Spaces:
Sleeping
Sleeping
johnnydevriese
commited on
Commit
β’
002b754
1
Parent(s):
ce51916
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
import numpy as np
|
4 |
+
|
5 |
+
# Flexoki colors for highlighting
|
6 |
+
HIGHLIGHT_COLORS = [
|
7 |
+
"#D14D41", # Red
|
8 |
+
"#879A39", # Green
|
9 |
+
"#66A1DC", # Blue
|
10 |
+
"#D0A215", # Yellow
|
11 |
+
"#8E5F26", # Brown
|
12 |
+
]
|
13 |
+
|
14 |
+
|
15 |
+
def highlight_diff(*values):
|
16 |
+
unique_values = set(str(v) for v in values if pd.notna(v))
|
17 |
+
if len(unique_values) == 1:
|
18 |
+
return str(values[0])
|
19 |
+
|
20 |
+
highlighted = []
|
21 |
+
for i, value in enumerate(values):
|
22 |
+
if pd.isna(value):
|
23 |
+
continue
|
24 |
+
highlighted.append(
|
25 |
+
f'<span style="background-color: {HIGHLIGHT_COLORS[i]}; color: white;">{value}</span>'
|
26 |
+
)
|
27 |
+
|
28 |
+
return " | ".join(highlighted)
|
29 |
+
|
30 |
+
|
31 |
+
def compare_csvs(*files):
|
32 |
+
valid_files = [f for f in files if f is not None]
|
33 |
+
if len(valid_files) < 2:
|
34 |
+
return "Please upload at least two CSV files.", None
|
35 |
+
|
36 |
+
# Read CSV files
|
37 |
+
dataframes = [pd.read_csv(file.name) for file in valid_files]
|
38 |
+
|
39 |
+
# Check if all dataframes have the same shape
|
40 |
+
if len(set(df.shape for df in dataframes)) > 1:
|
41 |
+
return (
|
42 |
+
"The CSV files have different shapes. Please ensure they all have the same number of rows and columns.",
|
43 |
+
None,
|
44 |
+
)
|
45 |
+
|
46 |
+
# Create a combined dataframe for comparison
|
47 |
+
combined_df = dataframes[0].copy()
|
48 |
+
for col in combined_df.columns:
|
49 |
+
combined_df[col] = [
|
50 |
+
highlight_diff(*values) for values in zip(*(df[col] for df in dataframes))
|
51 |
+
]
|
52 |
+
|
53 |
+
# Calculate summary
|
54 |
+
total_cells = dataframes[0].size
|
55 |
+
different_cells = sum((dataframes[0] != df).sum().sum() for df in dataframes[1:])
|
56 |
+
diff_percentage = (different_cells / (total_cells * (len(dataframes) - 1))) * 100
|
57 |
+
|
58 |
+
summary = f"Total cells: {total_cells}\n"
|
59 |
+
summary += f"Different cells: {different_cells}\n"
|
60 |
+
summary += f"Percentage of differences: {diff_percentage:.2f}%"
|
61 |
+
|
62 |
+
return summary, combined_df.to_html(escape=False)
|
63 |
+
|
64 |
+
|
65 |
+
with gr.Blocks() as app:
|
66 |
+
gr.Markdown("# π Kindness - CSV Comparison")
|
67 |
+
|
68 |
+
with gr.Row():
|
69 |
+
files = [gr.File(label=f"Upload CSV {i+1}") for i in range(5)]
|
70 |
+
|
71 |
+
compare_btn = gr.Button("Compare CSVs")
|
72 |
+
|
73 |
+
summary = gr.Textbox(label="Summary")
|
74 |
+
diff_output = gr.HTML(label="Differences")
|
75 |
+
|
76 |
+
compare_btn.click(compare_csvs, inputs=files, outputs=[summary, diff_output])
|
77 |
+
|
78 |
+
|
79 |
+
app.launch()
|
80 |
+
|