[BUG]: Feature selection in pycaret.classification setup function error

pycaret version checks

[X] I have checked that this issue has not already been reported here.
[X] I have confirmed this bug exists on the latest version of pycaret.
[x] I have confirmed this bug exists on the master branch of pycaret (pip install -U git+https://github.com/pycaret/pycaret.git@master).

Issue Description

When using the setup function with the feature_selection=True parameter in Pycaret 3.3.2, this error is returned. "ValueError: The feature names should match those that were passed during fit."

Reproducible Example

## At the Anaconda command line, run the following commands
conda create -n pycaret_332_310_2 python=3.10
# Press y when prompted
conda activate pycaret_332_310_2
pip install pycaret[full] ipykernel
python -m ipykernel install --user --name=pycaret_332_310_2
jupyter notebook

## Then open a new notebook, select the pycaret_332_310_2 kernel and run the following code.
from pycaret.datasets import get_data
data = get_data('diabetes')

from pycaret.classification import *
s = setup(data, target = 'Class variable', session_id = 123,
         feature_selection=True)

Expected Behavior

I expect the code to return a data table and a successful setup screen, which is what I get when I omit the feature_selection=True parameter.

Actual Results

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[2], line 5
      2 data = get_data('diabetes')
      4 from pycaret.classification import *
----> 5 s = setup(data, target = 'Class variable', session_id = 123
      6           , feature_selection=True)
      9 # functional API
     10 #best = compare_models()
     11 
   (...)
     16 
     17 #plot_model(best,'feature')

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\classification\functional.py:595, in setup(data, data_func, target, index, train_size, test_data, ordinal_features, numeric_features, categorical_features, date_features, text_features, ignore_features, keep_features, preprocess, create_date_columns, imputation_type, numeric_imputation, categorical_imputation, iterative_imputation_iters, numeric_iterative_imputer, categorical_iterative_imputer, text_features_method, max_encoding_ohe, encoding_method, rare_to_value, rare_value, polynomial_features, polynomial_degree, low_variance_threshold, group_features, drop_groups, remove_multicollinearity, multicollinearity_threshold, bin_numeric_features, remove_outliers, outliers_method, outliers_threshold, fix_imbalance, fix_imbalance_method, transformation, transformation_method, normalize, normalize_method, pca, pca_method, pca_components, feature_selection, feature_selection_method, feature_selection_estimator, n_features_to_select, custom_pipeline, custom_pipeline_position, data_split_shuffle, data_split_stratify, fold_strategy, fold, fold_shuffle, fold_groups, n_jobs, use_gpu, html, session_id, system_log, log_experiment, experiment_name, experiment_custom_tags, log_plots, log_profile, log_data, verbose, memory, profile, profile_kwargs)
    593 exp = _EXPERIMENT_CLASS()
    594 set_current_experiment(exp)
--> 595 return exp.setup(
    596     data=data,
    597     data_func=data_func,
    598     target=target,
    599     index=index,
    600     train_size=train_size,
    601     test_data=test_data,
    602     ordinal_features=ordinal_features,
    603     numeric_features=numeric_features,
    604     categorical_features=categorical_features,
    605     date_features=date_features,
    606     text_features=text_features,
    607     ignore_features=ignore_features,
    608     keep_features=keep_features,
    609     preprocess=preprocess,
    610     create_date_columns=create_date_columns,
    611     imputation_type=imputation_type,
    612     numeric_imputation=numeric_imputation,
    613     categorical_imputation=categorical_imputation,
    614     iterative_imputation_iters=iterative_imputation_iters,
    615     numeric_iterative_imputer=numeric_iterative_imputer,
    616     categorical_iterative_imputer=categorical_iterative_imputer,
    617     text_features_method=text_features_method,
    618     max_encoding_ohe=max_encoding_ohe,
    619     encoding_method=encoding_method,
    620     rare_to_value=rare_to_value,
    621     rare_value=rare_value,
    622     polynomial_features=polynomial_features,
    623     polynomial_degree=polynomial_degree,
    624     low_variance_threshold=low_variance_threshold,
    625     group_features=group_features,
    626     drop_groups=drop_groups,
    627     remove_multicollinearity=remove_multicollinearity,
    628     multicollinearity_threshold=multicollinearity_threshold,
    629     bin_numeric_features=bin_numeric_features,
    630     remove_outliers=remove_outliers,
    631     outliers_method=outliers_method,
    632     outliers_threshold=outliers_threshold,
    633     fix_imbalance=fix_imbalance,
    634     fix_imbalance_method=fix_imbalance_method,
    635     transformation=transformation,
    636     transformation_method=transformation_method,
    637     normalize=normalize,
    638     normalize_method=normalize_method,
    639     pca=pca,
    640     pca_method=pca_method,
    641     pca_components=pca_components,
    642     feature_selection=feature_selection,
    643     feature_selection_method=feature_selection_method,
    644     feature_selection_estimator=feature_selection_estimator,
    645     n_features_to_select=n_features_to_select,
    646     custom_pipeline=custom_pipeline,
    647     custom_pipeline_position=custom_pipeline_position,
    648     data_split_shuffle=data_split_shuffle,
    649     data_split_stratify=data_split_stratify,
    650     fold_strategy=fold_strategy,
    651     fold=fold,
    652     fold_shuffle=fold_shuffle,
    653     fold_groups=fold_groups,
    654     n_jobs=n_jobs,
    655     use_gpu=use_gpu,
    656     html=html,
    657     session_id=session_id,
    658     system_log=system_log,
    659     log_experiment=log_experiment,
    660     experiment_name=experiment_name,
    661     experiment_custom_tags=experiment_custom_tags,
    662     log_plots=log_plots,
    663     log_profile=log_profile,
    664     log_data=log_data,
    665     verbose=verbose,
    666     memory=memory,
    667     profile=profile,
    668     profile_kwargs=profile_kwargs,
    669 )

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\classification\oop.py:890, in ClassificationExperiment.setup(self, data, data_func, target, index, train_size, test_data, ordinal_features, numeric_features, categorical_features, date_features, text_features, ignore_features, keep_features, preprocess, create_date_columns, imputation_type, numeric_imputation, categorical_imputation, iterative_imputation_iters, numeric_iterative_imputer, categorical_iterative_imputer, text_features_method, max_encoding_ohe, encoding_method, rare_to_value, rare_value, polynomial_features, polynomial_degree, low_variance_threshold, group_features, drop_groups, remove_multicollinearity, multicollinearity_threshold, bin_numeric_features, remove_outliers, outliers_method, outliers_threshold, fix_imbalance, fix_imbalance_method, transformation, transformation_method, normalize, normalize_method, pca, pca_method, pca_components, feature_selection, feature_selection_method, feature_selection_estimator, n_features_to_select, custom_pipeline, custom_pipeline_position, data_split_shuffle, data_split_stratify, fold_strategy, fold, fold_shuffle, fold_groups, n_jobs, use_gpu, html, session_id, system_log, log_experiment, experiment_name, experiment_custom_tags, log_plots, log_profile, log_data, engine, verbose, memory, profile, profile_kwargs)
    887 if ("placeholder", None) in self.pipeline.steps and len(self.pipeline) > 1:
    888     self.pipeline.steps.remove(("placeholder", None))
--> 890 self.pipeline.fit(self.X_train, self.y_train)
    892 self.logger.info("Finished creating preprocessing pipeline.")
    893 self.logger.info(f"Pipeline: {self.pipeline}")

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\pipeline.py:273, in Pipeline.fit(self, X, y, **params)
    271 def fit(self, X=None, y=None, **params):
    272     routed_params = self._check_method_params(method="fit", props=params)
--> 273     X, y, _ = self._fit(X, y, routed_params)
    275     with _print_elapsed_time("Pipeline", self._log_message(len(self.steps) - 1)):
    276         if self._final_estimator != "passthrough":

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\pipeline.py:256, in Pipeline._fit(self, X, y, routed_params)
    248     # Fit or load the current transformer from cache
    249     fitted_transformer = self._memory_fit(
    250         transformer=cloned,
    251         X=X,
   (...)
    254         params=routed_params.get(name, {}),
    255     )
--> 256     X, y = self._memory_transform(
    257         transformer=fitted_transformer,
    258         X=X,
    259         y=y,
    260     )
    262 # Replace the transformer of the step with the fitted
    263 # transformer (necessary when loading from the cache)
    264 self.steps[step_idx] = (name, fitted_transformer)

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\joblib\memory.py:655, in MemorizedFunc.__call__(self, *args, **kwargs)
    654 def __call__(self, *args, **kwargs):
--> 655     return self._cached_call(args, kwargs)[0]

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\memory.py:392, in FastMemorizedFunc._cached_call(self, args, kwargs, shelving)
    389 if must_call:
    390     # PYCARET CHANGES
    391     self._cached_output_identifiers = func_id, args_id
--> 392     out, metadata = self.call(*args, **kwargs)
    393     if self.mmap_mode is not None and metadata is not None:
    394         # PYCARET CHANGES END
    395         # Memmap the output at the first call to be consistent with
    396         # later calls
    397         out = self.store_backend.load_item(
    398             [func_id, args_id], msg=msg, verbose=self._verbose
    399         )

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\memory.py:308, in FastMemorizedFunc.call(self, *args, **kwargs)
    306 # PYCARET CHANGES
    307 func_start_time = time.monotonic()
--> 308 output = self.func(*args, **kwargs)
    309 func_duration = time.monotonic() - func_start_time
    310 if func_duration >= self.min_time_to_cache:

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\pipeline.py:80, in _transform_one(transformer, X, y)
     78 if "y" in signature(transformer.transform).parameters:
     79     args.append(y)
---> 80 output = transformer.transform(*args)
     82 if isinstance(output, tuple):
     83     X, y = output[0], output[1]

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\sklearn\utils\_set_output.py:295, in _wrap_method_output.<locals>.wrapped(self, X, *args, **kwargs)
    293 @wraps(f)
    294 def wrapped(self, X, *args, **kwargs):
--> 295     data_to_wrap = f(self, X, *args, **kwargs)
    296     if isinstance(data_to_wrap, tuple):
    297         # only wrap the first output for cross decomposition
    298         return_tuple = (
    299             _wrap_data_with_container(method, data_to_wrap[0], X, self),
    300             *data_to_wrap[1:],
    301         )

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\pycaret\internal\preprocess\transformers.py:255, in TransformerWrapper.transform(self, X, y)
    252     elif "X" not in transform_params:
    253         return X, y
--> 255 output = self.transformer.transform(*args)
    257 # Transform can return X, y or both
    258 if isinstance(output, tuple):

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\sklearn\utils\_set_output.py:295, in _wrap_method_output.<locals>.wrapped(self, X, *args, **kwargs)
    293 @wraps(f)
    294 def wrapped(self, X, *args, **kwargs):
--> 295     data_to_wrap = f(self, X, *args, **kwargs)
    296     if isinstance(data_to_wrap, tuple):
    297         # only wrap the first output for cross decomposition
    298         return_tuple = (
    299             _wrap_data_with_container(method, data_to_wrap[0], X, self),
    300             *data_to_wrap[1:],
    301         )

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\sklearn\feature_selection\_base.py:107, in SelectorMixin.transform(self, X)
    103 preserve_X = output_config_dense != "default" and _is_pandas_df(X)
    105 # note: we use _safe_tags instead of _get_tags because this is a
    106 # public Mixin.
--> 107 X = self._validate_data(
    108     X,
    109     dtype=None,
    110     accept_sparse="csr",
    111     force_all_finite=not _safe_tags(self, key="allow_nan"),
    112     cast_to_ndarray=not preserve_X,
    113     reset=False,
    114 )
    115 return self._transform(X)

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\sklearn\base.py:608, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)
    537 def _validate_data(
    538     self,
    539     X="no_validation",
   (...)
    544     **check_params,
    545 ):
    546     """Validate input data and set or check the `n_features_in_` attribute.
    547 
    548     Parameters
   (...)
    606         validated.
    607     """
--> 608     self._check_feature_names(X, reset=reset)
    610     if y is None and self._get_tags()["requires_y"]:
    611         raise ValueError(
    612             f"This {self.__class__.__name__} estimator "
    613             "requires y to be passed, but the target y is None."
    614         )

File C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\lib\site-packages\sklearn\base.py:535, in BaseEstimator._check_feature_names(self, X, reset)
    530 if not missing_names and not unexpected_names:
    531     message += (
    532         "Feature names must be in the same order as they were in fit.\n"
    533     )
--> 535 raise ValueError(message)

ValueError: The feature names should match those that were passed during fit.
Feature names unseen at fit time:
- 2-Hour serum insulin (mu U/ml)
- Age (years)
- Body mass index (weight in kg/(height in m)^2)
- Diabetes pedigree function
- Diastolic blood pressure (mm Hg)
- ...
Feature names seen at fit time, yet now missing:
- 2-Hour_serum_insulin_(mu_U/ml)
- Age_(years)
- Body_mass_index_(weight_in_kg/(height_in_m)^2)
- Diabetes_pedigree_function
- Diastolic_blood_pressure_(mm_Hg)
- ...

Installed Versions

System: python: 3.10.14 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:44:50) [MSC v.1916 64 bit (AMD64)] executable: C:\ProgramData\Anaconda3\envs\pycaret_332_310_2\python.exe machine: Windows-10-10.0.17763-SP0 PyCaret required dependencies: pip: 24.2 setuptools: 72.1.0 pycaret: 3.3.2 IPython: 8.26.0 ipywidgets: 8.1.3 tqdm: 4.66.5 numpy: 1.26.4 pandas: 2.1.4 jinja2: 3.1.4 scipy: 1.11.4 joblib: 1.3.2 sklearn: 1.4.2 pyod: 2.0.1 imblearn: 0.12.3 category_encoders: 2.6.3 lightgbm: 4.5.0 numba: 0.60.0 requests: 2.32.3 matplotlib: 3.7.5 scikitplot: 0.3.7 yellowbrick: 1.5 plotly: 5.23.0 plotly-resampler: Not installed kaleido: 0.2.1 schemdraw: 0.15 statsmodels: 0.14.2 sktime: 0.26.0 tbats: 1.1.3 pmdarima: 2.0.4 psutil: 6.0.0 markupsafe: 2.1.5 pickle5: Not installed cloudpickle: 3.0.0 deprecation: 2.1.0 xxhash: 3.5.0 wurlitzer: Not installed PyCaret optional dependencies: shap: 0.44.1 interpret: 0.6.3 umap: 0.5.6 ydata_profiling: 4.9.0 explainerdashboard: 0.4.7 autoviz: Not installed fairlearn: 0.7.0 deepchecks: Not installed xgboost: 2.1.1 catboost: 1.2.5 kmodes: 0.12.2 mlxtend: 0.23.1 statsforecast: 1.5.0 tune_sklearn: Not installed ray: Not installed hyperopt: 0.2.7 optuna: 3.6.1 skopt: 0.10.2 mlflow: 2.15.1 gradio: 4.41.0 fastapi: 0.112.1 uvicorn: 0.30.6 m2cgen: 0.10.0 evidently: 0.4.36 fugue: 0.8.7 streamlit: Not installed prophet: Not installed

pycaret / pycaret