Code for Anomaly Detection

Estimating parameters for a Gaussian

function [mu sigma2] = estimateGaussian(X)

%ESTIMATEGAUSSIAN This function estimates the parameters of a 
%Gaussian distribution using the data in X
%   [mu sigma2] = estimateGaussian(X), 
%   The input X is the dataset with each n-dimensional data point in one row
%   The output is an n-dimensional vector mu, the mean of the data set
%   and the variances sigma^2, an n x 1 vector

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

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

% Instructions: Compute the mean of the data and the variances
%               In particular, mu(i) should contain the mean of
%               the data for the i-th feature and sigma2(i)
%               should contain variance of the i-th feature.
%
mu=mean(X);
sigma2=var(X);

end

Selecting the threshold, ε

function [bestEpsilon bestF1] = selectThreshold(yval, pval)

%SELECTTHRESHOLD Find the best threshold (epsilon) to use for selecting
%outliers
%   [bestEpsilon bestF1] = SELECTTHRESHOLD(yval, pval) finds the best
%   threshold to use for selecting outliers based on the results from a
%   validation set (pval) and the ground truth (yval).

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

stepsize = (max(pval) - min(pval)) / 1000;
for epsilon = min(pval):stepsize:max(pval)

    % Instructions: Compute the F1 score of choosing epsilon as the
    %               threshold and place the value in F1. The code at the
    %               end of the 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.
    %               
    % Note: You can use predictions = (pval < epsilon) to get a binary vector
    %       of 0's and 1's of the outlier predictions
    %  you can find out how many values in this vector are 0 by using: sum(v == 0). 

predictions=(pval<epsilon);      
tp=sum((yval==1)&(predictions==1));  
fp=sum((yval==0)&(predictions==1)); 
fn=sum((yval==1)&(predictions==0)); 
prec=tp/(tp+fp);
rec=tp/(tp+fn);  
F1=2*prec*rec/(prec+rec);

    if F1 > bestF1
       bestF1 = F1;
       bestEpsilon = epsilon;
    end
end

end