def LOAD(path):
with open(os.path.join(path, "counter-fitted-vectors.txt"), "r") as f:
id2vec = []
word2id = {}
for line in f.readlines():
tmp = line.strip().split(" ")
word = tmp[0]
embed = np.array([float(x) for x in tmp[1:]])
if len(embed) != 300:
continue
word2id[word] = len(word2id)
id2vec.append(embed)
id2vec = np.stack(id2vec)
return WordVector(word2id, id2vec)
def LOAD(path):
with open(os.path.join(path, "chinese-merge-word-embedding.txt"),
"r",
encoding="utf-8") as f:
id2vec = []
word2id = {}
# f.readline()
for line in f.readlines():
tmp = line.strip().split(' ')
word = tmp[0]
embed = np.array([float(x) for x in tmp[1:]])
if len(embed) != 300:
continue
word2id[word] = len(word2id)
id2vec.append(embed)
id2vec = np.stack(id2vec)
return WordVector(word2id, id2vec)
def LOAD(path):
word2id = pickle.load(open(os.path.join(path, "word2id.pkl"), "rb"))
wordvec = pickle.load(open(os.path.join(path, "wordvec.pkl"), "rb"))
return WordVector(word2id, wordvec)