Implement tests - Githubissues

Laouen / THOI

THOI: An efficient library for higher order interactions analysis based on Gaussian copulas enhanced by batch-processing

MIT License

8 stars 1 forks source link

Implement tests #5

Open Laouen opened 6 months ago

Laouen commented 6 months ago

We need to add enough tests to allow future developement of the library to mantain the same results consistency. We should add tests from the publication data so we now those result are mantained as a minimal robustness test across versions

Laouen commented 3 months ago

Some initial tests were added to test the most general multi_order_measures agains a precalculated value

Laouen commented 1 month ago

[ ] Make tests for all possible types of inputs (X as np.ndarray, torch.Tensor, List[np.ndarray], List[torch.Tensor]) for precomputed or not input data X and the rest of the parameters.
[ ] Test Greedy and Simulated Annealing
[ ] Gaussian copula
[x] Con más de un dataset
[ ] Create test using the Data published in the paper