def load(cls, path: str, reset_paths=True, verbose=True):
model = super().load(path=path,
reset_paths=reset_paths,
verbose=verbose)
if model._load_model:
try_import_autogluon_text()
from autogluon.multimodal import MultiModalPredictor
model.model = MultiModalPredictor.load(
os.path.join(path, cls._NN_MODEL_NAME))
model._load_model = None
return model
def load(cls, path: str, reset_paths=True, verbose=True):
model = super().load(path=path,
reset_paths=reset_paths,
verbose=verbose)
if model._load_model:
try_import_autogluon_text()
from autogluon.text import TextPredictor
model.model = TextPredictor.load(
os.path.join(path, cls.nn_model_name))
model._load_model = None
return model
def _fit(self,
X: pd.DataFrame,
y: pd.Series,
X_val: Optional[pd.DataFrame] = None,
y_val: Optional[pd.Series] = None,
time_limit: Optional[int] = None,
sample_weight=None,
**kwargs):
"""The internal fit function
Parameters
----------
X
Features of the training dataset
y
Labels of the training dataset
X_val
Features of the validation dataset
y_val
Labels of the validation dataset
time_limit
The time limits for the fit function
sample_weight
The weights of the samples
kwargs
Other keyword arguments
"""
try_import_autogluon_text()
from autogluon.multimodal import MultiModalPredictor
# Decide name of the label column
if 'label' in X.columns:
label_col_id = 0
while True:
self._label_column_name = 'label{}'.format(label_col_id)
if self._label_column_name not in X.columns:
break
label_col_id += 1
else:
self._label_column_name = 'label'
X_train = self.preprocess(X, fit=True)
if X_val is not None:
X_val = self.preprocess(X_val)
# Get arguments from kwargs
verbosity = kwargs.get('verbosity', 2)
num_gpus = kwargs.get('num_gpus', None)
if sample_weight is not None: # TODO: support
logger.log(
15,
"sample_weight not yet supported for MultiModalPredictorModel, "
"this model will ignore them in training.")
X_train.insert(len(X_train.columns), self._label_column_name, y)
if X_val is not None:
X_val.insert(len(X_val.columns), self._label_column_name, y_val)
verbosity_text = max(0, verbosity - 1)
root_logger = logging.getLogger('autogluon')
root_log_level = root_logger.level
self.model = MultiModalPredictor(label=self._label_column_name,
problem_type=self.problem_type,
path=self.path,
eval_metric=self.eval_metric,
verbosity=verbosity_text)
params = self._get_model_params()
if num_gpus is not None:
params['env.num_gpus'] = num_gpus
presets = params.pop('presets', None)
seed = params.pop('seed', 0)
self.model.fit(train_data=X_train,
tuning_data=X_val,
time_limit=time_limit,
presets=presets,
hyperparameters=params,
seed=seed)
self.model.set_verbosity(verbosity)
root_logger.setLevel(root_log_level) # Reset log level
def _set_default_params(self):
super()._set_default_params()
try_import_autogluon_text()
def _fit(self,
X: pd.DataFrame,
y: pd.Series,
X_val: Optional[pd.DataFrame] = None,
y_val: Optional[pd.Series] = None,
time_limit: Optional[int] = None,
sample_weight=None,
**kwargs):
"""The internal fit function
Parameters
----------
X
Features of the training dataset
y
Labels of the training dataset
X_val
Features of the validation dataset
y_val
Labels of the validation dataset
time_limit
The time limits for the fit function
kwargs
Other keyword arguments
"""
try_import_mxnet()
try_import_autogluon_text()
from autogluon.text import TextPredictor
# Decide name of the label column
if 'label' in X.columns:
label_col_id = 0
while True:
self._label_column_name = 'label{}'.format(label_col_id)
if self._label_column_name not in X.columns:
break
label_col_id += 1
else:
self._label_column_name = 'label'
X_train = self.preprocess(X, fit=True)
if X_val is not None:
X_val = self.preprocess(X_val)
# Get arguments from kwargs
verbosity = kwargs.get('verbosity', 2)
num_cpus = kwargs.get('num_cpus', None)
num_gpus = kwargs.get('num_gpus', None)
if sample_weight is not None: # TODO: support
logger.log(
15,
"sample_weight not yet supported for TextPredictorModel, this model will ignore them in training."
)
X_train.insert(len(X_train.columns), self._label_column_name, y)
if X_val is not None:
X_val.insert(len(X_val.columns), self._label_column_name, y_val)
assert self.params['tune_kwargs']['num_trials'] == 1 \
or self.params['tune_kwargs']['num_trials'] is None,\
'Currently, you cannot nest the hyperparameter search in text neural network ' \
'and the AutoGluon Tabular.'
verbosity_text = max(0, verbosity - 1)
root_logger = logging.getLogger()
root_log_level = root_logger.level
self.model = TextPredictor(label=self._label_column_name,
problem_type=self.problem_type,
path=self.path,
eval_metric=self.eval_metric,
verbosity=verbosity_text)
self.model.fit(train_data=X_train,
tuning_data=X_val,
time_limit=time_limit,
num_gpus=num_gpus,
num_cpus=num_cpus,
hyperparameters=self.params,
seed=self.params.get('seed', 0))
self.model.set_verbosity(verbosity)
root_logger.setLevel(root_log_level) # Reset log level
def _set_default_params(self):
super()._set_default_params()
try_import_autogluon_text()
from autogluon.text import ag_text_presets
self.params = ag_text_presets.create('default')
