Welcome to CEML’s documentation!¶
Counterfactuals for Explaining Machine Learning models - CEML¶
CEML is a Python toolbox for computing counterfactuals. Counterfactuals can be used to explain the predictions of machine learing models.
It supports many common machine learning frameworks:
scikit-learn (0.24.0)
PyTorch (1.7.1)
Keras & Tensorflow (2.4.0)
Furthermore, CEML is easy to use and can be extended very easily. See the following user guide for more information on how to use and extend ceml.
- ceml
- ceml.sklearn
- ceml.sklearn.counterfactual
- ceml.sklearn.plausibility
- ceml.sklearn.decisiontree
- ceml.sklearn.knn
- ceml.sklearn.linearregression
- ceml.sklearn.lvq
- ceml.sklearn.models
- ceml.sklearn.naivebayes
- ceml.sklearn.lda
- ceml.sklearn.qda
- ceml.sklearn.pipeline
- ceml.sklearn.randomforest
- ceml.sklearn.isolationforest
- ceml.sklearn.softmaxregression
- ceml.sklearn.utils
- ceml.tfkeras
- ceml.torch
- ceml.costfunctions
- ceml.model
- ceml.optim
- ceml.backend.jax
- ceml.backend.torch
- ceml.backend.tensorflow