In December 2018, I enrolled in an 3-month online applied machine learning course provided by Columbia University of New York. The course was very heavy in machine learning theory, with homework assigned to implement the algorithms from scratch in Python, using nothing but Pandas and Numpy.
This repository contains the Jupyter notebooks I worked on for my assignments in that course, plus the training and test data used in those Notebooks.
I implemented notebooks for the following algorithms:
- Least squares linear regression
- Ridge regression
- Bayesian linear regression
- Logistic regression
- K-nearest neighbor classifier
- Random forest classifier
- Adaptive Boosting
To be committed later (currently cleaning up the notebooks)
- k-means clustering with Gaussian Mixture Model
- Item recommendation system
- Hidden Markov Model
- Association Analysis