Merge e23173e6a3 into f3f32ae3ca

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.7.3 → v0.7.4](https://github.com/astral-sh/ruff-pre-commit/compare/v0.7.3...v0.7.4)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

.pre-commit-config.yaml

@@ -16,7 +16,7 @@ repos:
       - id: auto-walrus
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.2
+    rev: v0.7.4
     hooks:
       - id: ruff
       - id: ruff-format
@@ -42,7 +42,7 @@ repos:
         pass_filenames: false
 
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.22
+    rev: v0.23
     hooks:
       - id: validate-pyproject
 

data_structures/arrays/sudoku_solver.py

@@ -172,7 +172,7 @@ def solved(values):
 
 def from_file(filename, sep="\n"):
     "Parse a file into a list of strings, separated by sep."
-    return open(filename).read().strip().split(sep)  # noqa: SIM115
+    return open(filename).read().strip().split(sep)
 
 
 def random_puzzle(assignments=17):

machine_learning/ridge_regression.py

@@ -0,0 +1,125 @@
+import numpy as np
+import requests
+
+
+def collect_dataset():
+    """Collect dataset of CSGO
+    The dataset contains ADR vs Rating of a Player
+    :return : dataset obtained from the link, as matrix
+    """
+    response = requests.get(
+        "https://raw.githubusercontent.com/yashLadha/The_Math_of_Intelligence/"
+        "master/Week1/ADRvsRating.csv",
+        timeout=10,
+    )
+    lines = response.text.splitlines()
+    data = []
+    for item in lines:
+        item = item.split(",")
+        data.append(item)
+    data.pop(0)  # This is for removing the labels from the list
+    dataset = np.matrix(data)
+    return dataset
+
+
+def run_steep_gradient_descent(data_x, data_y, len_data, alpha, theta, lambda_reg):
+    """Run steep gradient descent and updates the Feature vector accordingly
+    :param data_x   : contains the dataset
+    :param data_y   : contains the output associated with each data-entry
+    :param len_data : length of the data
+    :param alpha    : Learning rate of the model
+    :param theta    : Feature vector (weights for our model)
+    :param lambda_reg: Regularization parameter
+    :return : Updated Features using
+              curr_features - alpha_ * gradient(w.r.t. feature)
+    """
+    n = len_data
+
+    prod = np.dot(theta, data_x.transpose())
+    prod -= data_y.transpose()
+    sum_grad = np.dot(prod, data_x)
+
+    # Add regularization to the gradient
+    theta_regularized = np.copy(theta)
+    theta_regularized[0, 0] = 0  # Don't regularize the bias term
+    sum_grad += lambda_reg * theta_regularized  # Add regularization to gradient
+
+    theta = theta - (alpha / n) * sum_grad
+    return theta
+
+
+def sum_of_square_error(data_x, data_y, len_data, theta, lambda_reg):
+    """Return sum of square error for error calculation
+    :param data_x    : contains our dataset
+    :param data_y    : contains the output (result vector)
+    :param len_data  : len of the dataset
+    :param theta     : contains the feature vector
+    :param lambda_reg: Regularization parameter
+    :return          : sum of square error computed from given features
+    """
+    prod = np.dot(theta, data_x.transpose())
+    prod -= data_y.transpose()
+    sum_elem = np.sum(np.square(prod))
+
+    # Add regularization to the cost function
+    regularization_term = lambda_reg * np.sum(
+        np.square(theta[:, 1:])
+    )  # Don't regularize the bias term
+    error = (sum_elem / (2 * len_data)) + (regularization_term / (2 * len_data))
+    return error
+
+
+def run_ridge_regression(data_x, data_y, lambda_reg=1.0):
+    """Implement Ridge Regression over the dataset
+    :param data_x  : contains our dataset
+    :param data_y  : contains the output (result vector)
+    :param lambda_reg: Regularization parameter
+    :return        : feature for line of best fit (Feature vector)
+    """
+    iterations = 100000
+    alpha = 0.0001550
+
+    no_features = data_x.shape[1]
+    len_data = data_x.shape[0]
+
+    theta = np.zeros((1, no_features))
+
+    for i in range(iterations):
+        theta = run_steep_gradient_descent(
+            data_x, data_y, len_data, alpha, theta, lambda_reg
+        )
+        error = sum_of_square_error(data_x, data_y, len_data, theta, lambda_reg)
+        print(f"At Iteration {i + 1} - Error is {error:.5f}")
+
+    return theta
+
+
+def mean_absolute_error(predicted_y, original_y):
+    """Return mean absolute error for error calculation
+    :param predicted_y   : contains the output of prediction (result vector)
+    :param original_y    : contains values of expected outcome
+    :return          : mean absolute error computed from given features
+    """
+    total = sum(abs(y - predicted_y[i]) for i, y in enumerate(original_y))
+    return total / len(original_y)
+
+
+def main():
+    """Driver function"""
+    data = collect_dataset()
+
+    len_data = data.shape[0]
+    data_x = np.c_[np.ones(len_data), data[:, :-1]].astype(float)
+    data_y = data[:, -1].astype(float)
+
+    lambda_reg = 1.0  # Set your desired regularization parameter
+    theta = run_ridge_regression(data_x, data_y, lambda_reg)
+
+    len_result = theta.shape[1]
+    print("Resultant Feature vector : ")
+    for i in range(len_result):
+        print(f"{theta[0, i]:.5f}")
+
+
+if __name__ == "__main__":
+    main()

scripts/validate_filenames.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python3
+#!python
 import os
 
 try: