Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -8,21 +8,21 @@ import tempfile
|
|
8 |
def clean_and_visualize(file, progress=gr.Progress()):
|
9 |
# Load the data
|
10 |
df = pd.read_csv(file.name)
|
11 |
-
|
12 |
# Clean the data
|
13 |
cleaned_df = None
|
14 |
nonconforming_cells_before = None
|
15 |
process_times = None
|
16 |
removed_columns = None
|
17 |
removed_rows = None
|
18 |
-
|
19 |
for progress_value, status_text in clean_data(df):
|
20 |
if isinstance(status_text, tuple):
|
21 |
cleaned_df, nonconforming_cells_before, process_times, removed_columns, removed_rows = status_text
|
22 |
progress(progress_value, desc="Cleaning completed")
|
23 |
else:
|
24 |
progress(progress_value, desc=status_text)
|
25 |
-
|
26 |
# Generate full visualization report
|
27 |
create_full_report(
|
28 |
df,
|
@@ -32,47 +32,58 @@ def clean_and_visualize(file, progress=gr.Progress()):
|
|
32 |
removed_columns,
|
33 |
removed_rows
|
34 |
)
|
35 |
-
|
36 |
# Save cleaned DataFrame to a temporary CSV file
|
37 |
with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as tmp_file:
|
38 |
cleaned_df.to_csv(tmp_file.name, index=False)
|
39 |
cleaned_csv_path = tmp_file.name
|
40 |
-
|
41 |
# Collect all generated images
|
42 |
image_files = [os.path.join(REPORT_DIR, f) for f in os.listdir(REPORT_DIR) if f.endswith('.png')]
|
43 |
-
|
44 |
return cleaned_csv_path, image_files
|
45 |
|
46 |
def launch_app():
|
47 |
with gr.Blocks() as app:
|
48 |
gr.Markdown("# Data Cleaning and Visualization App")
|
49 |
-
|
50 |
with gr.Row():
|
51 |
file_input = gr.File(label="Upload CSV File", file_count="single", file_types=[".csv"])
|
52 |
-
|
53 |
with gr.Row():
|
54 |
clean_button = gr.Button("Start Cleaning")
|
55 |
-
|
56 |
with gr.Row():
|
57 |
progress_bar = gr.Progress()
|
58 |
-
|
59 |
with gr.Row():
|
60 |
cleaned_file_output = gr.File(label="Cleaned CSV", visible=True)
|
61 |
-
|
62 |
with gr.Row():
|
63 |
-
output_gallery = gr.Gallery(
|
64 |
-
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
def process_and_show_results(file):
|
67 |
cleaned_csv_path, image_files = clean_and_visualize(file, progress=progress_bar)
|
68 |
-
return
|
69 |
-
|
|
|
|
|
|
|
70 |
clean_button.click(
|
71 |
fn=process_and_show_results,
|
72 |
inputs=file_input,
|
73 |
outputs=[cleaned_file_output, output_gallery]
|
74 |
)
|
75 |
-
|
76 |
app.launch()
|
77 |
|
78 |
if __name__ == "__main__":
|
|
|
8 |
def clean_and_visualize(file, progress=gr.Progress()):
|
9 |
# Load the data
|
10 |
df = pd.read_csv(file.name)
|
11 |
+
|
12 |
# Clean the data
|
13 |
cleaned_df = None
|
14 |
nonconforming_cells_before = None
|
15 |
process_times = None
|
16 |
removed_columns = None
|
17 |
removed_rows = None
|
18 |
+
|
19 |
for progress_value, status_text in clean_data(df):
|
20 |
if isinstance(status_text, tuple):
|
21 |
cleaned_df, nonconforming_cells_before, process_times, removed_columns, removed_rows = status_text
|
22 |
progress(progress_value, desc="Cleaning completed")
|
23 |
else:
|
24 |
progress(progress_value, desc=status_text)
|
25 |
+
|
26 |
# Generate full visualization report
|
27 |
create_full_report(
|
28 |
df,
|
|
|
32 |
removed_columns,
|
33 |
removed_rows
|
34 |
)
|
35 |
+
|
36 |
# Save cleaned DataFrame to a temporary CSV file
|
37 |
with tempfile.NamedTemporaryFile(delete=False, suffix='.csv') as tmp_file:
|
38 |
cleaned_df.to_csv(tmp_file.name, index=False)
|
39 |
cleaned_csv_path = tmp_file.name
|
40 |
+
|
41 |
# Collect all generated images
|
42 |
image_files = [os.path.join(REPORT_DIR, f) for f in os.listdir(REPORT_DIR) if f.endswith('.png')]
|
43 |
+
|
44 |
return cleaned_csv_path, image_files
|
45 |
|
46 |
def launch_app():
|
47 |
with gr.Blocks() as app:
|
48 |
gr.Markdown("# Data Cleaning and Visualization App")
|
49 |
+
|
50 |
with gr.Row():
|
51 |
file_input = gr.File(label="Upload CSV File", file_count="single", file_types=[".csv"])
|
52 |
+
|
53 |
with gr.Row():
|
54 |
clean_button = gr.Button("Start Cleaning")
|
55 |
+
|
56 |
with gr.Row():
|
57 |
progress_bar = gr.Progress()
|
58 |
+
|
59 |
with gr.Row():
|
60 |
cleaned_file_output = gr.File(label="Cleaned CSV", visible=True)
|
61 |
+
|
62 |
with gr.Row():
|
63 |
+
output_gallery = gr.Gallery(
|
64 |
+
label="Visualization Results",
|
65 |
+
show_label=True,
|
66 |
+
elem_id="gallery",
|
67 |
+
columns=[2],
|
68 |
+
rows=[2],
|
69 |
+
object_fit="contain",
|
70 |
+
height="auto",
|
71 |
+
visible=False # Initially set to invisible
|
72 |
+
)
|
73 |
+
|
74 |
def process_and_show_results(file):
|
75 |
cleaned_csv_path, image_files = clean_and_visualize(file, progress=progress_bar)
|
76 |
+
return (
|
77 |
+
cleaned_csv_path,
|
78 |
+
gr.Gallery(visible=True, value=image_files) # Make gallery visible and update its content
|
79 |
+
)
|
80 |
+
|
81 |
clean_button.click(
|
82 |
fn=process_and_show_results,
|
83 |
inputs=file_input,
|
84 |
outputs=[cleaned_file_output, output_gallery]
|
85 |
)
|
86 |
+
|
87 |
app.launch()
|
88 |
|
89 |
if __name__ == "__main__":
|