import gradio as gr
import pandas as pd
import json

def analyze_financial_statements(income_statement, balance_sheet):
    """Analyze uploaded financial statements"""
    try:
        # Read the uploaded files
        income_df = pd.read_csv(income_statement.name)
        balance_df = pd.read_csv(balance_sheet.name)
        
        # Calculate key metrics
        metrics = calculate_metrics(income_df, balance_df)
        
        # Generate analysis
        analysis = generate_analysis(metrics)
        
        # Format output
        return format_results(metrics, analysis)
        
    except Exception as e:
        return f"Error analyzing files: {str(e)}"

def calculate_metrics(income_df, balance_df):
    """Calculate financial metrics"""
    # Clean numeric data
    income_df = income_df.replace({'\$': '', ' ': '', ',': '', '\(': '-', '\)': ''}, regex=True)
    balance_df = balance_df.replace({'\$': '', ' ': '', ',': '', '\(': '-', '\)': ''}, regex=True)
    
    # Convert to numeric
    numeric_cols = ['Revenue', 'Net Income', 'Gross Profit', 'Total Assets', 
                   'Total Liabilities', "Shareholder's Equity"]
    
    for col in numeric_cols:
        if col in income_df.columns:
            income_df[col] = pd.to_numeric(income_df[col], errors='coerce')
        if col in balance_df.columns:
            balance_df[col] = pd.to_numeric(balance_df[col], errors='coerce')
    
    # Calculate metrics
    metrics = {
        "Profitability": {
            "Gross Margin (%)": round((income_df['Gross Profit'].iloc[-1] / 
                                     income_df['Revenue'].iloc[-1] * 100), 2),
            "Net Margin (%)": round((income_df['Net Income'].iloc[-1] / 
                                   income_df['Revenue'].iloc[-1] * 100), 2)
        },
        "Growth": {
            "Revenue Growth (%)": round(((income_df['Revenue'].iloc[-1] / 
                                        income_df['Revenue'].iloc[0] - 1) * 100), 2),
            "Net Income Growth (%)": round(((income_df['Net Income'].iloc[-1] / 
                                           income_df['Net Income'].iloc[0] - 1) * 100), 2)
        },
        "Financial Position": {
            "Debt to Equity": round(balance_df['Total Liabilities'].iloc[-1] / 
                                  balance_df["Shareholder's Equity"].iloc[-1], 2),
            "Equity Ratio (%)": round((balance_df["Shareholder's Equity"].iloc[-1] / 
                                     balance_df['Total Assets'].iloc[-1] * 100), 2)
        }
    }
    
    return metrics

def generate_analysis(metrics):
    """Generate insights and recommendations"""
    analysis = {
        "Key Insights": [],
        "Recommendations": [],
        "Risk Factors": []
    }
    
    # Analyze profitability
    net_margin = metrics["Profitability"]["Net Margin (%)"]
    if net_margin < 5:
        analysis["Key Insights"].append(
            "Low profit margins indicating operational efficiency challenges")
        analysis["Recommendations"].append({
            "Priority": "High",
            "Area": "Profitability",
            "Action": "Implement cost optimization program",
            "Impact": "Improve net margins by 2-3%"
        })
    
    # Analyze growth
    revenue_growth = metrics["Growth"]["Revenue Growth (%)"]
    if revenue_growth < 5:
        analysis["Key Insights"].append(
            "Slow revenue growth suggesting need for market expansion")
        analysis["Recommendations"].append({
            "Priority": "High",
            "Area": "Growth",
            "Action": "Develop market expansion strategy",
            "Impact": "Accelerate revenue growth to 8-10%"
        })
    
    # Analyze financial position
    equity_ratio = metrics["Financial Position"]["Equity Ratio (%)"]
    if equity_ratio > 70:
        analysis["Key Insights"].append(
            "High equity ratio suggests potential for leveraged growth")
        analysis["Recommendations"].append({
            "Priority": "Medium",
            "Area": "Capital Structure",
            "Action": "Evaluate growth financing options",
            "Impact": "Optimize capital structure"
        })
    
    return analysis

def format_results(metrics, analysis):
    """Format analysis results"""
    output = "# Financial Analysis Report\n\n"
    
    # Add Metrics
    output += "## Financial Metrics\n\n"
    for category, values in metrics.items():
        output += f"### {category}\n"
        for metric, value in values.items():
            output += f"- {metric}: {value}\n"
        output += "\n"
    
    # Add Insights
    output += "## Key Insights\n\n"
    for insight in analysis["Key Insights"]:
        output += f"- {insight}\n"
    output += "\n"
    
    # Add Recommendations
    output += "## Recommendations\n\n"
    for rec in analysis["Recommendations"]:
        output += f"### {rec['Area']} ({rec['Priority']} Priority)\n"
        output += f"- Action: {rec['Action']}\n"
        output += f"- Expected Impact: {rec['Impact']}\n\n"
    
    return output

# Create Gradio interface
iface = gr.Interface(
    fn=analyze_financial_statements,
    inputs=[
        gr.File(label="Income Statement (CSV)"),
        gr.File(label="Balance Sheet (CSV)")
    ],
    outputs=gr.Markdown(),
    title="Financial Statement Analysis",
    description="Upload your Income Statement and Balance Sheet (CSV format) for analysis.",
    examples=[
        [
            "OFINTECH-Income Statement-template.csv",
            "OFINTECH Balance Sheet template.csv"
        ]
    ]
)

# Launch the interface
if __name__ == "__main__":
    iface.launch()