def test_evaluation():
from sematch.utility import FileIO
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
question = FileIO.read_json_file('dataset/ned/question_ned_cleaned.txt')
tweet = FileIO.read_json_file('dataset/ned/tweet_ned_cleaned.txt')
print len(query)
print len(question)
print len(tweet)
def test_entity_feature():
from sematch.utility import FileIO
from sematch.nlp import EntityFeature
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
question = FileIO.read_json_file('dataset/ned/question_ned_cleaned.txt')
tweet = FileIO.read_json_file('dataset/ned/tweet_ned_cleaned.txt')
import itertools
candidates = list(itertools.chain.from_iterable(map(lambda x:x['candidate'], question)))
set_candidates = list(set(candidates))
print len(set_candidates)
EntityFeature.candidate_features(set_candidates, export_file='models/question_features.json')
def graph_ic_reader(self, filename):
"""
Load the saved IC values
:param filename: the file containing IC values of concepts
:return: a dictionary concept:IC
"""
data = FileIO.read_json_file(filename)
return {d['concept']:float(d['ic']) for d in data}
def load(cls, feature_dict_file='models/entity_features.json'):
from sematch.utility import FileIO
entity_features = FileIO.read_json_file(feature_dict_file)
entity_features = {
e['dbr']: (e['desc'], e['cat'])
for e in entity_features
}
return cls(entity_features)
def __init__(self,
graph_ic='models/yago_type_ic.txt',
mappings="models/type-linkings.txt"):
WordNetSimilarity.__init__(self)
self._graph_ic = GraphIC(graph_ic)
self._mappings = FileIO.read_json_file(mappings)
self._id2mappings = {data['offset']: data for data in self._mappings}
self._yago2id = {
data['yago_dbpedia']: data['offset']
for data in self._mappings
}
def test_feature_extractor():
from sematch.nlp import FeatureExtractor
from sematch.nlp import EntityFeature
from sematch.nlp import SpaCyNLP
from sematch.utility import FileIO
import itertools
sy = SpaCyNLP()
w_extractor = FeatureExtractor(sy.pos_tag)
features = EntityFeature.load(feature_dict_file='models/query_features.json')
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
candidates = list(itertools.chain.from_iterable(map(lambda x: x['candidate'], query)))
set_candidates = list(set(candidates))
for can in set_candidates[:10]:
print w_extractor.entity_word_features([can], features)
def candidate_features(cls, candidates, export_file='models/candidate_features.json',
feature_dict_file='models/entity_features.json'):
from sematch.utility import FileIO
entity_features = FileIO.read_json_file(feature_dict_file)
entity_features = {e['dbr']: (e['desc'], e['cat']) for e in entity_features}
features = []
for i, can in enumerate(candidates):
print i, " ", can
data = {}
data['dbr'] = can
data['desc'] = entity_features[can][0] if can in entity_features else None
data['cat'] = entity_features[can][1] if can in entity_features else []
features.append(data)
FileIO.save_json_file(export_file, features)
return features
def test_query_ned():
from sematch.nlp import FeatureExtractor
from sematch.nlp import EntityFeature
from sematch.nlp import SpaCyNLP
from sematch.utility import FileIO
from sematch.semantic.relatedness import TextRelatedness
from sematch.nel import EntityDisambiguation
import itertools
sy = SpaCyNLP()
features = EntityFeature.load(
feature_dict_file='models/query_features.json')
extractor = FeatureExtractor(features, sy.pos_tag)
ned = EntityDisambiguation(extractor)
rel = TextRelatedness()
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
#print wns.word_similarity('cooling', 'air_conditioner', 'li')
#similarity = lambda x,y : rel.text_similarity(x,y, model='lsa')
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
query = [q for q in query if extractor.context_features(q['query'])]
print len(query)
import warnings
warnings.filterwarnings("ignore")
metrics = ['path', 'wup', 'res', 'lin', 'jcn', 'wpath']
for m in metrics:
print m
similarity = lambda x, y: wns.word_similarity(x, y, m)
for k in range(1, 21):
gold = []
predict = []
for q in query:
gold.append(q['gold'])
#e = ned.text_disambiguate(q['query'], q['candidate'], similarity)
e = ned.word_disambiguate(q['query'],
q['candidate'],
similarity,
K=k)
predict.append(e)
from sklearn.metrics import precision_recall_fscore_support
#from sklearn.metrics import classification_report
#print classification_report(gold, predict)
print precision_recall_fscore_support(gold,
predict,
average='weighted')[2]
def test_query_ned():
from sematch.nlp import FeatureExtractor
from sematch.nlp import EntityFeature
from sematch.nlp import SpaCyNLP
from sematch.utility import FileIO
from sematch.semantic.relatedness import TextRelatedness
from sematch.nel import EntityDisambiguation
import itertools
sy = SpaCyNLP()
features = EntityFeature.load(feature_dict_file='models/query_features.json')
extractor = FeatureExtractor(features, sy.pos_tag)
ned = EntityDisambiguation(extractor)
rel = TextRelatedness()
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
#print wns.word_similarity('cooling', 'air_conditioner', 'li')
#similarity = lambda x,y : rel.text_similarity(x,y, model='lsa')
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
query = [q for q in query if extractor.context_features(q['query'])]
print len(query)
import warnings
warnings.filterwarnings("ignore")
metrics = ['path', 'wup', 'res', 'lin', 'jcn', 'wpath']
for m in metrics:
print m
similarity = lambda x, y: wns.word_similarity(x, y, m)
for k in range(1, 21):
gold = []
predict = []
for q in query:
gold.append(q['gold'])
#e = ned.text_disambiguate(q['query'], q['candidate'], similarity)
e = ned.word_disambiguate(q['query'], q['candidate'], similarity, K=k)
predict.append(e)
from sklearn.metrics import precision_recall_fscore_support
#from sklearn.metrics import classification_report
#print classification_report(gold, predict)
print precision_recall_fscore_support(gold, predict, average='weighted')[2]
def candidate_features(cls,
candidates,
export_file='models/candidate_features.json',
feature_dict_file='models/entity_features.json'):
from sematch.utility import FileIO
entity_features = FileIO.read_json_file(feature_dict_file)
entity_features = {
e['dbr']: (e['desc'], e['cat'])
for e in entity_features
}
features = []
for i, can in enumerate(candidates):
print i, " ", can
data = {}
data['dbr'] = can
data['desc'] = entity_features[can][
0] if can in entity_features else None
data['cat'] = entity_features[can][
1] if can in entity_features else []
features.append(data)
FileIO.save_json_file(export_file, features)
return features
def load_dataset(self):
data = FileIO.read_json_file('dataset/aspect/data.txt')
X, y = zip(*[(d['text'], d['label']) for d in data])
return X, y
def load_dataset(self):
data = FileIO.read_json_file('dataset/aspect/data.txt')
X, y = zip(*[(d['text'], d['label']) for d in data])
return X, y
def __init__(self, graph_ic='models/yago_type_ic.txt', mappings="models/type-linkings.txt"):
WordNetSimilarity.__init__(self)
self._graph_ic = GraphIC(graph_ic)
self._mappings = FileIO.read_json_file(mappings)
self._id2mappings = {data['offset']: data for data in self._mappings}
self._yago2id = {data['yago_dbpedia']: data['offset'] for data in self._mappings}
def load(cls, name_dict_file='models/name.dict'):
from sematch.utility import FileIO
name = FileIO.read_json_file(name_dict_file)
name = {n['name']: n['concepts'] for n in name}
return cls(name)
def load(cls, feature_dict_file='models/entity_features.json'):
from sematch.utility import FileIO
entity_features = FileIO.read_json_file(feature_dict_file)
entity_features = {e['dbr']: (e['desc'], e['cat']) for e in entity_features}
return cls(entity_features)
def load(cls, name_dict_file='models/name.dict'):
from sematch.utility import FileIO
name = FileIO.read_json_file(name_dict_file)
name = {n['name']: n['concepts'] for n in name}
return cls(name)
