import gradio as gr
import torch
from datasets import load_dataset

dataset = load_dataset("zeroshot/twitter-financial-news-sentiment", )

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased")
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")

def sentiment_score(review):
  tokens = tokenizer.encode(review, return_tensors='pt')
  result = model(tokens)
  return int(torch.argmax(result.logits))

dataset['sentiment'] = dataset['text'].apply(lambda x: sentiment_score(x[:512]))

print(dataset[:10])

"""
categories = ('Car in good condition','Damaged Car')

def is_car(x) : return x[0].isupper()

def image_classifier(img):
    pred,index,probs = learn.predict(img) 
    return dict(zip(categories, map(float,probs)))

# image = gr.inputs.Image(shape=(192,192))
image = gr.components.Image(shape=(192,192))
label = gr.components.Label()
examples = ['./car.jpg','./crash.jpg','./carf.jpg']

intf = gr.Interface(fn= image_classifier,inputs=image,outputs=label,examples=examples)
intf.launch()"""