/PCGCE

Primary LanguageJupyter Notebook

PCGCE

Package to test causal discovery algorithm on simulated and real data

Methods

Some algorithms are imported from other langauges such as R and Java

Test

To test algorithms on simulated data run:

python3 test_simulated_data_v2.py method structure graph_type n_samples num_processor verbose

  • method: causal dicovery algorithms, choose from [PCTCE, GangerLasso, TCDF, PCMCIplusCMIknn, oCSE, tsFCI, VarLiNGAM, TiMINO, Dynotears]
  • structure: causal structure, choose from [diamond, cycle, 7ts2h]
  • graph_type: choose from [acyclic, cyclic]
  • self_cause: chose from [True, False]
  • max_lag: maximal lag
  • n_samples: number of timestamps
  • num_processor: number of processors

Example: python3 test_fmri.py "PCTCE" "fork" 1000 1 1

To test algorithms on fmri data run:

python3 test_simulated_data.py method num_processor verbose

Example: python3 test_fmri.py "PCTCE" 1 1