Find anomalies from data

findAnomaly.m

function [mu sigma2] = estimateGaussian(X)
% To estimate parameters of Gaussian distribution using data

% Useful variables
[m, n] = size(X);

% You should return these values correctly
mu = zeros(n, 1);
sigma2 = zeros(n, 1);

% compute mean and variance
mu = mean(X);
sigma2 = sum((X - repmat(mu, m, 1)).^2)/m;

end

function [bestEpsilon bestF1] = selectThreshold(yval, pval)
% Find the best threshold (epsilon) to use for selecting outliers

bestEpsilon = 0;
bestF1 = 0;
F1 = 0;

stepsize = (max(pval) - min(pval)) / 1000;
for epsilon = min(pval):stepsize:max(pval)
    
    % Compute F1 score of choosing epsilon threshold. 
    % This code loop will compare the F1 score for this
    % choice of epsilon and set it to be the best epsilon if
    % it is better than the current choice of epsilon.

    predictions = (pval < epsilon);

    tp = sum(predictions.*yval);  % detects 1 1 (prediction, actual)
    fp = sum(predictions > yval); % detects 1 0 (prediction, actual)
    fn = sum(predictions < yval); % detects 0 1 (prediction, actual)
    
    prec = tp / (tp + fp);
    rec = tp / (tp + fn);

    F1 = 2 * prec * rec / (prec + rec);
    
    if F1 > bestF1
       bestF1 = F1;
       bestEpsilon = epsilon;
    end
end

end