import gradio as gr
import yfinance as yf
import pandas as pd
import requests
import json
from datetime import datetime, timedelta
import plotly.graph_objects as go
import plotly.express as px

# Tool 1: Get Stock Price
def get_stock_price(symbol):
    """Get real-time stock price and basic info"""
    try:
        stock = yf.Ticker(symbol.upper())
        hist = stock.history(period="1d")
        info = stock.info
        
        if hist.empty:
            return f"Error: Could not find stock data for {symbol}"
        
        current_price = hist['Close'].iloc[-1]
        prev_close = info.get('previousClose', hist['Close'].iloc[-1])
        change = current_price - prev_close
        change_percent = (change / prev_close) * 100
        
        result = f"""
📈 **{symbol.upper()} Stock Price**
💰 Current Price: ${current_price:.2f}
📊 Change: ${change:.2f} ({change_percent:+.2f}%)
📅 Previous Close: ${prev_close:.2f}
🏢 Company: {info.get('longName', 'N/A')}
📈 Market Cap: ${info.get('marketCap', 0):,}
        """
        return result
    except Exception as e:
        return f"Error fetching stock price for {symbol}: {str(e)}"

# Tool 2: Get Stock Fundamentals
def get_stock_fundamentals(symbol):
    """Get fundamental analysis data"""
    try:
        stock = yf.Ticker(symbol.upper())
        info = stock.info
        
        # Key fundamental metrics
        pe_ratio = info.get('trailingPE', 'N/A')
        forward_pe = info.get('forwardPE', 'N/A')
        price_to_book = info.get('priceToBook', 'N/A')
        debt_to_equity = info.get('debtToEquity', 'N/A')
        roe = info.get('returnOnEquity', 'N/A')
        profit_margin = info.get('profitMargins', 'N/A')
        revenue_growth = info.get('revenueGrowth', 'N/A')
        
        # Format percentages
        if isinstance(roe, (int, float)):
            roe = f"{roe*100:.2f}%"
        if isinstance(profit_margin, (int, float)):
            profit_margin = f"{profit_margin*100:.2f}%"
        if isinstance(revenue_growth, (int, float)):
            revenue_growth = f"{revenue_growth*100:.2f}%"
        
        result = f"""
🔍 **{symbol.upper()} Fundamental Analysis**

📊 **Valuation Metrics:**
• P/E Ratio: {pe_ratio}
• Forward P/E: {forward_pe}
• Price-to-Book: {price_to_book}

💰 **Financial Health:**
• Debt-to-Equity: {debt_to_equity}
• Return on Equity: {roe}
• Profit Margin: {profit_margin}
• Revenue Growth: {revenue_growth}

🏢 **Company Info:**
• Sector: {info.get('sector', 'N/A')}
• Industry: {info.get('industry', 'N/A')}
• Employees: {info.get('fullTimeEmployees', 'N/A'):,}
• Market Cap: ${info.get('marketCap', 0):,}
        """
        return result
    except Exception as e:
        return f"Error fetching fundamentals for {symbol}: {str(e)}"

# Tool 3: Compare Stocks
def compare_stocks(symbol1, symbol2, symbol3=""):
    """Compare 2-3 stocks side by side"""
    try:
        symbols = [s.upper().strip() for s in [symbol1, symbol2, symbol3] if s.strip()]
        
        if len(symbols) < 2:
            return "Please provide at least 2 stock symbols"
        
        comparison_data = []
        
        for symbol in symbols:
            stock = yf.Ticker(symbol)
            info = stock.info
            hist = stock.history(period="1d")
            
            if not hist.empty:
                current_price = hist['Close'].iloc[-1]
                comparison_data.append({
                    'Symbol': symbol,
                    'Company': info.get('longName', 'N/A')[:30],
                    'Price': f"${current_price:.2f}",
                    'P/E Ratio': info.get('trailingPE', 'N/A'),
                    'Market Cap': f"${info.get('marketCap', 0)/1e9:.1f}B",
                    'Sector': info.get('sector', 'N/A'),
                    'ROE': f"{info.get('returnOnEquity', 0)*100:.1f}%" if info.get('returnOnEquity') else 'N/A'
                })
        
        if not comparison_data:
            return "Could not fetch data for any of the provided symbols"
        
        # Create comparison table
        result = "📊 **Stock Comparison**\n\n"
        result += "| Metric | " + " | ".join([data['Symbol'] for data in comparison_data]) + " |\n"
        result += "|" + "---|" * (len(comparison_data) + 1) + "\n"
        
        metrics = ['Company', 'Price', 'P/E Ratio', 'Market Cap', 'Sector', 'ROE']
        
        for metric in metrics:
            result += f"| **{metric}** | "
            result += " | ".join([str(data.get(metric, 'N/A')) for data in comparison_data])
            result += " |\n"
        
        return result
        
    except Exception as e:
        return f"Error comparing stocks: {str(e)}"

# Tool 4: AI-Powered Investment Analysis
def analyze_stock_ai(symbol, analysis_type="comprehensive"):
    """AI-powered investment insights"""
    try:
        stock = yf.Ticker(symbol.upper())
        info = stock.info
        hist = stock.history(period="3mo")  # 3 months of data
        
        if hist.empty:
            return f"Could not fetch data for {symbol}"
        
        # Calculate technical indicators
        current_price = hist['Close'].iloc[-1]
        price_change_3m = ((current_price - hist['Close'].iloc[0]) / hist['Close'].iloc[0]) * 100
        avg_volume = hist['Volume'].mean()
        volatility = hist['Close'].pct_change().std() * 100
        
        # Get fundamental data
        pe_ratio = info.get('trailingPE', 0)
        market_cap = info.get('marketCap', 0)
        sector = info.get('sector', 'Unknown')
        
        # AI Analysis Logic
        analysis = f"""
🤖 **AI Investment Analysis for {symbol.upper()}**

📈 **Technical Analysis:**
• 3-Month Performance: {price_change_3m:+.2f}%
• Current Price: ${current_price:.2f}
• Volatility: {volatility:.2f}%
• Average Volume: {avg_volume:,.0f}

🎯 **Investment Signals:**
"""
        
        # Simple AI-like decision logic
        signals = []
        
        if price_change_3m > 10:
            signals.append("🟢 Strong upward momentum")
        elif price_change_3m > 0:
            signals.append("🟡 Positive trend")
        else:
            signals.append("🔴 Declining trend")
            
        if pe_ratio and 10 < pe_ratio < 25:
            signals.append("🟢 Reasonable valuation")
        elif pe_ratio and pe_ratio > 30:
            signals.append("🟡 High valuation - growth expected")
        elif pe_ratio and pe_ratio < 10:
            signals.append("🟡 Low valuation - value opportunity")
            
        if volatility < 20:
            signals.append("🟢 Low volatility - stable")
        elif volatility > 40:
            signals.append("🔴 High volatility - risky")
            
        for signal in signals:
            analysis += f"\n• {signal}"
            
        # Risk Assessment
        risk_level = "Low"
        if volatility > 30 or (pe_ratio and pe_ratio > 40):
            risk_level = "High"
        elif volatility > 20 or (pe_ratio and pe_ratio > 25):
            risk_level = "Medium"
            
        analysis += f"""

⚠️ **Risk Assessment:** {risk_level}
🏢 **Sector:** {sector}
💼 **Market Cap:** ${market_cap/1e9:.1f}B

📝 **AI Recommendation:**
Based on technical and fundamental analysis, this stock shows {signals[0].split()[1]} characteristics. 
Consider your risk tolerance and portfolio diversification before making investment decisions.

⚠️ *This is AI-generated analysis for educational purposes only. Not financial advice.*
        """
        
        return analysis
        
    except Exception as e:
        return f"Error in AI analysis for {symbol}: {str(e)}"

# Create Gradio Interface
def create_interface():
    with gr.Blocks(title="Financial Analyst MCP Tools", theme=gr.themes.Soft()) as demo:
        gr.Markdown("# 🏦 Financial Analyst - MCP Tools")
        gr.Markdown("Professional stock analysis tools powered by real-time data and AI insights")
        
        with gr.Tabs():
            # Tool 1: Stock Price
            with gr.Tab("📈 Stock Price"):
                gr.Markdown("### Get Real-time Stock Price")
                with gr.Row():
                    price_input = gr.Textbox(label="Stock Symbol", placeholder="e.g., AAPL, TSLA, GOOGL")
                    price_btn = gr.Button("Get Price", variant="primary")
                price_output = gr.Markdown()
                price_btn.click(get_stock_price, inputs=price_input, outputs=price_output)
            
            # Tool 2: Fundamentals
            with gr.Tab("🔍 Fundamentals"):
                gr.Markdown("### Stock Fundamental Analysis")
                with gr.Row():
                    fund_input = gr.Textbox(label="Stock Symbol", placeholder="e.g., AAPL, MSFT")
                    fund_btn = gr.Button("Analyze Fundamentals", variant="primary")
                fund_output = gr.Markdown()
                fund_btn.click(get_stock_fundamentals, inputs=fund_input, outputs=fund_output)
            
            # Tool 3: Compare Stocks
            with gr.Tab("⚖️ Compare Stocks"):
                gr.Markdown("### Side-by-side Stock Comparison")
                with gr.Row():
                    with gr.Column():
                        comp_input1 = gr.Textbox(label="Stock 1", placeholder="e.g., AAPL")
                        comp_input2 = gr.Textbox(label="Stock 2", placeholder="e.g., MSFT")
                        comp_input3 = gr.Textbox(label="Stock 3 (Optional)", placeholder="e.g., GOOGL")
                    comp_btn = gr.Button("Compare Stocks", variant="primary")
                comp_output = gr.Markdown()
                comp_btn.click(compare_stocks, inputs=[comp_input1, comp_input2, comp_input3], outputs=comp_output)
            
            # Tool 4: AI Analysis
            with gr.Tab("🤖 AI Analysis"):
                gr.Markdown("### AI-Powered Investment Insights")
                with gr.Row():
                    ai_input = gr.Textbox(label="Stock Symbol", placeholder="e.g., NVDA, AMD")
                    ai_btn = gr.Button("AI Analysis", variant="primary")
                ai_output = gr.Markdown()
                ai_btn.click(analyze_stock_ai, inputs=ai_input, outputs=ai_output)
        
        gr.Markdown("---")
        gr.Markdown("*⚠️ Disclaimer: This tool provides educational information only. Not financial advice. Always consult with financial professionals before making investment decisions.*")
    
    return demo

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