def concept_features_for_sentence(sentence, chunk_inds):
"""
concept_features()
@param sentence. A sentence in list of chunk format
@param chunk_inds. A list of indices for non-None-labeled chunks
@return A list of feature dictionaries
"""
# Get a feature set for each word in the sentence
features_list = []
for ind in chunk_inds:
features_list.append(
feat_word.concept_features_for_chunk(sentence, ind))
# Allow for particular features to be enabled
for feature in enabled_concept_features:
# Features: UMLS features
if (feature == "UMLS") and enabled['UMLS']:
umls_features = feat_umls.concept_features_for_chunks(
sentence, chunk_inds)
for i in range(len(chunk_inds)):
features_list[i].update(umls_features[i])
return features_list
def concept_features_for_sentence(sentence, chunk_inds):
"""
concept_features()
@param sentence. A sentence in list of chunk format
@param chunk_inds. A list of indices for non-None-labeled chunks
@return A list of feature dictionaries
"""
global dependency_parser
# Get a feature set for each word in the sentence
features_list = []
for ind in chunk_inds:
features_list.append(
feat_word.concept_features_for_chunk(sentence, ind))
dependencies = None
if dependency_parser is not None:
dependencies = dependency_parser.get_collapsed_dependencies(sentence)
# Allow for particular features to be enabled
for feature in enabled_concept_features:
# Features: UMLS features
if (feature == "UMLS") and enabled['UMLS']:
umls_features = feat_umls.concept_features_for_chunks(
sentence, chunk_inds)
for i in range(len(chunk_inds)):
features_list[i].update(umls_features[i])
if (feature == "grammar_features" and enabled["PY4J"]):
print "getting grammar features"
for i, target_index in enumerate(chunk_inds):
if dependencies is not None:
features_list[i].update(
dependency_parser.get_related_tokens(
target_index, sentence, dependencies))
if enabled_modules()["WORD2VEC"]:
print "getting vectors..."
for i, chunk_index in enumerate(chunk_inds):
chunk = sentence[chunk_index]
cluster = predict_sequence_cluster(chunk)
features_list[i].update({("cluster", cluster): 1})
return features_list