Блог

Я запускаю RandomizedGridSearchCV в XGBoostClassifier с набором параметров для запуска поиска по сетке, но при запуске кода для RandomizedGridCV программа сталкивается со следующей ошибкой —

 C:UsersShikharAppDataRoamingPythonPython38site-packagessklearnmodel_selection_search.py:285: UserWarning: The total space of parameters 6 is smaller than n_iter=500. Running 6 iterations. For exhaustive searches, use GridSearchCV.
  warnings.warn(
C:UsersShikharAppDataRoamingPythonPython38site-packagessklearnmodel_selection_search.py:918: UserWarning: One or more of the test scores are non-finite: [nan nan nan nan nan nan]
  warnings.warn(
C:ProgramDataAnaconda3libsite-packagesxgboostsklearn.py:888: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].
  warnings.warn(label_encoder_deprecation_msg, UserWarning)
---------------------------------------------------------------------------
XGBoostError                              Traceback (most recent call last)
<ipython-input-38-9e95bcb72de1> in <module>
     11 )
     12 
---> 13 trained_classifiers = classifier.fit(X_train[top_features], y_train)
     14 
     15 best_classifier = trained_classifiers.best_estimator_

~AppDataRoamingPythonPython38site-packagessklearnutilsvalidation.py in inner_f(*args, **kwargs)
     61             extra_args = len(args) - len(all_args)
     62             if extra_args <= 0:
---> 63                 return f(*args, **kwargs)
     64 
     65             # extra_args > 0

~AppDataRoamingPythonPython38site-packagessklearnmodel_selection_search.py in fit(self, X, y, groups, **fit_params)
    878             refit_start_time = time.time()
    879             if y is not None:
--> 880                 self.best_estimator_.fit(X, y, **fit_params)
    881             else:
    882                 self.best_estimator_.fit(X, **fit_params)

C:ProgramDataAnaconda3libsite-packagesxgboostcore.py in inner_f(*args, **kwargs)
    420         for k, arg in zip(sig.parameters, args):
    421             kwargs[k] = arg
--> 422         return f(**kwargs)
    423 
    424     return inner_f

C:ProgramDataAnaconda3libsite-packagesxgboostsklearn.py in fit(self, X, y, sample_weight, base_margin, eval_set, eval_metric, early_stopping_rounds, verbose, xgb_model, sample_weight_eval_set, feature_weights, callbacks)
    907             eval_group=None, label_transform=label_transform)
    908 
--> 909         self._Booster = train(xgb_options, train_dmatrix,
    910                               self.get_num_boosting_rounds(),
    911                               evals=evals,

C:ProgramDataAnaconda3libsite-packagesxgboosttraining.py in train(params, dtrain, num_boost_round, evals, obj, feval, maximize, early_stopping_rounds, evals_result, verbose_eval, xgb_model, callbacks)
    225     Booster : a trained booster model
    226     """
--> 227     bst = _train_internal(params, dtrain,
    228                           num_boost_round=num_boost_round,
    229                           evals=evals,

C:ProgramDataAnaconda3libsite-packagesxgboosttraining.py in _train_internal(params, dtrain, num_boost_round, evals, obj, feval, xgb_model, callbacks, evals_result, maximize, verbose_eval, early_stopping_rounds)
    100         # Skip the first update if it is a recovery step.
    101         if version % 2 == 0:
--> 102             bst.update(dtrain, i, obj)
    103             bst.save_rabit_checkpoint()
    104             version  = 1

C:ProgramDataAnaconda3libsite-packagesxgboostcore.py in update(self, dtrain, iteration, fobj)
   1278 
   1279         if fobj is None:
-> 1280             _check_call(_LIB.XGBoosterUpdateOneIter(self.handle,
   1281                                                     ctypes.c_int(iteration),
   1282                                                     dtrain.handle))

C:ProgramDataAnaconda3libsite-packagesxgboostcore.py in _check_call(ret)
    187     """
    188     if ret != 0:
--> 189         raise XGBoostError(py_str(_LIB.XGBGetLastError()))
    190 
    191 

XGBoostError: [22:30:15] C:UsersAdministratorworkspacexgboost-win64_release_1.3.0srcgbmgbm.cc:26: Unknown gbm type g

 

версия xgboost 1.3.3

Любой другой способ сделать то же самое будет высоко оценен.

В то время как я заменяю RandomizedGridSearchCV на GridSearchCV, программа запускается без каких-либо ошибок.

Код:

 import xgboost as xgb

model = xgb.XGBClassifier()

from sklearn.model_selection import RandomizedSearchCV, GridSearchCV

TRAINING_PARAMETERS = {
    "n_estimators" : [500, 300, 700],
    "learning_rate": [0.001, 0.1, 1],
    "subsample"    : [.7, 0.8, 0.9],
    "max_depth"    : [3, 4, 5]
}

classifier = RandomizedSearchCV(
    estimator = model,
    param_distributions = TRAINING_PARAMETERS,
    n_jobs = 16,
    n_iter = 500,
    cv = 3,
    #scoring = "roc_auc",
    #verbose = 15 
)

trained_classifiers = classifier.fit(X_train[top_features], y_train)
 

Данные состоят из 122 столбцов признаков и размера выборки 500 . Цель является двоичной (0 и 1).