Teery commited on
Commit
b02dea6
1 Parent(s): 5e65e3b

Update dopset.py

Browse files
Files changed (1) hide show
  1. dopset.py +4 -4
dopset.py CHANGED
@@ -1,13 +1,13 @@
1
  import string
2
  import torch
3
  import numpy as np
4
- from nltk.corpus import stopwords
5
- stop_words = set(stopwords.words('english'))
6
  import torch.nn as nn
7
  import pickle
8
  from transformers import BertTokenizer, BertModel, DistilBertTokenizer, DistilBertModel
9
  from sklearn.linear_model import LogisticRegression
10
- import nltk
11
 
12
 
13
 
@@ -48,7 +48,7 @@ class LSTMClassifier(nn.Module):
48
  def data_preprocessing(text: str) -> str:
49
  text = text.lower()
50
  text = ''.join([c for c in text if c not in string.punctuation])# Remove punctuation
51
- text = [word for word in text.split() if word not in stop_words]
52
  text = ' '.join(text)
53
  return text
54
 
 
1
  import string
2
  import torch
3
  import numpy as np
4
+ # from nltk.corpus import stopwords
5
+ # stop_words = set(stopwords.words('english'))
6
  import torch.nn as nn
7
  import pickle
8
  from transformers import BertTokenizer, BertModel, DistilBertTokenizer, DistilBertModel
9
  from sklearn.linear_model import LogisticRegression
10
+ # import nltk
11
 
12
 
13
 
 
48
  def data_preprocessing(text: str) -> str:
49
  text = text.lower()
50
  text = ''.join([c for c in text if c not in string.punctuation])# Remove punctuation
51
+ # text = [word for word in text.split() if word not in stop_words]
52
  text = ' '.join(text)
53
  return text
54