Coursera Machine Learning Exercises using Python
In this repository you will find Python-implementations of (most of) the programming exercises in Andrew Ng's Machine Learning course (which is actually taught using Octave/Matlab).
Every exercise folder includes a data-subfolder containing files provided by the course, which are needed to complete the specific exercise. For most exercises, two different jupyter notebook files are included, one containing an implementation using numpy (where most of the needed functionality is written from scratch or translated from the Octave/Matlab code) and another using scikit-learn (which provides most of the needed functionality out of the box).
Notebooks
| Exercise | Implementations |
|---|---|
| 1 - Linear Regression | numpy, scikit-learn |
| 2 - Logistic Regression | numpy, scikit-learn |
| 3 - Multi-class Classification and Neural Networks | numpy, scikit-learn |
| 4 - Neural Networks Learning | numpy, scikit-learn |
| 5 - Regularized Linear Regression and Bias v.s. Variance | numpy, scikit-learn |
| 6 - Support Vector Machines | scikit-learn |
| 7 - K-means Clustering and Principal Component Analysis | numpy, scikit-learn |
| 8 - Anomaly Detection and Recommender Systems | numpy |