From eec42adec8e24c349d9721bc1b9290d1c8f5d4a3 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:13:06 +0600
Subject: [PATCH 01/24] Add __init__.py file

---
 machine_learning/neural_network/__init__.py | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 machine_learning/neural_network/__init__.py

diff --git a/machine_learning/neural_network/__init__.py b/machine_learning/neural_network/__init__.py
new file mode 100644
index 000000000000..e69de29bb2d1

From 836c8ac4f8649a6cd851090a98a63dc4ee460434 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:15:20 +0600
Subject: [PATCH 02/24] Add __init__.py file

---
 machine_learning/{neural_network => neural_networks}/__init__.py | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename machine_learning/{neural_network => neural_networks}/__init__.py (100%)

diff --git a/machine_learning/neural_network/__init__.py b/machine_learning/neural_networks/__init__.py
similarity index 100%
rename from machine_learning/neural_network/__init__.py
rename to machine_learning/neural_networks/__init__.py

From 74b6229caea3becb75c4d72fd86563871f9a70d1 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:25:01 +0600
Subject: [PATCH 03/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 .../neural_networks/fully_connected_mnist.py  | 53 +++++++++++++++++++
 1 file changed, 53 insertions(+)
 create mode 100644 machine_learning/neural_networks/fully_connected_mnist.py

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
new file mode 100644
index 000000000000..6540aac40d56
--- /dev/null
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -0,0 +1,53 @@
+import tensorflow as tf
+from tensorflow.keras import layers, models
+import numpy as np
+
+# Load the MNIST dataset from Keras
+mnist = tf.keras.datasets.mnist
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+# Normalize the images from 0-255 to 0-1 by dividing by 255
+X_train, X_test = X_train / 255.0, X_test / 255.0
+
+# Print TensorFlow and Keras information
+print(f"TensorFlow Version: {tf.__version__}")
+print(f"Keras Layers Module: {layers.__name__}")
+print(f"Keras Models Module: {models.__name__}")
+
+# Build a simple Sequential model
+model = models.Sequential()
+
+# Flatten the 28x28 images into vectors of length 784
+model.add(layers.Flatten(input_shape=(28, 28)))
+
+# First hidden layer with 128 neurons and ReLU activation
+model.add(layers.Dense(128, activation='relu'))
+
+# Dropout layer to prevent overfitting (randomly drops 20% of neurons)
+model.add(layers.Dropout(0.2))
+
+# Second hidden layer with 64 neurons and ReLU activation
+model.add(layers.Dense(64, activation='relu'))
+
+# Output layer with 10 neurons (one for each digit class 0-9), softmax for probabilities
+model.add(layers.Dense(10, activation='softmax'))
+
+# Compile the model
+model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+
+# Train the model on the MNIST training data
+model.fit(X_train, y_train, epochs=5, batch_size=32)
+
+# Evaluate the model on the test set
+test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
+print(f'\nTest accuracy: {test_acc}')
+
+# Make a prediction on a random test image
+random_index = np.random.randint(0, len(X_test))
+random_image = np.expand_dims(X_test[random_index], axis=0)
+prediction = model.predict(random_image)
+predicted_digit = np.argmax(prediction)
+
+# Print the predicted result and actual label
+print(f'Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}')
+

From f4e3b979dcb46942b69a1a53df19421157764410 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:35:16 +0600
Subject: [PATCH 04/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 .../neural_networks/fully_connected_mnist.py       | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index 6540aac40d56..ec6821b19828 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -1,3 +1,17 @@
+"""
+Fully Connected Neural Network for MNIST Classification
+
+Goal: This script implements a fully connected feed-forward neural network using TensorFlow and Keras to classify the
+    MNIST dataset (28x28 grayscale images of handwritten digits from 0 to 9). The network has two hidden layers with ReLU
+    activations and dropout for regularization.
+
+Objectives:
+- Normalize and preprocess MNIST data.
+- Build a basic neural network with dense layers.
+- Train the model, evaluate its accuracy and loss at each epoch, and predict sample outputs.
+"""
+
+
 import tensorflow as tf
 from tensorflow.keras import layers, models
 import numpy as np

From bc1f9b98dc4571b62c857ab9ba07dd3a8f2a312f Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:39:19 +0600
Subject: [PATCH 05/24] cnn_mnist.py: For the Convolutional Neural Network
 (CNN) model.

---
 machine_learning/neural_networks/cnn_mnist.py | 70 +++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 machine_learning/neural_networks/cnn_mnist.py

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
new file mode 100644
index 000000000000..b6611a497253
--- /dev/null
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -0,0 +1,70 @@
+"""
+Convolutional Neural Network (CNN) for MNIST Classification
+
+Goal: This script builds a deep CNN to classify the MNIST dataset using TensorFlow and Keras. It leverages
+    convolutional layers for feature extraction and pooling layers for down-sampling, followed by fully connected layers
+    for classification.
+
+Objectives:
+- Load and preprocess MNIST data (reshape for CNN input).
+- Build a CNN with multiple convolutional, pooling, and batch normalization layers.
+- Train the CNN, evaluate its accuracy, and display model performance.
+
+"""
+
+
+import tensorflow as tf
+from tensorflow.keras import layers, models
+from tensorflow.keras.datasets import mnist
+from tensorflow.keras.utils import to_categorical
+
+# Load and preprocess the MNIST data
+(X_train, y_train), (X_test, y_test) = mnist.load_data()
+
+# Normalize the pixel values (0 to 1)
+X_train = X_train.reshape(-1, 28, 28, 1).astype('float32') / 255
+X_test = X_test.reshape(-1, 28, 28, 1).astype('float32') / 255
+
+# Convert labels to one-hot encoding
+y_train = to_categorical(y_train, 10)
+y_test = to_categorical(y_test, 10)
+
+# Building the CNN model
+model = models.Sequential()
+
+# 1st Convolutional Layer
+model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
+model.add(layers.MaxPooling2D((2, 2)))
+model.add(layers.BatchNormalization())
+
+# 2nd Convolutional Layer
+model.add(layers.Conv2D(64, (3, 3), activation='relu'))
+model.add(layers.MaxPooling2D((2, 2)))
+model.add(layers.BatchNormalization())
+
+# 3rd Convolutional Layer
+model.add(layers.Conv2D(128, (3, 3), activation='relu'))
+model.add(layers.BatchNormalization())
+
+# Flattening the data before fully connected layers
+model.add(layers.Flatten())
+
+# Fully Connected (Dense) Layer with Dropout for regularization
+model.add(layers.Dense(128, activation='relu'))
+model.add(layers.Dropout(0.5))
+
+# Output Layer for classification
+model.add(layers.Dense(10, activation='softmax'))
+
+# Compile the model
+model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+
+# Display the model summary
+model.summary()
+
+# Train the model
+history = model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))
+
+# Evaluate the model on test data
+test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
+print(f'\nTest accuracy: {test_acc}')

From 96c374a820825d54d8bb46b3608c76ba065c38f0 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 01:40:08 +0600
Subject: [PATCH 06/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 machine_learning/neural_networks/fully_connected_mnist.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index ec6821b19828..f6bd7d07c048 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -64,4 +64,3 @@
 
 # Print the predicted result and actual label
 print(f'Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}')
-

From e4dcab860f28ebb6e39a3e67a410c6b2d42c0e2d Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 18 Sep 2024 20:04:55 +0000
Subject: [PATCH 07/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/neural_networks/cnn_mnist.py | 23 ++++++++++---------
 .../neural_networks/fully_connected_mnist.py  | 15 ++++++------
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index b6611a497253..4f9c2a342dd9 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -12,7 +12,6 @@
 
 """
 
-
 import tensorflow as tf
 from tensorflow.keras import layers, models
 from tensorflow.keras.datasets import mnist
@@ -22,8 +21,8 @@
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 
 # Normalize the pixel values (0 to 1)
-X_train = X_train.reshape(-1, 28, 28, 1).astype('float32') / 255
-X_test = X_test.reshape(-1, 28, 28, 1).astype('float32') / 255
+X_train = X_train.reshape(-1, 28, 28, 1).astype("float32") / 255
+X_test = X_test.reshape(-1, 28, 28, 1).astype("float32") / 255
 
 # Convert labels to one-hot encoding
 y_train = to_categorical(y_train, 10)
@@ -33,38 +32,40 @@
 model = models.Sequential()
 
 # 1st Convolutional Layer
-model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
+model.add(layers.Conv2D(32, (3, 3), activation="relu", input_shape=(28, 28, 1)))
 model.add(layers.MaxPooling2D((2, 2)))
 model.add(layers.BatchNormalization())
 
 # 2nd Convolutional Layer
-model.add(layers.Conv2D(64, (3, 3), activation='relu'))
+model.add(layers.Conv2D(64, (3, 3), activation="relu"))
 model.add(layers.MaxPooling2D((2, 2)))
 model.add(layers.BatchNormalization())
 
 # 3rd Convolutional Layer
-model.add(layers.Conv2D(128, (3, 3), activation='relu'))
+model.add(layers.Conv2D(128, (3, 3), activation="relu"))
 model.add(layers.BatchNormalization())
 
 # Flattening the data before fully connected layers
 model.add(layers.Flatten())
 
 # Fully Connected (Dense) Layer with Dropout for regularization
-model.add(layers.Dense(128, activation='relu'))
+model.add(layers.Dense(128, activation="relu"))
 model.add(layers.Dropout(0.5))
 
 # Output Layer for classification
-model.add(layers.Dense(10, activation='softmax'))
+model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
 
 # Display the model summary
 model.summary()
 
 # Train the model
-history = model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))
+history = model.fit(
+    X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test)
+)
 
 # Evaluate the model on test data
 test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
-print(f'\nTest accuracy: {test_acc}')
+print(f"\nTest accuracy: {test_acc}")
diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index f6bd7d07c048..a716043a4d2e 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -11,7 +11,6 @@
 - Train the model, evaluate its accuracy and loss at each epoch, and predict sample outputs.
 """
 
-
 import tensorflow as tf
 from tensorflow.keras import layers, models
 import numpy as np
@@ -35,26 +34,28 @@
 model.add(layers.Flatten(input_shape=(28, 28)))
 
 # First hidden layer with 128 neurons and ReLU activation
-model.add(layers.Dense(128, activation='relu'))
+model.add(layers.Dense(128, activation="relu"))
 
 # Dropout layer to prevent overfitting (randomly drops 20% of neurons)
 model.add(layers.Dropout(0.2))
 
 # Second hidden layer with 64 neurons and ReLU activation
-model.add(layers.Dense(64, activation='relu'))
+model.add(layers.Dense(64, activation="relu"))
 
 # Output layer with 10 neurons (one for each digit class 0-9), softmax for probabilities
-model.add(layers.Dense(10, activation='softmax'))
+model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+model.compile(
+    optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
+)
 
 # Train the model on the MNIST training data
 model.fit(X_train, y_train, epochs=5, batch_size=32)
 
 # Evaluate the model on the test set
 test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
-print(f'\nTest accuracy: {test_acc}')
+print(f"\nTest accuracy: {test_acc}")
 
 # Make a prediction on a random test image
 random_index = np.random.randint(0, len(X_test))
@@ -63,4 +64,4 @@
 predicted_digit = np.argmax(prediction)
 
 # Print the predicted result and actual label
-print(f'Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}')
+print(f"Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}")

From 1a69f8ae996cd393c01d2fc8f33bbac7bdbf0a8f Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 02:40:17 +0600
Subject: [PATCH 08/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 .../neural_networks/fully_connected_mnist.py   | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index f6bd7d07c048..e84a422b178a 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -1,20 +1,25 @@
 """
 Fully Connected Neural Network for MNIST Classification
 
-Goal: This script implements a fully connected feed-forward neural network using TensorFlow and Keras to classify the
-    MNIST dataset (28x28 grayscale images of handwritten digits from 0 to 9). The network has two hidden layers with ReLU
-    activations and dropout for regularization.
+Goal: This script implements a fully connected feed-forward neural network
+    using TensorFlow and Keras to classify the MNIST dataset (28x28 grayscale
+    images of handwritten digits from 0 to 9).
+    The network has two hidden layers with ReLU activations and dropout
+    for regularization.
 
 Objectives:
 - Normalize and preprocess MNIST data.
 - Build a basic neural network with dense layers.
-- Train the model, evaluate its accuracy and loss at each epoch, and predict sample outputs.
+- Train the model, evaluate its accuracy and loss at each epoch,
+  and predict sample outputs.
+
 """
 
 
+import numpy as np
 import tensorflow as tf
 from tensorflow.keras import layers, models
-import numpy as np
+
 
 # Load the MNIST dataset from Keras
 mnist = tf.keras.datasets.mnist
@@ -57,7 +62,8 @@
 print(f'\nTest accuracy: {test_acc}')
 
 # Make a prediction on a random test image
-random_index = np.random.randint(0, len(X_test))
+rng = np.random.default_rng()
+random_index = rng.integers(0, len(X_test))
 random_image = np.expand_dims(X_test[random_index], axis=0)
 prediction = model.predict(random_image)
 predicted_digit = np.argmax(prediction)

From 860c0c2bd481646de453c256d265c8f4d3ee1a09 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 02:40:30 +0600
Subject: [PATCH 09/24] cnn_mnist.py: For the Convolutional Neural Network
 (CNN) model.

---
 machine_learning/neural_networks/cnn_mnist.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index b6611a497253..7ec691f4c8c2 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -1,9 +1,10 @@
 """
 Convolutional Neural Network (CNN) for MNIST Classification
 
-Goal: This script builds a deep CNN to classify the MNIST dataset using TensorFlow and Keras. It leverages
-    convolutional layers for feature extraction and pooling layers for down-sampling, followed by fully connected layers
-    for classification.
+Goal: This script builds a deep CNN to classify the MNIST dataset
+    using TensorFlow and Keras. It leverages convolutional layers
+    for feature extraction and pooling layers for down-sampling,
+    followed by fully connected layers for classification.
 
 Objectives:
 - Load and preprocess MNIST data (reshape for CNN input).
@@ -13,7 +14,7 @@
 """
 
 
-import tensorflow as tf
+# import tensorflow as tf
 from tensorflow.keras import layers, models
 from tensorflow.keras.datasets import mnist
 from tensorflow.keras.utils import to_categorical

From 99a58be312d130c7971e8ff2b4c7f3612f44393a Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 18 Sep 2024 20:43:37 +0000
Subject: [PATCH 10/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/neural_networks/cnn_mnist.py | 23 ++++++++++---------
 .../neural_networks/fully_connected_mnist.py  | 15 ++++++------
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index b6611a497253..4f9c2a342dd9 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -12,7 +12,6 @@
 
 """
 
-
 import tensorflow as tf
 from tensorflow.keras import layers, models
 from tensorflow.keras.datasets import mnist
@@ -22,8 +21,8 @@
 (X_train, y_train), (X_test, y_test) = mnist.load_data()
 
 # Normalize the pixel values (0 to 1)
-X_train = X_train.reshape(-1, 28, 28, 1).astype('float32') / 255
-X_test = X_test.reshape(-1, 28, 28, 1).astype('float32') / 255
+X_train = X_train.reshape(-1, 28, 28, 1).astype("float32") / 255
+X_test = X_test.reshape(-1, 28, 28, 1).astype("float32") / 255
 
 # Convert labels to one-hot encoding
 y_train = to_categorical(y_train, 10)
@@ -33,38 +32,40 @@
 model = models.Sequential()
 
 # 1st Convolutional Layer
-model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
+model.add(layers.Conv2D(32, (3, 3), activation="relu", input_shape=(28, 28, 1)))
 model.add(layers.MaxPooling2D((2, 2)))
 model.add(layers.BatchNormalization())
 
 # 2nd Convolutional Layer
-model.add(layers.Conv2D(64, (3, 3), activation='relu'))
+model.add(layers.Conv2D(64, (3, 3), activation="relu"))
 model.add(layers.MaxPooling2D((2, 2)))
 model.add(layers.BatchNormalization())
 
 # 3rd Convolutional Layer
-model.add(layers.Conv2D(128, (3, 3), activation='relu'))
+model.add(layers.Conv2D(128, (3, 3), activation="relu"))
 model.add(layers.BatchNormalization())
 
 # Flattening the data before fully connected layers
 model.add(layers.Flatten())
 
 # Fully Connected (Dense) Layer with Dropout for regularization
-model.add(layers.Dense(128, activation='relu'))
+model.add(layers.Dense(128, activation="relu"))
 model.add(layers.Dropout(0.5))
 
 # Output Layer for classification
-model.add(layers.Dense(10, activation='softmax'))
+model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
 
 # Display the model summary
 model.summary()
 
 # Train the model
-history = model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))
+history = model.fit(
+    X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test)
+)
 
 # Evaluate the model on test data
 test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
-print(f'\nTest accuracy: {test_acc}')
+print(f"\nTest accuracy: {test_acc}")
diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index f6bd7d07c048..a716043a4d2e 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -11,7 +11,6 @@
 - Train the model, evaluate its accuracy and loss at each epoch, and predict sample outputs.
 """
 
-
 import tensorflow as tf
 from tensorflow.keras import layers, models
 import numpy as np
@@ -35,26 +34,28 @@
 model.add(layers.Flatten(input_shape=(28, 28)))
 
 # First hidden layer with 128 neurons and ReLU activation
-model.add(layers.Dense(128, activation='relu'))
+model.add(layers.Dense(128, activation="relu"))
 
 # Dropout layer to prevent overfitting (randomly drops 20% of neurons)
 model.add(layers.Dropout(0.2))
 
 # Second hidden layer with 64 neurons and ReLU activation
-model.add(layers.Dense(64, activation='relu'))
+model.add(layers.Dense(64, activation="relu"))
 
 # Output layer with 10 neurons (one for each digit class 0-9), softmax for probabilities
-model.add(layers.Dense(10, activation='softmax'))
+model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+model.compile(
+    optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
+)
 
 # Train the model on the MNIST training data
 model.fit(X_train, y_train, epochs=5, batch_size=32)
 
 # Evaluate the model on the test set
 test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
-print(f'\nTest accuracy: {test_acc}')
+print(f"\nTest accuracy: {test_acc}")
 
 # Make a prediction on a random test image
 random_index = np.random.randint(0, len(X_test))
@@ -63,4 +64,4 @@
 predicted_digit = np.argmax(prediction)
 
 # Print the predicted result and actual label
-print(f'Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}')
+print(f"Predicted digit: {predicted_digit}, Actual digit: {y_test[random_index]}")

From c004e54419024a9342eb59e98030ff7d90a79cc7 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 02:45:56 +0600
Subject: [PATCH 11/24] cnn_mnist.py: For the Convolutional Neural Network
 (CNN) model.

---
 machine_learning/neural_networks/cnn_mnist.py | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index 4f9c2a342dd9..5a4bbe70dfeb 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -1,9 +1,10 @@
 """
 Convolutional Neural Network (CNN) for MNIST Classification
 
-Goal: This script builds a deep CNN to classify the MNIST dataset using TensorFlow and Keras. It leverages
-    convolutional layers for feature extraction and pooling layers for down-sampling, followed by fully connected layers
-    for classification.
+Goal: This script builds a deep CNN to classify the MNIST dataset using
+    TensorFlow and Keras. It leverages convolutional layers for feature
+    extraction and pooling layers for down-sampling, followed by fully
+    connected layers for classification.
 
 Objectives:
 - Load and preprocess MNIST data (reshape for CNN input).
@@ -12,7 +13,7 @@
 
 """
 
-import tensorflow as tf
+# import tensorflow as tf
 from tensorflow.keras import layers, models
 from tensorflow.keras.datasets import mnist
 from tensorflow.keras.utils import to_categorical
@@ -56,7 +57,8 @@
 model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
+model.compile(optimizer="adam", loss="categorical_crossentropy",
+              metrics=["accuracy"])
 
 # Display the model summary
 model.summary()

From 35b13cf831057c4078f76836318fb493fe2fa5fb Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 18 Sep 2024 20:46:46 +0000
Subject: [PATCH 12/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/neural_networks/cnn_mnist.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index 5a4bbe70dfeb..e4ef937b60bd 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -57,8 +57,7 @@
 model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer="adam", loss="categorical_crossentropy",
-              metrics=["accuracy"])
+model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
 
 # Display the model summary
 model.summary()

From 83e5295f760a03532f3503b389bf6f370cce3c79 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 02:48:19 +0600
Subject: [PATCH 13/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 .../neural_networks/fully_connected_mnist.py  | 24 ++++++++++++-------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index a716043a4d2e..30d951e1f67e 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -1,19 +1,24 @@
 """
 Fully Connected Neural Network for MNIST Classification
 
-Goal: This script implements a fully connected feed-forward neural network using TensorFlow and Keras to classify the
-    MNIST dataset (28x28 grayscale images of handwritten digits from 0 to 9). The network has two hidden layers with ReLU
-    activations and dropout for regularization.
+Goal: This script implements a fully connected feed-forward neural network
+    using TensorFlow and Keras to classify the MNIST dataset
+    (28x28 grayscale images of handwritten digits from 0 to 9).
+    The network has two hidden layers with ReLU activations and dropout
+    for regularization.
 
 Objectives:
 - Normalize and preprocess MNIST data.
 - Build a basic neural network with dense layers.
-- Train the model, evaluate its accuracy and loss at each epoch, and predict sample outputs.
+- Train the model, evaluate its accuracy and loss at each epoch,
+  and predict sample outputs.
+
 """
 
+import numpy as np
 import tensorflow as tf
 from tensorflow.keras import layers, models
-import numpy as np
+
 
 # Load the MNIST dataset from Keras
 mnist = tf.keras.datasets.mnist
@@ -42,12 +47,14 @@
 # Second hidden layer with 64 neurons and ReLU activation
 model.add(layers.Dense(64, activation="relu"))
 
-# Output layer with 10 neurons (one for each digit class 0-9), softmax for probabilities
+# Output layer with 10 neurons (one for each digit class 0-9),
+# softmax for probabilities
 model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
 model.compile(
-    optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
+    optimizer="adam", loss="sparse_categorical_crossentropy",
+    metrics=["accuracy"]
 )
 
 # Train the model on the MNIST training data
@@ -58,7 +65,8 @@
 print(f"\nTest accuracy: {test_acc}")
 
 # Make a prediction on a random test image
-random_index = np.random.randint(0, len(X_test))
+rng = np.random.default_rng()
+random_index = rng.integers(0, len(X_test))
 random_image = np.expand_dims(X_test[random_index], axis=0)
 prediction = model.predict(random_image)
 predicted_digit = np.argmax(prediction)

From aa47df00f45579f088833677b4c86913d99df848 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 02:50:25 +0600
Subject: [PATCH 14/24] cnn_mnist.py: For the Convolutional Neural Network
 (CNN) model.

---
 machine_learning/neural_networks/cnn_mnist.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index e4ef937b60bd..5a4bbe70dfeb 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -57,7 +57,8 @@
 model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
+model.compile(optimizer="adam", loss="categorical_crossentropy",
+              metrics=["accuracy"])
 
 # Display the model summary
 model.summary()

From 35ba5dffdfa27b4f90ce349d1c7e413ad47352a1 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 18 Sep 2024 20:51:48 +0000
Subject: [PATCH 15/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/neural_networks/cnn_mnist.py             | 3 +--
 machine_learning/neural_networks/fully_connected_mnist.py | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index 5a4bbe70dfeb..e4ef937b60bd 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -57,8 +57,7 @@
 model.add(layers.Dense(10, activation="softmax"))
 
 # Compile the model
-model.compile(optimizer="adam", loss="categorical_crossentropy",
-              metrics=["accuracy"])
+model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
 
 # Display the model summary
 model.summary()
diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index 30d951e1f67e..82dd0d75f2c7 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -53,8 +53,7 @@
 
 # Compile the model
 model.compile(
-    optimizer="adam", loss="sparse_categorical_crossentropy",
-    metrics=["accuracy"]
+    optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
 )
 
 # Train the model on the MNIST training data

From 7d69b82bba5511467ee74b2f9204184aceea1cc1 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 03:01:18 +0600
Subject: [PATCH 16/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 machine_learning/neural_networks/fully_connected_mnist.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index 30d951e1f67e..ac7d115af50e 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -15,11 +15,14 @@
 
 """
 
+# Standard library imports
+# (None in this case)
+
+# Third-party imports
 import numpy as np
 import tensorflow as tf
 from tensorflow.keras import layers, models
 
-
 # Load the MNIST dataset from Keras
 mnist = tf.keras.datasets.mnist
 (X_train, y_train), (X_test, y_test) = mnist.load_data()

From 2603c8ac3745581cb70a500295c4cd17deca6bb5 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 03:24:12 +0600
Subject: [PATCH 17/24] fully_connected_mnist.py: For the basic fully connected
 neural network.

---
 .../neural_networks/fully_connected_mnist.py         | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/machine_learning/neural_networks/fully_connected_mnist.py b/machine_learning/neural_networks/fully_connected_mnist.py
index 24da20de8717..1b7188c4c224 100644
--- a/machine_learning/neural_networks/fully_connected_mnist.py
+++ b/machine_learning/neural_networks/fully_connected_mnist.py
@@ -25,10 +25,10 @@
 
 # Load the MNIST dataset from Keras
 mnist = tf.keras.datasets.mnist
-(X_train, y_train), (X_test, y_test) = mnist.load_data()
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
 
 # Normalize the images from 0-255 to 0-1 by dividing by 255
-X_train, X_test = X_train / 255.0, X_test / 255.0
+x_train, x_test = x_train / 255.0, x_test / 255.0
 
 # Print TensorFlow and Keras information
 print(f"TensorFlow Version: {tf.__version__}")
@@ -60,16 +60,16 @@
 )
 
 # Train the model on the MNIST training data
-model.fit(X_train, y_train, epochs=5, batch_size=32)
+model.fit(x_train, y_train, epochs=5, batch_size=32)
 
 # Evaluate the model on the test set
-test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
+test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
 print(f"\nTest accuracy: {test_acc}")
 
 # Make a prediction on a random test image
 rng = np.random.default_rng()
-random_index = rng.integers(0, len(X_test))
-random_image = np.expand_dims(X_test[random_index], axis=0)
+random_index = rng.integers(0, len(x_test))
+random_image = np.expand_dims(x_test[random_index], axis=0)
 prediction = model.predict(random_image)
 predicted_digit = np.argmax(prediction)
 

From 0d9804abbaa2a048da4554fc2f26ccfe8df8c684 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Thu, 19 Sep 2024 03:34:54 +0600
Subject: [PATCH 18/24] cnn_mnist.py: For the Convolutional Neural Network
 (CNN) model.

---
 machine_learning/neural_networks/cnn_mnist.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index e4ef937b60bd..60ca2f10850b 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -19,11 +19,11 @@
 from tensorflow.keras.utils import to_categorical
 
 # Load and preprocess the MNIST data
-(X_train, y_train), (X_test, y_test) = mnist.load_data()
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
 
 # Normalize the pixel values (0 to 1)
-X_train = X_train.reshape(-1, 28, 28, 1).astype("float32") / 255
-X_test = X_test.reshape(-1, 28, 28, 1).astype("float32") / 255
+x_train = x_train.reshape(-1, 28, 28, 1).astype("float32") / 255
+x_test = x_test.reshape(-1, 28, 28, 1).astype("float32") / 255
 
 # Convert labels to one-hot encoding
 y_train = to_categorical(y_train, 10)
@@ -64,9 +64,9 @@
 
 # Train the model
 history = model.fit(
-    X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test)
+    x_train, y_train, epochs=5, batch_size=32, validation_data=(x_test, y_test)
 )
 
 # Evaluate the model on test data
-test_loss, test_acc = model.evaluate(X_test, y_test, verbose=2)
+test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
 print(f"\nTest accuracy: {test_acc}")

From 037b0073632ca959b5a1ae90a6173ddb37c8e4a3 Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Fri, 20 Sep 2024 00:21:14 +0600
Subject: [PATCH 19/24] fixed size sliding window technique

---
 .../sliding_window/fixed_size_window.py       | 59 +++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 data_structures/sliding_window/fixed_size_window.py

diff --git a/data_structures/sliding_window/fixed_size_window.py b/data_structures/sliding_window/fixed_size_window.py
new file mode 100644
index 000000000000..20db7846d395
--- /dev/null
+++ b/data_structures/sliding_window/fixed_size_window.py
@@ -0,0 +1,59 @@
+"""
+Fixed-Size Sliding Window Algorithm
+
+This module contains an implementation of the fixed-size
+sliding window algorithm with doctests.
+
+Examples:
+    >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
+    12
+
+    >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
+    11
+"""
+
+
+def max_sum_subarray(arr: list[int], k: int) -> int:
+    """
+    Find the maximum sum of any subarray of size `k`.
+
+    Args:
+        arr: The input array of integers.
+        k: The size of the subarray.
+
+    Returns:
+        The maximum sum of a subarray of size `k`.
+
+    Raises:
+        ValueError: If the length of the array is less than `k`.
+
+    Examples:
+        >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
+        12
+
+        >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
+        11
+
+        >>> max_sum_subarray([1, 2], 3)
+        Traceback (most recent call last):
+            ...
+        ValueError: Array length must be at least as large as the window size.
+    """
+    if len(arr) < k:
+        raise ValueError("Array length must be at least as large as the window size.")
+
+    max_sum = float('-inf')
+    window_sum = sum(arr[:k])
+    max_sum = max(max_sum, window_sum)
+
+    for i in range(len(arr) - k):
+        window_sum = window_sum - arr[i] + arr[i + k]
+        max_sum = max(max_sum, window_sum)
+
+    return max_sum
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()

From 947ff7f1ced0828cc768639d1592188405352d6f Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Fri, 20 Sep 2024 00:21:28 +0600
Subject: [PATCH 20/24] Add __init__.py file

---
 data_structures/sliding_window/__init__.py | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 data_structures/sliding_window/__init__.py

diff --git a/data_structures/sliding_window/__init__.py b/data_structures/sliding_window/__init__.py
new file mode 100644
index 000000000000..e69de29bb2d1

From 8d068c835d76522763335f296804d3066dd850f3 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 19 Sep 2024 18:22:15 +0000
Subject: [PATCH 21/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 data_structures/sliding_window/fixed_size_window.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/data_structures/sliding_window/fixed_size_window.py b/data_structures/sliding_window/fixed_size_window.py
index 20db7846d395..42a80b7bc9c0 100644
--- a/data_structures/sliding_window/fixed_size_window.py
+++ b/data_structures/sliding_window/fixed_size_window.py
@@ -42,7 +42,7 @@ def max_sum_subarray(arr: list[int], k: int) -> int:
     if len(arr) < k:
         raise ValueError("Array length must be at least as large as the window size.")
 
-    max_sum = float('-inf')
+    max_sum = float("-inf")
     window_sum = sum(arr[:k])
     max_sum = max(max_sum, window_sum)
 

From 33b6162a7320af1e608753f795b4f04e931448be Mon Sep 17 00:00:00 2001
From: asif <asahmed8890@gmail.com>
Date: Fri, 20 Sep 2024 00:34:16 +0600
Subject: [PATCH 22/24] Add __init__.py file

---
 data_structures/sliding_window/__init__.py    |  0
 .../sliding_window/fixed_size_window.py       | 59 -------------------
 2 files changed, 59 deletions(-)
 delete mode 100644 data_structures/sliding_window/__init__.py
 delete mode 100644 data_structures/sliding_window/fixed_size_window.py

diff --git a/data_structures/sliding_window/__init__.py b/data_structures/sliding_window/__init__.py
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/data_structures/sliding_window/fixed_size_window.py b/data_structures/sliding_window/fixed_size_window.py
deleted file mode 100644
index 20db7846d395..000000000000
--- a/data_structures/sliding_window/fixed_size_window.py
+++ /dev/null
@@ -1,59 +0,0 @@
-"""
-Fixed-Size Sliding Window Algorithm
-
-This module contains an implementation of the fixed-size
-sliding window algorithm with doctests.
-
-Examples:
-    >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
-    12
-
-    >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
-    11
-"""
-
-
-def max_sum_subarray(arr: list[int], k: int) -> int:
-    """
-    Find the maximum sum of any subarray of size `k`.
-
-    Args:
-        arr: The input array of integers.
-        k: The size of the subarray.
-
-    Returns:
-        The maximum sum of a subarray of size `k`.
-
-    Raises:
-        ValueError: If the length of the array is less than `k`.
-
-    Examples:
-        >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
-        12
-
-        >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
-        11
-
-        >>> max_sum_subarray([1, 2], 3)
-        Traceback (most recent call last):
-            ...
-        ValueError: Array length must be at least as large as the window size.
-    """
-    if len(arr) < k:
-        raise ValueError("Array length must be at least as large as the window size.")
-
-    max_sum = float('-inf')
-    window_sum = sum(arr[:k])
-    max_sum = max(max_sum, window_sum)
-
-    for i in range(len(arr) - k):
-        window_sum = window_sum - arr[i] + arr[i + k]
-        max_sum = max(max_sum, window_sum)
-
-    return max_sum
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod()

From 2cae46588dd0ea9bd6a2022706079ac86f8265ae Mon Sep 17 00:00:00 2001
From: Asif Ahmed <121171874+asRot0@users.noreply.github.com>
Date: Fri, 20 Sep 2024 00:35:45 +0600
Subject: [PATCH 23/24] Delete data_structures/sliding_window directory

---
 data_structures/sliding_window/__init__.py    |  0
 .../sliding_window/fixed_size_window.py       | 59 -------------------
 2 files changed, 59 deletions(-)
 delete mode 100644 data_structures/sliding_window/__init__.py
 delete mode 100644 data_structures/sliding_window/fixed_size_window.py

diff --git a/data_structures/sliding_window/__init__.py b/data_structures/sliding_window/__init__.py
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/data_structures/sliding_window/fixed_size_window.py b/data_structures/sliding_window/fixed_size_window.py
deleted file mode 100644
index 42a80b7bc9c0..000000000000
--- a/data_structures/sliding_window/fixed_size_window.py
+++ /dev/null
@@ -1,59 +0,0 @@
-"""
-Fixed-Size Sliding Window Algorithm
-
-This module contains an implementation of the fixed-size
-sliding window algorithm with doctests.
-
-Examples:
-    >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
-    12
-
-    >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
-    11
-"""
-
-
-def max_sum_subarray(arr: list[int], k: int) -> int:
-    """
-    Find the maximum sum of any subarray of size `k`.
-
-    Args:
-        arr: The input array of integers.
-        k: The size of the subarray.
-
-    Returns:
-        The maximum sum of a subarray of size `k`.
-
-    Raises:
-        ValueError: If the length of the array is less than `k`.
-
-    Examples:
-        >>> max_sum_subarray([1, 2, 3, 4, 5], 3)
-        12
-
-        >>> max_sum_subarray([2, 1, 5, 1, 3, 2], 4)
-        11
-
-        >>> max_sum_subarray([1, 2], 3)
-        Traceback (most recent call last):
-            ...
-        ValueError: Array length must be at least as large as the window size.
-    """
-    if len(arr) < k:
-        raise ValueError("Array length must be at least as large as the window size.")
-
-    max_sum = float("-inf")
-    window_sum = sum(arr[:k])
-    max_sum = max(max_sum, window_sum)
-
-    for i in range(len(arr) - k):
-        window_sum = window_sum - arr[i] + arr[i + k]
-        max_sum = max(max_sum, window_sum)
-
-    return max_sum
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod()

From 00f7f7cf536476fd4e47bd314b07699a303013e0 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 19 Sep 2024 18:39:41 +0000
Subject: [PATCH 24/24] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/neural_networks/cnn_mnist.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/machine_learning/neural_networks/cnn_mnist.py b/machine_learning/neural_networks/cnn_mnist.py
index 1b2a8c48233c..60ca2f10850b 100644
--- a/machine_learning/neural_networks/cnn_mnist.py
+++ b/machine_learning/neural_networks/cnn_mnist.py
@@ -70,4 +70,3 @@
 # Evaluate the model on test data
 test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
 print(f"\nTest accuracy: {test_acc}")
-