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.vstack([self.infer_on_batch(d) for d in data])
if predict_proba:
return preds
else:
pl = proba2labels(preds,
confident_threshold=self.confident_threshold,
classes=self.classes)
tl = proba2labels(
preds, confident_threshold=0, classes=self.classes
) # [self.classes[np.argmax(preds[i,:])-1] for i in range(len(self.classes))]
return [(pl[i], dict(zip(tl[i], preds[i])))
for i in range(len(pl))] # [[y[0]] for y in pl]
def __predict(self, model, input_text):
rp = model.pipe[0][-1]([input_text])
for i in range(1, len(model.pipe) - 1):
rp = model.pipe[i][-1](rp)
res = model.pipe[-1][-1](rp, predict_proba=True)
dec = proba2labels(
res,
confident_threshold=model.pipe[-1][-1].confident_threshold,
classes=model.pipe[-1][-1].classes)[0]
return {
'decision': dec,
'confidence': np.sort(res)[0, -len(dec):].tolist()[::-1]
}
def __call__(self, data: List[List[str]], *args) -> Tuple[List[list], List[dict]]:
"""
Infer on the given data
Args:
data: list of tokenized text samples
*args: additional arguments
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), dtype="float64")
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, *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: List[List[str]],
*args) -> Tuple[List[list], List[dict]]:
"""
Infer on the given data
Args:
data: list of tokenized text samples
*args: additional arguments
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), dtype="float64")
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])
]