lecrapaud 0.19.0__tar.gz → 0.19.2__tar.gz

{lecrapaud-0.19.0 → lecrapaud-0.19.2}/PKG-INFO

@@ -1,8 +1,9 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: lecrapaud
-Version: 0.19.0
+Version: 0.19.2
 Summary: Framework for machine and deep learning, with regression, classification and time series analysis
 License: Apache License
+License-File: LICENSE
 Author: Pierre H. Gallet
 Requires-Python: ==3.12.*
 Classifier: License :: Other/Proprietary License

{lecrapaud-0.19.0 → lecrapaud-0.19.2}/lecrapaud/db/models/experiment.py

@@ -272,10 +272,13 @@ class Experiment(Base):
                 return None
 
             # Normalize scores (subtract min and divide by range)
+            # Guard against division by zero when only one observation or all equal
             min_rmse = min(rmse_scores)
-            range_rmse = max(rmse_scores) - min_rmse
+            max_rmse = max(rmse_scores)
+            range_rmse = max_rmse - min_rmse
             min_logloss = min(logloss_scores)
-            range_logloss = max(logloss_scores) - min_logloss
+            max_logloss = max(logloss_scores)
+            range_logloss = max_logloss - min_logloss
 
             # Calculate combined score for each experiment
             experiment_scores = []
@@ -283,9 +286,17 @@ class Experiment(Base):
                 if experiment.avg_rmse is None or experiment.avg_logloss is None:
                     continue
 
-                # Normalize both scores
-                norm_rmse = (experiment.avg_rmse - min_rmse) / range_rmse
-                norm_logloss = (experiment.avg_logloss - min_logloss) / range_logloss
+                # Normalize both scores (safe when range == 0)
+                norm_rmse = (
+                    0.0
+                    if range_rmse == 0
+                    else (experiment.avg_rmse - min_rmse) / range_rmse
+                )
+                norm_logloss = (
+                    0.0
+                    if range_logloss == 0
+                    else (experiment.avg_logloss - min_logloss) / range_logloss
+                )
 
                 # Calculate combined score (average of normalized scores)
                 combined_score = (norm_rmse + norm_logloss) / 2

{lecrapaud-0.19.0 → lecrapaud-0.19.2}/lecrapaud/feature_engineering.py

@@ -629,6 +629,7 @@ class PreprocessFeature:
         """
 
         pcas_dict = {}
+        index_saved = df.index
 
         for pca_cross_sectional in self.pca_cross_sectional:
             name, index_col, columns_col, value_col = (
@@ -659,6 +660,7 @@ class PreprocessFeature:
             scores_df = pd.DataFrame(scores, index=pivot.index, columns=cols)
 
             df = df.merge(scores_df.reset_index(), on=index_col, how="left")
+            df.index = index_saved
             pcas_dict.update({name: pipe})
 
         return df, pcas_dict

{lecrapaud-0.19.0 → lecrapaud-0.19.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lecrapaud"
-version = "0.19.0"
+version = "0.19.2"
 description = "Framework for machine and deep learning, with regression, classification and time series analysis"
 authors = [
     {name = "Pierre H. Gallet"}