app.py

import gradio as gr
import pandas as pd
import sweetviz as sv
import tempfile
import os
import category_encoders as ce
import umap
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from autoviz.AutoViz_Class import AutoViz_Class
import shutil
import warnings
warnings.filterwarnings('ignore')

class DataAnalyzer:
    def __init__(self):
        self.temp_dir = tempfile.mkdtemp()
        self.df = None
        self.AV = AutoViz_Class()
        
    def generate_sweetviz_report(self, df):
        if df is None:
            return "Please upload a dataset first"
        
        self.df = df
        report = sv.analyze(df)
        report_path = os.path.join(self.temp_dir, "report.html")
        report.show_html(report_path, open_browser=False)
        
        with open(report_path, 'r', encoding='utf-8') as f:
            html_content = f.read()
        
        html_with_table = f"""
        <table width="100%" style="border-collapse: collapse;">
            <tr>
                <td style="padding: 20px; border: 1px solid #ddd;">
                    <div style="height: 800px; overflow: auto;">
                        {html_content}
                    </div>
                </td>
            </tr>
        </table>
        """
        
        os.remove(report_path)
        return html_with_table

    def generate_autoviz_report(self, df):
        if df is None:
            return "Please upload a dataset first"
            
        viz_temp_dir = os.path.join(self.temp_dir, "autoviz_output")
        if os.path.exists(viz_temp_dir):
            shutil.rmtree(viz_temp_dir)
        os.makedirs(viz_temp_dir)

        try:
            # Data preprocessing
            df = df.copy()
            
            # Handle datetime columns
            for col in df.columns:
                try:
                    df[col] = pd.to_datetime(df[col], errors='ignore')
                except:
                    pass
                    
            datetime_columns = df.select_dtypes(include=['datetime64']).columns
            for col in datetime_columns:
                df[f'{col}_year'] = df[col].dt.year
                df[f'{col}_month'] = df[col].dt.month
                df = df.drop(columns=[col])
            
            # Try to convert string columns to numeric where possible
            for col in df.select_dtypes(include=['object']).columns:
                try:
                    df[col] = pd.to_numeric(df[col], errors='ignore')
                except:
                    pass
            
            # Convert remaining string columns to categorical if cardinality is low
            object_columns = df.select_dtypes(include=['object']).columns
            for col in object_columns:
                if df[col].nunique() < 50:
                    df[col] = df[col].astype('category')
            
            # Sample data if needed
            if len(df) > 5000:
                df = df.sample(n=5000, random_state=42)
            
            # Print data info for debugging
            print("\nDataset Info:")
            print(df.info())
            print("\nColumn Types:")
            print(df.dtypes)
            
            plt.close('all')
            
            # Run AutoViz
            dfte = self.AV.AutoViz(
                filename='',
                sep=',',
                depVar='',
                dfte=df,
                header=0,
                verbose=1,
                lowess=False,
                chart_format='svg',
                max_rows_analyzed=5000,
                max_cols_analyzed=30,
                save_plot_dir=viz_temp_dir
            )

            # Collect visualizations
            html_parts = []
            if os.path.exists(viz_temp_dir):
                for file in sorted(os.listdir(viz_temp_dir)):
                    if file.endswith('.html') or file.endswith('.svg'):
                        file_path = os.path.join(viz_temp_dir, file)
                        try:
                            with open(file_path, 'r', encoding='utf-8') as f:
                                content = f.read()
                                if content.strip():
                                    html_parts.append(content)
                        except Exception as e:
                            print(f"Error reading file {file}: {str(e)}")

            if not html_parts:
                return f"""
                <div style="padding: 20px; border: 1px solid #ddd; border-radius: 5px;">
                    <h3>Data Summary</h3>
                    <p>Total Rows: {len(df)}</p>
                    <p>Total Columns: {len(df.columns)}</p>
                    <p>Column Types:</p>
                    <pre>{df.dtypes.to_string()}</pre>
                    <hr>
                    <h3>No visualizations were generated</h3>
                    <p>This might be due to:</p>
                    <ul>
                        <li>All columns being categorical with high cardinality</li>
                        <li>No numeric columns for analysis</li>
                        <li>Data format not suitable for visualization</li>
                    </ul>
                </div>
                """

            combined_html = f"""
            <div style="padding: 20px; border: 1px solid #ddd; border-radius: 5px;">
                <h2 style="text-align: center;">AutoViz Analysis Report</h2>
                <div style="margin: 20px;">
                    <h3>Dataset Summary</h3>
                    <p>Rows analyzed: {len(df)}</p>
                    <p>Columns: {len(df.columns)}</p>
                    <p>Column Types:</p>
                    <pre>{df.dtypes.to_string()}</pre>
                </div>
                <hr>
                {'<hr>'.join(html_parts)}
            </div>
            """
            
            return combined_html

        except Exception as e:
            import traceback
            error_message = f"""
            <div style="padding: 20px; border: 1px solid red; border-radius: 5px;">
                <h3>Error in AutoViz Analysis</h3>
                <p>Error details: {str(e)}</p>
                <p>Stack trace:</p>
                <pre>{traceback.format_exc()}</pre>
                <p>Dataset Info:</p>
                <pre>
                Rows: {len(df)}
                Columns: {len(df.columns)}
                Types:\n{df.dtypes.to_string()}
                </pre>
            </div>
            """
            return error_message
        finally:
            if os.path.exists(viz_temp_dir):
                shutil.rmtree(viz_temp_dir)

def create_interface():
    analyzer = DataAnalyzer()
    
    with gr.Blocks(theme=gr.themes.Soft()) as demo:
        gr.Markdown("# Data Analysis Dashboard")
        
        # Store the dataframe in a state variable
        current_df = gr.State(None)
        
        with gr.Tabs():
            # First Tab: Data Upload & Preview
            with gr.TabItem("Data Upload & Preview"):
                with gr.Row():
                    file_input = gr.File(label="Upload CSV")
                data_preview = gr.Dataframe(label="Data Preview", interactive=False)
                
                def load_data(file):
                    if file is None:
                        return None, None
                    try:
                        df = pd.read_csv(file.name)
                        return df.head(), df
                    except Exception as e:
                        return None, None
                
                file_input.change(
                    fn=load_data,
                    inputs=[file_input],
                    outputs=[data_preview, current_df]
                )
            
            # Second Tab: Sweetviz Analysis
            with gr.TabItem("Sweetviz Analysis"):
                with gr.Row():
                    sweetviz_button = gr.Button("Generate Sweetviz Report")
                sweetviz_output = gr.HTML(label="Sweetviz Report")
                
                def generate_sweetviz(df):
                    if df is None:
                        return "Please upload a dataset first"
                    return analyzer.generate_sweetviz_report(df)
                
                sweetviz_button.click(
                    fn=generate_sweetviz,
                    inputs=[current_df],
                    outputs=[sweetviz_output]
                )
            
            # Third Tab: AutoViz Analysis
            with gr.TabItem("AutoViz Analysis"):
                with gr.Row():
                    autoviz_button = gr.Button("Generate AutoViz Report")
                autoviz_output = gr.HTML(label="AutoViz Report")
                
                def generate_autoviz(df):
                    if df is None:
                        return "Please upload a dataset first"
                    return analyzer.generate_autoviz_report(df)
                
                autoviz_button.click(
                    fn=generate_autoviz,
                    inputs=[current_df],
                    outputs=[autoviz_output]
                )

    return demo

if __name__ == "__main__":
    demo = create_interface()
    demo.launch(show_error=True)