Scikit-mine : pattern mining in Python

• Descriptive analysis, leading to interpretable, concise descriptions using the Minimum Description Length Principle
• Fast Algorithms
• Simple, extendable API, inspired by scikit-learn

Resources

• Free software: BSD license
• GitHub: /~https://github.com/scikit-mine/scikit-mine
• Documentation: https://scikit-mine.github.io/scikit-mine/

Quickstart

scikit-mine is a Python module for pattern mining built on top of Pandas/Numpy/SciPy and is distributed under the 3-Clause BSD license.

It is currently maintained by a team of volunteers.

See examples in the tutorials; the notebooks are available here. To execute the tutorials, you will have to install jupyter notebook or jupyterlab (https://jupyter.org/install)

Dependencies

scikit-mine requires Python>=3.8, and some extra dependencies

• scipy>=1.2.1
• pandas>=1.0.0
• pyroaring>=0.3.4
• joblib>=0.11.1
• sortedcontainers>=2.1.0
• dataclasses>=0.6
• networkx
• wget>=3.2
• scikit-learn
• graphviz
• matplotlib
• pydot

Development

This project benefitted from fundings from the INRIA center in Rennes, Brittany, France, as well as from the CNRS PNRIA Programme.

We welcome new contributors of all experience levels.

Internal Contributors

• Rémi Adon (/~https://github.com/remiadon)
• Hermann Courteille (/~https://github.com/hermann74)
• Cyril Regan (/~https://github.com/cyril-data)
• Thomas Betton (/~https://github.com/thomasbtnfr)
• Esther Galbrun (/~https://github.com/nurblageij)
• Peggy Cellier (/~https://github.com/PeggyCellier)
• Alexandre Termier (/~https://github.com/alexandre-termier)
• Luis Galárraga (/~https://github.com/lgalarra)
• Josie Signe (/~https://github.com/Darlysia)
• Francesco Bariatti (/~https://github.com/fbariatti)
• Mensah-David Assigbi (/~https://github.com/davidassigbi)
• Arnauld-Cyriaque Djedjemel (/~https://github.com/Ariaque)