gismo 0.3.0

Features

Gismo combines three main ideas:

• TF-IDTF: a symmetric version of the TF-IDF embedding.

• DI-Iteration: a fast, push-based, variant of the PageRank algorithm.

• Fuzzy dendrogram: a variant of the Louvain clustering algorithm.

Quickstart

Install gismo:

$ pip install gismo

Import gismo in a Python project:

import gismo as gs

Credits

Thomas Bonald, Anne Bouillard, Marc-Olivier Buob, Dohy Hong.

This package was created with Cookiecutter and the francois-durand/package_helper project template.

0.3.0 (2020-05-13)

• dblp module: url2source function added to directly load a small dblp source in memory instead of using a FileSource approach.

• Possibility to disable query distortion in gismo.

• XGismo class to cross analyze embeddings.

• Tutorials updated

0.2.5 (2020-05-11)

• auto_k feature: if not specified, a query-dependent, reasonable, number of results k is estimated.

• covering methods added to gismo. It is now possible to use get_covering_* instead of get_ranked_* to maximize coverage and/or eliminate redundancy.

0.2.4 (2020-05-07)

• Tutorials for ACM and DBLP added. After cleaning, there is currently 3 tutorials:

  • Toy model, to get the hang of Gismo on a tiny example,

  • ACM, to play with Gismo on a small example,

  • DBLP, to play with a large dataset.

0.2.3 (2020-05-04)

• ACM and DBLP dataset creation added.

0.2.2 (2020-05-04)

• Notebook tutorials added (early version)

0.2.1 (2020-05-03)

• Actual code

• Coverage badge

0.1.0 (2020-04-30)

• First release on PyPI.