Update README.md
Browse files
README.md
CHANGED
@@ -2,4 +2,43 @@
|
|
2 |
library_name: transformers
|
3 |
language:
|
4 |
- id
|
5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
library_name: transformers
|
3 |
language:
|
4 |
- id
|
5 |
+
---
|
6 |
+
# Model description
|
7 |
+
This model is a fine-tuned model of [```intfloat/multilingual-e5-large```](https://huggingface.co/intfloat/multilingual-e5-large), trained with Indonesian police news data.
|
8 |
+
# How to use this model:
|
9 |
+
```python
|
10 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
11 |
+
|
12 |
+
tokenizer = AutoTokenizer.from_pretrained("faizaulia/e5-fine-tune-polri-news-emotion")
|
13 |
+
model = AutoModelForSequenceClassification.from_pretrained("faizaulia/e5-fine-tune-polri-news-emotion")
|
14 |
+
```
|
15 |
+
# Label description:
|
16 |
+
0: Angry, 1: Fear, 2: Sad, 3: Neutral, 4: Happy, 5: Love
|
17 |
+
# Input text example:
|
18 |
+
>LAMPUNG, KOMPAS.com - Komplotan perampok yang menyekap satu keluarga di Kabupaten Lampung Timur ditembak aparat kepolisian. Komplotan ini menggondol uang sebanyak Rp 50 juta milik korban. Kapolres Lampung Timur, AKBP M Rizal Muchtar mengatakan, tiga dari empat pelaku ini telah ditangkap pada Senin (27/2/2023) dini hari.
|
19 |
+
# Preprocesssing:
|
20 |
+
```python
|
21 |
+
nltk.download('stopwords')
|
22 |
+
nltk.download('wordnet')
|
23 |
+
|
24 |
+
stop_words = set(stopwords.words('indonesian'))
|
25 |
+
|
26 |
+
def remove_stopwords(text):
|
27 |
+
words = text.split()
|
28 |
+
words = [word for word in words if word not in stop_words]
|
29 |
+
return ' '.join(words)
|
30 |
+
|
31 |
+
def clean_texts(text):
|
32 |
+
text = re.sub('\n',' ',text) # Remove every '\n'
|
33 |
+
text = re.sub(' +', ' ', text) # Remove extra spaces
|
34 |
+
text = re.sub('[\u2013\u2014]', '-', text) # Sub — and – char to -
|
35 |
+
text = re.sub('(.{0,40})-', '', text) # Remove news website/location at the beginning
|
36 |
+
text = re.sub(r'[^a-zA-Z\s]', '', text) # Remove non alphanbet characters
|
37 |
+
return text
|
38 |
+
|
39 |
+
def preprocess_text(text):
|
40 |
+
text = text.lower()
|
41 |
+
text = clean_texts(text)
|
42 |
+
text = remove_stopwords(text)
|
43 |
+
return text
|
44 |
+
```
|