Update loss_functions.py

Author: Addyk-24

machine_learning/loss_functions.py

@@ -663,7 +663,7 @@ def kullback_leibler_divergence(y_true: np.ndarray, y_pred: np.ndarray) -> float
     return np.sum(kl_loss)
 
 
-def root_mean_squared_error(y_true, y_pred):
+def root_mean_squared_error(y_true: np.array, y_pred:np.array) -> float:
     """
     Root Mean Squared Error (RMSE)
 
@@ -682,15 +682,10 @@ def root_mean_squared_error(y_true, y_pred):
     Returns:
         float: The RMSE Loss function between y_pred and y_true
 
-    >>> true_labels = np.array([100, 200, 300])
-    >>> predicted_probs = np.array([110, 190, 310])
+    >>> true_labels = np.array([2, 4, 6, 8])
+    >>> predicted_probs = np.array([3, 5, 7, 10])
     >>> root_mean_squared_error(true_labels, predicted_probs)
-    3.42
-
-    >>> true_labels = [2, 4, 6, 8]
-    >>> predicted_probs = [3, 5, 7, 10]
-    >>> root_mean_squared_error(true_labels, predicted_probs)
-    1.2247
+    1.3228
 
     >>> true_labels = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
     >>> predicted_probs = np.array([0.3, 0.8, 0.9, 0.2])
@@ -703,7 +698,7 @@ def root_mean_squared_error(y_true, y_pred):
         raise ValueError("Input arrays must have the same length.")
     y_true, y_pred = np.array(y_true), np.array(y_pred)
 
-    mse = np.mean((y_pred - y_true) ** 2)
+    mse = np.mean((y_true - y_pred) ** 2)
     return np.sqrt(mse)