Last active
August 1, 2020 14:11
-
-
Save arunm8489/57068e56d15766bbf841be624c098660 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 tockenize(X_train,X_test): | |
""" | |
bow encoding | |
""" | |
word_list = [] | |
for sent in X_train: | |
for word in sent.split(): | |
word_list.append(word) | |
corpus = Counter(word_list) | |
# sorting on the basis of most common words | |
corpus_ = sorted(corpus,key=corpus.get,reverse=True) | |
# creating a dict | |
onehot_dict = {w:i+1 for i,w in enumerate(corpus_)} | |
train_vec = [] | |
test_vec = [] | |
for sent in X_train: | |
train_vec.append([onehot_dict[word] for word in sent.split() if word in onehot_dict.keys()]) | |
for sent in X_test: | |
test_vec.append([onehot_dict[word] for word in sent.split() if word in onehot_dict.keys()]) | |
return train_vec,test_vec,corpus_ | |
essay_train = X_train['essay'].values | |
essay_test = X_test['essay'].values | |
# encoding | |
essay_train_p,essay_test_p,corpus = tockenize(essay_train,essay_test) | |
print(len(corpus)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment