upgini 1.2.17a1__tar.gz → 1.2.19__tar.gz

{upgini-1.2.17a1 → upgini-1.2.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.17a1
+Version: 1.2.19
 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-1.2.19/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.19"

{upgini-1.2.17a1 → upgini-1.2.19}/src/upgini/features_enricher.py

@@ -3894,10 +3894,10 @@ class FeaturesEnricher(TransformerMixin):
                 search_id=self._search_task.search_task_id,
                 email=self.rest_client.get_current_email(),
                 search_keys=[str(sk) for sk in self.search_keys.values()],
-                dislay_id=display_id,
+                display_id=display_id,
                 display_handle=display_handle,
             )
-        except Exception as e:
+        except Exception:
             pass
 
     def __validate_importance_threshold(self, importance_threshold: Optional[float]) -> float:

{upgini-1.2.17a1 → upgini-1.2.19}/src/upgini/metrics.py

@@ -343,11 +343,16 @@ class EstimatorWrapper:
             }
             if len(average_shap_values) == 0:
                 average_shap_values = None
+            else:
+                average_shap_values = self.process_shap_values(average_shap_values)
         else:
             average_shap_values = None
 
         return self.post_process_metric(metric), average_shap_values
 
+    def process_shap_values(self, shap_values: Dict[str, float]) -> Dict[str, float]:
+        return shap_values
+
     def check_fold_metrics(self, metrics_by_fold: List[float]):
         first_metric_sign = 1 if metrics_by_fold[0] >= 0 else -1
         for metric in metrics_by_fold[1:]:
@@ -558,13 +563,20 @@ class CatBoostWrapper(EstimatorWrapper):
 
         return df, [emb_name]
 
+    def process_shap_values(self, shap_values: Dict[str, float]) -> Dict[str, float]:
+        if "__grouped_embeddings" in shap_values:
+            for emb_feature in self.emb_features:
+                shap_values[emb_feature] = shap_values["__grouped_embeddings"]
+            del shap_values["__grouped_embeddings"]
+        return shap_values
+
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         if self.exclude_features:
             x = x.drop(columns=self.exclude_features)
         x, y, params = super()._prepare_to_calculate(x, y)
         if self.text_features:
             params["text_features"] = self.text_features
-        if self.emb_features:
+        if self.grouped_embedding_features:
             x, emb_columns = self.group_embeddings(x)
             params["embedding_features"] = emb_columns
         if self.cat_features:

upgini-1.2.17a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.17a1"