fix: Feedback changed fixed from Sarah by Celine

README.md

@@ -12,18 +12,21 @@ matrics_calculator provides a lightweight and easy-to-use alternative for calcul
 This package consists of four functions:
 - `r2`:
     - This function calculates the R-squared of the model, which measures how well the model explains the variation in the data. 
-- `mean_absolute_error`: 
+- `MAE`: 
     - This function finds the average difference between predicted and actual values.
-- `mean_squared_error`:
-    - This function calculates the average of the squared differences between predictions and actual values. 
-- `mean_absolute_percentage_error`:
+- `MSE`:
+    - This fuction calculates the average of the squared differences between predictions and actual values. 
+- `MAPE`:
     - This function shows prediction error as a percentage, making it easy to understand.
 
 ##  matrics_calculator in the Python Ecosystem
 
 `matrics_calculator` works alongside Python libraries like `scikit-learn` by providing simple implementations of regression metrics. Unlike `scikit-learn`’s full toolkit for modeling and evaluation, this package focuses only on metrics, making it easy to use for quick analysis or custom workflows.
 
 ## Installation
+
+`matrics_calculator` requires Python **3.7 or later**.
+
 To install the package, navigate to the root directory of the project and run:
 ```bash
 $ pip install matrics_calculator

src/matrics_calculator/MAE.py

@@ -32,8 +32,11 @@ def mean_absolute_error(y_true, y_pred):
     >>> mean_absolute_error(y_true, y_pred)
     10.0
     """
+    # Ensure the input lists have the same length; otherwise, raise an error
     if len(y_true) != len(y_pred):
         raise ValueError("The lengths of y_true and y_pred must be the same.")
 
+    # Compute the absolute differences between actual and predicted values, sum them, 
+    # and divide by the total number of observations to calculate MAE
     mae = sum(abs(true - pred) for true, pred in zip(y_true, y_pred)) / len(y_true)
     return mae

src/matrics_calculator/MSE.py

@@ -22,6 +22,10 @@ def mean_squared_error(y_true, y_pred):
 
     Notes
     -----
+    MSE is defined as:
+        MSE = (1 / n) * sum((y_true - y_pred)²)
+    where `n` is the number of observations.
+
     This function assumes that the input `y_true` and `y_pred` have the same length.
 
     Examples
@@ -31,9 +35,13 @@ def mean_squared_error(y_true, y_pred):
     >>> mean_squared_error(y_true, y_pred)
     0.375
     """
+
+    # Ensure the input lists have the same length; otherwise, raise an error
     if len(y_true) != len(y_pred):
         raise ValueError("The lengths of y_true and y_pred must be the same.")
-
+
+    # Compute the squared differences between actual and predicted values, sum them, 
+    # and divide by the total number of observations to calculate MSE
     mse = sum((true - pred) ** 2 for true, pred in zip(y_true, y_pred)) / len(y_true)
     return mse
 

src/matrics_calculator/r2.py

@@ -35,23 +35,35 @@ def r2(y_pred, y_true):
     from sklearn.linear_model import LinearRegression
     import numpy as np
 
+   # Ensure inputs are lists    
     if not isinstance(y_pred, list) or not isinstance(y_pred, list):
         print('Input must be lists')
         return None
-
+
+    # Check for empty lists
     if len(y_pred) == 0 or len(y_true) == 0:
         print('Input cannot be empty')
         return None
-
+
+    # Convert lists to NumPy arrays if they are still   in list format        
     if isinstance(y_pred,list):
         y_pred = np.array(y_pred)
     if isinstance(y_true,list):
         y_true = np.array(y_true)
 
+    # Create a linear regression model and fit it to the data         
     model = LinearRegression()
     model.fit(y_pred.reshape(-1,1),y_true)
     y_true_predicted =  model.predict(y_pred.reshape(-1,1))
+
+    # Calculate the mean of y_true
     y_true_mean = np.mean(y_true)
+
+    # Compute Residual Sum of Squares
     RSS = sum(((y_true-y_true_predicted) ** 2))
+
+    # Compute Total Sum of Squares (TSS)   
     TSS = sum(((y_true-y_true_mean) ** 2))
+
+    # Compute R-squared value and round it to 3 decimal places
     return round(1 - (RSS/TSS),3)