Matlab Linear Regression Sample Code

Three type of datasets have been analyzed for this technique:

(1) Linearly separable data(LS)

(2) Inseparable data(NLS)

(3) Banana data (BD)

For a binary classification problem. Split the datasets into 70% training and 30% testing randomly in five folds. This is a old code done as a part of an assignment. Compatibility with newer versions may happen.

% This is for binary class problem, where we are fitting in k dimension.

%This is the code for classification using linear regression.

function linearRegression_LSData()
disp(‘..Starting linear 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 );

    testSet = test1(1:rowtest, 1 : coltest -1 );
    testLabels = test1(1:rowtest, coltest );


    disp('training length');
    disp(trainLengthCol);
    disp(trainLengthRow);
    disp(rowtest);
    disp(coltest);       

    weights(1:trainLengthCol)=0;
    [weights] = train1LinearReg(trainingSet,trainingLabels);
    disp(weights);

    [correctlyClassified,count0,count1,unClassified,v] =  testLinearReg(testSet,testLabels, weights);
    vtot = vtot +v ;

end
disp(‘TP, TN, FP, FN, TP/(TP+FP), TP/P, 2PR / (P+R) , correctlyClassified/trainLengthRow’);
%taking average of all quantaties of TP, TN, FP, FN etc.
vtot = vtot ./ 5
end

%Method to do train the Linear Regression Model
%——-Paramaeters————
%trainingSet: The training set
%trainingLabels: The traingin labels corresponding to training Set
%————Return Type——————-
%weights: weights computed by linear regression
function [weights] = train1LinearReg(trainingSet,trainingLabels)

[trainLengthRow, trainLengthCol] = size(trainingSet);
weights(1:trainLengthCol+1)=0;
Y=trainingLabels;
X(1:trainLengthRow, 1:trainLengthCol+1) = 0;
X(1:trainLengthRow, 1)= 1;
X(1:trainLengthRow, 2:trainLengthCol+1) = trainingSet;
disp(X);
disp(Y);
Z= X'* X;
weights = (inv(Z)) *(X' * Y);    


%the following is for display of plots and surfaces 
y1=weights' * X';

%Plotting the regression line
 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;

     k=5;

 figure     
 scatter3(x1,x2,trainingLabels,10);     
 axis([-1*k,k,-1*k,k,-1*k,k])

 figure     
 plot3(x1,x2,y1); 
 axis([-1*k,k,-1*k,k,-1*k,k])


 xx=(-1*k:1:k);
 yy=(-1*k:1:k);
 [xx1,yy1]=meshgrid(xx,yy);

 %drawing the surface
 sum = -1 .* (weights(1)+weights(2).*xx1+weights(3).*yy1);
 zz= 1 ./(1 + expm(sum));     
 figure
 surf(xx1,yy1,zz);
 title('Surface');
 xlabel('x');
 ylabel('y')
 zlabel('z');

end

%This function tests the test set with testlabels and the computed outputs
%———–paramaters———–
%testSet: The Test Set for testing
%testLables: Corresponding test labels
%weights: weights computed from the training
%—————Return—————–
% correctlyClassified: correctly classified number of samples
% unClassified: 10 unclassified samples
%v: vector that stores TP ;TN;FP; FN ; P; R; F; Accuracy
%count0: Number of class -1 unclassified upto max val of 5
%count1: Number of class +1 unclassified upto max val of 5
function [correctlyClassified,count0,count1,unClassified,v] = testLinearReg(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

    % setting the outputs
    if(sum > 0)
        O=1;
    else 
        O=-1;
    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)==-1 )
            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