Reduced features v2

README.md

@@ -27,8 +27,8 @@ The stereo regression training pipeline uses multi-target XGBoost to predict res
 
 By default, regression uses the extended feature set. An optional reduced set can
 be selected with `--feature_profile reduced`; it contains the array-level geometry
-and energy quantities plus `width_length`, `R_core`, and `loss` summaries for
-telescope positions 0--3. The default is unchanged with `--feature_profile extended`.
+and energy quantities plus `R_core` and `loss` summaries for telescope positions
+0--3. The default is unchanged with `--feature_profile extended`.
 
 **Key techniques:**
 

src/eventdisplay_ml/config.py

@@ -45,8 +45,8 @@ def configure_training(analysis_type):
             default="extended",
             help=(
                 "Regression feature set. 'extended' retains all non-target features; "
-                "'reduced' uses array-level quantities and width/length, R_core, "
-                "and loss summaries for telescope positions 0-3."
+                "'reduced' uses array-level quantities plus R_core and loss summaries "
+                "for telescope positions 0-3."
             ),
         )
     if analysis_type == "classification":

src/eventdisplay_ml/data_processing.py

@@ -1388,9 +1388,6 @@ def flatten_telescope_variables(
             new_cols[f"loss_dist_{i}"] = df_flat[f"loss_{i}"] * df_flat[f"dist_{i}"]
         if f"size_{i}" in df_flat and f"dist_{i}" in df_flat and keep_size_vars:
             new_cols[f"size_dist2_{i}"] = df_flat[f"size_{i}"] / (df_flat[f"dist_{i}"] ** 2 + 1e-6)
-        if f"width_{i}" in df_flat and f"length_{i}" in df_flat:
-            new_cols[f"width_length_{i}"] = df_flat[f"width_{i}"] / (df_flat[f"length_{i}"] + 1e-6)
-
     df_flat = pd.concat([df_flat, pd.DataFrame(new_cols, index=index)], axis=1)
 
     # inspect ordering and magnitudes before clipping/log10

src/eventdisplay_ml/features.py

@@ -135,7 +135,6 @@ def regression_feature_columns(columns, profile="extended"):
         "EmissionHeight",
         "Geomagnetic_Angle",
         "array_footprint",
-        *[f"width_length_{i}" for i in range(4)],
         *[f"R_core_{i}" for i in range(4)],
         *[f"loss_{i}" for i in range(4)],
     ]

tests/test_data_processing_remaining.py

@@ -152,6 +152,7 @@ def test_flatten_feature_data_drops_size_columns_for_classification(tel_config):
 
     assert "size_0" not in result.columns
     assert "size_dist2_0" not in result.columns
+    assert "width_length_0" not in result.columns
     assert "cosphi_0" in result.columns
     assert "ze_bin" in result.columns
 

tests/test_features.py

@@ -88,7 +88,6 @@ def test_reduced_regression_feature_columns_are_stable_and_exact():
         "EmissionHeight",
         "Geomagnetic_Angle",
         "array_footprint",
-        *[f"width_length_{i}" for i in range(4)],
         *[f"R_core_{i}" for i in range(4)],
         *[f"loss_{i}" for i in range(4)],
         "E_residual",
@@ -107,7 +106,6 @@ def test_reduced_regression_feature_columns_are_stable_and_exact():
         "EmissionHeight",
         "Geomagnetic_Angle",
         "array_footprint",
-        *[f"width_length_{i}" for i in range(4)],
         *[f"R_core_{i}" for i in range(4)],
         *[f"loss_{i}" for i in range(4)],
     ]
@@ -129,7 +127,6 @@ def test_reduced_regression_feature_columns_require_all_requested_columns():
                 "EmissionHeight",
                 "Geomagnetic_Angle",
                 "array_footprint",
-                *[f"width_length_{i}" for i in range(4)],
                 *[f"R_core_{i}" for i in range(4)],
                 *[f"loss_{i}" for i in range(3)],
             ],

tests/test_regression_contracts.py

@@ -130,7 +130,6 @@ def test_regression_training_reduced_profile_selects_requested_columns(monkeypat
         "EmissionHeight",
         "Geomagnetic_Angle",
         "array_footprint",
-        *[f"width_length_{i}" for i in range(4)],
         *[f"R_core_{i}" for i in range(4)],
         *[f"loss_{i}" for i in range(4)],
     ]