[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

machine_learning/multilayer_perceptron_classifier_from_scratch.py

@@ -2,7 +2,10 @@
 from tqdm import tqdm
 from numpy.random import default_rng
 from numpy.random import seed
+
 seed(42)
+
+
 class Dataloader:
     """
     DataLoader class for handling dataset, including data shuffling, one-hot encoding, and train-test splitting.
@@ -45,7 +48,9 @@ def __init__(self, features: list[list[float]], labels: list[int]) -> None:
         self.y = np.array(labels)
         self.class_weights = {0: 1.0, 1: 1.0}  # Example class weights, adjust as needed
 
-    def get_Train_test_data(self) -> tuple[list[np.ndarray], list[np.ndarray], list[np.ndarray], list[np.ndarray]]:
+    def get_Train_test_data(
+        self,
+    ) -> tuple[list[np.ndarray], list[np.ndarray], list[np.ndarray], list[np.ndarray]]:
         """
         Splits the data into training and testing sets. Here, we manually split the data.
 
@@ -56,13 +61,21 @@ def get_Train_test_data(self) -> tuple[list[np.ndarray], list[np.ndarray], list[
             - Test data
             - Test labels
         """
-        train_data = np.array([self.X[0], self.X[1], self.X[2]])  # First 3 samples for training
-        train_labels = [np.array([self.y[0]]), np.array([self.y[1]]), np.array([self.y[2]])]  # Labels as np.ndarray
+        train_data = np.array(
+            [self.X[0], self.X[1], self.X[2]]
+        )  # First 3 samples for training
+        train_labels = [
+            np.array([self.y[0]]),
+            np.array([self.y[1]]),
+            np.array([self.y[2]]),
+        ]  # Labels as np.ndarray
         test_data = np.array([self.X[3]])  # Last sample for testing
         test_labels = [np.array([self.y[3]])]  # Labels as np.ndarray
         return train_data, train_labels, test_data, test_labels
 
-    def shuffle_data(self, paired_data: list[tuple[np.ndarray, int]]) -> list[tuple[np.ndarray, int]]:
+    def shuffle_data(
+        self, paired_data: list[tuple[np.ndarray, int]]
+    ) -> list[tuple[np.ndarray, int]]:
         """
         Shuffles the data randomly.
 
@@ -99,40 +112,43 @@ def one_hot_encode(labels: list[int], num_classes: int) -> np.ndarray:
         return one_hot
 
 
-class MLP():
+class MLP:
+    """
+    A custom MLP class for implementing a simple multi-layer perceptron with
+    forward propagation, backpropagation.
+
+    Attributes:
+        learning_rate (float): Learning rate for gradient descent.
+        gamma (float): Parameter to control learning rate adjustment.
+        epoch (int): Number of epochs for training.
+        hidden_dim (int): Dimension of the hidden layer.
+        batch_size (int): Number of samples per mini-batch.
+        train_loss (List[float]): List to store training loss for each fold.
+        train_accuracy (List[float]): List to store training accuracy for each fold.
+        test_loss (List[float]): List to store test loss for each fold.
+        test_accuracy (List[float]): List to store test accuracy for each fold.
+        dataloader (Dataloader): DataLoader object for handling training data.
+        inter_variable (dict): Dictionary to store intermediate variables for backpropagation.
+        weights1_list (List[Tuple[np.ndarray, np.ndarray]]): List of weights for each fold.
+
+    Methods:
+        get_inout_dim:obtain input dimension and output dimension.
+        relu: Apply the ReLU activation function.
+        relu_derivative: Compute the derivative of the ReLU function.
+        forward: Perform a forward pass through the network.
+        back_prop: Perform backpropagation to compute gradients.
+        update_weights: Update the weights using gradients.
+        update_learning_rate: Adjust the learning rate based on test accuracy.
+        accuracy: Compute accuracy of the model.
+        loss: Compute weighted MSE loss.
+        train: Train the MLP over multiple folds with early stopping.
+
+
     """
-        A custom MLP class for implementing a simple multi-layer perceptron with
-        forward propagation, backpropagation.
-
-        Attributes:
-            learning_rate (float): Learning rate for gradient descent.
-            gamma (float): Parameter to control learning rate adjustment.
-            epoch (int): Number of epochs for training.
-            hidden_dim (int): Dimension of the hidden layer.
-            batch_size (int): Number of samples per mini-batch.
-            train_loss (List[float]): List to store training loss for each fold.
-            train_accuracy (List[float]): List to store training accuracy for each fold.
-            test_loss (List[float]): List to store test loss for each fold.
-            test_accuracy (List[float]): List to store test accuracy for each fold.
-            dataloader (Dataloader): DataLoader object for handling training data.
-            inter_variable (dict): Dictionary to store intermediate variables for backpropagation.
-            weights1_list (List[Tuple[np.ndarray, np.ndarray]]): List of weights for each fold.
-
-        Methods:
-            get_inout_dim:obtain input dimension and output dimension.
-            relu: Apply the ReLU activation function.
-            relu_derivative: Compute the derivative of the ReLU function.
-            forward: Perform a forward pass through the network.
-            back_prop: Perform backpropagation to compute gradients.
-            update_weights: Update the weights using gradients.
-            update_learning_rate: Adjust the learning rate based on test accuracy.
-            accuracy: Compute accuracy of the model.
-            loss: Compute weighted MSE loss.
-            train: Train the MLP over multiple folds with early stopping.
-
-
-        """
-    def __init__(self, dataloader, epoch: int, learning_rate: float, gamma=1, hidden_dim=2):
+
+    def __init__(
+        self, dataloader, epoch: int, learning_rate: float, gamma=1, hidden_dim=2
+    ):
         self.learning_rate = learning_rate  #
         self.gamma = gamma  # learning_rate decay hyperparameter gamma
         self.epoch = epoch
@@ -215,13 +231,12 @@ def relu_derivative(self, input_array: np.ndarray) -> np.ndarray:
         """
         return (input_array > 0).astype(float)
 
-
     def forward(
-            self,
-            input_data: np.ndarray,
-            W1: np.ndarray,
-            W2: np.ndarray,
-            no_gradient: bool = False
+        self,
+        input_data: np.ndarray,
+        W1: np.ndarray,
+        W2: np.ndarray,
+        no_gradient: bool = False,
     ) -> np.ndarray:
         """
         Performs a forward pass through the neural network with one hidden layer.
@@ -261,11 +276,11 @@ def forward(
             return a2
 
     def back_prop(
-            self,
-            input_data: np.ndarray,
-            true_labels: np.ndarray,
-            W1: np.ndarray,
-            W2: np.ndarray
+        self,
+        input_data: np.ndarray,
+        true_labels: np.ndarray,
+        W1: np.ndarray,
+        W2: np.ndarray,
     ) -> tuple[np.ndarray, np.ndarray]:
         """
         Performs backpropagation to compute gradients for the weights.
@@ -307,20 +322,22 @@ def back_prop(
         grad_w2 = (
             np.dot(a1.T, delta_k) / batch_size
         )  # (hidden, batch).dot(batch, output) = (hidden, output)
-        input_data_flat = input_data.reshape(input_data.shape[0], -1)  # (batch_size, input_dim)
+        input_data_flat = input_data.reshape(
+            input_data.shape[0], -1
+        )  # (batch_size, input_dim)
         grad_w1 = (
             np.dot(input_data_flat.T, delta_j) / batch_size
         )  # (input_dim, batch_size).dot(batch, hidden) = (input, hidden)
 
         return grad_w1, grad_w2
 
     def update_weights(
-            self,
-            w1: np.ndarray,
-            w2: np.ndarray,
-            grad_w1: np.ndarray,
-            grad_w2: np.ndarray,
-            learning_rate: float
+        self,
+        w1: np.ndarray,
+        w2: np.ndarray,
+        grad_w1: np.ndarray,
+        grad_w2: np.ndarray,
+        learning_rate: float,
     ) -> tuple[np.ndarray, np.ndarray]:
         """
         Updates the weight matrices using the computed gradients and learning rate.
@@ -355,7 +372,6 @@ def update_weights(
         w2 -= learning_rate * grad_w2
         return w1, w2
 
-
     def update_learning_rate(self, learning_rate: float) -> float:
         """
         Updates the learning rate by applying the decay factor gamma.
@@ -451,12 +467,13 @@ def train(self) -> None:
         """
 
         learning_rate = self.learning_rate
-        train_data, train_labels, test_data, test_labels = self.dataloader.get_Train_test_data()
+        train_data, train_labels, test_data, test_labels = (
+            self.dataloader.get_Train_test_data()
+        )
 
         train_data = np.c_[train_data, np.ones(train_data.shape[0])]
         test_data = np.c_[test_data, np.ones(test_data.shape[0])]
 
-
         _, total_label_num = self.dataloader.get_inout_dim()
 
         train_labels = self.dataloader.one_hot_encode(train_labels, total_label_num)
@@ -471,13 +488,16 @@ def train(self) -> None:
 
         for j in tqdm(range(self.epoch)):
             for k in range(0, train_data.shape[0], batch_size):  # retrieve every image
+                batch_imgs = train_data[k : k + batch_size]
+                batch_labels = train_labels[k : k + batch_size]
 
-                batch_imgs = train_data[k: k + batch_size]
-                batch_labels = train_labels[k: k + batch_size]
-
-                output = self.forward(input_data=batch_imgs, W1=W1, W2=W2, no_gradient=False)
+                output = self.forward(
+                    input_data=batch_imgs, W1=W1, W2=W2, no_gradient=False
+                )
 
-                grad_W1, grad_W2 = self.back_prop(input_data=batch_imgs, true_labels=batch_labels, W1=W1, W2=W2)
+                grad_W1, grad_W2 = self.back_prop(
+                    input_data=batch_imgs, true_labels=batch_labels, W1=W1, W2=W2
+                )
 
                 W1, W2 = self.update_weights(W1, W2, grad_W1, grad_W2, learning_rate)
 
@@ -492,10 +512,10 @@ def train(self) -> None:
 
         self.test_accuracy = test_accuracy_list
         self.test_loss = test_loss_list
-        print(f"Test accuracy:", sum(test_accuracy_list)/len(test_accuracy_list))
+        print(f"Test accuracy:", sum(test_accuracy_list) / len(test_accuracy_list))
 
 
 if __name__ == "__main__":
     import doctest
 
-    doctest.testmod()
+    doctest.testmod()