def run(
self,
aspect_lex: PathLike = None,
opinion_lex: PathLike = None,
data: PathLike = None,
parsed_data: PathLike = None,
inference_results: PathLike = None,
) -> Optional[pd.DataFrame]:
opinions = load_opinion_lex(opinion_lex)
if not opinions:
raise ValueError("Empty opinion lexicon!")
aspects = pd.read_csv(aspect_lex, header=None, encoding="utf-8")[0]
if aspects.empty:
raise ValueError("Empty aspect lexicon!")
if inference_results:
with open(inference_results, encoding="utf-8") as f:
results = json.loads(f.read(),
object_hook=SentimentDoc.decoder)
elif data or parsed_data:
inference = SentimentInference(aspect_lex, opinions, parse=False)
parse = None
if not parsed_data: # source data is raw text, need to parse
from nlp_architect.pipelines.spacy_bist import SpacyBISTParser
parse = SpacyBISTParser().parse
results = {}
print("Running inference on data files... (Iterating data files)")
data_source = parsed_data if parsed_data else data
for file, doc in self._iterate_docs(data_source):
parsed_doc = (parse(doc) if parse else json.loads(
doc, object_hook=CoreNLPDoc.decoder))
sentiment_doc = inference.run(parsed_doc=parsed_doc)
if sentiment_doc:
results[file] = sentiment_doc
with open(SENTIMENT_OUT / "inference_results.json",
"w",
encoding="utf-8") as f:
json.dump(results,
f,
cls=SentimentDocEncoder,
indent=4,
sort_keys=True)
else:
print(
"No input given. Please supply one of: "
"data directory, parsed data directory, or inference results.")
return None
print("\nComputing statistics...")
stats = self._compute_stats(results, aspects, opinions)
print("Done.")
return stats
def __init__(self,
aspect_lex: PathLike,
opinion_lex: PathLike or dict,
parse: bool = True):
"""Inits SentimentInference with given aspect and opinion lexicons."""
INFERENCE_OUT.mkdir(parents=True, exist_ok=True)
self.opinion_lex = \
opinion_lex if type(opinion_lex) is dict else load_opinion_lex(opinion_lex)
self.aspect_lex = _load_aspect_lexicon(aspect_lex)
self.intensifier_lex = _read_lexicon_from_csv('IntensifiersLex.csv')
self.negation_lex = _read_lexicon_from_csv('NegationSentLex.csv')
if parse:
from nlp_architect.pipelines.spacy_bist import SpacyBISTParser
self.parser = SpacyBISTParser()
else:
self.parser = None
def __init__(
self,
aspect_lex: Union[str, PathLike],
opinion_lex: Union[str, PathLike, dict],
parse: bool = True,
):
"""Inits SentimentInference with given aspect and opinion lexicons."""
INFERENCE_OUT.mkdir(parents=True, exist_ok=True)
self.opinion_lex = (opinion_lex if type(opinion_lex) is dict else
load_opinion_lex(Path(opinion_lex)))
self.aspect_lex = _load_aspect_lexicon(Path(aspect_lex))
self.intensifier_lex = _read_lexicon_from_csv("IntensifiersLex.csv")
self.negation_lex = _read_lexicon_from_csv("NegationSentLex.csv")
if parse:
from nlp_architect.pipelines.spacy_bist import SpacyBISTParser
self.parser = SpacyBISTParser(spacy_model="en")
else:
self.parser = None
def __init__(
self,
aspect_lex: Union[str, PathLike],
opinion_lex: Union[str, PathLike, dict],
parse: bool = True,
parser="spacy",
spacy_model="en_core_web_sm",
):
"""Inits SentimentInference with given aspect and opinion lexicons."""
INFERENCE_OUT.mkdir(parents=True, exist_ok=True)
self.opinion_lex = (
opinion_lex if type(opinion_lex) is dict else load_opinion_lex(Path(opinion_lex))
)
self.aspect_lex = _load_aspect_lexicon(Path(aspect_lex))
self.intensifier_lex = _read_lexicon_from_csv("IntensifiersLex.csv")
self.negation_lex = _read_lexicon_from_csv("NegationSentLex.csv")
self.parser_name = parser
if parse:
if parser == "bist":
from nlp_architect.pipelines.spacy_bist import SpacyBISTParser
self.parser = SpacyBISTParser(spacy_model=spacy_model)
elif parser == "spacy":
from nlp_architect.utils.text import SpacyInstance
disable = [
"merge_noun_chunks",
"ner",
"entity_linker",
"textcat",
"entity_ruler",
"sentencizer",
"merge_entities",
]
self.parser = SpacyInstance(
model=spacy_model, disable=disable, ptb_pos=True, n_jobs=1
)
else:
self.parser = None
