def get_features_for_row(row):
#OPTS = config.GENE['F']
features = []
f = Feature(doc_id=row.doc_id,
section_id=row.section_id,
mention_id=row.mention_id,
name=None)
# (1) Get generic ddlib features
sentence = util.create_ddlib_sentence(row)
span = ddlib.Span(begin_word_id=row.mention_wordidxs[0],
length=len(row.mention_wordidxs))
generic_features = [
f._replace(name=feat)
for feat in ddlib.get_generic_features_mention(sentence, span)
]
features += generic_features
features += [f._replace(name=feat) for feat in get_custom_features(row)]
# (2) Include gene type as a feature
# Note: including this as feature creates massive overfitting, for obvious reasons
# We need neg supervision of canonical & noncanonical symbols, then can / should try adding this feature
"""
for t in ENSEMBL_TYPES:
if re.search(re.escape(t), row.mention_type, flags=re.I):
features.append(f._replace(name='GENE_TYPE[%s]' % t))
break
"""
return features
def get_features_for_row(row):
OPTS = config.PHENO_ACRONYMS['F']
features = []
f = Feature(doc_id=row.doc_id,
section_id=row.section_id,
mention_id=row.mention_id,
name=None)
# (1) Get generic ddlib features
sentence = util.create_ddlib_sentence(row)
allWordIdxs = row.short_wordidxs + row.long_wordidxs
start = min(allWordIdxs)
length = max(allWordIdxs) - start
span = ddlib.Span(begin_word_id=start, length=length)
assert len(span) > 0, row
assert start + length < len(row.words), (start + length, len(row.words),
row)
generic_features = [
f._replace(name=feat)
for feat in ddlib.get_generic_features_mention(sentence, span)
]
# Optionally filter out some generic features
if OPTS.get('exclude_generic'):
generic_features = filter(
lambda feat: not feat.startswith(tuple(OPTS['exclude_generic'])),
generic_features)
features += generic_features
return features
def get_features_for_candidate(row):
"""Extract features for candidate mention- both generic ones from ddlib & custom features"""
features = []
f = Feature(doc_id=row.doc_id,
section_id=row.section_id,
relation_id=row.relation_id,
name=None)
dds = util.create_ddlib_sentence(row)
# (1) GENERIC FEATURES from ddlib
gene_span = ddlib.Span(begin_word_id=row.gene_wordidxs[0],
length=len(row.gene_wordidxs))
pheno_span = ddlib.Span(begin_word_id=row.pheno_wordidxs[0],
length=len(row.pheno_wordidxs))
for feat in ddlib.get_generic_features_relation(dds, gene_span,
pheno_span):
if take_feature(feat):
features.append(f._replace(name=feat))
features.extend(
[f._replace(name=feat) for feat in get_custom_features(row, dds)])
# these seem to be hurting (?)
# start_span = ddlib.Span(begin_word_id=0, length=4)
# for feat in ddlib.get_generic_features_mention(dds, start_span, length_bin_size=2):
# features.append(f._replace(name='START_SENT_%s' % feat))
# WITH these custom features, I get a little LESS precision and a little MORE recall (!)
# features += [f._replace(name=feat) for feat in create_ners_between(row.gene_wordidxs, row.pheno_wordidxs, row.ners)]
return features
def get_features_for_candidate(row):
"""Extract features for candidate mention- both generic ones from ddlib & custom features"""
features = []
f = Feature(doc_id=row.doc_id,
section_id=row.section_id,
relation_id=row.relation_id,
name=None)
dds = util.create_ddlib_sentence(row)
# (1) GENERIC FEATURES from ddlib
genevar_span = ddlib.Span(begin_word_id=row.genevar_wordidxs[0],
length=len(row.genevar_wordidxs))
pheno_span = ddlib.Span(begin_word_id=row.pheno_wordidxs[0],
length=len(row.pheno_wordidxs))
features += [f._replace(name=feat) \
for feat in ddlib.get_generic_features_relation(dds, genevar_span, pheno_span)]
return features
def get_features_for_candidate(row):
"""Extract features for candidate mention- both generic ones from ddlib & custom features"""
features = []
dds = util.create_ddlib_sentence(row)
# (1) GENERIC FEATURES from ddlib
span = ddlib.Span(begin_word_id=row.mention_wordidxs[0],
length=len(row.mention_wordidxs))
features += [(row.doc_id, row.section_id, row.mention_id, feat) \
for feat in ddlib.get_generic_features_mention(dds, span)]
# (2) Add the closest verb by raw distance
if OPTS.get('closest-verb'):
verb_idxs = [i for i, p in enumerate(row.poses) if p.startswith("VB")]
if len(verb_idxs) > 0:
dists = filter(lambda d : d[0] > 0, \
[(min([abs(i-j) for j in row.mention_wordidxs]), i) for i in verb_idxs])
if len(dists) > 0:
verb = row.lemmas[min(dists)[1]]
features.append((row.doc_id, row.section_id, row.mention_id,
'NEAREST_VERB_[%s]' % (verb, )))
return features