upgini 1.2.114a2__tar.gz → 1.2.114a3__tar.gz

{upgini-1.2.114a2 → upgini-1.2.114a3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.114a2
+Version: 1.2.114a3
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.2.114a3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.114a3"

{upgini-1.2.114a2 → upgini-1.2.114a3}/src/upgini/features_enricher.py

@@ -1516,6 +1516,8 @@ class FeaturesEnricher(TransformerMixin):
             checking_eval_set_df, cat_features, date_column, self.logger, model_task_type
         )
 
+        self.logger.info(f"PSI values by sparsity: {psi_values_sparse}")
+
         unstable_by_sparsity = [feature for feature, psi in psi_values_sparse.items() if psi > stability_threshold]
         if unstable_by_sparsity:
             self.logger.info(f"Unstable by sparsity features: {sorted(unstable_by_sparsity)}")
@@ -1524,6 +1526,8 @@ class FeaturesEnricher(TransformerMixin):
             checking_eval_set_df, cat_features, date_column, self.logger, model_task_type
         )
 
+        self.logger.info(f"PSI values by value: {psi_values}")
+
         unstable_by_value = [feature for feature, psi in psi_values.items() if psi > stability_threshold]
         if unstable_by_value:
             self.logger.info(f"Unstable by value features: {sorted(unstable_by_value)}")

{upgini-1.2.114a2 → upgini-1.2.114a3}/src/upgini/utils/psi.py

@@ -77,7 +77,7 @@ def calculate_features_psi(
     psi_features_params: StabilityParams = DEFAULT_FEATURES_PARAMS,
     psi_target_params: StabilityParams = DEFAULT_TARGET_PARAMS,
 ) -> Dict[str, float]:
-    empty_res = pd.Series(index=df.columns, data=0)
+    empty_res = {col: 0.0 for col in df.columns if col not in [TARGET, date_column]}
 
     if not is_numeric_dtype(df[date_column]):
         df[date_column] = pd.to_datetime(df[date_column]).dt.floor("D").astype(np.int64) / 10**6
@@ -113,9 +113,9 @@ def calculate_features_psi(
             cat_top_pct=psi_target_params.cat_top_pct,
             agg_func=target_agg_func,
         )
-        if target_psi is None:
+        if target_psi is None or np.isnan(target_psi):
             logger.info("Cannot determine target PSI. Skip feature PSI check")
-            return pd.Series(index=df.columns, data=0)
+            return empty_res
 
         if target_psi > psi_target_params.threshold:
             logger.info(

upgini-1.2.114a2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.114a2"