def transform_one(self, obs, target, id):
val_list = []
obs_tokens = nlp_utils._tokenize(obs, token_pattern)
target_tokens = nlp_utils._tokenize(target, token_pattern)
for obs_token in obs_tokens:
_val_list = []
if obs_token in self.model:
for target_token in target_tokens:
if target_token in self.model:
sim = dist_utils._cosine_sim(self.model[obs_token], self.model[target_token])
_val_list.append(sim)
if len(_val_list) == 0:
_val_list = [config.MISSING_VALUE_NUMERIC]
val_list.append( _val_list )
if len(val_list) == 0:
val_list = [[config.MISSING_VALUE_NUMERIC]]
return val_list
def _get_cosine_sim(self, sent1, sent2):
vect1 = self._get_vector(sent1)
vect2 = self._get_vector(sent2)
return dist_utils._cosine_sim(vect1, vect2)
def _get_cosine_sim(self, sent1, sent2):
vect1 = self._get_vector(sent1)
vect2 = self._get_vector(sent2)
return dist_utils._cosine_sim(vect1, vect2)