def feature(self, words):
"""average words' vectors"""
feature_vec = np.zeros((self.dimension,), dtype="float32")
retrieved_words = 0
for token in words:
try:
feature_vec = np.add(feature_vec, self.embeddings[token])
retrieved_words += 1
except KeyError:
pass # if a word is not in the embeddings' vocabulary discard it
np.seterr(divide='ignore', invalid='ignore')
feature_vec = np.divide(feature_vec, retrieved_words)
return feature_vec
评论列表
文章目录