Spaces:
Sleeping
Sleeping
Commit
·
b62caf4
1
Parent(s):
8ddc24b
Fix column mismatch in results DataFrame - add rank column
Browse files
app.py
CHANGED
|
@@ -164,6 +164,7 @@ def run_evaluation(dataset_name: str, dialect: str, case_selection: str,
|
|
| 164 |
|
| 165 |
# Format for display using config
|
| 166 |
results.append([
|
|
|
|
| 167 |
model_name,
|
| 168 |
formatting["composite_score"].format(result['composite_score']),
|
| 169 |
formatting["correctness_exact"].format(result['correctness_exact']),
|
|
@@ -194,7 +195,7 @@ def run_evaluation(dataset_name: str, dialect: str, case_selection: str,
|
|
| 194 |
except Exception as e:
|
| 195 |
error_msg = f"Error evaluating {model_name}: {str(e)}"
|
| 196 |
print(error_msg)
|
| 197 |
-
results.append([model_name, "ERROR", "ERROR", "ERROR", "ERROR", "ERROR"])
|
| 198 |
detailed_results.append(f"**Error with {model_name}:** {error_msg}\n\n---\n")
|
| 199 |
|
| 200 |
# Create results DataFrame using config
|
|
|
|
| 164 |
|
| 165 |
# Format for display using config
|
| 166 |
results.append([
|
| 167 |
+
len(results) + 1, # Rank (1-based)
|
| 168 |
model_name,
|
| 169 |
formatting["composite_score"].format(result['composite_score']),
|
| 170 |
formatting["correctness_exact"].format(result['correctness_exact']),
|
|
|
|
| 195 |
except Exception as e:
|
| 196 |
error_msg = f"Error evaluating {model_name}: {str(e)}"
|
| 197 |
print(error_msg)
|
| 198 |
+
results.append([len(results) + 1, model_name, "ERROR", "ERROR", "ERROR", "ERROR", "ERROR"])
|
| 199 |
detailed_results.append(f"**Error with {model_name}:** {error_msg}\n\n---\n")
|
| 200 |
|
| 201 |
# Create results DataFrame using config
|