upgini 1.2.114a5__tar.gz → 1.2.114a6__tar.gz

{upgini-1.2.114a5 → upgini-1.2.114a6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.114a5
+Version: 1.2.114a6
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -749,6 +749,36 @@ enricher.fit(
 )
 ```
 
+### Control feature stability with PSI parameters
+
+`FeaturesEnricher` supports Population Stability Index (PSI) calculation on eval_set to evaluate feature stability over time. You can control this behavior using stability parameters in `fit` and `fit_transform` methods:
+
+```python
+enricher = FeaturesEnricher(
+    search_keys={"registration_date": SearchKey.DATE}
+)
+
+# Control feature stability during fit
+enricher.fit(
+    X, y, 
+    stability_threshold=0.2,  # PSI threshold: features with PSI above this value will be dropped
+    stability_agg_func="max"  # Aggregation function for stability values: "max", "min", "mean"
+)
+
+# Same parameters work for fit_transform
+enriched_df = enricher.fit_transform(
+    X, y,
+    stability_threshold=0.1,   # Stricter threshold for more stable features
+    stability_agg_func="mean"  # Use mean aggregation instead of max
+)
+```
+
+**Stability parameters:**
+- `stability_threshold` (float, default=0.2): PSI threshold value. Features with PSI below this threshold will be excluded from the final feature set. Lower values mean stricter stability requirements.
+- `stability_agg_func` (str, default="max"): Function to aggregate PSI values across time intervals. Options: "max" (most conservative), "min" (least conservative), "mean" (balanced approach).
+
+**PSI (Population Stability Index)** measures how much feature distribution changes over time. Lower PSI values indicate more stable features, which are generally more reliable for production ML models.
+
 ### Use custom loss function in feature selection & metrics calculation
 
 `FeaturesEnricher` can be initialized with additional string parameter `loss`. 

{upgini-1.2.114a5 → upgini-1.2.114a6}/README.md

@@ -703,6 +703,36 @@ enricher.fit(
 )
 ```
 
+### Control feature stability with PSI parameters
+
+`FeaturesEnricher` supports Population Stability Index (PSI) calculation on eval_set to evaluate feature stability over time. You can control this behavior using stability parameters in `fit` and `fit_transform` methods:
+
+```python
+enricher = FeaturesEnricher(
+    search_keys={"registration_date": SearchKey.DATE}
+)
+
+# Control feature stability during fit
+enricher.fit(
+    X, y, 
+    stability_threshold=0.2,  # PSI threshold: features with PSI above this value will be dropped
+    stability_agg_func="max"  # Aggregation function for stability values: "max", "min", "mean"
+)
+
+# Same parameters work for fit_transform
+enriched_df = enricher.fit_transform(
+    X, y,
+    stability_threshold=0.1,   # Stricter threshold for more stable features
+    stability_agg_func="mean"  # Use mean aggregation instead of max
+)
+```
+
+**Stability parameters:**
+- `stability_threshold` (float, default=0.2): PSI threshold value. Features with PSI below this threshold will be excluded from the final feature set. Lower values mean stricter stability requirements.
+- `stability_agg_func` (str, default="max"): Function to aggregate PSI values across time intervals. Options: "max" (most conservative), "min" (least conservative), "mean" (balanced approach).
+
+**PSI (Population Stability Index)** measures how much feature distribution changes over time. Lower PSI values indicate more stable features, which are generally more reliable for production ML models.
+
 ### Use custom loss function in feature selection & metrics calculation
 
 `FeaturesEnricher` can be initialized with additional string parameter `loss`. 

upgini-1.2.114a6/src/upgini/__about__.py

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

{upgini-1.2.114a5 → upgini-1.2.114a6}/src/upgini/features_enricher.py

@@ -443,7 +443,7 @@ class FeaturesEnricher(TransformerMixin):
         search_id_callback: Optional[Callable[[str], Any]] = None,
         select_features: bool = True,
         auto_fe_parameters: Optional[AutoFEParameters] = None,
-        stability_threshold: float = 0.15,
+        stability_threshold: float = 0.2,
         stability_agg_func: str = "max",
         **kwargs,
     ):
@@ -479,7 +479,7 @@ class FeaturesEnricher(TransformerMixin):
             If True, return only selected features both from input and data sources.
             Otherwise, return all features from input and only selected features from data sources.
 
-        stability_threshold: float, optional (default=0.15)
+        stability_threshold: float, optional (default=0.2)
             Stability threshold for selected features PSI calculation. If PSI is less than this threshold,
             then feature will be dropped.
 
@@ -592,7 +592,7 @@ class FeaturesEnricher(TransformerMixin):
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
         select_features: bool = True,
         auto_fe_parameters: Optional[AutoFEParameters] = None,
-        stability_threshold: float = 0.15,
+        stability_threshold: float = 0.2,
         stability_agg_func: str = "max",
         **kwargs,
     ) -> pd.DataFrame:
@@ -629,7 +629,7 @@ class FeaturesEnricher(TransformerMixin):
             If True, return only selected features both from input and data sources.
             Otherwise, return all features from input and only selected features from data sources.
 
-        stability_threshold: float, optional (default=0.15)
+        stability_threshold: float, optional (default=0.2)
             Stability threshold for selected features PSI calculation. If PSI is less than this threshold,
             then feature will be dropped.
 

upgini-1.2.114a5/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.114a5"