import streamlit as st
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
import matplotlib.pyplot as plt

# Load model and tokenizer
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

# Streamlit interface
st.title("Sentiment Analysis with Hugging Face Transformers")

prompt_text = "create a nlp transformer example using pytorch that will run hugging face, put a streamlit interface on it that will take the appropriate inputs and outputs include a matplotlib graph if necessary with the output. The code should be all together to make it easy to cut and paste."
st.write(f"**Prompt:** {prompt_text}")

st.write("Enter text to analyze its sentiment:")

input_text = st.text_area("Input Text", height=200)

if st.button("Analyze"):
    if input_text:
        # Perform sentiment analysis
        results = classifier(input_text)
        
        # Display results
        st.write("Results:")
        st.write(results)
        
        # Extract scores for plotting
        scores = results[0]['score']
        labels = results[0]['label']
        
        # Plotting
        fig, ax = plt.subplots()
        ax.bar(labels, scores, color='skyblue')
        ax.set_ylabel('Score')
        ax.set_title('Sentiment Analysis Result')
        
        st.pyplot(fig)
    else:
        st.write("Please enter text to analyze.")