import gradio as gr
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
import numpy as np
from scipy.special import softmax

# Setup
model_path = f"GhylB/Sentiment_Analysis_DistilBERT"

tokenizer = AutoTokenizer.from_pretrained(model_path)
config = AutoConfig.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)

# Functions

# Preprocess text (username and link placeholders)


def preprocess(text):
    new_text = []
    for t in text.split(" "):
        t = '@user' if t.startswith('@') and len(t) > 1 else t
        t = 'http' if t.startswith('http') else t
        new_text.append(t)
    return " ".join(new_text)


def sentiment_analysis(text):
    text = preprocess(text)

    # PyTorch-based models
    encoded_input = tokenizer(text, return_tensors='pt')
    output = model(**encoded_input)
    scores_ = output[0][0].detach().numpy()
    scores_ = softmax(scores_)

    # Format output dict of scores
    labels = ['Negative', 'Neutral', 'Positive']
    scores = {l: float(s) for (l, s) in zip(labels, scores_)}

    return scores


demo = gr.Interface(
    fn=sentiment_analysis,
    inputs=gr.Textbox(placeholder="Copy and paste/Write a tweet here..."),
    outputs="text",
    interpretation="default",
    examples=[["What's up with the vaccine"],
              ["Covid cases are increasing fast!"],
              ["Covid has been invented by Mavis"],
              ["I'm going to party this weekend"],
              ["Covid is hoax"]],
    title="Tutorial : Sentiment Analysis App",
    description="This Application assesses if a twitter post relating to vaccinations is positive, neutral, or negative.", )

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0", server_port=7860) # 8080