Recreate environment:
conda env create -f requirements.yml
conda activate experiments
conda install -c anaconda ipykernel
python -m ipykernel install --user --name=experiments
- The code to run the algorithms described in the paper can be found in
Certification/cert_utils.ipynb
. - To reproduce the figures in the paper, please see the Jupiter Notebook
Certification/Identifiability_plots.ipynb
.
- The algorithms for estimation of the causal effects implemented in
Estimation/src/python
andEstimation/src/matlab
. - To reproduce the results one can run the jupyter-notebooks
Estimation/main_laplace.ipynb
andEstimation/main_exponential.ipynb
. Please note that:- RICA algorithm is implemented in matlab. Therefore installed matlab is required to reproduce all the results. Please change the value of variable
RUN_MATLAB
toFalse
in jupyter-notebooks to reproduce the results of all other algorithms except RICA.
- RICA algorithm is implemented in matlab. Therefore installed matlab is required to reproduce all the results. Please change the value of variable
See LICENSE
for more information.
Daniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Mathias Drton, Negar Kiyavash.