Exercises from the highly recommended, and free, online course offered at :: https://www.coursera.org/learn/machine-learning This is easily one of the most - if not the most - popular introductory online machine learning class. For an introduction course it covers a fair bit of ground covering various algorithms in machine learning such as Linear Regression, Logistic Regression, Neural Networks, Support Vector Machines, Unsupervised Learning, Anomaly Detection, Recommender Systems, etc. But, what I (and I'm sure many others) , love about this course is that it explains the math behind the various algorithms in addition to getting you hands on with the coding.

The course uses GNU Octave as the programming language, since we're largely dealing with numerical computations. While many might consider it as a downer, I was quite happy to get introduced to MATLAB thru it. I then rewrote the whole set of exercises in Python 3, which further helped cement my understanding of the course material.

Each folder consists of the exercises in Octave, and Python 3.

exercise-01/
    octave/
        ex1.m
        ...
    python/
exercise-02/
    octave/
    python/
...
exercise/08/
    octave/
    python/

The Python code will not run out of the box. There are several additional modules that need to be installed (.e.g via sudo pip3 install ) The additional modules required are:

• numpy
• matplotlib
• pandas
• scipy

Additionally, certain routine that are commonly used in all exercises, e.g. loading a file, plotting the data, etc, are saved as a common utility, and saved in tool/kit.py.