def run_multiple(
self,
data: Union[str, PathLike] = None,
parsed_data: Union[str, PathLike] = None,
out_dir: Union[str, PathLike] = INFERENCE_OUT,
):
if not parsed_data:
if not self.parser:
raise RuntimeError("Parser not initialized (try parse=True at init)")
parsed_dir = Path(out_dir) / "parsed" / Path(data).stem
parsed_data = self.parse_data(data, out_dir=parsed_dir)
sentiment_docs = {}
for f, parsed_doc in tqdm(_load_parsed_docs_from_dir(out_dir)):
sentiment_doc = self.run(parsed_doc=parsed_doc)
sentiment_docs[f] = sentiment_doc
return sentiment_docs
def acquire_lexicons(self, parsed_dir: str or PathLike):
"""Acquire new opinion and aspect lexicons.
Args:
parsed_dir (PathLike): Path to parsed documents folder.
"""
parsed_docs = _load_parsed_docs_from_dir(parsed_dir)
dataset_sentence_len = 0
for parsed_doc in parsed_docs.values():
dataset_sentence_len += len(parsed_doc.sentences)
add_to_thresholds = int(
dataset_sentence_len / self.NUM_OF_SENTENCES_PER_OPINION_AND_ASPECT_TERM_INC
)
self.min_freq_opinion_candidate += add_to_thresholds
self.min_freq_aspect_candidate += add_to_thresholds
for iteration_num in range(self.max_num_of_iterations):
if (
len(self.opinion_candidate_list_prev_iter) == 0
and len(self.aspects_candidate_list_prev_iter) == 0
):
break
print("\n#Iteration: {}".format(iteration_num + 1))
self.extract_opinion_and_aspect_terms(iter(parsed_docs.values()), len(parsed_docs))
self._insert_new_terms_to_tables()
self.opinion_candidates_list_final = generate_final_opinion_candidates_list(
self.opinion_candidate_list_raw,
self.opinion_candidates_list_final,
self.min_freq_opinion_candidate,
)
self.aspect_candidates_list_final = _generate_final_aspect_candidates_list(
self.aspect_candidate_list_raw,
self.aspect_candidates_list_final,
self.min_freq_aspect_candidate,
)
self._write_candidate_opinion_lex()
aspect_dict = _add_lemmas_aspect_lex(self.aspect_candidates_list_final)
return aspect_dict
def acquire_lexicons(self, parsed_dir: str or PathLike):
"""Acquire new opinion and aspect lexicons.
Args:
parsed_dir (PathLike): Path to parsed documents folder.
"""
parsed_docs = _load_parsed_docs_from_dir(parsed_dir)
dataset_sentence_len = 0
for parsed_doc in parsed_docs.values():
dataset_sentence_len += len(parsed_doc.sentences)
add_to_thresholds = \
int(dataset_sentence_len / self.NUM_OF_SENTENCES_PER_OPINION_AND_ASPECT_TERM_INC)
self.min_freq_opinion_candidate += add_to_thresholds
self.min_freq_aspect_candidate += add_to_thresholds
for iteration_num in range(self.MAX_NUM_OF_ITERATIONS):
if len(self.opinion_candidate_list_prev_iter) == 0 \
and len(self.aspects_candidate_list_prev_iter) == 0:
break
print("\n#Iteration: {}".format(iteration_num + 1))
self.extract_opinion_and_aspect_terms(iter(parsed_docs.values()),
len(parsed_docs))
self._insert_new_terms_to_tables()
self.opinion_candidates_list_final = \
generate_final_opinion_candidates_list(
self.opinion_candidate_list_raw, self.opinion_candidates_list_final,
self.min_freq_opinion_candidate)
self.aspect_candidates_list_final = \
_generate_final_aspect_candidates_list(
self.aspect_candidate_list_raw,
self.aspect_candidates_list_final,
self.min_freq_aspect_candidate)
self._write_output()
aspect_dict = {}
for cand_term in self.aspect_candidates_list_final:
aspect_dict[cand_term.term[0]] = cand_term.frequency
return aspect_dict