import gradio as gr
# from transformers import pipeline
from transformers import AutoTokenizer
from transformers import AutoModelForSequenceClassification
from scipy.special import softmax

MODEL = f"cardiffnlp/twitter-roberta-base-sentiment"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModelForSequenceClassification.from_pretrained(MODEL)

def polarity_scores_roberta(example):
    encoded_text = tokenizer(example, return_tensors='pt')
    output = model(**encoded_text)
    scores = output[0][0].detach().numpy()
    scores = softmax(scores)
    scores_dict = {
        'roberta_neg' : scores[0],
        'roberta_neu' : scores[1],
        'roberta_pos' : scores[2]
    }
    x=max(scores[0],scores[1],scores[2])
    if x==scores[0]:
      return 'Negative'
    elif x==scores[1]:
      return 'Neutral'
    else:
      return 'Positive'


def greet(name):
    return "Hello " + name + "!!"

iface = gr.Interface(fn=polarity_scores_roberta, inputs="text", outputs="text")
iface.launch()