---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/preprocess/transformers.py:135, in TransformerWrapper._reorder_cols(self, df, original_df)
    134 try:
--> 135     original_df.index = df.index
    136 except ValueError:  # Length mismatch

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pandas/core/generic.py:5588, in NDFrame.__setattr__(self, name, value)
   5587     object.__getattribute__(self, name)
-> 5588     return object.__setattr__(self, name, value)
   5589 except AttributeError:

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pandas/_libs/properties.pyx:70, in pandas._libs.properties.AxisProperty.__set__()

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pandas/core/generic.py:769, in NDFrame._set_axis(self, axis, labels)
    768 labels = ensure_index(labels)
--> 769 self._mgr.set_axis(axis, labels)
    770 self._clear_item_cache()

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pandas/core/internals/managers.py:214, in BaseBlockManager.set_axis(self, axis, new_labels)
    212 def set_axis(self, axis: int, new_labels: Index) -> None:
    213     # Caller is responsible for ensuring we have an Index object.
--> 214     self._validate_set_axis(axis, new_labels)
    215     self.axes[axis] = new_labels

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pandas/core/internals/base.py:69, in DataManager._validate_set_axis(self, axis, new_labels)
     68 elif new_len != old_len:
---> 69     raise ValueError(
     70         f"Length mismatch: Expected axis has {old_len} elements, new "
     71         f"values have {new_len} elements"
     72     )

ValueError: Length mismatch: Expected axis has 10000 elements, new values have 19894 elements

During handling of the above exception, another exception occurred:

IndexError                                Traceback (most recent call last)
Cell In[72], line 2
      1 # finalize_model(best_model)
----> 2 finalize_model(tuned_model)

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/utils/generic.py:965, in check_if_global_is_not_none.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
    963     if globals_d[name] is None:
    964         raise ValueError(message)
--> 965 return func(*args, **kwargs)

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/classification/functional.py:2229, in finalize_model(estimator, fit_kwargs, groups, model_only, experiment_custom_tags)
   2177 @check_if_global_is_not_none(globals(), _CURRENT_EXPERIMENT_DECORATOR_DICT)
   2178 def finalize_model(
   2179     estimator,
   (...)
   2183     experiment_custom_tags: Optional[Dict[str, Any]] = None,
   2184 ) -> Any:
   2185     """
   2186     This function trains a given estimator on the entire dataset including the
   2187     holdout set.
   (...)
   2226 
   2227     """
-> 2229     return _CURRENT_EXPERIMENT.finalize_model(
   2230         estimator=estimator,
   2231         fit_kwargs=fit_kwargs,
   2232         groups=groups,
   2233         model_only=model_only,
   2234         experiment_custom_tags=experiment_custom_tags,
   2235     )

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/classification/oop.py:2875, in ClassificationExperiment.finalize_model(self, estimator, fit_kwargs, groups, model_only, experiment_custom_tags)
   2823 def finalize_model(
   2824     self,
   2825     estimator,
   (...)
   2829     experiment_custom_tags: Optional[Dict[str, Any]] = None,
   2830 ) -> Any:
   2831     """
   2832     This function trains a given estimator on the entire dataset including the
   2833     holdout set.
   (...)
   2872 
   2873     """
-> 2875     return super().finalize_model(
   2876         estimator=estimator,
   2877         fit_kwargs=fit_kwargs,
   2878         groups=groups,
   2879         model_only=model_only,
   2880         experiment_custom_tags=experiment_custom_tags,
   2881     )

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pycaret_experiment/supervised_experiment.py:4730, in _SupervisedExperiment.finalize_model(self, estimator, fit_kwargs, groups, model_only, experiment_custom_tags)
   4727 np.random.seed(self.seed)
   4729 self.logger.info(f"Finalizing {estimator}")
-> 4730 pipeline_final, model_fit_time = self._create_model(
   4731     estimator=estimator,
   4732     cross_validation=False,
   4733     verbose=False,
   4734     system=False,
   4735     X_train_data=self.X,
   4736     y_train_data=self.y,
   4737     fit_kwargs=fit_kwargs or {},
   4738     predict=False,
   4739     groups=self._get_groups(groups, data=self.X),
   4740     add_to_model_list=False,
   4741     model_only=False,
   4742 )
   4744 # dashboard logging
   4745 if self.logging_param:

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pycaret_experiment/supervised_experiment.py:1507, in _SupervisedExperiment._create_model(self, estimator, fold, round, cross_validation, predict, fit_kwargs, groups, refit, probability_threshold, experiment_custom_tags, verbose, system, add_to_model_list, X_train_data, y_train_data, metrics, display, model_only, return_train_score, error_score, **kwargs)
   1502 """
   1503 MONITOR UPDATE ENDS
   1504 """
   1506 if not cross_validation:
-> 1507     model, model_fit_time = self._create_model_without_cv(
   1508         model=model,
   1509         data_X=data_X,
   1510         data_y=data_y,
   1511         fit_kwargs=fit_kwargs,
   1512         round=round,
   1513         predict=predict,
   1514         system=system,
   1515         display=display,
   1516         model_only=model_only,
   1517         return_train_score=return_train_score,
   1518     )
   1520     display.move_progress()
   1522     self.logger.info(str(model))

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pycaret_experiment/supervised_experiment.py:1032, in _SupervisedExperiment._create_model_without_cv(self, model, data_X, data_y, fit_kwargs, round, predict, system, display, model_only, return_train_score)
   1030 model_fit_start = time.time()
   1031 with redirect_output(self.logger):
-> 1032     pipeline_with_model.fit(data_X, data_y, **fit_kwargs)
   1033 model_fit_end = time.time()
   1035 model_fit_time = np.array(model_fit_end - model_fit_start).round(2)

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pipeline.py:270, in Pipeline.fit(self, X, y, **fit_params)
    268 def fit(self, X=None, y=None, **fit_params):
    269     fit_params_steps = self._check_fit_params(**fit_params)
--> 270     X, y, _ = self._fit(X, y, **fit_params_steps)
    272     with _print_elapsed_time("Pipeline", self._log_message(len(self.steps) - 1)):
    273         if self._final_estimator != "passthrough":

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pipeline.py:253, in Pipeline._fit(self, X, y, **fit_params_steps)
    245     # Fit or load the current transformer from cache
    246     fitted_transformer = self._memory_fit(
    247         transformer=cloned,
    248         X=X,
   (...)
    251         **fit_params_steps.get(name, {}),
    252     )
--> 253     X, y = self._memory_transform(
    254         transformer=fitted_transformer,
    255         X=X,
    256         y=y,
    257     )
    259 # Replace the transformer of the step with the fitted
    260 # transformer (necessary when loading from the cache)
    261 self.steps[step_idx] = (name, fitted_transformer)

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/joblib/memory.py:353, in NotMemorizedFunc.__call__(self, *args, **kwargs)
    352 def __call__(self, *args, **kwargs):
--> 353     return self.func(*args, **kwargs)

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/pipeline.py:79, in _transform_one(transformer, X, y)
     77 if "y" in signature(transformer.transform).parameters:
     78     args.append(y)
---> 79 output = transformer.transform(*args)
     81 if isinstance(output, tuple):
     82     X, y = output[0], output[1]

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/sklearn/utils/_set_output.py:140, in _wrap_method_output.<locals>.wrapped(self, X, *args, **kwargs)
    138 @wraps(f)
    139 def wrapped(self, X, *args, **kwargs):
--> 140     data_to_wrap = f(self, X, *args, **kwargs)
    141     if isinstance(data_to_wrap, tuple):
    142         # only wrap the first output for cross decomposition
    143         return (
    144             _wrap_data_with_container(method, data_to_wrap[0], X, self),
    145             *data_to_wrap[1:],
    146         )

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/preprocess/transformers.py:259, in TransformerWrapper.transform(self, X, y)
    257 # Transform can return X, y or both
    258 if isinstance(output, tuple):
--> 259     new_X = self._prepare_df(X, output[0])
    260     new_y = to_series(output[1], index=new_X.index, name=y.name)
    261 else:

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/preprocess/transformers.py:196, in TransformerWrapper._prepare_df(self, X, out)
    194 # Reorder columns if only a subset was used
    195 if len(self._include) != X.shape[1]:
--> 196     return self._reorder_cols(out, X)
    197 else:
    198     return out

File ~/opt/anaconda3/envs/pycaret/lib/python3.8/site-packages/pycaret/internal/preprocess/transformers.py:137, in TransformerWrapper._reorder_cols(self, df, original_df)
    135     original_df.index = df.index
    136 except ValueError:  # Length mismatch
--> 137     raise IndexError(
    138         f"Length of values ({len(df)}) does not match length of "
    139         f"index ({len(original_df)}). This usually happens when "
    140         "transformations that drop rows aren't applied on all "
    141         "the columns."
    142     )
    144 # Define new column order
    145 # Use OrderedDict as ordered set (only keys matter)
    146 # We want a set to avoid duplicate column names, which can happen
    147 # if we have eg. COL_A and COL_A_2 encoded using OHE
    148 columns = OrderedDict()

IndexError: Length of values (19894) does not match length of index (10000). This usually happens when transformations that drop rows aren't applied on all the columns.