
//
// arguments:
// Data d: input data points
// Matrix M: within class scatter matrix
//
// return : none
d536 1a536 3 // this method determines the within class scatter matrix
//
public void withinClass(Matrix M)
a537 5 // declare local variables
//
int size = 0;
double x[] = null;
double y[] = null;
d539 1a539 3 DisplayScale scale = output_panel_d.disp_area_d.getDisplayScale();
// declare the covariance object
d541 3a543 1 Covariance cov = new Covariance();
d545 1a545 1 // compute the propabilities of each data set
d547 3a549 10 double maxsamples = set1_d.size() + set2_d.size() + set3_d.size() + set4_d.size();
double p1 = set1_d.size() / maxsamples;
double p2 = set2_d.size() / maxsamples;
double p3 = set3_d.size() / maxsamples;
double p4 = set4_d.size() / maxsamples;
// get the first data set size
//
size = set1_d.size();
d551 1a551 1 // initialize arrays to store the samples
d553 2a554 2 x = new double[size];
y = new double[size];
d556 1a556 2 // set up⌨️ 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 + -