import streamlit as st
import pandas as pd
from huggingface_hub import InferenceClient

# Page configuration
st.set_page_config(
    page_title="📊 LLM Data Analyzer",
    page_icon="📊",
    layout="wide",
    initial_sidebar_state="expanded"
)

st.title("📊 LLM Data Analyzer")
st.write("*Analyze data and chat with AI powered by Hugging Face Inference API*")

# Initialize HF Inference Client
@st.cache_resource
def get_hf_client():
    """Get Hugging Face Inference Client"""
    try:
        return InferenceClient()
    except Exception as e:
        st.error(f"Error initializing HF client: {e}")
        return None

client = get_hf_client()

if client is None:
    st.error("Failed to initialize Hugging Face client")
    st.stop()

# Create tabs
tab1, tab2, tab3 = st.tabs(["📤 Upload & Analyze", "💬 Chat", "📊 About"])

# ============================================================================
# TAB 1: Upload & Analyze
# ============================================================================
with tab1:
    st.header("📤 Upload and Analyze Data")
    
    uploaded_file = st.file_uploader(
        "Upload a CSV or Excel file",
        type=["csv", "xlsx", "xls"],
        help="Supported formats: CSV, Excel"
    )
    
    if uploaded_file is not None:
        st.success(f"✅ File uploaded: {uploaded_file.name}")
        
        try:
            if uploaded_file.name.endswith('.csv'):
                df = pd.read_csv(uploaded_file)
            else:
                df = pd.read_excel(uploaded_file)
            
            # Display data preview
            st.subheader("📋 Data Preview")
            st.dataframe(df.head(10), use_container_width=True)
            
            # Display statistics
            st.subheader("📊 Data Statistics")
            col1, col2, col3 = st.columns(3)
            
            with col1:
                st.metric("Rows", df.shape[0])
            with col2:
                st.metric("Columns", df.shape[1])
            with col3:
                st.metric("Memory", f"{df.memory_usage(deep=True).sum() / 1024:.2f} KB")
            
            # Detailed statistics
            st.write(df.describe().T)
            
            # Ask AI about the data
            st.subheader("❓ Ask AI About Your Data")
            question = st.text_input(
                "What would you like to know about this data?",
                placeholder="e.g., What is the average value in column X?"
            )
            
            if question:
                with st.spinner("🤔 AI is analyzing your data..."):
                    try:
                        data_summary = df.describe().to_string()
                        prompt = f"""You are a data analyst expert. You have the following data summary:

{data_summary}

Column names: {', '.join(df.columns.tolist())}

User's question: {question}

Please provide a clear, concise analysis based on the data summary."""
                        
                        # Use Hugging Face Inference API
                        response = client.text_generation(
                            prompt,
                            max_new_tokens=300,
                            temperature=0.7,
                        )
                        
                        st.success("✅ Analysis Complete")
                        st.write(response)
                    except Exception as e:
                        st.error(f"Error analyzing data: {e}")
        
        except Exception as e:
            st.error(f"Error reading file: {e}")

# ============================================================================
# TAB 2: Chat
# ============================================================================
with tab2:
    st.header("💬 Chat with AI Assistant")
    st.write("Have a conversation with an AI assistant powered by Hugging Face.")
    
    # Initialize session state for chat history
    if "messages" not in st.session_state:
        st.session_state.messages = []
    
    # Display chat history
    for message in st.session_state.messages:
        with st.chat_message(message["role"]):
            st.markdown(message["content"])
    
    # Chat input
    user_input = st.chat_input("Type your message here...")
    
    if user_input:
        # Add user message to history
        st.session_state.messages.append({"role": "user", "content": user_input})
        
        # Display user message
        with st.chat_message("user"):
            st.markdown(user_input)
        
        # Generate AI response
        with st.chat_message("assistant"):
            with st.spinner("⏳ Generating response..."):
                try:
                    prompt = f"User: {user_input}\n\nAssistant:"
                    
                    response = client.text_generation(
                        prompt,
                        max_new_tokens=300,
                        temperature=0.7,
                    )
                    
                    assistant_message = response.strip()
                    st.markdown(assistant_message)
                    
                    # Add assistant message to history
                    st.session_state.messages.append({
                        "role": "assistant",
                        "content": assistant_message
                    })
                except Exception as e:
                    st.error(f"Error generating response: {e}")

# ============================================================================
# TAB 3: About
# ============================================================================
with tab3:
    st.header("ℹ️ About This App")
    
    st.markdown("""
    ### 🎯 What is this?
    
    **LLM Data Analyzer** is an AI-powered tool for analyzing data and having conversations with an intelligent assistant.
    
    ### 🔧 Technology Stack
    
    - **Framework:** Streamlit
    - **AI Engine:** Hugging Face Inference API
    - **Hosting:** Hugging Face Spaces (Free Tier)
    - **Language:** Python
    
    ### ⚡ Features
    
    1. **Data Analysis**: Upload CSV/Excel and ask questions about your data
    2. **Chat**: Have conversations with an AI assistant
    3. **Statistics**: View data summaries and insights
    
    ### 📝 How to Use
    
    1. **Upload Data** - Start by uploading a CSV or Excel file
    2. **Preview** - Review your data and statistics
    3. **Ask Questions** - Get AI-powered analysis
    4. **Chat** - Have follow-up conversations
    
    ### 🌐 Powered By
    
    - [Hugging Face](https://huggingface.co/) - AI models and hosting
    - [Streamlit](https://streamlit.io/) - Web framework
    
    ### 📖 Quick Tips
    
    - Keep questions focused and specific for best results
    - Responses may take a few seconds
    - Data is processed locally, not stored on server
    
    ### 🔗 Links
    
    - [GitHub Repository](https://github.com/Arif-Badhon/LLM-Data-Analyzer)
    - [Hugging Face Hub](https://huggingface.co/)
    
    ---
    
    **Version:** 1.0 | **Last Updated:** Dec 2025
    """)