Shared utilities for implementing different interpretable models.

Expand source code

'''Shared utilities for implementing different interpretable models.
'''

Sub-modules

imodels.util.apply: Map samples to the leaves they land in, like sklearn's tree.apply.
imodels.util.arguments
imodels.util.automl
imodels.util.checks
imodels.util.convert
imodels.util.data_util
imodels.util.distillation
imodels.util.ensemble
imodels.util.explain_errors
imodels.util.extract
imodels.util.get_rules: Extract the rules of a fitted model as a pandas DataFrame …
imodels.util.metrics
imodels.util.model_trees: Find the scikit-learn trees behind a fitted imodels model …
imodels.util.neural_nets: Bridging random forests and deep neural networks. Code to convert a sklearn decision tree to a pytorch neural network following "Neural Random …
imodels.util.prune
imodels.util.rule
imodels.util.score
imodels.util.sklearn_compat: Thin wrappers over private sklearn helpers whose signatures change between versions.
imodels.util.transforms: Shared transforms between different interpretable models
imodels.util.tree
imodels.util.tree_interaction_utils
imodels.util.tree_viz: Plot imodels trees with dtreeviz …