Spaces:
Running
Running
Delete preprocessing.py
Browse files- preprocessing.py +0 -20
preprocessing.py
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
import re
|
| 2 |
-
from arabert.preprocess import ArabertPreprocessor
|
| 3 |
-
model_name = "aubmindlab/bert-base-arabertv02-twitter"
|
| 4 |
-
arabic_prep = ArabertPreprocessor(model_name=model_name)
|
| 5 |
-
|
| 6 |
-
def clean_obfuscation(text):
|
| 7 |
-
text = str(text)
|
| 8 |
-
text = re.sub(r'https?://\S+|www\.\S+|@\S+|#', '', text)
|
| 9 |
-
text = re.sub(r'(?<=[أ-ي])[^\sأ-ي](?=[أ-ي])', '', text)
|
| 10 |
-
text = re.sub(r'(?<=[أ-ي])\s(?=[أ-ي]\s|[أ-ي]$)', '', text)
|
| 11 |
-
text = re.sub(r'ـ+', '', text)
|
| 12 |
-
text = re.sub(r'(.)\1{2,}', r'\1\1', text)
|
| 13 |
-
text = re.sub(r'[^\w\s\.]', ' ', text)
|
| 14 |
-
text = re.sub(r'\s+', ' ', text)
|
| 15 |
-
return text.strip()
|
| 16 |
-
|
| 17 |
-
def full_preprocess(text):
|
| 18 |
-
text_no_trickery = clean_obfuscation(text)
|
| 19 |
-
final_text = arabic_prep.preprocess(text_no_trickery)
|
| 20 |
-
return final_text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|