[BUG]: pycaret create duplicates #3616
Description
pycaret version checks
-
I have checked that this issue has not already been reported here.
-
I have confirmed this bug exists on the latest version of pycaret.
-
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
My notebook has several setups, there comes a time when 1 of the setups creates duplicate values, I think it is in the automatic transformation, and then the command xgboost = create_model('xgboost') ends up giving an error.
As xgboost doesn't show what the resources are, I already opened an issue on their github, but while they don't solve it, I changed the code directly on my laptop, so I can know what the resources are.
if i convert to integers this problem doesn't happen
Reproducible Example
setup(data=dados_treino, target = 'n2', fold_shuffle=False, polynomial_features=False, ignore_features=['data', 'n3', 'n4', 'n5', 'ns', 'soma', 'posicao_chave', 'linha1', 'linha2', 'linha3', 'linha4', 'linha5', 'linha6', 'linha7', 'coluna1', 'coluna2', 'coluna3', 'coluna4', 'coluna5', 'coluna6', 'coluna7', 'cor_n1', 'cor_n2', 'cor_n3', 'cor_n4', 'cor_n5', 'n1_p_i', 'n2_p_i', 'n3_p_i', 'n4_p_i', 'n5_p_i', 'anel_1', 'anel_2', 'anel_3', 'qx1', 'qx2', 'qx3', 'qx4',
'qq1', 'qq2', 'qq3', 'qq4', 'q1', 'q2', 'q3', 'q4', 'qp1', 'qp2', 'qp3', 'qp4', 'qp5', 'fppc_n1', 'fppc_n2', 'fppc_n3', 'fppc_n4', 'fppc_n5',
'n1_primo', 'n2_primo', 'n3_primo', 'n4_primo', 'n5_primo', 'n1_sdi', 'n2_sdi', 'n3_sdi', 'n4_sdi', 'n5_sdi', 'n_1_10', 'n_11_20', 'n_21_30', 'n_31_40',
'n_41_49', 'num_sorteios_last_premio', 'n1_ausencias', 'n2_ausencias', 'n3_ausencias', 'n4_ausencias', 'n5_ausencias', 'n1_media_last5',
'n2_media_last5', 'n3_media_last5', 'n4_media_last5', 'n5_media_last5', 'n1_media_last10', 'n2_media_last10', 'n3_media_last10', 'n4_media_last10',
'n5_media_last10', 'n1_n2_ausencias', 'n1_n3_ausencias', 'n1_n4_ausencias', 'n1_n5_ausencias', 'n2_n3_ausencias', 'n2_n4_ausencias', 'n2_n5_ausencias',
'n3_n4_ausencias', 'n3_n5_ausencias', 'n4_n5_ausencias'], fold_strategy='timeseries', use_gpu=True, normalize=True, session_id=123)
xgboost = create_model('xgboost')Expected Behavior
without stop with error
Actual Results
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[89], line 1
----> 1 xgboost = create_model('xgboost')
File ~\anaconda3\lib\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 ~\anaconda3\lib\site-packages\pycaret\classification\functional.py:1009, in create_model(estimator, fold, round, cross_validation, fit_kwargs, groups, probability_threshold, experiment_custom_tags, engine, verbose, return_train_score, **kwargs)
880 @check_if_global_is_not_none(globals(), _CURRENT_EXPERIMENT_DECORATOR_DICT)
881 def create_model(
882 estimator: Union[str, Any],
(...)
893 **kwargs,
894 ) -> Any:
895 """
896 This function trains and evaluates the performance of a given estimator
897 using cross validation. The output of this function is a score grid with
(...)
1006
1007 """
-> 1009 return _CURRENT_EXPERIMENT.create_model(
1010 estimator=estimator,
1011 fold=fold,
1012 round=round,
1013 cross_validation=cross_validation,
1014 fit_kwargs=fit_kwargs,
1015 groups=groups,
1016 probability_threshold=probability_threshold,
1017 experiment_custom_tags=experiment_custom_tags,
1018 engine=engine,
1019 verbose=verbose,
1020 return_train_score=return_train_score,
1021 **kwargs,
1022 )
File ~\anaconda3\lib\site-packages\pycaret\classification\oop.py:1354, in ClassificationExperiment.create_model(self, estimator, fold, round, cross_validation, fit_kwargs, groups, experiment_custom_tags, probability_threshold, engine, verbose, return_train_score, **kwargs)
1351 self._set_engine(estimator=estimator, engine=engine, severity="error")
1353 try:
-> 1354 return_values = super().create_model(
1355 estimator=estimator,
1356 fold=fold,
1357 round=round,
1358 cross_validation=cross_validation,
1359 fit_kwargs=fit_kwargs,
1360 groups=groups,
1361 verbose=verbose,
1362 experiment_custom_tags=experiment_custom_tags,
1363 probability_threshold=probability_threshold,
1364 return_train_score=return_train_score,
1365 **kwargs,
1366 )
1367 finally:
1368 if engine is not None:
1369 # Reset the models back to the default engines
File ~\anaconda3\lib\site-packages\pycaret\internal\pycaret_experiment\supervised_experiment.py:1751, in _SupervisedExperiment.create_model(self, estimator, fold, round, cross_validation, predict, fit_kwargs, groups, refit, probability_threshold, experiment_custom_tags, verbose, return_train_score, **kwargs)
1739 # TODO improve error message
1740 assert not any(
1741 x
1742 in (
(...)
1749 for x in kwargs
1750 )
-> 1751 return self._create_model(
1752 estimator=estimator,
1753 fold=fold,
1754 round=round,
1755 cross_validation=cross_validation,
1756 predict=predict,
1757 fit_kwargs=fit_kwargs,
1758 groups=groups,
1759 refit=refit,
1760 probability_threshold=probability_threshold,
1761 experiment_custom_tags=experiment_custom_tags,
1762 verbose=verbose,
1763 return_train_score=return_train_score,
1764 **kwargs,
1765 )
File ~\anaconda3\lib\site-packages\pycaret\internal\pycaret_experiment\supervised_experiment.py:1519, 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, **kwargs)
1516 return model, model_fit_time
1517 return model
-> 1519 model, model_fit_time, model_results, _ = self._create_model_with_cv(
1520 model,
1521 data_X,
1522 data_y,
1523 fit_kwargs,
1524 round,
1525 cv,
1526 groups,
1527 metrics,
1528 refit,
1529 system,
1530 display,
1531 return_train_score=return_train_score,
1532 )
1534 # end runtime
1535 runtime_end = time.time()
File ~\anaconda3\lib\site-packages\pycaret\internal\pycaret_experiment\supervised_experiment.py:1114, in _SupervisedExperiment._create_model_with_cv(self, model, data_X, data_y, fit_kwargs, round, cv, groups, metrics, refit, system, display, return_train_score)
1112 model_fit_start = time.time()
1113 with redirect_output(self.logger):
-> 1114 scores = cross_validate(
1115 pipeline_with_model,
1116 data_X,
1117 data_y,
1118 cv=cv,
1119 groups=groups,
1120 scoring=metrics_dict,
1121 fit_params=fit_kwargs,
1122 n_jobs=n_jobs,
1123 return_train_score=return_train_score,
1124 error_score=0,
1125 )
1126 model_fit_end = time.time()
1127 model_fit_time = np.array(model_fit_end - model_fit_start).round(2)
File ~\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py:285, in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
265 parallel = Parallel(n_jobs=n_jobs, verbose=verbose, pre_dispatch=pre_dispatch)
266 results = parallel(
267 delayed(_fit_and_score)(
268 clone(estimator),
(...)
282 for train, test in cv.split(X, y, groups)
283 )
--> 285 _warn_or_raise_about_fit_failures(results, error_score)
287 # For callabe scoring, the return type is only know after calling. If the
288 # return type is a dictionary, the error scores can now be inserted with
289 # the correct key.
290 if callable(scoring):
File ~\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py:367, in _warn_or_raise_about_fit_failures(results, error_score)
360 if num_failed_fits == num_fits:
361 all_fits_failed_message = (
362 f"\nAll the {num_fits} fits failed.\n"
363 "It is very likely that your model is misconfigured.\n"
364 "You can try to debug the error by setting error_score='raise'.\n\n"
365 f"Below are more details about the failures:\n{fit_errors_summary}"
366 )
--> 367 raise ValueError(all_fits_failed_message)
369 else:
370 some_fits_failed_message = (
371 f"\n{num_failed_fits} fits failed out of a total of {num_fits}.\n"
372 "The score on these train-test partitions for these parameters"
(...)
376 f"Below are more details about the failures:\n{fit_errors_summary}"
377 )
ValueError:
All the 10 fits failed.
It is very likely that your model is misconfigured.
You can try to debug the error by setting error_score='raise'.
Below are more details about the failures:
--------------------------------------------------------------------------------
4 fits failed with the following error:
Traceback (most recent call last):
File "C:\Users\celes\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 260, in fit
fitted_estimator = self._memory_fit(
File "C:\Users\celes\anaconda3\lib\site-packages\joblib\memory.py", line 655, in __call__
return self._cached_call(args, kwargs)[0]
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 398, in _cached_call
out, metadata = self.call(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 309, in call
output = self.func(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 66, in _fit_one
transformer.fit(*args, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 1502, in fit
train_dmatrix, evals = _wrap_evaluation_matrices(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 527, in _wrap_evaluation_matrices
train_dmatrix = create_dmatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 950, in _create_dmatrix
return QuantileDMatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1411, in __init__
self._init(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1470, in _init
it.reraise()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 470, in reraise
raise exc # pylint: disable=raising-bad-type
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 451, in _handle_exception
return fn()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 523, in <lambda>
return self._handle_exception(lambda: self.next(input_data), 0)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\data.py", line 1252, in next
input_data(**self.kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 515, in input_data
self.proxy.set_info(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 825, in set_info
self.feature_names = feature_names
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1162, in feature_names
raise ValueError('feature_names must be unique. Duplicates found: {}'.format(duplicates)) #line changed
ValueError: feature_names must be unique. Duplicates found: ['n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual']
--------------------------------------------------------------------------------
2 fits failed with the following error:
Traceback (most recent call last):
File "C:\Users\celes\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 260, in fit
fitted_estimator = self._memory_fit(
File "C:\Users\celes\anaconda3\lib\site-packages\joblib\memory.py", line 655, in __call__
return self._cached_call(args, kwargs)[0]
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 398, in _cached_call
out, metadata = self.call(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 309, in call
output = self.func(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 66, in _fit_one
transformer.fit(*args, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 1502, in fit
train_dmatrix, evals = _wrap_evaluation_matrices(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 527, in _wrap_evaluation_matrices
train_dmatrix = create_dmatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 950, in _create_dmatrix
return QuantileDMatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1411, in __init__
self._init(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1470, in _init
it.reraise()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 470, in reraise
raise exc # pylint: disable=raising-bad-type
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 451, in _handle_exception
return fn()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 523, in <lambda>
return self._handle_exception(lambda: self.next(input_data), 0)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\data.py", line 1252, in next
input_data(**self.kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 515, in input_data
self.proxy.set_info(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 825, in set_info
self.feature_names = feature_names
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1162, in feature_names
raise ValueError('feature_names must be unique. Duplicates found: {}'.format(duplicates)) #line changed
ValueError: feature_names must be unique. Duplicates found: ['n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual']
--------------------------------------------------------------------------------
4 fits failed with the following error:
Traceback (most recent call last):
File "C:\Users\celes\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 260, in fit
fitted_estimator = self._memory_fit(
File "C:\Users\celes\anaconda3\lib\site-packages\joblib\memory.py", line 655, in __call__
return self._cached_call(args, kwargs)[0]
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 398, in _cached_call
out, metadata = self.call(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\memory.py", line 309, in call
output = self.func(*args, **kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\pycaret\internal\pipeline.py", line 66, in _fit_one
transformer.fit(*args, **fit_params)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 1502, in fit
train_dmatrix, evals = _wrap_evaluation_matrices(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 527, in _wrap_evaluation_matrices
train_dmatrix = create_dmatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\sklearn.py", line 950, in _create_dmatrix
return QuantileDMatrix(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1411, in __init__
self._init(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1470, in _init
it.reraise()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 470, in reraise
raise exc # pylint: disable=raising-bad-type
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 451, in _handle_exception
return fn()
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 523, in <lambda>
return self._handle_exception(lambda: self.next(input_data), 0)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\data.py", line 1252, in next
input_data(**self.kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 515, in input_data
self.proxy.set_info(
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 609, in inner_f
return func(**kwargs)
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 825, in set_info
self.feature_names = feature_names
File "C:\Users\celes\anaconda3\lib\site-packages\xgboost\core.py", line 1162, in feature_names
raise ValueError('feature_names must be unique. Duplicates found: {}'.format(duplicates)) #line changed
ValueError: feature_names must be unique. Duplicates found: ['n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_desconhecido', 'n1_sdi_anterior_1_desconhecido', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_subiu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_desceu', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_igual', 'n1_sdi_anterior_1_desconhecido', 'n1_sdi_anterior_1_desconhecido', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_igual', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_desceu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_2_subiu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_desceu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_subiu', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_desconhecido', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_3_igual', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_subiu', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_igual', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desceu', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_4_desconhecido', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_desceu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_subiu', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_5_igual', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_subiu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_desceu', 'n1_sdi_anterior_6_igual', 'n1_sdi_anterior_6_igual']Installed Versions
System:
python: 3.10.11 | packaged by Anaconda, Inc. | (main, Apr 20 2023, 18:56:50) [MSC v.1916 64 bit (AMD64)]
executable: C:\Users\celes\anaconda3\python.exe
machine: Windows-10-10.0.22621-SP0
PyCaret required dependencies:
pip: 23.1.2
setuptools: 68.0.0
pycaret: 3.0.2
IPython: 8.14.0
ipywidgets: 8.0.6
tqdm: 4.65.0
numpy: 1.25.0
pandas: 2.1.0.dev0+1029.gaf83376640
jinja2: 3.1.2
scipy: 1.10.1
joblib: 1.3.0.dev0
sklearn: 1.2.2
pyod: 1.0.9
imblearn: 0.10.1
category_encoders: 2.6.1
lightgbm: 3.3.5
numba: 0.57.1
requests: 2.31.0
matplotlib: 3.7.1
scikitplot: 0.3.7
yellowbrick: 1.5
plotly: 5.15.0
kaleido: 0.2.1
statsmodels: 0.14.0
sktime: 0.19.2
tbats: 1.1.3
pmdarima: 2.0.3
psutil: 5.9.5
PyCaret optional dependencies:
shap: 0.41.0
interpret: 0.4.2
umap: 0.5.3
pandas_profiling: 4.3.1
explainerdashboard: 0.4.2.2
autoviz: 0.1.720
fairlearn: 0.8.0
xgboost: 2.0.0-dev
catboost: 1.2
kmodes: 0.12.2
mlxtend: 0.22.0
statsforecast: 1.5.0
tune_sklearn: 0.4.5
ray: 2.5.1
hyperopt: 0.2.7
optuna: 3.2.0
skopt: 0.9.0
mlflow: 2.4.1
gradio: 3.35.2
fastapi: 0.98.0
uvicorn: 0.22.0
m2cgen: 0.10.0
evidently: 0.3.3
fugue: 0.8.5
streamlit: Not installed
prophet: Not installed