def dump_line(self, outputs: JsonDict) -> str: # pylint: disable=no-self-use
"""
If you don't want your outputs in JSON-lines format
you can override this function to output them differently.
"""
keys = ['citedPaperId', 'citingPaperId', 'excerptCitationIntents']
for k in outputs.copy():
if k not in keys:
outputs.pop(k)
return json.dumps(outputs, cls=JsonFloatEncoder) + "\n"
def dump_line(self, outputs: JsonDict) -> str: # pylint: disable=no-self-use
"""
If you don't want your outputs in JSON-lines format
you can override this function to output them differently.
"""
keys = ['citation_id', 'prediction', 'probabilities', 'citation_text']
for k in outputs.copy():
if k not in keys:
outputs.pop(k)
return json.dumps(outputs, cls=JsonFloatEncoder) + "\n"
def dump_line(self, output: JsonDict) -> str: # pylint: disable=no-self-use
output.pop('class_probabilities', None)
output['hierplane_tree'].pop('linkNameToLabel', None)
output['hierplane_tree'].pop('nodeTypeToStyle', None)
tree = output['hierplane_tree']
# Spans are 4-tuple with (start, end (exclusive), span_text, span_label)
spans = self.get_parse_spans(tree, [])
sentence_id = None
if "sentence_id" in output['metadata']:
sentence_id = output['metadata']['sentence_id']
tokens = output['metadata']['tokens']
output_jsonl_dict = {
'sentence_id': sentence_id,
'tokens': tokens,
'spans': spans
}
return json.dumps(output_jsonl_dict) + "\n"
def predict_json(self, inputs: JsonDict) -> JsonDict:
n = inputs.pop('n', 10)
if 'track_id' in inputs:
if self.index is None:
raise AttributeError("Please build an index before searching by track.")
idx = self.vocab.get_token_to_index_vocabulary("labels")[inputs['track_id']]
nns = self.index.get_nns_by_item(idx, n+1)[1:]
#scores = self.index.get_item_vector(idx)
tracks = self.neighbors_to_tracks(nns)
return tracks
#return {'tracks': tracks, 'scores': scores}
instance = self._json_to_instance(inputs)
output_dict = self.predict_instance(instance)
output_dict['inputs'] = inputs
if self.index:
logits = output_dict.get('logits')
nns = self.index.get_nns_by_vector(logits, n)
return self.neighbors_to_tracks(nns)
#output_dict['tracks'] = self.neighbors_to_tracks(nns)
return output_dict
def get_most_important_part(self, instance: Instance, output: JsonDict):
if "alphas" not in output:
return output
alphas = output.pop("alphas")
best_span = argmax(alphas)
tokens = instance["tokens"].tokens
nom = 0
span = (0, 0)
length = len(tokens)
flag = False
for i in range(1, length - 1):
for j in range(i, length - 1):
span = (i, j)
if nom == best_span:
flag = True
break
nom += 1
i, j = span
best_tokens = tokens[i:j + 1]
output["best_span"] = " ".join([token.text for token in best_tokens])
output["nom"] = nom
output["ij"] = [i, j]
output["break"] = flag
output["val"] = alphas[best_span]
def predict(self, inputs: JsonDict):
# For compatability with other RC models.
if "passage" in inputs:
inputs["context"] = inputs.pop("passage")
return super().predict(inputs)