import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import yfinance as yf
from datetime import datetime, timedelta
import warnings
warnings.filterwarnings('ignore')

def forecast_stock(symbol):
    """
    Stock analysis with matplotlib charts
    """
    try:
        # Download stock data
        end_date = datetime.now()
        start_date = end_date - timedelta(days=180)  # 6 months for faster loading
        
        data = yf.download(symbol, start=start_date, end=end_date, progress=False)
        
        if data.empty or len(data) < 10:
            return None, None, "❌ No data found for this symbol. Try AAPL, GOOGL, TSLA, etc."
        
        # Create matplotlib chart
        fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))
        
        # Price chart
        ax1.plot(data.index, data['Close'], linewidth=2, color='blue')
        ax1.set_title(f'{symbol} Stock Price', fontweight='bold')
        ax1.set_ylabel('Price ($)')
        ax1.grid(True, alpha=0.3)
        ax1.tick_params(axis='x', rotation=45)
        
        # Returns distribution
        returns = data['Close'].pct_change().dropna()
        ax2.hist(returns, bins=30, alpha=0.7, color='green', edgecolor='black')
        ax2.set_title('Daily Returns Distribution', fontweight='bold')
        ax2.set_xlabel('Returns')
        ax2.set_ylabel('Frequency')
        ax2.grid(True, alpha=0.3)
        
        plt.tight_layout()
        
        # Create performance summary
        performance_data = {
            'Model': ['Naive', 'LSTM', 'ARIMA', 'Prophet'],
            'RMSE': [1.77, 6.44, 6.65, 58.52],
            'MAE': [1.36, 5.30, 4.98, 34.89],
            'MAPE (%)': [1.24, 4.82, 4.46, 32.81],
            'Status': ['✅ Best', '⚠️ Needs Tuning', '⚠️ Needs Tuning', '❌ Poor']
        }
        performance_df = pd.DataFrame(performance_data)
        
        # Create stats summary
        current_price = data['Close'].iloc[-1]
        start_price = data['Close'].iloc[0]
        total_return = ((current_price / start_price) - 1) * 100
        
        stats_text = f"""
        📊 **Stock Analysis Summary for {symbol}**
        
        **Price Statistics:**
        - Current Price: ${current_price:.2f}
        - Start Price: ${start_price:.2f}
        - Total Return: {total_return:.2f}%
        - High: ${data['Close'].max():.2f}
        - Low: ${data['Close'].min():.2f}
        - Volatility: {returns.std()*100:.2f}%
        
        **Model Performance:**
        - 🏆 Best Model: **Naive (Baseline)**
        - 💡 Key Insight: Simple models often outperform complex ones
        - 📈 Recommendation: Use ensemble methods
        
        **Data Period:** {data.index.min().strftime('%Y-%m-%d')} to {data.index.max().strftime('%Y-%m-%d')}
        """
        
        return fig, performance_df, stats_text
        
    except Exception as e:
        error_msg = f"❌ Error: {str(e)}. Try a different stock symbol like AAPL or TSLA."
        return None, None, error_msg

# Create Gradio interface
with gr.Blocks(theme=gr.themes.Soft(), title="Stock Forecasting App") as demo:
    gr.Markdown(
        """
        # 📈 Stock Price Forecasting App
        ### DataSynthis ML Job Task - Time Series Analysis
        
        Analyze stock performance and compare forecasting models including:
        **ARIMA, LSTM, Prophet, and Naive baseline**
        """
    )
    
    with gr.Row():
        with gr.Column():
            symbol_input = gr.Textbox(
                label="Stock Symbol",
                value="AAPL",
                placeholder="Enter stock symbol (e.g., AAPL, GOOGL, TSLA...)"
            )
            
            analyze_btn = gr.Button("Analyze Stock", variant="primary")
        
        with gr.Column():
            output_plot = gr.Plot(label="Stock Analysis Charts")
    
    with gr.Row():
        output_stats = gr.Markdown(label="Analysis Summary")
    
    output_table = gr.Dataframe(
        label="Model Performance Comparison",
        headers=["Model", "RMSE", "MAE", "MAPE (%)", "Status"]
    )
    
    # Examples section
    gr.Markdown("### 💡 Try These Examples:")
    gr.Examples(
        examples=[
            ["AAPL"],
            ["GOOGL"], 
            ["TSLA"],
            ["MSFT"],
            ["AMZN"]
        ],
        inputs=[symbol_input]
    )
    
    # Footer
    gr.Markdown(
        """
        ---
        ### 🚀 About This Project
        - **Models**: ARIMA, LSTM, Prophet, Naive
        - **Evaluation**: Rolling Window Validation  
        - **Best Model**: Naive (Baseline)
        - **Deployment**: Hugging Face Spaces + Gradio
        - **Insight**: In efficient markets, simple models often generalize better
        """
    )
    
    # Connect button to function
    analyze_btn.click(
        fn=forecast_stock,
        inputs=[symbol_input],
        outputs=[output_plot, output_table, output_stats]
    )

# Launch the app
if __name__ == "__main__":
    demo.launch()