def pipeline(collection, metamap, splitter, parser, ptb2dep, neg_detector, cuis, extra_args):
"""
Args:
collection(BioCCollection):
metamap(MetaMap): MetaMap instance
splitter (NegBioSSplitter):
parser (NegBioParser)
ptb2dep (NegBioPtb2DepConverter)
neg_detector (Detector):
Returns:
BioCCollection
"""
for document in collection.documents:
splitter.split_doc(document)
dner_mm.run_metamap_col(collection, metamap, cuis, extra_args)
for document in collection.documents:
document = parser.parse_doc(document)
document = ptb2dep.convert_doc(document)
document = negdetect.detect(document, neg_detector)
# remove sentence
for passage in document.passages:
del passage.sentences[:]
return collection
def classify(self, collection):
"""Classify each mention into one of
negative, uncertain, or positive."""
documents = collection.documents
if self.verbose:
print("Classifying mentions...")
documents = tqdm(documents)
for document in documents:
# Parse the impression text in place.
parse.parse(document, self.parser)
# Add the universal dependency graph in place.
ptb2ud.convert(document, self.ptb2dep, self.lemmatizer)
# Detect the negation and uncertainty rules in place.
negdetect.detect(document, self.detector)
# To reduce memory consumption, remove sentences text.
del document.passages[0].sentences[:]
def pipeline(document, splitter, parser, ptb2dep, lemmatizer, neg_detector):
document = ssplit.ssplit(document, splitter)
document = parse.parse(document, parser)
document = ptb2ud.convert(document, ptb2dep, lemmatizer)
document = negdetect.detect(document, neg_detector)
# remove sentence
for passage in document.passages:
del passage.sentences[:]
return document
def pipeline(collection, metamap, splitter, parser, ptb2dep, lemmatizer, neg_detector, cuis):
for document in collection.documents:
ssplit.ssplit(document, splitter)
dner_mm.run_metamap_col(collection, metamap, cuis)
for document in collection.documents:
document = parse.parse(document, parser)
document = ptb2ud.convert(document, ptb2dep, lemmatizer)
document = negdetect.detect(document, neg_detector)
# remove sentence
for passage in document.passages:
del passage.sentences[:]
return collection
def process_collection(collection, metamap, splitter, parser, ptb2dep, lemmatizer, neg_detector, cuis, sec_title_patterns):
for document in collection.documents:
normalize_mimiccxr.normalize(document)
section_split.split_document(document, sec_title_patterns)
ssplit.ssplit(document, splitter)
dner_mm.run_metamap_col(collection, metamap, cuis)
for document in collection.documents:
document = parse.parse(document, parser)
document = ptb2ud.convert(document, ptb2dep, lemmatizer)
document = negdetect.detect(document, neg_detector)
cleanup.clean_sentences(document)
return collection
def pipeline(collection,
loader,
ssplitter,
extractor,
parser,
ptb2dep,
neg_detector,
aggregator,
verbose=False):
"""
Args:
loader (NegBioLoader)
ssplitter (NegBioSSplitter)
parser (NegBioParser)
extractor (NegBioExtractor)
ptb2dep (NegBioPtb2DepConverter)
neg_detector (ModifiedDetector)
aggregator (NegBioAggregator)
"""
# for document in collection.documents:
#
# for passage in document.passages:
# passage.text = clean(passage.text)
# ssplitter.split_doc(document)
for document in tqdm.tqdm(collection.documents, disable=not verbose):
document = loader.clean_doc(document)
document = ssplitter.split_doc(document)
document = extractor.extract_doc(document)
document = parser.parse_doc(document)
document = ptb2dep.convert_doc(document)
document = negdetect.detect(document, neg_detector)
document = aggregator.aggregate_doc(document)
# remove sentence
for passage in document.passages:
del passage.sentences[:]
return collection
