def _fit(self, X_train, y_train, X_val=None, y_val=None, time_limit=None, **kwargs):
start_time = time.time()
invalid_params = ['num_threads', 'num_gpus']
for invalid in invalid_params:
if invalid in self.params:
self.params.pop(invalid)
params = self.params.copy()
max_category_levels = params.pop('proc.max_category_levels', 100)
verbosity = kwargs.get('verbosity', 2)
if verbosity <= 2:
verbose = False
elif verbosity == 3:
verbose = True
verbose_eval = 50
else:
verbose = True
verbose_eval = 1
X_train = self.preprocess(X_train, is_train=True, max_category_levels=max_category_levels)
num_rows_train = X_train.shape[0]
eval_set = []
eval_metric = self.get_eval_metric()
if X_val is None:
early_stopping_rounds = 150
eval_set.append((X_train, y_train)) # TODO: if the train dataset is large, use sample of train dataset for validation
else:
modifier = 1 if num_rows_train <= 10000 else 10000 / num_rows_train
early_stopping_rounds = max(round(modifier * 150), 10)
X_val = self.preprocess(X_val, is_train=False)
eval_set.append((X_val, y_val))
try_import_xgboost()
from .callbacks import print_evaluation, early_stop_custom
callbacks = []
if verbose:
callbacks.append(print_evaluation(verbose_eval))
# TODO: disable early stopping during refit_full
callbacks.append(early_stop_custom(early_stopping_rounds, start_time=start_time, time_limit=time_limit, verbose=verbose))
from xgboost import XGBClassifier, XGBRegressor
model_type = XGBClassifier if self.problem_type in PROBLEM_TYPES_CLASSIFICATION else XGBRegressor
self.model = model_type(**params)
self.model.fit(
X=X_train,
y=y_train,
eval_set=eval_set,
eval_metric=eval_metric,
verbose=False,
callbacks=callbacks
)
bst = self.model.get_booster()
self.params_trained['n_estimators'] = bst.best_ntree_limit
self._best_ntree_limit = bst.best_ntree_limit
def _fit(self,
X,
y,
X_val=None,
y_val=None,
time_limit=None,
num_gpus=0,
num_cpus=None,
sample_weight=None,
sample_weight_val=None,
verbosity=2,
**kwargs):
# TODO: utilize sample_weight_val in early-stopping if provided
start_time = time.time()
ag_params = self._get_ag_params()
params = self._get_model_params()
if num_cpus:
params['n_jobs'] = num_cpus
max_category_levels = params.pop('proc.max_category_levels', 100)
if verbosity <= 2:
verbose = False
log_period = None
elif verbosity == 3:
verbose = True
log_period = 50
else:
verbose = True
log_period = 1
X = self.preprocess(X,
is_train=True,
max_category_levels=max_category_levels)
num_rows_train = X.shape[0]
eval_set = []
eval_metric = self.get_eval_metric()
if X_val is None:
early_stopping_rounds = None
eval_set = None
else:
X_val = self.preprocess(X_val, is_train=False)
eval_set.append((X_val, y_val))
early_stopping_rounds = ag_params.get('ag.early_stop', 'adaptive')
if isinstance(early_stopping_rounds, (str, tuple, list)):
early_stopping_rounds = self._get_early_stopping_rounds(
num_rows_train=num_rows_train,
strategy=early_stopping_rounds)
if num_gpus != 0:
params['tree_method'] = 'gpu_hist'
if 'gpu_id' not in params:
params['gpu_id'] = 0
elif 'tree_method' not in params:
params['tree_method'] = 'hist'
try_import_xgboost()
from .callbacks import EarlyStoppingCustom
from xgboost.callback import EvaluationMonitor
callbacks = []
if eval_set is not None:
if log_period is not None:
callbacks.append(EvaluationMonitor(period=log_period))
callbacks.append(
EarlyStoppingCustom(early_stopping_rounds,
start_time=start_time,
time_limit=time_limit,
verbose=verbose))
from xgboost import XGBClassifier, XGBRegressor
model_type = XGBClassifier if self.problem_type in PROBLEM_TYPES_CLASSIFICATION else XGBRegressor
if 'eval_metric' not in params and params.get(
'objective') == 'binary:logistic':
# avoid unnecessary warning from XGBoost v1.3.0
params['eval_metric'] = 'logloss'
self.model = model_type(**params)
self.model.fit(X=X,
y=y,
eval_set=eval_set,
eval_metric=eval_metric,
verbose=False,
callbacks=callbacks,
sample_weight=sample_weight)
bst = self.model.get_booster()
# TODO: Investigate speed-ups from GPU inference
# bst.set_param({"predictor": "gpu_predictor"})
self.params_trained['n_estimators'] = bst.best_ntree_limit
def _fit(self,
X,
y,
X_val=None,
y_val=None,
time_limit=None,
num_gpus=0,
sample_weight=None,
sample_weight_val=None,
verbosity=2,
**kwargs):
# TODO: utilize sample_weight_val in early-stopping if provided
start_time = time.time()
ag_params = self._get_ag_params()
params = self._get_model_params()
max_category_levels = params.pop('proc.max_category_levels', 100)
if verbosity <= 2:
verbose = False
verbose_eval = None
elif verbosity == 3:
verbose = True
verbose_eval = 50
else:
verbose = True
verbose_eval = 1
X = self.preprocess(X,
is_train=True,
max_category_levels=max_category_levels)
num_rows_train = X.shape[0]
eval_set = []
eval_metric = self.get_eval_metric()
if X_val is None:
early_stopping_rounds = None
eval_set.append(
(X, y)
) # TODO: if the train dataset is large, use sample of train dataset for validation
else:
X_val = self.preprocess(X_val, is_train=False)
eval_set.append((X_val, y_val))
early_stopping_rounds = ag_params.get('ag.early_stop', 'auto')
if isinstance(early_stopping_rounds, str):
early_stopping_rounds = self._get_early_stopping_rounds(
num_rows_train=num_rows_train,
strategy=early_stopping_rounds)
if num_gpus != 0:
params['tree_method'] = 'gpu_hist'
if 'gpu_id' not in params:
params['gpu_id'] = 0
try_import_xgboost()
from .callbacks import EarlyStoppingCustom
from xgboost.callback import EvaluationMonitor
callbacks = []
if verbose_eval is not None:
callbacks.append(EvaluationMonitor(period=verbose_eval))
# TODO: disable early stopping during refit_full
callbacks.append(
EarlyStoppingCustom(early_stopping_rounds,
start_time=start_time,
time_limit=time_limit,
verbose=verbose))
from xgboost import XGBClassifier, XGBRegressor
model_type = XGBClassifier if self.problem_type in PROBLEM_TYPES_CLASSIFICATION else XGBRegressor
self.model = model_type(**params)
self.model.fit(X=X,
y=y,
eval_set=eval_set,
eval_metric=eval_metric,
verbose=False,
callbacks=callbacks,
sample_weight=sample_weight)
bst = self.model.get_booster()
# TODO: Investigate speed-ups from GPU inference
# bst.set_param({"predictor": "gpu_predictor"})
self.params_trained['n_estimators'] = bst.best_ntree_limit
self._best_ntree_limit = bst.best_ntree_limit
def _fit(self,
X_train,
y_train,
X_val=None,
y_val=None,
time_limit=None,
num_gpus=0,
**kwargs):
start_time = time.time()
params = self.params.copy()
max_category_levels = params.pop('proc.max_category_levels', 100)
verbosity = kwargs.get('verbosity', 2)
if verbosity <= 2:
verbose = False
verbose_eval = None
elif verbosity == 3:
verbose = True
verbose_eval = 50
else:
verbose = True
verbose_eval = 1
X_train = self.preprocess(X_train,
is_train=True,
max_category_levels=max_category_levels)
num_rows_train = X_train.shape[0]
eval_set = []
eval_metric = self.get_eval_metric()
if X_val is None:
early_stopping_rounds = 150
eval_set.append(
(X_train, y_train)
) # TODO: if the train dataset is large, use sample of train dataset for validation
else:
modifier = 1 if num_rows_train <= 10000 else 10000 / num_rows_train
early_stopping_rounds = max(round(modifier * 150), 10)
X_val = self.preprocess(X_val, is_train=False)
eval_set.append((X_val, y_val))
if num_gpus != 0:
params['tree_method'] = 'gpu_hist'
if 'gpu_id' not in params:
params['gpu_id'] = 0
try_import_xgboost()
from .callbacks import EarlyStoppingCustom
from xgboost.callback import EvaluationMonitor
callbacks = []
if verbose_eval is not None:
callbacks.append(EvaluationMonitor(period=verbose_eval))
# TODO: disable early stopping during refit_full
callbacks.append(
EarlyStoppingCustom(early_stopping_rounds,
start_time=start_time,
time_limit=time_limit,
verbose=verbose))
from xgboost import XGBClassifier, XGBRegressor
model_type = XGBClassifier if self.problem_type in PROBLEM_TYPES_CLASSIFICATION else XGBRegressor
self.model = model_type(**params)
self.model.fit(X=X_train,
y=y_train,
eval_set=eval_set,
eval_metric=eval_metric,
verbose=False,
callbacks=callbacks)
bst = self.model.get_booster()
# TODO: Investigate speed-ups from GPU inference
# bst.set_param({"predictor": "gpu_predictor"})
self.params_trained['n_estimators'] = bst.best_ntree_limit
self._best_ntree_limit = bst.best_ntree_limit
