def LF_cause(c):
"""
If the causual keywords are between disease and gene then should be positive predictor
"""
if len(cause_words.intersection(get_between_tokens(c))) > 0:
return 1
return 0
def neg_nearby(c):
if (len(negative.intersection(get_between_tokens(c))) > 0):
return True
elif (len(negative.intersection(get_left_tokens(c, window=15))) > 0):
return True
else:
return False
def LF_DEBUG(c):
"""
This label function is for debugging purposes. Feel free to ignore.
keyword arguments:
c - The candidate object to be labeled
"""
print(c)
print()
print("Left Tokens")
print(list(get_left_tokens(c[0], window=5)))
print()
print("Right Tokens")
print(list(get_right_tokens(c[0])))
print()
print("Between Tokens")
print(list(get_between_tokens(c)))
print()
print("Tagged Text")
print(get_tagged_text(c))
print(re.search(r'{{B}} .* is a .* {{A}}', get_tagged_text(c)))
print()
print("Get between Text")
print(get_text_between(c))
print(len(get_text_between(c)))
print()
print("Parent Text")
print(c.get_parent())
print()
return 0
def LF_GiG_METHOD_DESC(c):
sentence_tokens = " ".join(c.get_parent().words[0:20])
if re.search(ltp(method_indication), sentence_tokens, flags=re.I):
return -1
elif re.search(ltp(method_indication), " ".join(get_between_tokens(c)), flags=re.I):
return -1
else:
return 0
def LF_DG_METHOD_DESC(c):
"""
This label function is designed to look for phrases
that imply a sentence is description an experimental design
"""
sentence_tokens = " ".join(c.get_parent().words[0:20])
if re.search(ltp(method_indication), sentence_tokens, flags=re.I):
return -1
elif re.search(ltp(method_indication), " ".join(get_between_tokens(c)), flags=re.I):
return -1
else:
return 0
def LF_DEBUG(C):
print "Left Tokens"
print get_left_tokens(c, window=3)
print
print "Right Tokens"
print get_right_tokens(c)
print
print "Between Tokens"
print get_between_tokens(c)
print
print "Tagged Text"
print get_tagged_text(c)
print re.search(r'{{B}} .* is a .* {{A}}', get_tagged_text(c))
print
print "Get between Text"
print get_text_between(c)
print len(get_text_between(c))
print
print "Parent Text"
print c.get_parent()
print
return 0
def LF_positive(c):
if (len(positive.intersection(get_between_tokens(c))) > 0) and not neg_nearby(c):
return 1
elif (len(positive.intersection(get_left_tokens(c[0], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(positive.intersection(get_left_tokens(c[1], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(positive.intersection(get_right_tokens(c[0], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(positive.intersection(get_right_tokens(c[1], window=20))) > 0) and not neg_nearby(c):
return 1
else:
return 0
def LF_other_verbs(c):
if (len(other_verbs.intersection(get_between_tokens(c))) > 0) and not neg_nearby(c):
return 1
elif (len(other_verbs.intersection(get_left_tokens(c[0], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(other_verbs.intersection(get_left_tokens(c[1], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(other_verbs.intersection(get_right_tokens(c[0], window=20))) > 0) and not neg_nearby(c):
return 1
elif (len(other_verbs.intersection(get_right_tokens(c[1], window=20))) > 0) and not neg_nearby(c):
return 1
else:
return 0
def LF_neg_assertions(c):
if (len(negative.intersection(get_between_tokens(c))) > 0):
return -1
elif (len(negative.intersection(get_left_tokens(c[0], window=10))) > 0):
return -1
elif (len(negative.intersection(get_left_tokens(c[1], window=20))) > 0):
return -1
elif (len(negative.intersection(get_right_tokens(c[0], window=20))) > 0):
return -1
# elif (len(negative.intersection(get_right_tokens(c[1], window=20))) > 0):
# return -1
else:
return 0
def LF_isolate(c):
if len(isolate.intersection(get_between_tokens(c))) > 0 and not neg_nearby(c):
return 1
elif len(isolate.intersection(get_left_tokens(c[0], window=20))) > 0 and not neg_nearby(c):
return 1
elif len(isolate.intersection(get_left_tokens(c[1], window=20))) > 0 and not neg_nearby(c):
return 1
elif len(isolate.intersection(get_right_tokens(c[0], window=20))) > 0 and not neg_nearby(c):
return 1
elif len(isolate.intersection(get_right_tokens(c[1], window=20))) > 0 and not neg_nearby(c):
return 1
else:
return 0
def LF_between_detect_refined(c):
cl, cr = c
candidate_predicates = list(get_between_tokens(c))
prepositions = {'at', 'to', 'from'}
intransitive_predicates = {
'enrolled', 'graduated', 'studied', 'went', 'returned', 'educated'
}
transitive_predicates = {'attended'}
phrases = {'member', 'of'}
return 1 if len(transitive_predicates.intersection(candidate_predicates))>0 or \
len(prepositions.intersection(candidate_predicates))>0 and \
len(intransitive_predicates.intersection(candidate_predicates))>0 \
or len(phrases.intersection(candidate_predicates))>1 \
else -1
def LF_DG_TITLE(c):
"""
This label function is designed to look for phrases that inditcates
a paper title
"""
if re.search(r'^(\[|\[ )?'+ltp(title_indication), get_tagged_text(c), flags=re.I):
return -1
elif re.search(ltp(title_indication)+r'$', get_tagged_text(c), flags=re.I):
return -1
elif "(author's transl)" in get_tagged_text(c):
return -1
elif ":" in get_between_tokens(c):
return -1
else:
return 0
def LF_distant_supervision_and_words(c):
try:
subject_span = getattr(c, "subject").get_span()
object_span = getattr(c, "object").get_span()
if subject_span == object_span:
return -1
if (len(words.intersection(c.get_parent().words)) < 1 \
or len(not_words.intersection(get_between_tokens(c)))>0) :
return 0
if subject_span == object_span:
return -1
if is_in_known_samples(predicate_resume, sentimantic_session,
subject_span, object_span):
return 1
sample_subject_span = getattr(c, "subject")
sample_subjects = get_nouns(sample_subject_span, subject_type_end)
sample_object_span = getattr(c, "object")
sample_objects = get_nouns(sample_object_span, object_type_end)
sample_subjects.append(subject_span)
sample_objects.append(object_span)
for sample_subject in sample_subjects:
for sample_object in sample_objects:
# if (sample_subject, sample_object)in known_samples:
if is_in_known_samples(predicate_resume,
sentimantic_session, sample_subject,
sample_object):
return 1
#todo implement date
return 0
except Exception as e:
print(e)
print("Not found candidate" + str(c.id))
return 0
def LF_combined_refined(c):
taboo = {'later', 'here', 'there'}
return 1 if LF_combined(c) == 1 and not len(
taboo.intersection(get_between_tokens(c))) > 0 else -1
def LF_combined(c):
return 1 if (LF_between_detect_refined(c) == 1 or 'at'
in get_between_tokens(c)) and LF_right_detect(c) == 1 else -1
def LF_familial_relationship(c):
return -1 if len(family.intersection(get_between_tokens(c))) > 0 else 0
def LF_words_between(c):
if len(words.intersection(get_between_tokens(c))) > 0:
return 1
return 0
def LF_familial_relationship(c):
return -1 if len(family.intersection(get_between_tokens(c))) > 0 else 0
def LF_husband_wife(c):
return 1 if len(spouses.intersection(get_between_tokens(c))) > 0 else 0
def LF_DG_DISTANCE_SHORT(c):
"""
This LF is designed to make sure that the disease mention
and the gene mention aren't right next to each other.
"""
return -1 if len(list(get_between_tokens(c))) <= 2 else 0
def LF_crime_detect(c):
return 1 if len(crime_tags.intersection(get_between_tokens(c))) > 0 else 0
def LF_political_title(c):
return 1 if len(titles.intersection(set(get_between_tokens(c)))) > 0 else 0
def LF_husband_wife(c):
return 1 if len(spouses.intersection(get_between_tokens(c))) > 0 else 0
def LF_not_words(c):
return -1 if len(not_words.intersection(
get_between_tokens(c))) > 0 else 0
def LF_DG_DISTANCE_LONG(c):
"""
This LF is designed to make sure that the disease mention
and the gene mention aren't too far from each other.
"""
return -1 if len(list(get_between_tokens(c))) > 50 else 0
def LF_too_far_apart(c):
return -1 if len(get_between_tokens(c)) > 10 else 0
def LF_and_married(c):
return 1 if 'and' in get_between_tokens(
c) and 'married' in get_right_tokens(c) else 0
def LF_nospace(c):
return 1 if [] == get_between_tokens(c) else 0
def LF_other_relationship(c):
return -1 if len(other.intersection(get_between_tokens(c))) > 0 else 0
def LF_betweentokens(c):
if len(get_between_tokens(c)) < 2:
return 1
else:
return 0
def LF_and_married(c):
return 1 if 'and' in get_between_tokens(c) and 'married' in get_right_tokens(c) else 0
def HELPER_VERB_BTWN(c):
return 1 if len(
helper_vbs.intersection(
set(get_between_tokens(c, attrib='lemmas', n_max=3)))) > 0 else 0
def LF_other_relationship(c):
return -1 if len(other.intersection(get_between_tokens(c))) > 0 else 0
def PREP_PHRASE_BTWN(c):
return 1 if len(
helper_vbs.intersection(
set(get_between_tokens(c, attrib='lemmas', n_max=3)))) > 0 else 0
