import streamlit as st
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np  
# Load sentiment analysis model
@st.cache_resource
def load_model():
    model_name = "distilbert-base-uncased-finetuned-sst-2-english"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    return pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)

classifier = load_model()

# Streamlit UI
st.title("Sentiment Analysis App")
st.header("Analyze Text Sentiment")

user_input = st.text_area("Enter text to analyze:", "I love studying NLP! It's awesome.")

if st.button("Analyze"):
    if user_input:
        result = classifier(user_input)
        sentiment = result[0]['label']
        confidence = result[0]['score']
        
        st.subheader("Result:")
        if sentiment == 'POSITIVE':
            st.success(f"Positive sentiment (confidence: {confidence:.2%})")
        else:
            st.error(f"Negative sentiment (confidence: {confidence:.2%})")
    else:
        st.warning("Please enter some text to analyze!")