% % this is for two class problem for more than two class code changes
% % ————-Parameters————-
% numIteration =1000; The Number of maximum iterations
% % errorBound = 0.0001; This is the permissible error.
% The experiments have been done keep in view both the error condition
% reached or maximum iteration reached whichever comes first.
% % eta = 0.5; This is the learning rate, experiments have been
% done on various learning rates
% I have written two codes for logistic regression one using matrices other
% using array indexes.
function logisticRegression_Matrix_LSData()
disp(‘..Starting logistic regression Algorithm….’);
%reading data
A = load('BananaData.mat');
data = A.data;
[N,col]= size(data);
vtot=[0, 0, 0, 0,0, 0, 0 , 0];
%5 folds with 70-30 ratio
for i = 1:5
P=.3;
groups=data(:,3);
[train,test] = crossvalind('holdout',groups, P);
train1= data(train, 1: 3);
test1=data(test, 1:3);
[trainLengthRow, trainLengthCol]=size(train1);
[rowtest,coltest]= size(test1);
trainingSet = train1(1:trainLengthRow, 1 : trainLengthCol -1 );
trainingLabels = train1(1:trainLengthRow, trainLengthCol );
%converting data to 1 and 0 class instead of 1 and -1 class as
%using logit
for p=1:trainLengthRow
if trainingLabels(p)== -1
trainingLabels(p) = 0;
end
end
testSet = test1(1:rowtest, 1 : coltest -1 );
testLabels = test1(1:rowtest, coltest );
%converting data to 1 and 0 class instead of 1 and -1 class as
%using logit
for p=1:rowtest
if testLabels(p)== -1
testLabels(p) = 0;
end
end
[weights] = trainLogReg( trainingSet,trainingLabels);
[correctlyClassified,count0,count1,unClassified,v] = testLogReg(testSet,testLabels, weights) ;
vtot = vtot +v ;
end
% taking average of all such entries
disp(‘TP, TN, FP, FN, TP/(TP+FP), TP/P, 2PR / (P+R) , correctlyClassified/trainLengthRow’);
vtot = vtot ./ 5
end
%This mathod is for tarining the logestic regression problem
% —–Parameters—-
%trainingSet: the training set
%trainingLabels: the labels corresponding to the traiining set
%—–Return Types——
%weights: the final weights obtained from traiining
%
function [weights] = trainLogReg( trainingSet,trainingLabels)
numIteration =1000;
eta = 0.5;
errorBound = 0.0001;
[trainLengthRow, trainLengthCol] = size(trainingSet);
errorVec=ones(trainLengthCol+1);
weightsFinal = zeros(trainLengthCol+1);
W_Old(1:trainLengthCol+1) = 0;
W_New(1:trainLengthCol+1) = 0;
P(1:trainLengthRow) = 0;
Y = trainingLabels';
X(1:trainLengthRow , 1:trainLengthCol+1) = 0;
X(1:trainLengthRow ,1) = 1;
X(1:trainLengthRow ,2:trainLengthCol+1) = trainingSet(1:trainLengthRow,1:trainLengthCol);
error=1.0;
k=1;
while ((error >= errorBound ) && (k < numIteration))
error=0;
for t=1: trainLengthRow
sum = W_Old(1);
for j=1: trainLengthCol
sum = sum + W_Old(j+1)*trainingSet(t,j);
end;
P(t) = 1/(1+ exp(-1*sum));
end;
Z= (X') * (Y-P)';
%computing the new weights
W_New = W_Old + eta * Z';
W_New ;
errorVec = (W_New - W_Old).*(W_New - W_Old)
for i = 1: trainLengthCol+1
error=error+errorVec(i);
end
error= sqrt(error);
k=k+1;
W_Old = W_New;
end
%Now computing the final y using the final weights
disp('final weights : number of iterations : error');
W_Old
k
error
y1(1:trainLengthRow)=0;
y0(1:trainLengthRow)=0;
for i =1: trainLengthRow
sum = W_Old(1);
for j=1: trainLengthCol
sum = sum + W_Old(j+1)*trainingSet(i,j);
end;
y1(i) = 1/(1+ exp(-1*sum));
y0(i) = 1/(1+ exp(sum));
end;
data(1:trainLengthRow, 1:trainLengthCol+1)=0;
data(1:trainLengthRow, 1:trainLengthCol)= trainingSet;
for p=1:trainLengthRow
data(p, trainLengthCol+1)= y1(p);
end;
labels={'x1','x2','y'};
%figure
% parallelcoords(data,'Labels',labels);
for p=1:trainLengthRow
x1(p)= trainingSet(p,1);
end;
for p=1:trainLengthRow
x2(p)= trainingSet(p,2);
end;
for p=1:trainLengthRow
yOrginal(p)= trainingLabels(p);
end;
figure(1)
scatter3(x1,x2,trainingLabels,10);
axis([-5,5,-5,5,-5,5])
figure(1)
plot3(x1,x2,y1);
axis([-5,5,-5,5,-5,5])
xx=(-10:1:10);
yy=(-10:1:10);
[xx1,yy1]=meshgrid(xx,yy);
sum1 = -1 .* (W_Old(1)+W_Old(2).*xx1+W_Old(3).*yy1);
zz= 1 ./(1 + expm(sum1));
[p1,m1]=size(zz);
for p=1: p1
for m=1:m1
% if (zz(p,m)== NaN)
% zz(p,m) = 1; % as we are using logit function
expVal = exp(sum1(p,m));
zz(p,m) = 1 / (1+ expVal);
% end
end
end
figure(1)
surf(xx1,yy1,zz);
title('title');
xlabel('x');
ylabel('y')
zlabel('z');
weights =W_Old;
end
function [correctlyClassified,count0,count1,unClassified,v] = testLogReg(testSet,testLabels, weights)
correctlyClassified = 0;
count0 = 0; count1=0; TP=0; TN=0; FP=0; FN =0; P=0; R=0; F=0;
[testLengthRow,testLengthCol]=size(testSet);
unClassified(1:10 ,1: testLengthCol) = 0;
% checking accuracy by number of correctly classified
for k=(1: testLengthRow )
x=[1, testSet(k,1:testLengthCol)];
O1= x' .* weights' ;
%computing the value of vector with plane
sum =0;
for p=1:length(O1)
sum = sum +O1(p);
end
y1x = 1/(1+ exp(-1*sum));
if(y1x>=0.5)
%disp('class 1');
O =1;
else
%disp('class 0');
O =0;
end
% error as output approaching target
if (O == testLabels(k))
% correctly classified examples
correctlyClassified=correctlyClassified+1;
%compute TP, TN
if(testLabels(k)==1)
TP = TP+1;
else
TN = TN +1;
end
else
% wrongly classified examples
if(testLabels(k)==1)
FN = FN+1;
else
FP = FP +1;
end
%storing 5 misclassified classes from each class
if(count1<5 && testLabels(k)==1)
count1 = count1 + 1;
unClassified(count1,1: testLengthCol) = testSet(k,1: testLengthCol);
end
if(count0<5 && testLabels(k)==0 )
count0 = count0 + 1;
unClassified(count0,1: testLengthCol) = testSet(k,1: testLengthCol);
end
end
end
k
P= TP/(TP+FP)
R= TP/(TP+FN)
v=[TP, TN, FP, FN, P, R, 2*P*R / (P+R) , correctlyClassified/testLengthRow]
disp('TP, TN, FP, FN, TP/(TP+FP), TP/P, 2*P*R / (P+R) , correctlyClassified/trainLengthRow');
unClassified;
accuracy = correctlyClassified/testLengthRow ;
accuracy
end