def infer(self, data, predict_proba=False, *args):
"""
Infer on the given data
Args:
data: single sentence or [list of sentences, list of labels] or
[list of sentences] or generator of sentences
predict_proba: whether to return probabilities distribution or only labels-predictions
*args:
Returns:
for each sentence:
vector of probabilities to belong with each class
or list of labels sentence belongs with
"""
if type(data) is str:
preds = self.infer_on_batch([data])[0]
preds = np.array(preds)
if predict_proba:
return preds
else:
return proba2labels([preds], confident_threshold=self.confident_threshold, classes=self.classes)[0]
elif inspect.isgeneratorfunction(data):
preds = []
for step, batch in enumerate(data):
preds.extend(self.infer_on_batch(batch))
preds = np.array(preds)
elif type(data) is list:
preds = self.infer_on_batch(data)
preds = np.array(preds)
else:
raise ConfigError("Not understand data type for inference")
if predict_proba:
return preds
else:
return proba2labels(preds, confident_threshold=self.confident_threshold, classes=self.classes)
def __call__(self, data, *args):
"""
Infer on the given data
Args:
data: [list of sentences]
*args:
Returns:
for each sentence:
vector of probabilities to belong with each class
or list of labels sentence belongs with
"""
preds = np.array(self.infer_on_batch(data))
labels = proba2labels(preds, confident_threshold=self.opt['confident_threshold'], classes=self.classes)
return labels, [dict(zip(self.classes, preds[i])) for i in range(preds.shape[0])]
def __call__(self, data, predict_proba=False, *args):
"""
Infer on the given data
Args:
data: [list of sentences]
predict_proba: whether to return probabilities distribution or only labels-predictions
*args:
Returns:
for each sentence:
vector of probabilities to belong with each class
or list of labels sentence belongs with
"""
preds = np.array(self.infer_on_batch(data))
if predict_proba:
return preds
else:
return proba2labels(preds, confident_threshold=self.confident_threshold, classes=self.classes)