Commit
·
c6d6e01
1
Parent(s):
d6a0c44
Fixed the validation message
Browse files- validation.py +8 -1
validation.py
CHANGED
|
@@ -236,7 +236,14 @@ def validate_dataframe(df: pd.DataFrame, submission_type: str = "GDPa1") -> None
|
|
| 236 |
results_df = evaluate(predictions_df=df, target_df=df_gdpa1, dataset_name=submission_type)
|
| 237 |
# Check that the Spearman correlations are not too high
|
| 238 |
if results_df["spearman"].max() > 0.9:
|
| 239 |
-
raise gr.Error(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
|
| 241 |
|
| 242 |
def validate_csv_file(file_content: str, submission_type: str = "GDPa1") -> None:
|
|
|
|
| 236 |
results_df = evaluate(predictions_df=df, target_df=df_gdpa1, dataset_name=submission_type)
|
| 237 |
# Check that the Spearman correlations are not too high
|
| 238 |
if results_df["spearman"].max() > 0.9:
|
| 239 |
+
raise gr.Error(
|
| 240 |
+
message="⚠️ Your submission shows abnormally high correlations (>0.9) on the public set. "
|
| 241 |
+
"Please check that you're not overfitting/don't have data leakage on the public set and are using cross-validation if training a new model.\n"
|
| 242 |
+
"This will result in a better model for eventually submitting to the heldout test set.\n"
|
| 243 |
+
"If you think this is a mistake, please contact [email protected].",
|
| 244 |
+
duration=30,
|
| 245 |
+
title="Data Leakage Warning",
|
| 246 |
+
)
|
| 247 |
|
| 248 |
|
| 249 |
def validate_csv_file(file_content: str, submission_type: str = "GDPa1") -> None:
|