This repository contains code for the Introduction to Machine Learning course. The course covers the basics of machine learning, including supervised and unsupervised learning, classification, regression, clustering, and more.
The diagonal_vs_egocentric.py
program shows the Bayes theorem for generalization error. It predicts the theoretical bound for Pr[abs(error_in-error_out) > eps] and calculates the approximated probability of Pr[abs(error_in-error_out) > eps] by the frequency - number of occurrences divided by the number of hypotheses. It then compares the theoretical and approximated probabilities for diagonal and egocentric models.
The pokemon_classification.py
program compares several SKLearn models to classify pokemons based on a Kaggle dataset. The program takes in the dataset and trains several models, including logistic regression, decision trees, and random forests. It then compares the accuracy of the models and outputs the results.