Programmation of Maximum a Posteriori (MAP) and Maximum Likelihood (ML) classifier problem

i need help In this project.

program two classifiers, the one based on the principle of maximizing likelihood (ML), and the principle of maximizing posterior probability (MAP),

You will study the effect of imbalance on classification accuracy.

To do this, in the generation of the data, you will set the number of examples of a class, NA and you will vary the number of examples of the other class as follows:

Nb= 𝛼NA

𝛂 varies in range [1, 10, 100, 1000].

To estimate the fdp of the two classes, you use the distance of mahalanobis:

Where 1 is the inverse of the covariance matrix.

The estimation of the covariance matrix will be done for each class.

You draw the decision boundary for each case of the value of α.