def reload_external_labels(session: SnorkelSession,
input_file: Union[str, Path],
annotator_name: str = "gold"):
Education = get_candidate_class()
with open(str(input_file), "r") as f:
lbls = ujson.load(f)
for lbl in lbls:
# we check if the label already exists, in case this cell was already executed
context_stable_ids = "~~".join((lbl['person'], lbl['organization']))
query = session.query(StableLabel).filter(
StableLabel.context_stable_ids == context_stable_ids)
query = query.filter(StableLabel.annotator_name == annotator_name)
if query.count() == 0:
session.add(
StableLabel(context_stable_ids=context_stable_ids,
annotator_name=annotator_name,
value=lbl['value']))
# commit session
session.commit()
# reload annotator labels
reload_annotator_labels(session,
Education,
annotator_name,
split=1,
filter_label_split=False)
reload_annotator_labels(session,
Education,
annotator_name,
split=2,
filter_label_split=False)
random.shuffle(cand_list)
#take 10 percent from here
train_cand_list += cand_list[0:int(len(cand_list) * 0.4)]
print(" -number of pairs:", len(cand_dict))
print(" -number of signals:", n)
print(" -number of pair to train GEN model", len(train_cand_list))
for i, cand in enumerate(cand_list):
split = 0 if cand in train_cand_list else 1
raw_text = RawText(stable_id=cand, name=cand, text=cand)
tweet = Tweet(tweet=raw_text, split=split)
session.add(tweet)
session.commit()
print("Commit to snorkel database done...")
#writing label generator
def worker_label_generator(t):
for worker_id in cand_dict[t.tweet.stable_id]:
yield worker_id, cand_dict[t.tweet.stable_id][worker_id]
np.random.seed(1701)
labeler = LabelAnnotator(label_generator=worker_label_generator)
L_train = labeler.apply(split=0)
print(L_train.lf_stats(session))
def run(candidate1, candidate2, pairing_name, cand1_ngrams, cand2_ngrams,
cand1Matcher, cand2Matcher, model_name, output_file_name,
corpus_parser):
print "Started"
session = SnorkelSession()
# The following line is for testing only. Feel free to ignore it.
candidate_pair = candidate_subclass(pairing_name, [candidate1, candidate2])
sentences = set()
docs = session.query(Document).order_by(Document.name).all()
for doc in docs:
for s in doc.sentences:
sentences.add(s)
cand_1_ngrams = Ngrams(n_max=cand1_ngrams)
# condition_ngrams = Ngrams(n_max=7)
cand_2_ngrams = Ngrams(n_max=cand2_ngrams)
# medium_ngrams = Ngrams(n_max=5)
# type_ngrams = Ngrams(n_max=5) # <--- Q: should we cut these down?
# # level_ngrams = Ngrams(n_max=1)
# unit_ngrams = Ngrams(n_max=1)
# Construct our Matchers
# cMatcher = matchers.getConditionMatcher()
# mMatcher = matchers.getMediumMatcher()
# tMatcher = matchers.getTypeMatcher()
# lMatcher = matchers.getLevelMatcher()
# uMatcher = matchers.getUnitMatcher()
# Building the CandidateExtractors
# candidate_extractor_BC = CandidateExtractor(BiomarkerCondition, [biomarker_ngrams, condition_ngrams], [bMatcher, cMatcher])
candidate_extractor = CandidateExtractor(candidate_pair,
[cand_1_ngrams, cand_2_ngrams],
[cand1Matcher, cand2Matcher])
# candidate_extractor_BM = CandidateExtractor(BiomarkerMedium, [biomarker_ngrams, medium_ngrams], [bMatcher, mMatcher])
# candidate_extractor_BT = CandidateExtractor(BiomarkerType, [biomarker_ngrams, type_ngrams], [bMatcher, tMatcher])
# candidate_extractor_BLU = CandidateExtractor(BiomarkerLevelUnit, [biomarker_ngrams, level_ngrams, unit_ngrams], [bMatcher, lMatcher, uMatcher])
# List of Candidate Sets for each relation type: [train, dev, test]
candidate_extractor.apply(sentences, split=4, clear=True)
cands = session.query(candidate_pair).filter(
candidate_pair.split == 4).order_by(candidate_pair.id).all()
session.commit()
# cands_BD = grabCandidates(candidate_extractor_BD, BiomarkerDrug)
# cands_BM = grabCandidates(candidate_extractor_BM, BiomarkerMedium)
# cands_BT = grabCandidates(candidate_extractor_BT, BiomarkerType)
# cands_BLU = grabCandidates(candidate_extractor_BLU, BiomarkerLevelUnit)
if (len(cands)) == 0:
print "No Candidates Found"
return
if (pairing_name == 'BiomarkerCondition'):
# session.rollback()
# print "Number of dev BC candidates without adj. boosting: ", len(cands_BC[1])
add_adj_candidate_BC(session, candidate_pair, cands, 4)
# fix_specificity(session, BiomarkerCondition, cands_BC[1])
# print "Number of dev BC candidates with adj. boosting: ", session.query(BiomarkerCondition).filter(BiomarkerCondition.split == 4).count()
session.commit()
lstm = reRNN(seed=1701, n_threads=None)
lstm.load(model_name)
predictions = lstm.predictions(cands)
output_file = open(output_file_name, 'wb')
import csv
csvWriter = csv.writer(output_file)
csvWriter.writerow(
['doc_id', 'sentence', candidate1, candidate2, 'prediction'])
for i in range(len(cands)):
doc_string = 'PMC' + str(cands[i].get_parent().get_parent())[9:]
sentence_string = cands[i].get_parent().text
cand_1_string = cands[i].get_contexts()[0].get_span()
cand_2_string = cands[i].get_contexts()[1].get_span()
prediction = predictions[i]
csvWriter.writerow([
unidecode(doc_string),
unidecode(sentence_string),
unidecode(cand_1_string),
unidecode(cand_2_string), prediction
])
