Use empty, rename

include/LightGBM/objective_function.h

@@ -68,6 +68,7 @@ class ObjectiveFunction {
   virtual data_size_t NumPositiveData() const { return 0; }
 
   virtual void ConvertOutputs(const int num_data, const double* inputs, double* outputs) const {
+    #pragma omp parallel for num_threads(OMP_NUM_THREADS()) schedule(static)
     for (int i = 0; i < num_data; i ++) {
       ConvertOutput(inputs + i, outputs + i);
     }

python-package/lightgbm/basic.py

@@ -5331,7 +5331,7 @@ def init(self, dataset: Dataset) -> "ObjectiveFunction":
         """
         return self.__init_from_dataset(dataset)
 
-    def convert_outputs(self, scores: np.ndarray) -> np.ndarray:
+    def convert_raw_scores(self, scores: np.ndarray) -> np.ndarray:
         """
         Convert the raw scores to the final predictions.
 
@@ -5353,7 +5353,7 @@ def convert_outputs(self, scores: np.ndarray) -> np.ndarray:
             scores = _data_to_2d_numpy(scores, dtype=np.float64, name="scores")
 
         num_data = scores.size
-        out_preds = np.zeros_like(scores, dtype=np.float64)
+        out_preds = np.empty_like(scores, dtype=np.float64)
 
         _safe_call(
             _LIB.LGBM_ObjectiveFunctionConvertOutputs(
@@ -5387,8 +5387,8 @@ def get_gradients(self, y_pred: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
             raise ValueError("ObjectiveFunction was not created properly")
 
         data_shape = self.num_data * self.num_class
-        grad = np.zeros(dtype=np.float32, shape=data_shape)
-        hess = np.zeros(dtype=np.float32, shape=data_shape)
+        grad = np.empty(dtype=np.float32, shape=data_shape)
+        hess = np.empty(dtype=np.float32, shape=data_shape)
 
         _safe_call(
             _LIB.LGBM_ObjectiveFunctionGetGradients(

src/objective/multiclass_objective.hpp

@@ -130,6 +130,7 @@ class MulticlassSoftmax: public ObjectiveFunction {
   }
 
   void ConvertOutputs(const int num_data, const double* inputs, double* outputs) const override {
+    #pragma omp parallel for num_threads(OMP_NUM_THREADS()) schedule(static)
     for (int i = 0; i < num_data; i += num_class_) {
       ConvertOutput(inputs + i, outputs + i);
     }
@@ -243,6 +244,7 @@ class MulticlassOVA: public ObjectiveFunction {
   }
 
   void ConvertOutputs(const int num_data, const double* inputs, double* outputs) const override {
+    #pragma omp parallel for num_threads(OMP_NUM_THREADS()) schedule(static)
     for (int i = 0; i < num_data; i += num_class_) {
       ConvertOutput(inputs + i, outputs + i);
     }

tests/python_package_test/test_engine.py

@@ -4423,7 +4423,7 @@ def test_objective_function_class(use_weight, num_boost_round, custom_objective,
         "device": "cpu",
     }
     builtin_loss = builtin_objective(objective_name, copy.deepcopy(params))
-    builtin_convert_outputs = lgb.ObjectiveFunction(objective_name, copy.deepcopy(params)).convert_outputs
+    builtin_convert_scores = lgb.ObjectiveFunction(objective_name, copy.deepcopy(params)).convert_raw_scores
 
     params["objective"] = builtin_loss
     booster_exposed = lgb.train(params, lgb_train, num_boost_round=num_boost_round)
@@ -4440,4 +4440,4 @@ def test_objective_function_class(use_weight, num_boost_round, custom_objective,
     y_pred = np.zeros_like(booster.predict(X, raw_score=True))
     np.testing.assert_allclose(builtin_loss(y_pred, lgb_train), custom_objective(y_pred, lgb_train))
 
-    np.testing.assert_allclose(builtin_convert_outputs(booster_exposed.predict(X)), booster.predict(X))
+    np.testing.assert_allclose(builtin_convert_scores(booster_exposed.predict(X)), booster.predict(X))