Machine Learning Tutorials

This repository contains my machine learning tutorials. Each Jupyter notebook illustrates a fundamental concept or method using a toy dataset. Most of the tutorials are built around scikit-learn.

• evaluation/ -- Model evaluation techniques such as cross-validation, confusion matrices, precision-recall curves, etc.
• preprocessing/ -- Data preprocessing techniques such as imputation, encoding, scaling, etc.
• special-topics/ -- Miscellaneous or advanced topics such as computer vision, survival analysis, time series analysis, etc.
• supervised/ -- Examples of supervised learning methods like classification and regression
• unsupervised/ -- Examples of unsupervised learning methods like clustering

To run the Jupyter notebooks, you can install the necessary Python packages using either conda or pip:

$ conda install --file requirements_conda.txt

$ pip install -r requirements_pip.txt

References:

CPSC 330: Applied Machine Learning (University of British Columbia, 2020)