Merge pull request #16 from UBC-MDS/mae

Add Mean Absolute Error (MAE) function with detailed documentation

src/matrics_calculator/MAE.py

@@ -0,0 +1,34 @@
+# Mean Absolute Error (MAE) calculation
+def mean_absolute_error(y_true, y_pred):
+    """
+    Calculate the Mean Absolute Error (MAE) metric for regression.
+
+    This function computes the average absolute difference between the predicted values (`y_pred`) 
+    and the actual values (`y_true`). It measures the magnitude of errors in prediction, providing 
+    a straightforward evaluation of a model's accuracy.
+
+    Parameters:
+    ----------
+    y_true : array-like
+        True values of the target variable.
+    y_pred : array-like
+        Predicted values from the model.
+
+    Returns:
+    -------
+    float
+        The Mean Absolute Error.
+
+    Notes:
+    ------
+    MAE is defined as:
+        MAE = (1 / n) * sum(|y_true - y_pred|)
+    where n is the number of observations.
+
+    Examples:
+    ---------
+    >>> y_true = [100, 200, 300]
+    >>> y_pred = [110, 190, 290]
+    >>> mean_absolute_error(y_true, y_pred)
+    10.0
+    """