# Example script to run the demo without AI model dependencies for local testing
# Saves this as demo.py

import gradio as gr
from app import read_file, analyze_data, generate_visualizations, display_analysis

def simple_process_file(file):
    """Simplified version without AI models for testing"""
    # Read the file
    df = read_file(file)
    
    if isinstance(df, str):  # If error message
        return df, None, None, None
    
    # Analyze data
    analysis = analyze_data(df)
    
    # Generate visualizations
    visualizations = generate_visualizations(df)
    
    # Placeholder for AI recommendations
    cleaning_recommendations = """
    ## Data Cleaning Recommendations
    
    * Handle missing values by either removing rows or imputing with mean/median/mode
    * Remove duplicate rows if present
    * Convert date-like string columns to proper datetime format
    * Standardize text data by removing extra spaces and converting to lowercase
    * Check for and handle outliers in numerical columns
    
    Note: This is a demo recommendation (AI model not connected in demo mode)
    """
    
    # Placeholder for AI insights
    analysis_insights = """
    ## Data Analysis Insights
    
    1. Examine the distribution of each numeric column
    2. Analyze correlations between numeric features
    3. Look for patterns in categorical data
    4. Consider creating visualizations like histograms and scatter plots
    5. Explore relationships between different variables
    
    Note: This is a demo insight (AI model not connected in demo mode)
    """
    
    return analysis, visualizations, cleaning_recommendations, analysis_insights

def demo_ui(file):
    """Demo mode UI function"""
    if file is None:
        return "Please upload a file to begin analysis.", None, None, None
    
    # Process the file
    analysis, visualizations, cleaning_recommendations, analysis_insights = simple_process_file(file)
    
    # Format analysis for display
    analysis_html = display_analysis(analysis)
    
    # Prepare visualizations for display
    viz_html = ""
    if visualizations and not isinstance(visualizations, str):
        for viz_name, fig in visualizations.items():
            # Convert plotly figure to HTML
            viz_html += f'<div style="margin-bottom: 30px;">{fig.to_html(full_html=False, include_plotlyjs="cdn")}</div>'
    
    # Combine analysis and visualizations
    result_html = f"""
    <div style="display: flex; flex-direction: column;">
        <div>{analysis_html}</div>
        <h2>Data Visualizations</h2>
        <div>{viz_html}</div>
    </div>
    """
    
    return result_html, visualizations, cleaning_recommendations, analysis_insights

# Create Gradio interface for demo mode
with gr.Blocks(title="Data Visualization & Cleaning AI (Demo Mode)") as demo:
    gr.Markdown("# Data Visualization & Cleaning AI")
    gr.Markdown("**DEMO MODE** - Upload your data file (CSV, Excel, JSON, or TXT) and get automatic analysis and visualizations.")
    
    with gr.Row():
        file_input = gr.File(label="Upload Data File")
    
    with gr.Tabs():
        with gr.TabItem("Data Analysis"):
            with gr.Row():
                analyze_button = gr.Button("Analyze Data")
            
            with gr.Tabs():
                with gr.TabItem("Analysis & Visualizations"):
                    output = gr.HTML(label="Results")
                with gr.TabItem("AI Cleaning Recommendations"):
                    cleaning_recommendations_output = gr.Markdown(label="AI Recommendations")
                with gr.TabItem("AI Analysis Insights"):
                    analysis_insights_output = gr.Markdown(label="Analysis Insights")
                with gr.TabItem("Raw Visualization Objects"):
                    viz_output = gr.JSON(label="Visualization Objects")
    
    # Connect the button to function
    analyze_button.click(
        fn=demo_ui, 
        inputs=[file_input], 
        outputs=[output, viz_output, cleaning_recommendations_output, analysis_insights_output]
    )

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