Update app.py
Browse files
app.py
CHANGED
|
@@ -277,6 +277,7 @@ def generate_summary_html_by_category(df):
|
|
| 277 |
Generates HTML summary blocks for each unique category in the DataFrame,
|
| 278 |
following the user's desired executive summary format.
|
| 279 |
Splits multi-line text into bullet points.
|
|
|
|
| 280 |
"""
|
| 281 |
if df.empty or 'Category' not in df.columns:
|
| 282 |
return "<p style='color:orange;'>No categories found or data is empty for detailed summarization. This could be due to issues with the AI's output parsing or content generation.</p>"
|
|
@@ -290,7 +291,11 @@ def generate_summary_html_by_category(df):
|
|
| 290 |
df[col] = 'N/A'
|
| 291 |
if col == 'Count': df[col] = 0
|
| 292 |
|
| 293 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 294 |
total_count = category_df['Count'].sum()
|
| 295 |
|
| 296 |
# --- Issue Description (Summary) ---
|
|
@@ -339,24 +344,34 @@ def generate_summary_html_by_category(df):
|
|
| 339 |
resolution_steps = f"<ul style='margin-top: 5px; margin-bottom: 5px;'>{''.join(resolution_steps_list)}</ul>" if resolution_steps_list else "<p>No specific steps identified.</p>"
|
| 340 |
|
| 341 |
|
| 342 |
-
# --- Future Prediction & Proactive Measures ---
|
| 343 |
-
|
| 344 |
for pred_text in category_df['Future Prediction'].astype(str).drop_duplicates().tolist():
|
| 345 |
-
# Use regex to split based on potential bullet patterns or just newlines
|
| 346 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', pred_text)
|
| 347 |
for line in lines:
|
| 348 |
line = line.strip()
|
| 349 |
if line and line.lower() != 'n/a':
|
| 350 |
-
|
|
|
|
|
|
|
| 351 |
for proactive_text in category_df['Proactive Measures'].astype(str).drop_duplicates().tolist():
|
| 352 |
-
# Use regex to split based on potential bullet patterns or just newlines
|
| 353 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', proactive_text)
|
| 354 |
for line in lines:
|
| 355 |
line = line.strip()
|
| 356 |
if line and line.lower() != 'n/a':
|
| 357 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 358 |
|
| 359 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
|
| 361 |
|
| 362 |
summary_html += f"""
|
|
@@ -376,7 +391,7 @@ def generate_summary_html_by_category(df):
|
|
| 376 |
{resolution_steps}
|
| 377 |
|
| 378 |
<p style="font-weight: bold; color: #555; margin-bottom: 5px;">Future Prediction & Proactive Measures:</p>
|
| 379 |
-
{
|
| 380 |
</div>
|
| 381 |
"""
|
| 382 |
return summary_html
|
|
@@ -1016,9 +1031,11 @@ def generate_docx_report(selected_timezone):
|
|
| 1016 |
doc.add_heading("Aggregated Issue Summaries", level=2)
|
| 1017 |
doc.add_paragraph("")
|
| 1018 |
|
| 1019 |
-
#
|
| 1020 |
-
|
| 1021 |
-
|
|
|
|
|
|
|
| 1022 |
total_count = category_df['Count'].sum()
|
| 1023 |
|
| 1024 |
cat_heading = doc.add_heading(f"{category} ({total_count})", level=3)
|
|
@@ -1084,32 +1101,39 @@ def generate_docx_report(selected_timezone):
|
|
| 1084 |
doc.add_paragraph("• No specific steps identified.", style='List Bullet')
|
| 1085 |
doc.add_paragraph("")
|
| 1086 |
|
| 1087 |
-
|
| 1088 |
-
|
| 1089 |
-
|
| 1090 |
for pred_text in category_df['Future Prediction'].astype(str).drop_duplicates().tolist():
|
| 1091 |
-
# Use regex to split based on potential bullet patterns or just newlines
|
| 1092 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', pred_text)
|
| 1093 |
for line in lines:
|
| 1094 |
line = line.strip()
|
| 1095 |
if line and line.lower() != 'n/a':
|
| 1096 |
-
|
| 1097 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1098 |
for proactive_text in category_df['Proactive Measures'].astype(str).drop_duplicates().tolist():
|
| 1099 |
-
# Use regex to split based on potential bullet patterns or just newlines
|
| 1100 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', proactive_text)
|
| 1101 |
for line in lines:
|
| 1102 |
line = line.strip()
|
| 1103 |
if line and line.lower() != 'n/a':
|
| 1104 |
-
|
| 1105 |
-
|
| 1106 |
-
|
| 1107 |
-
for item in prediction_and_proactive_items:
|
| 1108 |
doc.add_paragraph(f"• {item}", style='List Bullet')
|
| 1109 |
else:
|
| 1110 |
-
doc.add_paragraph("• No
|
| 1111 |
doc.add_paragraph("")
|
| 1112 |
|
|
|
|
| 1113 |
doc.add_heading("Disclaimer", level=2)
|
| 1114 |
doc.add_paragraph(
|
| 1115 |
"*Note: AI-generated insights, especially 'Root Cause', 'Future Prediction', and 'Proactive Measures', are inferred based on the provided ticket descriptions. "
|
|
@@ -1194,9 +1218,10 @@ with gr.Blocks(theme=gr.themes.Soft(), css="""
|
|
| 1194 |
* Bullet points of AI-inferred underlying reasons for the issues.
|
| 1195 |
* **Resolution Steps:**
|
| 1196 |
* Bullet points of strategic steps to resolve issues.
|
| 1197 |
-
* **Future Prediction
|
| 1198 |
-
*
|
| 1199 |
-
|
|
|
|
| 1200 |
"""
|
| 1201 |
)
|
| 1202 |
|
|
|
|
| 277 |
Generates HTML summary blocks for each unique category in the DataFrame,
|
| 278 |
following the user's desired executive summary format.
|
| 279 |
Splits multi-line text into bullet points.
|
| 280 |
+
Categories are sorted from max to min count.
|
| 281 |
"""
|
| 282 |
if df.empty or 'Category' not in df.columns:
|
| 283 |
return "<p style='color:orange;'>No categories found or data is empty for detailed summarization. This could be due to issues with the AI's output parsing or content generation.</p>"
|
|
|
|
| 291 |
df[col] = 'N/A'
|
| 292 |
if col == 'Count': df[col] = 0
|
| 293 |
|
| 294 |
+
# Group by category, sum the counts, and then sort by count in descending order
|
| 295 |
+
category_counts = df.groupby('Category')['Count'].sum().sort_values(ascending=False)
|
| 296 |
+
|
| 297 |
+
for category in category_counts.index: # Iterate through categories in sorted order (max to min count)
|
| 298 |
+
category_df = df[df['Category'] == category] # Get the DataFrame for the current category
|
| 299 |
total_count = category_df['Count'].sum()
|
| 300 |
|
| 301 |
# --- Issue Description (Summary) ---
|
|
|
|
| 344 |
resolution_steps = f"<ul style='margin-top: 5px; margin-bottom: 5px;'>{''.join(resolution_steps_list)}</ul>" if resolution_steps_list else "<p>No specific steps identified.</p>"
|
| 345 |
|
| 346 |
|
| 347 |
+
# --- Future Prediction & Proactive Measures (Revised) ---
|
| 348 |
+
future_prediction_html_list = []
|
| 349 |
for pred_text in category_df['Future Prediction'].astype(str).drop_duplicates().tolist():
|
|
|
|
| 350 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', pred_text)
|
| 351 |
for line in lines:
|
| 352 |
line = line.strip()
|
| 353 |
if line and line.lower() != 'n/a':
|
| 354 |
+
future_prediction_html_list.append(f"<li>{line}</li>")
|
| 355 |
+
|
| 356 |
+
proactive_measures_html_list = []
|
| 357 |
for proactive_text in category_df['Proactive Measures'].astype(str).drop_duplicates().tolist():
|
|
|
|
| 358 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', proactive_text)
|
| 359 |
for line in lines:
|
| 360 |
line = line.strip()
|
| 361 |
if line and line.lower() != 'n/a':
|
| 362 |
+
proactive_measures_html_list.append(f"<li>{line}</li>")
|
| 363 |
+
|
| 364 |
+
prediction_and_proactive_html = ""
|
| 365 |
+
if future_prediction_html_list:
|
| 366 |
+
prediction_and_proactive_html += "<p style='font-weight: bold; color: #6A1B9A; margin-top: 10px; margin-bottom: 5px;'>Future Prediction:</p>"
|
| 367 |
+
prediction_and_proactive_html += f"<ul style='margin-top: 5px; margin-bottom: 5px;'>{''.join(future_prediction_html_list)}</ul>"
|
| 368 |
|
| 369 |
+
if proactive_measures_html_list:
|
| 370 |
+
prediction_and_proactive_html += "<p style='font-weight: bold; color: #6A1B9A; margin-top: 10px; margin-bottom: 5px;'>Proactive Measures:</p>"
|
| 371 |
+
prediction_and_proactive_html += f"<ul style='margin-top: 5px; margin-bottom: 5px;'>{''.join(proactive_measures_html_list)}</ul>"
|
| 372 |
+
|
| 373 |
+
if not prediction_and_proactive_html:
|
| 374 |
+
prediction_and_proactive_html = "<p>No future prediction or proactive measures identified.</p>"
|
| 375 |
|
| 376 |
|
| 377 |
summary_html += f"""
|
|
|
|
| 391 |
{resolution_steps}
|
| 392 |
|
| 393 |
<p style="font-weight: bold; color: #555; margin-bottom: 5px;">Future Prediction & Proactive Measures:</p>
|
| 394 |
+
{prediction_and_proactive_html}
|
| 395 |
</div>
|
| 396 |
"""
|
| 397 |
return summary_html
|
|
|
|
| 1031 |
doc.add_heading("Aggregated Issue Summaries", level=2)
|
| 1032 |
doc.add_paragraph("")
|
| 1033 |
|
| 1034 |
+
# Group by category, sum the counts, and then sort by count in descending order
|
| 1035 |
+
category_counts = df.groupby('Category')['Count'].sum().sort_values(ascending=False)
|
| 1036 |
+
|
| 1037 |
+
for category in category_counts.index: # Iterate through categories in sorted order
|
| 1038 |
+
category_df = df[df['Category'] == category] # Get the DataFrame for the current category
|
| 1039 |
total_count = category_df['Count'].sum()
|
| 1040 |
|
| 1041 |
cat_heading = doc.add_heading(f"{category} ({total_count})", level=3)
|
|
|
|
| 1101 |
doc.add_paragraph("• No specific steps identified.", style='List Bullet')
|
| 1102 |
doc.add_paragraph("")
|
| 1103 |
|
| 1104 |
+
# --- Future Prediction (Revised for DOCX) ---
|
| 1105 |
+
doc.add_paragraph("Future Prediction:").runs[0].bold = True
|
| 1106 |
+
future_prediction_items = []
|
| 1107 |
for pred_text in category_df['Future Prediction'].astype(str).drop_duplicates().tolist():
|
|
|
|
| 1108 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', pred_text)
|
| 1109 |
for line in lines:
|
| 1110 |
line = line.strip()
|
| 1111 |
if line and line.lower() != 'n/a':
|
| 1112 |
+
future_prediction_items.append(line)
|
| 1113 |
+
if future_prediction_items:
|
| 1114 |
+
for item in future_prediction_items:
|
| 1115 |
+
doc.add_paragraph(f"• {item}", style='List Bullet')
|
| 1116 |
+
else:
|
| 1117 |
+
doc.add_paragraph("• No future predictions identified.", style='List Bullet')
|
| 1118 |
+
doc.add_paragraph("")
|
| 1119 |
+
|
| 1120 |
+
# --- Proactive Measures (Revised for DOCX) ---
|
| 1121 |
+
doc.add_paragraph("Proactive Measures:").runs[0].bold = True
|
| 1122 |
+
proactive_measures_items = []
|
| 1123 |
for proactive_text in category_df['Proactive Measures'].astype(str).drop_duplicates().tolist():
|
|
|
|
| 1124 |
lines = re.split(r'\s*[\*\-]\s*|\s*\n\s*', proactive_text)
|
| 1125 |
for line in lines:
|
| 1126 |
line = line.strip()
|
| 1127 |
if line and line.lower() != 'n/a':
|
| 1128 |
+
proactive_measures_items.append(line)
|
| 1129 |
+
if proactive_measures_items:
|
| 1130 |
+
for item in proactive_measures_items:
|
|
|
|
| 1131 |
doc.add_paragraph(f"• {item}", style='List Bullet')
|
| 1132 |
else:
|
| 1133 |
+
doc.add_paragraph("• No proactive measures identified.", style='List Bullet')
|
| 1134 |
doc.add_paragraph("")
|
| 1135 |
|
| 1136 |
+
|
| 1137 |
doc.add_heading("Disclaimer", level=2)
|
| 1138 |
doc.add_paragraph(
|
| 1139 |
"*Note: AI-generated insights, especially 'Root Cause', 'Future Prediction', and 'Proactive Measures', are inferred based on the provided ticket descriptions. "
|
|
|
|
| 1218 |
* Bullet points of AI-inferred underlying reasons for the issues.
|
| 1219 |
* **Resolution Steps:**
|
| 1220 |
* Bullet points of strategic steps to resolve issues.
|
| 1221 |
+
* **Future Prediction:**
|
| 1222 |
+
* Bullet points of predictions if issues aren't fixed.
|
| 1223 |
+
* **Proactive Measures:**
|
| 1224 |
+
* Bullet points of preventive steps.
|
| 1225 |
"""
|
| 1226 |
)
|
| 1227 |
|