error in plotting Index in position 2 exceeds array bounds.

Hello

Im quite new to matlab

currently im trying to plot as in

https://uk.mathworks.com/help/stats/classificationecoc.html

using dataset from

https://www.kaggle.com/uciml/human-activity-recognition-with-smartphones

my code is below

clear; close all; clc;

T = readtable('train.csv');

X = T(:,(1:562));
Y = T(:,{'Activity'});


t = templateSVM('Standardize',true,'SaveSupportVectors',true);
predictorNames = {'alfa','beta'};

responseName = 'Human Activity';
classNames =  {'STANDING','SITTING','LAYING','WALKING','WALKING_DOWNSTAIRS','WALKING_UPSTAIRS'}; % Specify class order
Mdl = fitcecoc(X,Y);

Mdl.ClassNames

Mdl.CodingMatrix

L = size(Mdl.CodingMatrix,6); % Number of SVMs
sv = cell(L,1); % Preallocate for support vector indices


for j = 1:L
    SVM = Mdl.BinaryLearners{j};
    sv{j} = SVM.SupportVectors;
    sv{j} = sv{j}.*SVM.Sigma + SVM.Mu;
end


hold on
markers = {'ko','ko','ko','ko','ko','ko','ko'}; % Should be of length L
for j = 1:L
    svs = sv{j};
    plot(svs(:,1),svs(:,2),markers{j},...
        'MarkerSize',10 + (j - 1)*3);
end
title('Fisher''s Iris -- ECOC Support Vectors')
xlabel(predictorNames{1})
ylabel(predictorNames{2})
legend([classNames,{'Support vectors - SVM 1',...
    'Support vectors - SVM 2','Support vectors - SVM 3'}],...
    'Location','Best')
hold off

unfortunettly im getting error

Index in position 2 exceeds array bounds.Index in position 2 exceeds array bounds.

Error in learningmulticlasCVN (line 35)

plot(svs(:,1),svs(:,2),markers{j},..

Answer 1

[Rajani Mishra]

I tried running your code and debugged for the error encountered. Error – “Exceeds array bounds” is faced when index out of array size is accessed, which was the case in the line with a call to plot() function.

I have made some changes in the code provided:

1. I have changed as the way input X and Y are passed to function to fitcecoc():

T = readtable('train.csv');
Y = T(:,{'Activity'});
X = T(:,(1:562));
X = X{:,:};
Y = Y{:,:};
t = templateSVM('Standardize',true,'SaveSupportVectors',true);
predictorNames = {'alfa','beta'};
responseName = 'Human Activity';
classNames =  {'STANDING','SITTING','LAYING','WALKING','WALKING_DOWNSTAIRS','WALKING_UPSTAIRS'}; % Specify class order
Mdl = fitcecoc(X,Y,'Learners',t,'ResponseName',responseName,'ClassNames',classNames)

2. I have changed the second argument passed to size () function, as the second argument defines the dimension along which you want to calculate the size of the matrix. As here “Mdl.Codingmatrix” is of size 6* 16, its second dimension whose size is required.

L = size(Mdl.CodingMatrix,2); % Number of SVMs

3. Definition of markers array

markers = {'ko','ko','ko','ko','ko','ko','ko','ko','ko','ko','ko','ko','ko','ko','ko'}; % Should be of length L

I have attached the result after making the above changes.

Hope this helps!

[Tomasz Kaczmarski]

great thanks !