Created
December 28, 2018 06:46
-
-
Save Jirayut558/b8b6e29262270a3083a68f5bff297c6b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def word_index(listword): | |
dataset = [] | |
for sentence in listword: | |
tmp = [] | |
for w in sentence: | |
tmp.append(word2idx(w)) | |
dataset.append(tmp) | |
return np.array(dataset) | |
def word2idx(word): | |
index = 0 | |
try: | |
index = wv_model.wv.vocab[word].index | |
except: | |
try: | |
sim = similar_word(word) | |
index = wv_model.wv.vocab[sim].index | |
except: | |
index = wv_model.wv.vocab["<NONE>"].index | |
return index | |
def similar_word(word): | |
sim_word = difflib.get_close_matches(word, word_list) | |
try: | |
return sim_word[0] | |
except: | |
return "<NONE>" | |
X1 = word_index(X1) | |
X2 = word_index(X2) | |
Y = word_index(Y) | |
Y = to_categorical(Y, num_classes=max_word+1) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment