Skip to content

ML

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

ML

README.md

Coursera Machine Learning MOOC by Andrew Ng

Python Programming Assignments

This repositry contains the python versions of the programming assignments for the Machine Learning online class taught by Professor Andrew Ng. This is perhaps the most popular introductory online machine learning class. In addition to being popular, it is also one of the best Machine learning classes any interested student can take to get started with machine learning. An unfortunate aspect of this class is that the programming assignments are in MATLAB or OCTAVE, probably because this class was made before python became the go-to language in machine learning.

The Python machine learning ecosystem has grown exponentially in the past few years, and is still gaining momentum. I suspect that many students who want to get started with their machine learning journey would like to start it with Python also. It is for those reasons I have decided to re-write all the programming assignments in Python, so students can get acquainted with its ecosystem from the start of their learning journey.

These assignments work seamlessly with the class and do not require any of the materials published in the MATLAB assignments. Here are some new and useful features for these sets of assignments:

  • The assignments use Jupyter Notebook, which provides an intuitive flow easier than the original MATLAB/OCTAVE assignments.
  • The original assignment instructions have been completely re-written and the parts which used to reference MATLAB/OCTAVE functionality have been changed to reference its python counterpart.
  • The re-written instructions are now embedded within the Jupyter Notebook along with the python starter code. For each assignment, all work is done solely within the notebook.
  • The python assignments can be submitted for grading. They were tested to work perfectly well with the original Coursera grader that is currently used to grade the MATLAB/OCTAVE versions of the assignments.
  • After each part of a given assignment, the Jupyter Notebook contains a cell which prompts the user for submitting the current part of the assignment for grading.

Online workspace

You can work on the assignments in an online workspace called Deepnote. This allows you to play around with the code and access the assignments from your browser.

Downloading the Assignments

To get started, you can start by either downloading a zip file of these assignments by clicking on the Clone or download button. If you have git installed on your system, you can clone this repository using :

git clone https://github.com/Travor278/ml-coursera-python-assignments.git

Each assignment is contained in a separate folder. For example, assignment 1 is contained within the folder Exercise1. Each folder contains two files:

  • The assignment jupyter notebook, which has a .ipynb extension. All the code which you need to write will be written within this notebook.
  • A python module utils.py which contains some helper functions needed for the assignment. Functions within the utils module are called from the python notebook. You do not need to modify or add any code to this file.

Requirements

The original upstream notebooks were developed using an older Python stack:

- python==3.6.4
- numpy==1.13.3
- scipy==1.0.0
- matplotlib==2.1.2
- jupyter==1.0.0
- jupyter-client==5.0.1

This fork is currently being used on the following modern local environment:

- python==3.13.9
- numpy==2.3.5
- scipy==1.16.3
- matplotlib==3.10.6
- notebook==7.4.5
- jupyter-client==8.6.3
- requests==2.32.5

Python 2 is not supported.

Python Installation

We recommend using Anaconda or Miniconda for installing Python. A simple way to create a modern environment similar to the one used in this fork is:

conda create -n machine_learning python=3.13 numpy scipy matplotlib notebook jupyter_client requests

After the environment is created, activate it with:

conda activate machine_learning

To reduce notebook-only diffs across different computers, you can enable the local pre-commit hook in this repo with:

python scripts/install_git_hooks.py

This will run scripts/normalize_notebooks.py before each commit so notebook outputs, execution counts, and machine-specific kernel metadata do not get committed accidentally.

Now we have our python environment all set up, we can start working on the assignments. To do so, navigate to the directory where the assignments were installed, and launch Jupyter from the terminal using either command below:

jupyter notebook

or

jupyter lab

This should automatically open a tab in the default browser. To start with assignment 1, open the notebook ./Exercise1/exercise1.ipynb.

Python Tutorials

If you are new to python and to jupyter notebooks, no worries! There is a plethora of tutorials and documentation to get you started. Here are a few links which might be of help:

Caveats and tips

  • In many of the exercises, the regularization parameter $\lambda$ is denoted as the variable name lambda_, notice the underscore at the end of the name. This is because lambda is a reserved python keyword, and should never be used as a variable name.

  • In numpy, the function dot is used to perform matrix multiplication. The operation '*' only does element-by-element multiplication (unlike MATLAB). If you are using python version 3.5+, the operator '@' is the new matrix multiplication, and it is equivalent to the dot function.

Acknowledgements

  • I would like to thank professor Andrew Ng and the crew of the Stanford Machine Learning class on Coursera for such an awesome class.

  • Some of the material used, especially the code for submitting assignments for grading is based on mstampfer's python implementation of the assignments.