src/streamlit_app.py

import streamlit as st
import requests
import json

st.set_page_config(
    page_title="Sentiment Analysis App",
    page_icon="😊",
    layout="centered"
)

st.title("Sentiment Analysis App")
st.write("Enter text to analyze its sentiment using Hugging Face's API")

# API credentials input
api_key = st.text_input("Enter your Hugging Face API key:", type="password", help="Your Hugging Face API token")

# Model selection
model_options = {
    "DistilBERT (SST-2)": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
    "Twitter-roBERTa-base": "cardiffnlp/twitter-roberta-base-sentiment",
    "BERT-base-multilingual": "nlptown/bert-base-multilingual-uncased-sentiment"
}
selected_model = st.selectbox("Select a sentiment analysis model:", options=list(model_options.keys()))

# Text input area
text_input = st.text_area("Enter text to analyze:", height=150)

# Function to call the Hugging Face API
def analyze_sentiment(text, model, api_key):
    API_URL = f"https://api-inference.huggingface.co/models/{model}"
    headers = {
        "Authorization": f"Bearer {api_key}"
    }
    
    payload = {
        "inputs": text,
    }
    
    try:
        response = requests.post(API_URL, headers=headers, json=payload)
        return response.json()
    except Exception as e:
        return {"error": str(e)}

# Submit button
if st.button("Analyze Sentiment"):
    if not api_key:
        st.error("Please enter your Hugging Face API key")
    elif not text_input:
        st.error("Please enter some text to analyze")
    else:
        with st.spinner("Analyzing sentiment..."):
            selected_model_path = model_options[selected_model]
            result = analyze_sentiment(text_input, selected_model_path, api_key)
            
            # Process and display results
            try:
                if "error" in result:
                    st.error(f"Error: {result['error']}")
                elif isinstance(result, list) and len(result) > 0:
                    # Process the results
                    if isinstance(result[0], list):
                        items = result[0]
                    else:
                        items = result
                    
                    # Find the highest scoring sentiment
                    highest_item = max(items, key=lambda x: x['score'])
                    score = highest_item['score']
                    label = highest_item['label'].lower()
                    
                    # Display emoji based on sentiment and score
                    st.subheader("Sentiment:")
                    col1, col2 = st.columns([1, 3])
                    
                    # Select emoji based on sentiment label and score
                    if 'positive' in label or 'pos' in label or '5' in label or '4' in label:
                        if score > 0.9:
                            emoji = "😍"
                        elif score > 0.7:
                            emoji = "😁"
                        else:
                            emoji = "🙂"
                        sentiment_text = f"Positive ({score:.2f})"
                    elif 'negative' in label or 'neg' in label or '1' in label or '2' in label:
                        if score > 0.9:
                            emoji = "😡"
                        elif score > 0.7:
                            emoji = "😠"
                        else:
                            emoji = "☹"
                        sentiment_text = f"Negative ({score:.2f})"
                    else:  # neutral or '3' in label
                        emoji = "😐"
                        sentiment_text = f"Neutral ({score:.2f})"
                    
                    with col1:
                        st.markdown(f"<h1 style='font-size:4rem; text-align:center;'>{emoji}</h1>", unsafe_allow_html=True)
                    with col2:
                        st.markdown(f"<h2>{sentiment_text}</h2>", unsafe_allow_html=True)
                        
                        # Add confidence meter
                        st.progress(score)
                else:
                    st.warning("Unexpected response format. Please check your API key and try again.")
                    st.json(result)
            except Exception as e:
                st.error(f"Error processing results: {str(e)}")
                st.json(result)

# Footer
st.markdown("---")
st.markdown("Built with Streamlit and Hugging Face API")