embeddings_dict = {}
with io.open(config.data_path+config.global_vector_name, 'r', encoding='utf-8') as f:
for line in f:
values = line.split()
token = values[0]
vector = np.asarray(values[1:], "float32")
embeddings_dict[token] = vector
def train_data_context(unique_train_data_word):
#pdb.set_trace()
unique_train_data ={}
#unique_train_data_word_embeed = []
for i in unique_train_data_word:
try:
#unique_train_data_matrix.append(embeddings_dict[i].tolist())
unique_train_data.update({i:embeddings_dict[i].tolist()})
except:
continue
Matching_data= pd.DataFrame(unique_train_data.items(), columns=['unique_train_data_word_embeed', 'unique_train_data_matrix'])
return Matching_data