AttributeError: 'Pipeline' object has no attribute '_check_fit_params'

[YuantingMaSC]

Zhining, Sorry to bother you, but when I use EasyEnsembleClassifier in imbens.ensemble, I got the error "AttributeError: 'Pipeline' object has no attribute '_check_fit_params'", I can't figure out why this happened, could u please help me with it, the code is as follows:

---

from imbens.ensemble import EasyEnsembleClassifier from sklearn.datasets import make_classification from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier

X, y = make_classification(n_classes=2, class_sep=2, n_features=100, weights=[0.3,0.7], n_informative=2, n_redundant=1, flip_y=0.01, n_clusters_per_class=1, n_samples=10000, random_state=10) X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.5, random_state=42)

init_kwargs1 = {'estimator': DecisionTreeClassifier(),}

easyens = EasyEnsembleClassifier(**init_kwargs1).fit(X_train, y_train) pred = easyens.predict(X_valid)

---

The errors are as follows:

Traceback (most recent call last): File "f:\MYT\EEGP\smote_compare.py", line 176, in easyens = EasyEnsembleClassifier(init_kwargs1).fit(X_train, y_train) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\utils_validation.py", line 604, in inner_f return f(kwargs) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\ensemble_under_sampling\easy_ensemble.py", line 285, in fit return self._fit( File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\utils_validation.py", line 604, in inner_f return f(kwargs) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\ensemble_bagging.py", line 480, in _fit all_results = Parallel( File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\sklearn\utils\parallel.py", line 67, in call return super().call(iterable_with_config) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\joblib\parallel.py", line 1863, in call return output if self.return_generator else list(output) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\joblib\parallel.py", line 1792, in _get_sequential_output res = func(*args, *kwargs) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\sklearn\utils\parallel.py", line 129, in call return self.function(args, kwargs) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\ensemble_bagging.py", line 163, in _parallel_build_estimators estimator.fit((X[indices])[:, features], y[indices]) File "D:\ProgramData\anaconda3\envs\EEG\lib\site-packages\imbens\pipeline.py", line 273, in fit fit_params_steps = self._check_fit_params(**fit_params) AttributeError: 'Pipeline' object has no attribute '_check_fit_params'

packages version: scikit-learn 1.4.0 imbalanced-ensemble 0.2.1

[ZhiningLiu1998]

Hi, this is due to the implementation change of Pipeline in scikit-learn 1.4.0, you can either:

• reverse to sklearn 1.3.0
• or clone imbens with the latest commit I made and install locally via pip install .

[YuantingMaSC]

thanks !