Spaces:
Running
Running
File size: 5,738 Bytes
0cb60c7 67f471c 771365f 947739b 7617875 0cb60c7 c9d2489 67f471c 771365f 947739b 771365f 8d8e69e cb5dc7e 8d8e69e 947739b cb5dc7e 7617875 947739b cb5dc7e 8d8e69e 947739b cb5dc7e 947739b 8d8e69e 947739b 7617875 8d8e69e 7617875 8d8e69e 7617875 8d8e69e 947739b 8d8e69e 947739b 0cb60c7 830b865 0cb60c7 cb5dc7e 8d8e69e 276ed24 cb5dc7e 7617875 cb5dc7e 7617875 cb5dc7e 8d8e69e 0cb60c7 cb5dc7e 7617875 cb5dc7e 947739b 7617875 0cb60c7 9a72b36 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
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"
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:
plt.close('all')
dfte = self.AV.AutoViz(
filename='',
sep=',',
depVar='',
dfte=df,
header=0,
verbose=0,
lowess=False,
chart_format='html',
max_rows_analyzed=5000,
max_cols_analyzed=30,
save_plot_dir=viz_temp_dir
)
html_parts = []
if os.path.exists(viz_temp_dir):
for file in sorted(os.listdir(viz_temp_dir)):
if file.endswith('.html'):
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 "No visualizations were generated. Please check your data."
combined_html = "<br><hr><br>".join(html_parts)
return combined_html
except Exception as e:
return f"Error in AutoViz: {str(e)}"
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) |