Add check_estimator tests. We can't test the survival, instrumental, or causal forests because they don't conform to sklearn's regressor conventions.
In doing so we add validation to ensure check_estimator passes. We also add logic to ensure that passing sample_weight of ones is equivalent to passing None.
Changes:
Change self.n_features_ to self.n_features_in_
Add sample weight validation to ensure that passing weights of ones results in identical output when passing None.
Use self._validate_data in lieu of check_X_y when possible
Use self._check_n_features in lieu of manually setting n features
Manually add estimator tags to forests which don't inherit from RegressorMixin
Add self._check_num_samples to ensure check_estimator properly detect exception when less than 1 record is passed.
Add
check_estimatortests. We can't test the survival, instrumental, or causal forests because they don't conform to sklearn's regressor conventions.In doing so we add validation to ensure check_estimator passes. We also add logic to ensure that passing sample_weight of ones is equivalent to passing None.
Changes:
self.n_features_toself.n_features_in_self._validate_datain lieu ofcheck_X_ywhen possibleself._check_n_featuresin lieu of manually setting n featuresRegressorMixinself._check_num_samplesto ensurecheck_estimatorproperly detect exception when less than 1 record is passed.https://scikit-learn.org/stable/modules/generated/sklearn.utils.estimator_checks.check_estimator.html
Closes #31