Material for the EPFL master course "A Network Tour of Data Science", edition 2018.
Alternatives To Ntds_2018
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
3 years agomitJupyter Notebook
Material for the EPFL master course "A Network Tour of Data Science", edition 2017.
3 years agootherJupyter Notebook
Material for the EPFL master course "A Network Tour of Data Science", edition 2018.
3 years agootherJupyter Notebook
Material for the EPFL master course "A Network Tour of Data Science", edition 2019.
Tdf Starters Rul12
3 years agogpl-3.0Jupyter Notebook
Using a neural network with LSTMs to predict the career end of Tour de France starters between 1995 and 2019.
6 years agoClojure
Compositional Pattern Producing Networks explorer
Knight Tour Neural Network2
4 years agogpl-3.0Python
Implementation Of Knight Tour Problem Using Neural Networks
Alternatives To Ntds_2018
Select To Compare

Alternative Project Comparisons

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 course material revolves around the following topics: Network Science, Spectral Graph Theory, Graph Signal Processing, Data Science, Machine Learning.

Theoretical knowledge is taught during lectures. Practical knowledge is taught through tutorials. Both are practiced and evaluated through a semester project. Below are slides about the organization of the course.

  1. Course organization
  2. Project expectations
  3. Concluding remarks

The content is similar to the 2017 edition and is further developed in the 2019 edition. Compared to the 2016 edition, the course has been refocused on graph and network sciences.


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

  1. Installation instructions
  2. Introduction
  3. Building graphs from edge lists
  4. Building graphs from features
  5. Plotting with matplotlib
  6. Interactive graph visualization with gephi
  7. Sparse matrices with scipy
  8. Linear algebra for graphs and networkx
  9. Graph signal processing with pygsp

For this course, we'll introduce and use the following tools: conda & anaconda, python, jupyter, git, numpy, scipy, matplotlib, pandas, networkx, graph-tool, pygsp, gephi.


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

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

Below is the work of the 180 students enrolled that year.


As each team stored their code in a github repository, all their code can conveniently be downloaded with git clone --recurse-submodules https://github.com/mdeff/ntds_2018. One folder per team will be populated in projects/code.


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. Navigate to the folder where you want to store the course material with cd path/to/ntds. Windows users may need \ instead of / as the path separator.
  5. Download this repository with git clone https://github.com/mdeff/ntds_2018.
  6. Enter the repository with cd ntds_2018.
  7. Create an environment with the packages required for the course with conda env create -f environment.yml.
  8. If everything went fine, you should be able to run the test_install.ipynb notebook after following the above steps.

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. Navigate to the folder where you stored the course material with cd path/to/ntds_2018.
  4. Start Jupyter with jupyter notebook or jupyter lab. The command should open a new tab in your web browser.
  5. Edit and run the notebooks from your browser.



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

Popular Tour Projects
Popular Network Projects
Popular User Interface Components Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Jupyter Notebook
Data Science