Release 12 (from main)

models/linear_regression/README.md

@@ -11,8 +11,8 @@ These parameters are defined in the `model.yaml` under `model.input_map` and are
 | `degree`           | `2`     | Degree of the polynomial used to create polynomial features.               |
 | `interaction_only` | `true`  | Whether to include only interaction features in polynomial features.       |
 | `verbose`          | `true`  | Enable verbose output during model execution.                              |
-| `clipping_max`     | `100`   | Maximum value for clipping prediction output.                              |
-| `clipping_min`     | `0`     | Minimum value for clipping prediction output.                              |
+| `clipping_max`     | `100`   | Optional maximum for prediction output (number, decimals allowed).         |
+| `clipping_min`     | `0`     | Optional minimum for prediction output (number, decimals allowed).         |
 
 ## Data Preprocessor (`DataPreprocessor`)
 
@@ -59,7 +59,7 @@ Neither method mutates the passed DataFrames.
 - If `variable_columns` is not set, it is inferred during `fit` as all columns except the target.
 - Polynomial features are created automatically when `degree > 1`.
 - Rows with NaN in any model input get a NaN prediction (the output always has one value per input row); rows with NaN features or NaN target are left out of the fit.
-- `clipping` uses Q1/Q3 of the training target when replacing out-of-bounds predictions.
+- `clipping` uses Q1/Q3 of the training target when replacing out-of-bounds predictions: a prediction above `clipping_max` becomes Q3, one below `clipping_min` becomes Q1 (a prediction equal to the limit is kept). Each limit is optional and independent — set only one and only that side is checked.
 - The wrapper enforces that `wrapper.target` is set before training or retraining; otherwise, a `ValueError` is raised to fail fast when the configuration is incomplete.
 
 All parameters documented above **must stay in sync** between:

models/linear_regression/index.yaml

@@ -9,7 +9,7 @@ requirements:
 - mlflow==3.8.1
 - git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.11.0
 - git+ssh://git@github.com/Aignosi/sientia-model-library.git@0.14.3
-version: 1.2.2
+version: 1.2.3
 type: model
 model:
   class: LinearRegressionModel

models/linear_regression/linear_regression_model.py

@@ -73,6 +73,15 @@ class LinearRegressionModel(BaseEstimator, TransformerMixin):
                 + ', '.join(missing_model_features)
             )
 
+    def _apply_clipping(self, predictions: np.ndarray) -> None:
+        """Replace in place predictions above max with Q3 and below min with Q1."""
+        for i in range(len(predictions)):
+            # Each limit is optional on its own (SIENTIAPDE-2219)
+            if 'max' in self.clipping and predictions[i] > self.clipping['max']:
+                predictions[i] = self.q3_target
+            elif 'min' in self.clipping and predictions[i] < self.clipping['min']:
+                predictions[i] = self.q1_target
+
     def create_poly_features(self, input_data: pd.DataFrame, fit: bool = False) -> pd.DataFrame:
         """
         Function to create polynomial features
@@ -289,13 +298,8 @@ class LinearRegressionModel(BaseEstimator, TransformerMixin):
             print(f'X_test shape after removing NaN rows: {x_valid.shape}')
 
         valid_pred = self.regr.predict(x_valid[model_features])
-
         if self.clipping:
-            for i in range(len(valid_pred)):
-                if valid_pred[i] > self.clipping['max']:
-                    valid_pred[i] = self.q3_target
-                elif valid_pred[i] < self.clipping['min']:
-                    valid_pred[i] = self.q1_target
+            self._apply_clipping(valid_pred)
 
         y_pred[row_mask.to_numpy()] = valid_pred
         return y_pred

models/linear_regression/schemas.yaml

@@ -23,12 +23,12 @@ components:
           example: true
           description: "Enable verbose output during model execution."
         clipping_max:
-          type: integer
+          type: number
           default: null
           example: 100
           description: "Maximum value for clipping prediction output."
         clipping_min:
-          type: integer
+          type: number
           default: null
           example: 0
           description: "Minimum value for clipping prediction output."