def read_csv_file(source_file):
topic_models_lists = {}
with open(source_file,"rb") as f:
spamreader = csv.reader(f)
for row in spamreader:
labels = row[1].split()
single_model = Model(remove_stopwords=False,text_string=row[2],
need_stem=True, input_stemmed=True)
single_model.to_dirichlet()
for topic in labels:
if topic not in topic_models_lists:
topic_models_lists[topic] = []
topic_models_lists[topic].append(single_model)
topic_models = {}
for topic in topic_models_lists:
topic_models[topic] = Model(remove_stopwords=False,
need_stem=True, input_stemmed=True)
for single_model in topic_models_lists[topic]:
topic_models[topic] += single_model
topic_models[topic].to_dirichlet()
print "Finished Reading models"
return topic_models
def get_model_for_entities(source_dir):
models = {}
for instance in os.walk(source_dir).next()[2]:
data = json.load(open(os.path.join(source_dir, instance)))
for entity_type in data:
if entity_type not in models:
temp = Model(True, need_stem=True)
temp.normalize()
models[entity_type] = temp
for entity in data[entity_type]:
temp = Model(True,
text_dict=data[entity_type][entity],
need_stem=True,
input_stemmed=True)
temp.normalize()
models[entity_type] += temp
return models
def get_all_words(example_result_tuples):
word_model = Model(True, need_stem=True)
for single_tuple in example_result_tuples:
word_model += Sentence(single_tuple['sentence'],
remove_stopwords=True).stemmed_model
word_model.normalize()
return word_model
def get_all_words(result_tuples):
word_model = Model(False, need_stem=False)
for single_tuple in result_tuples:
word_model += Sentence(single_tuple['sentence'],
remove_stopwords=False).raw_model
word_model.to_dirichlet()
return word_model
def get_all_words(tuple_results):
words = {}
for identifier in tuple_results:
word_model = Model(True,need_stem=True)
for single_tuple in tuple_results[identifier]:
word_model += Sentence(single_tuple['sentence'],remove_stopwords=True).stemmed_model
word_model.normalize()
for word in word_model.model:
if word not in words:
words[word] = 0
words[word] += word_model.model[word]
return words
def get_verbs(tuple_result):
verbs = {}
for identifier in tuple_result:
verb_model = Model(True)
for single_tuple in tuple_result[identifier]:
verb = single_tuple['verb']
if verb not in NO_NEED:
verb_model.update(text_list=[verb])
verb_model.normalize()
for verb in verb_model.model:
if verb not in verbs:
verbs[verb] = 0
verbs[verb] += verb_model.model[verb]
return verbs
def get_single_model(candidate_dir):
candidate_models = {}
files = os.walk(candidate_dir).next()[2]
for a_file in files:
candidate_models[a_file] = {}
temp_model = json.load(open(os.path.join(candidate_dir, a_file)))
for w in temp_model:
if w not in candidate_models:
temp = Model(True,
text_dict=temp_model[w],
need_stem=True,
input_stemmed=True)
temp.normalize()
candidate_models[a_file][w] = temp
return candidate_models
def get_all_verbs(example_result_tuples):
verb_model = Model(True, need_stem=True)
for single_tuple in example_result_tuples:
word = single_tuple['verb']
if single_tuple['verb_label'] != 'VB':
word = WordNetLemmatizer().lemmatize(word, 'v')
try:
verb_model.update(text_list=[str(word)])
except TypeError:
print "Wrong Word!"
print word
print type(word)
print single_tuple
sys.exit(0)
verb_model.normalize()
return verb_model
def get_all_verbs(result_tuples):
verb_model = Model(False, need_stem=False)
for single_tuple in result_tuples:
word = single_tuple['verb']
# if single_tuple['verb_label'] != 'VB':
# word = WordNetLemmatizer().lemmatize(word,'v')
try:
verb_model.update(text_list=[str(word)])
except TypeError:
print "Wrong Word!"
print word
print type(word)
print single_tuple
sys.exit(0)
verb_model.to_dirichlet()
return verb_model
def get_sentence_window(entity_map,sentence,windows):
"""
Use the whole sentence as the context
"""
#print sentence
for w in entity_map:
# if w != u'Jefferson County':
# continue
# else:
# pass
# print "YES!"
if sentence.find(w) != -1:
#print "found sentence %s" %sentence
if entity_map[w]:
w = entity_map[w]
if w not in windows:
windows[w] = Model(True,need_stem=True)
windows[w] += Sentence(re.sub("\n"," ",sentence),remove_stopwords=True).stemmed_model
def get_sub_features(model, size):
"""
get top terms as features
"""
data = Model(True, need_stem=True, input_stemmed=True)
for instance in model:
for w in model[instance]:
data += model[instance][w]
data.normalize()
terms = data.model
sorted_terms = sorted(terms.items(), key=lambda x: x[1], reverse=True)
i = 0
features = {}
for (w, v) in sorted_terms:
features[w] = v
i += 1
if i == size:
print "break when i is", i
break
print "get %d features" % (len(features))
return features