upgini 1.1.253a3__tar.gz → 1.1.253a5__tar.gz

{upgini-1.1.253a3/src/upgini.egg-info → upgini-1.1.253a5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.253a3
+Version: 1.1.253a5
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.253a3 → upgini-1.1.253a5}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.253a3"
+version = "1.1.253a5"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.253a3 → upgini-1.1.253a5}/src/upgini/features_enricher.py

@@ -3022,6 +3022,7 @@ class FeaturesEnricher(TransformerMixin):
         return result_train, result_eval_sets
 
     def __prepare_feature_importances(self, trace_id: str, x_columns: List[str], silent=False):
+        llm_source = "LLM with external data augmentation"
         if self._search_task is None:
             raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
         features_meta = self._search_task.get_all_features_metadata_v2()
@@ -3076,6 +3077,8 @@ class FeaturesEnricher(TransformerMixin):
                     return ""
                 elif not link:
                     return value
+                elif value == llm_source:
+                    return value
                 else:
                     return f"<a href='{link}' target='_blank' rel='noopener noreferrer'>{value}</a>"
 
@@ -3092,7 +3095,7 @@ class FeaturesEnricher(TransformerMixin):
                 provider = to_anchor("https://upgini.com", "Upgini")
 
             internal_source = feature_meta.data_source or (
-                "LLM with external data augmentation"
+                llm_source
                 if not feature_meta.name.endswith("_country") and not feature_meta.name.endswith("_postal_code")
                 else ""
             )

{upgini-1.1.253a3 → upgini-1.1.253a5}/src/upgini/utils/target_utils.py

@@ -152,7 +152,7 @@ def balance_undersample(
         # fill up to min_sample_threshold by majority class
         minority_class = df[df[target_column] == min_class_value]
         majority_class = df[df[target_column] != min_class_value]
-        sample_size = min(len(majority_class, min_sample_threshold - min_class_count))
+        sample_size = min(len(majority_class), min_sample_threshold - min_class_count)
         sampled_majority_class = majority_class.sample(
             n=sample_size, random_state=random_state
         )

{upgini-1.1.253a3 → upgini-1.1.253a5/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.253a3
+Version: 1.1.253a5
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.253a3 → upgini-1.1.253a5}/tests/test_features_enricher.py

@@ -2574,9 +2574,9 @@ def test_unsupported_arguments(requests_mock: Mocker):
 
     df = pd.DataFrame(
         {
-            "date": ["2021-01-01", "2021-01-02", "2023-01-01", "2023-01-02"],
-            "feature": [11, 10, 12, 13],
-            "target": [0, 1, 0, 1],
+            "date": ["2021-01-01", "2021-01-02", "2023-01-01", "2023-01-02", "2023-01-03"],
+            "feature": [11, 10, 12, 13, 14],
+            "target": [0, 1, 0, 1, 0],
         }
     )
 
@@ -2603,13 +2603,14 @@ def test_unsupported_arguments(requests_mock: Mocker):
 
         enricher.transform(df.drop(columns="target"), "unsupported_positional_argument", unsupported_key_argument=False)
 
-        enricher.calculate_metrics(
-            df.drop(columns="target"),
-            df["target"],
-            [(df.drop(columns="target"), df["target"])],
-            "unsupported_positional_argument",
-            unsupported_key_argument=False,
-        )
+        with pytest.raises(ValueError, match="Only one class present in y_true. ROC AUC score is not defined in that case."):
+            enricher.calculate_metrics(
+                df.drop(columns="target"),
+                df["target"],
+                [(df.drop(columns="target"), df["target"])],
+                "unsupported_positional_argument",
+                unsupported_key_argument=False,
+            )
     finally:
         Dataset.MIN_ROWS_COUNT = original_min_rows
 

{upgini-1.1.253a3 → upgini-1.1.253a5}/tests/test_metrics.py

@@ -258,9 +258,9 @@ def test_demo_metrics(requests_mock: Mocker):
             segment_header: [train_segment],
             rows_header: [464],
             target_mean_header: [100.7802],
-            baseline_mae: [21.5089],
-            enriched_mae: [20.8841],
-            uplift: [0.624774],
+            baseline_mae: [21.18862],
+            enriched_mae: [20.862484],
+            uplift: [0.326136],
         }
     )