ahmedrachid
commited on
Commit
•
11c83cd
1
Parent(s):
1c151cf
Update README.md
Browse files
README.md
CHANGED
@@ -39,24 +39,24 @@ The evaluation metrics used are: Precision, Recall and F1-score. The following i
|
|
39 |
### How to use
|
40 |
The model can be used thanks to Transformers pipeline for sentiment analysis.
|
41 |
```python
|
42 |
-
|
43 |
-
|
44 |
|
45 |
-
|
46 |
-
|
47 |
|
48 |
-
|
49 |
|
50 |
-
|
51 |
"Bids or offers include at least 1,000 shares and the value of the shares must correspond to at least EUR 4,000.",
|
52 |
"Raute reported a loss per share of EUR 0.86 for the first half of 2009 , against EPS of EUR 0.74 in the corresponding period of 2008.",
|
53 |
]
|
54 |
-
|
55 |
-
|
56 |
|
57 |
[{'label': 'positive', 'score': 0.9998133778572083},
|
58 |
{'label': 'neutral', 'score': 0.9997822642326355},
|
59 |
{'label': 'negative', 'score': 0.9877365231513977}]
|
60 |
```
|
61 |
|
62 |
-
>Created by [Ahmed Rachid Hazourli](https://www.linkedin.com/in/ahmed-rachid/)
|
|
|
39 |
### How to use
|
40 |
The model can be used thanks to Transformers pipeline for sentiment analysis.
|
41 |
```python
|
42 |
+
from transformers import BertTokenizer, BertForSequenceClassification
|
43 |
+
from transformers import pipeline
|
44 |
|
45 |
+
model = BertForSequenceClassification.from_pretrained("ahmedrachid/FinancialBERT-Sentiment-Analysis",num_labels=3)
|
46 |
+
tokenizer = BertTokenizer.from_pretrained("ahmedrachid/FinancialBERT-Sentiment-Analysis")
|
47 |
|
48 |
+
nlp = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
|
49 |
|
50 |
+
sentences = ["Operating profit rose to EUR 13.1 mn from EUR 8.7 mn in the corresponding period in 2007 representing 7.7 % of net sales.",
|
51 |
"Bids or offers include at least 1,000 shares and the value of the shares must correspond to at least EUR 4,000.",
|
52 |
"Raute reported a loss per share of EUR 0.86 for the first half of 2009 , against EPS of EUR 0.74 in the corresponding period of 2008.",
|
53 |
]
|
54 |
+
results = nlp(sentences)
|
55 |
+
print(results)
|
56 |
|
57 |
[{'label': 'positive', 'score': 0.9998133778572083},
|
58 |
{'label': 'neutral', 'score': 0.9997822642326355},
|
59 |
{'label': 'negative', 'score': 0.9877365231513977}]
|
60 |
```
|
61 |
|
62 |
+
> Created by [Ahmed Rachid Hazourli](https://www.linkedin.com/in/ahmed-rachid/)
|