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_models(results,index_dir):
models = {}
for qid in results:
if qid not in models:
models[qid] = {}
for day in results[qid]:
single_model = Model(True,need_stem=True)
for tid in results[qid][day]:
text = get_text(index_dir,tid)
if text:
single_model.update(text_string=text)
single_model.normalize()
models[qid][day] = single_model.model
return 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_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