SIENTIAPDE-1579: Added extra test files and support filters implementation

model_manager/utils/repository/training_repository.py

@@ -47,6 +47,68 @@ def _ensure_date_column_parsed(data: pd.DataFrame, params: TrainModelParams) ->
     return data
 
 
+def _apply_support_filters(
+    data_view: pd.DataFrame,
+    target_variable: str,
+    support_filters: dict,
+) -> pd.DataFrame:
+    """
+    Keep only rows where (var, target) lies between the two guide lines for each variable.
+
+    For each variable in support_filters, the condition is lower(x_var) <= target <= upper(x_var),
+    where lower/upper are the two lines (intercept + slope from angle, scaled by y_range/x_range).
+    Global mask is AND across all variables. Matches DEMO logic in template_01.py.
+
+    Args:
+        data_view: DataFrame after preprocessor transform.
+        target_variable: Name of the target column (y axis).
+        support_filters: Per-variable config with upper_line/lower_line, each {intercept, angle}.
+
+    Returns:
+        data_view filtered to rows satisfying all variable conditions; unchanged if support_filters empty.
+    """
+    if not support_filters or target_variable not in data_view.columns:
+        return data_view
+
+    combined_keep_mask = np.ones(len(data_view), dtype=bool)
+
+    for var_col, config in support_filters.items():
+        if var_col not in data_view.columns:
+            continue
+
+        upper = config.get('upper_line') or config.get('upperLine')
+        lower = config.get('lower_line') or config.get('lowerLine')
+        if not upper or not lower:
+            continue
+
+        x_vals = data_view[var_col].astype(float).to_numpy()
+        y_vals = data_view[target_variable].astype(float).to_numpy()
+
+        xmin, xmax = float(np.nanmin(x_vals)), float(np.nanmax(x_vals))
+        ymin, ymax = float(np.nanmin(y_vals)), float(np.nanmax(y_vals))
+        x_range = (xmax - xmin) if (xmax - xmin) != 0 else 1.0
+        y_range = (ymax - ymin) if (ymax - ymin) != 0 else 1.0
+        scale_ratio = y_range / x_range
+
+        b1 = float(upper.get('intercept', 0))
+        deg1 = float(upper.get('angle', 0))
+        b2 = float(lower.get('intercept', 0))
+        deg2 = float(lower.get('angle', 0))
+
+        m1 = np.tan(np.deg2rad(deg1)) * scale_ratio
+        m2 = np.tan(np.deg2rad(deg2)) * scale_ratio
+        y1 = m1 * x_vals + b1
+        y2 = m2 * x_vals + b2
+        lower_bound = np.minimum(y1, y2)
+        upper_bound = np.maximum(y1, y2)
+        keep_mask = (y_vals >= lower_bound) & (y_vals <= upper_bound)
+
+        if len(keep_mask) == len(combined_keep_mask):
+            combined_keep_mask &= keep_mask
+
+    return data_view.loc[combined_keep_mask]
+
+
 class TrainingRepository:
     """
     Repository for machine learning model training operations.
@@ -105,6 +167,13 @@ class TrainingRepository:
         process_data.fit(data)
         data_view = process_data.transform(data)
 
+        if params.support_filters:
+            data_view = _apply_support_filters(
+                data_view,
+                params.target_variable,
+                params.support_filters,
+            )
+
         if len(data_view) <= 0:
             raise ValueError('Data view is empty after transformation')