Spaces:
Running
Running
File size: 4,474 Bytes
0cb60c7 |
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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 |
import gradio as gr
import pandas as pd
from ydata_profiling import ProfileReport
import sweetviz as sv
from dataprep.eda import create_report
import io
class DataAnalyzer:
def __init__(self):
self.current_df = None
def generate_profile_report(self, df, minimal=False):
profile = ProfileReport(
df,
minimal=minimal,
title="Pandas Profiling Report",
explorative=True,
dark_mode=True
)
# Get HTML directly as string
return profile.to_html()
def generate_sweetviz_report(self, df):
report = sv.analyze(df)
# Use StringIO to capture the HTML output
html_io = io.StringIO()
report.show_html(filepath=html_io, open_browser=False)
return html_io.getvalue()
def generate_dataprep_report(self, df):
report = create_report(df)
# Get HTML directly as string
return report.html()
def get_dataset_info(self, df):
return {
"Rows": len(df),
"Columns": len(df.columns),
"Memory Usage (MB)": df.memory_usage(deep=True).sum() / 1024**2,
"Missing Values": df.isnull().sum().sum(),
"Data Types": df.dtypes.value_counts().to_dict()
}
def create_interface():
analyzer = DataAnalyzer()
with gr.Blocks(theme=gr.themes.Soft()) as demo:
gr.Markdown("""
# Data Analysis Dashboard
Upload your CSV file to generate interactive analysis reports
""")
with gr.Row():
file_input = gr.File(label="Upload CSV")
dataset_info = gr.JSON(label="Dataset Information")
with gr.Row():
report_type = gr.Radio(
choices=["Full", "Minimal"],
value="Full",
label="Report Type"
)
with gr.Tabs():
with gr.TabItem("Pandas Profiling"):
profile_html = gr.HTML()
with gr.TabItem("Sweetviz"):
sweet_html = gr.HTML()
with gr.TabItem("DataPrep"):
prep_html = gr.HTML()
def process_file(file, report_type):
if file is None:
return None, None, None, None
try:
df = pd.read_csv(file.name)
analyzer.current_df = df
# Get dataset info
info = analyzer.get_dataset_info(df)
# Generate reports
minimal = report_type == "Minimal"
with gr.Progress() as progress:
progress(0, desc="Generating Pandas Profiling report...")
profile_html = analyzer.generate_profile_report(df, minimal)
progress(0.33, desc="Generating Sweetviz report...")
sweet_html = analyzer.generate_sweetviz_report(df)
progress(0.66, desc="Generating DataPrep report...")
prep_html = analyzer.generate_dataprep_report(df)
progress(1.0, desc="Done!")
return (
info,
profile_html,
sweet_html,
prep_html
)
except Exception as e:
return str(e), None, None, None
file_input.change(
fn=process_file,
inputs=[file_input, report_type],
outputs=[dataset_info, profile_html, sweet_html, prep_html]
)
report_type.change(
fn=process_file,
inputs=[file_input, report_type],
outputs=[dataset_info, profile_html, sweet_html, prep_html]
)
return demo
# Add custom CSS for better HTML rendering
custom_css = """
<style>
.report-container {
width: 100%;
height: 800px;
overflow: auto;
}
.report-container iframe {
width: 100%;
height: 100%;
border: none;
}
</style>
"""
# Launch the interface
if __name__ == "__main__":
demo = create_interface()
demo.launch(
share=True, # Enable sharing
height=1000, # Set interface height
show_error=True, # Show detailed error messages
custom_css=custom_css # Apply custom styling
) |