File size: 2,402 Bytes
0cb60c7
 
 
67f471c
 
0cb60c7
 
c9d2489
67f471c
c9d2489
0cb60c7
 
830b865
 
 
 
 
 
 
0cb60c7
 
 
 
 
830b865
0cb60c7
 
 
67f471c
0cb60c7
1fdc206
 
0cb60c7
9138597
0cb60c7
67f471c
0cb60c7
 
 
830b865
1fdc206
830b865
 
 
 
 
 
 
 
 
c9d2489
 
1fdc206
 
 
 
 
 
 
 
0cb60c7
 
830b865
0cb60c7
 
 
9138597
67f471c
0cb60c7
 
 
 
 
 
830b865
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import gradio as gr
import pandas as pd
import sweetviz as sv
import tempfile
import os

class DataAnalyzer:
    def __init__(self):
        self.temp_dir = tempfile.mkdtemp()
    
    def generate_sweetviz_report(self, df):
        report = sv.analyze(df)
        report_path = os.path.join(self.temp_dir, "sweetviz_report.html")
        report.show_html(report_path, open_browser=False)
        
        with open(report_path, 'r', encoding='utf-8') as f:
            html_content = f.read()
        os.remove(report_path)
        return html_content

def create_interface():
    analyzer = DataAnalyzer()
    
    with gr.Blocks(theme=gr.themes.Soft()) as demo:
        gr.Markdown("# Data Analysis Dashboard")
        
        with gr.Row():
            file_input = gr.File(label="Upload CSV")
            dataset_info = gr.JSON(label="Dataset Information")
        
        # Correct HTML component initialization
        report_html = gr.HTML(label="Analysis Report")
        
        def process_file(file):
            if file is None:
                return None, None
            
            try:
                df = pd.read_csv(file.name)
                
                # Basic dataset info
                info = {
                    "Rows": len(df),
                    "Columns": len(df.columns),
                    "Memory Usage (MB)": round(df.memory_usage(deep=True).sum() / 1024**2, 2),
                    "Missing Values": df.isnull().sum().sum(),
                    "Column Types": df.dtypes.astype(str).to_dict()
                }
                
                # Generate Sweetviz report
                report = analyzer.generate_sweetviz_report(df)
                
                # Add custom CSS to control height
                report_with_style = f"""
                <div style="height: 800px; overflow: auto;">
                    {report}
                </div>
                """
                
                return info, report_with_style
                
            except Exception as e:
                return {"error": str(e)}, f"Error generating report: {str(e)}"
        
        file_input.change(
            fn=process_file,
            inputs=[file_input],
            outputs=[dataset_info, report_html]
        )
    
    return demo

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