This is the first classification of sentiment analysis for (redacted) task

### How to use this code

```python
import torch
from transformers import BertForSequenceClassification, BertTokenizer, BertConfig

tokenizer = BertTokenizer.from_pretrained("nfhakim/sentiment-analysis-c1")
config = BertConfig.from_pretrained("nfhakim/sentiment-analysis-c1")
model = BertForSequenceClassification.from_pretrained("nfhakim/sentiment-analysis-c1", config=config)

text = 'INSERT TEXT - MINIMUM 3 SENTENCES FOR BETTER PREDICITONS'
subwords = tokenizer.encode(text)
subwords = torch.LongTensor(subwords).view(1, -1).to(model.device)

i2w = {0: 'positive',  1: 'non-positive'}

logits = model(subwords)[0]
label = torch.topk(logits, k=1, dim=-1)[1].squeeze().item()

print(f'Text: {text} | Label : {i2w[label]} ({torch.nn.functional.softmax(logits, dim=-1).squeeze()[label] * 100:.3f}%)')
```