Material for the EPFL master course "A Network Tour of Data Science", edition 2018.
Switch branches/tags
Nothing to show
Clone or download

README.md

A Network Tour of Data Science, edition 2018

Binder   (Jupyter lab or notebook)

This repository contains the material for the practical work associated with the EPFL master course EE-558 A Network Tour of Data Science (moodle), taught in fall 2018. The content is similar to the 2017 edition. Compared to the 2016 edition, the course has been refocused on graph and network sciences. The course material revolves around the following topics:

  1. Network Science,
  2. Spectral Graph Theory,
  3. Graph Signal Processing,
  4. Data Science,
  5. Machine Learning.

Theoretical knowledge is taught during lectures. Practical knowledge is taught through tutorials. Both are practiced and evaluated through a semester project. More information about the course is found in those slides.

Tutorials

Below is the teaching material you'll find in this repository.

  1. Practical informations about the organization of the course
  2. Installation instructions
  3. Introduction: conda & anaconda, python, jupyter, git
  4. Data exploration with pandas
  5. Numerical computing with numpy
  6. Plotting with matplotlib
  7. Interactive graph visualization with gephi
  8. Sparse matrices with scipy
  9. Network science with networkx and graph-tool
  10. Graph signal processing with pygsp
  11. Concluding remarks

Projects

During the course of a semester project, students exercise the theory seen in class on real data and networks. Projects are carried out by groups of four students, and are to be chosen in the list of proposed projects. The students have to deliver four milestones, following the theory seen in class:

  1. Network properties: measure and interpret some properties of the network.
  2. Network models: fit some relevant network models and comment on their fitness.
  3. Spectral graph theory: visualize or cluster your graph using the spectrum of the graph Laplacian.
  4. Graph signal processing: analyze data (signals, features) on the graph.

After completing those milestones, they are free to pursue any other direction of interest. Those data projects are meant to jointly evaluate their theoretical network analysis skills and practical Data Science skills.

Below is their work.

  • [report, slides, code] Project name

Installation

Click the binder badge to play with the notebooks from your browser without installing anything.

For a local installation, you will need git, Python, and packages from the Python scientific stack. If you don't know how to install those on your platform, we recommend to install Miniconda or Anaconda, a distribution of the conda package and environment manager. Follow the below instructions to install it and create an environment for the course.

  1. Download the Python 3.x installer for Windows, macOS, or Linux from https://conda.io/miniconda.html and install with default settings. Skip this step if you have conda already installed (from Miniconda or Anaconda). Linux users may prefer to use their package manager.
    • Windows: Double-click on Miniconda3-latest-Windows-x86_64.exe.
    • macOS: Run bash Miniconda3-latest-MacOSX-x86_64.sh in your terminal.
    • Linux: Run bash Miniconda3-latest-Linux-x86_64.sh in your terminal.
  2. Open a terminal. Windows: open the Anaconda Prompt from the Start menu.
  3. Install git with conda install git.
  4. Download this repository by running git clone https://github.com/mdeff/ntds_2018.
  5. Create an environment with the packages required for the course with conda env create -f ntds_2018/environment.yml.

Every time you want to work, do the following:

  1. Open a terminal. Windows: open the Anaconda Prompt from the Start menu.
  2. Activate the environment with conda activate ntds_2018 (or activate ntds_2018, or source activate ntds_2018).
  3. Start Jupyter with jupyter notebook or jupyter lab. The command should open a new tab in your web browser.
  4. Edit and run the notebooks from your browser.

Team

License

The content is released under the terms of the MIT License.