Skip to content

Latest commit

 

History

History
16 lines (10 loc) · 752 Bytes

readme.md

File metadata and controls

16 lines (10 loc) · 752 Bytes

Code for the paper "Block-Structure Based Time-Series Models For Graph Sequences" (2017)

This codebase is for algorithms proposed in the aforementioned paper. It consists of the following python3 scripts:

  • graph_generators.py : has the synthetic/real instance generators
  • graph_estimators.py : has the proposed algorithms
  • experiments.py : calls algorithms on various instances
  • plots_paper.py : generates plots given in the paper

The easiest way to get started is to look at experiments.py and go from there.

Dependencies

The prominent are: numpy, networkx, graph-tool, pulp, matplotlib.

Please make a pull request if you spot bugs or have suggestions!