perf(qav3): fine tune the label window optimisation

Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>

diff --git a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
index 9af3c6400bd1944ac68d7792428e24d78764ace5..24baa087cbfc914d30794e0d89712e80257881b2 100644 (file)
--- a/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
+++ b/quickadapter/user_data/freqaimodels/LightGBMRegressorQuickAdapterV35.py
@@ -593,18 +593,13 @@ def period_objective(
     y_test = y_test.iloc[-fit_live_predictions_candles:].to_numpy()
     test_weights = test_weights[-fit_live_predictions_candles:]
     y_pred = y_pred[-fit_live_predictions_candles:]
-    y_test = [
-        y_test[i : i + label_period_candles]
-        for i in range(0, len(y_test), label_period_candles)
-    ]
+    label_window: int = label_period_candles * 2
+    y_test = [y_test[i : i + label_window] for i in range(0, len(y_test), label_window)]
     test_weights = [
-        test_weights[i : i + label_period_candles]
-        for i in range(0, len(test_weights), label_period_candles)
-    ]
-    y_pred = [
-        y_pred[i : i + label_period_candles]
-        for i in range(0, len(y_pred), label_period_candles)
+        test_weights[i : i + label_window]
+        for i in range(0, len(test_weights), label_window)
     ]
+    y_pred = [y_pred[i : i + label_window] for i in range(0, len(y_pred), label_window)]
 
     error = 0.0
     for y_t, y_p, t_w in zip(y_test, y_pred, test_weights):

diff --git a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
index 751067f18decef3435dd371549c7fcb731a1ae25..bdec0f6510249ad4ccd7e20b21d02985d24350c8 100644 (file)
--- a/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
+++ b/quickadapter/user_data/freqaimodels/XGBoostRegressorQuickAdapterV35.py
@@ -601,18 +601,13 @@ def period_objective(
     y_test = y_test.iloc[-fit_live_predictions_candles:].to_numpy()
     test_weights = test_weights[-fit_live_predictions_candles:]
     y_pred = y_pred[-fit_live_predictions_candles:]
-    y_test = [
-        y_test[i : i + label_period_candles]
-        for i in range(0, len(y_test), label_period_candles)
-    ]
+    label_window: int = label_period_candles * 2
+    y_test = [y_test[i : i + label_window] for i in range(0, len(y_test), label_window)]
     test_weights = [
-        test_weights[i : i + label_period_candles]
-        for i in range(0, len(test_weights), label_period_candles)
-    ]
-    y_pred = [
-        y_pred[i : i + label_period_candles]
-        for i in range(0, len(y_pred), label_period_candles)
+        test_weights[i : i + label_window]
+        for i in range(0, len(test_weights), label_window)
     ]
+    y_pred = [y_pred[i : i + label_window] for i in range(0, len(y_pred), label_window)]
 
     error = 0.0
     for y_t, y_p, t_w in zip(y_test, y_pred, test_weights):