Implementation of Adaboost algorithm while boosting the Linear Regression based weak classifier, plotting training vs testing error and seeing how training error goes to 0, plotting a histogram of important features along with alphas and epsilons as a function of the number of iterations.

Implementing Naive Bayes algorithm from scratch using numpy in Python. The dataset has 57 features, out of which the first 54 follow Bernoulli Distribution and the other 3 come from a Pareto Distribution.

Implementing K-Nearest Neighbors Classification Algorithm using numpy in Python and visualizing how varying the parameter K affects the classification accuracy

Implementing logistic regression using numpy in Python and visualizing the objective function variation as a function of iterations. The log likelihood function for logistic regression is maximized over w using Steepest Ascent and Newton's Method

Implementing ridge regression using numpy in Python and visualizing the importance of features and the effect of varying hyperparameters on the degree of freedom and RMSE