Expand source code 
from .figs_ensembles import FIGSExtRegressor, FIGSExtClassifier

# re-exported for callers; listed so the intent is explicit
__all__ = [
    "FIGSExtClassifier", "FIGSExtRegressor",
]

Sub-modules

imodels.experimental.bartpy
imodels.experimental.figs_ensembles
imodels.experimental.figs_shrinkage
imodels.experimental.stablelinear
imodels.experimental.stableskope
imodels.experimental.tree_gam_simple
imodels.experimental.util

Classes

class FIGSExtClassifier (max_rules: int = None, posthoc_ridge: bool = False, include_linear: bool = False, max_features=None, min_impurity_decrease: float = 0.0, k1: int = 0, k2: int = 0)

FIGSExt (sum of trees) classifier. Fast Interpretable Greedy-Tree Sums (FIGS) is an algorithm for fitting concise rule-based models. Specifically, FIGS generalizes CART to simultaneously grow a flexible number of trees in a summation. The total number of splits across all the trees can be restricted by a pre-specified threshold, keeping the model interpretable. Experiments across a wide array of real-world datasets show that FIGS achieves state-of-the-art prediction performance when restricted to just a few splits (e.g. less than 20). https://arxiv.org/abs/2201.11931

max_features The number of features to consider when looking for the best split k1: number of iterations of tree-prediction backfitting to do after making each split k2: number of iterations of tree-prediction backfitting to do after the end of the entire tree-growing phase

Expand source code 
class FIGSExtClassifier(FIGSExt):
    def _init_prediction_task(self):
        self.prediction_task = 'classification'

Ancestors

  • FIGSExt
  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester

Inherited members

class FIGSExtRegressor (max_rules: int = None, posthoc_ridge: bool = False, include_linear: bool = False, max_features=None, min_impurity_decrease: float = 0.0, k1: int = 0, k2: int = 0)

FIGSExt (sum of trees) classifier. Fast Interpretable Greedy-Tree Sums (FIGS) is an algorithm for fitting concise rule-based models. Specifically, FIGS generalizes CART to simultaneously grow a flexible number of trees in a summation. The total number of splits across all the trees can be restricted by a pre-specified threshold, keeping the model interpretable. Experiments across a wide array of real-world datasets show that FIGS achieves state-of-the-art prediction performance when restricted to just a few splits (e.g. less than 20). https://arxiv.org/abs/2201.11931

max_features The number of features to consider when looking for the best split k1: number of iterations of tree-prediction backfitting to do after making each split k2: number of iterations of tree-prediction backfitting to do after the end of the entire tree-growing phase

Expand source code 
class FIGSExtRegressor(FIGSExt):
    def _init_prediction_task(self):
        self.prediction_task = 'regression'

Ancestors

  • FIGSExt
  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester

Inherited members