Last active
September 15, 2024 10:24
-
-
Save Momellouky/bc854a1f21a232a1fba175486ce4925e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| from sklearn.preprocessing import add_dummy_feature | |
| class LinearRegression: | |
| def __init__(self): | |
| self.X = None | |
| self.y = None | |
| self.theta = None | |
| self.coaf_ = None | |
| self.intercept_ = None | |
| def predict(self, X): | |
| ''' | |
| With the input X the functions uses the model to makes predictions | |
| :param X: The independent variables. | |
| :return: A numpy array containing the predicted values. | |
| ''' | |
| predictions = np.array([]) | |
| for element in X: | |
| predictions = np.append(predictions, element * self.coaf_ + self.intercept_) | |
| return predictions | |
| def fit(self, X, y, epoch=1000, learning_rate=0.1): | |
| ''' | |
| train the linear regressor using the Batch Gradient Descent algorithm | |
| :param X: The independent variables. | |
| :param y: The dependent variables. | |
| :return: the trained model. | |
| ''' | |
| self.X = X | |
| self.y = y | |
| self.X = add_dummy_feature(self.X) | |
| np.random.seed(42) | |
| self.theta = np.random.randn(self.X.shape[1]) # Random initialisation | |
| self.theta = self.theta.reshape(-1, 1) | |
| m = self.X.shape[0] # The number of items | |
| for i in range(epoch): | |
| predictions = (self.X @ self.theta).reshape(-1, 1) | |
| gradient = 2 / m * self.X.T @ (predictions - self.y) | |
| self.theta = self.theta - learning_rate * gradient | |
| self.coaf_ = self.theta[1:] | |
| self.intercept_ = self.theta[0] | |
| return self | |
| def score(self, X, y): | |
| ''' | |
| Evaluates the model on the test data using Mean Squared Error | |
| :param X: independent variables. | |
| :param y: dependent variables. | |
| :return: Mean Squared Error value | |
| ''' | |
| predictions = self.predict(X) | |
| m = predictions.shape[0] # the size of the test data. | |
| mae = 0 | |
| for i in range(m): | |
| mae = mae + (y[i] - predictions[i]) ** 2 | |
| mae = mae / m | |
| return mae | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import linear_regression.linear_regression as LinearRegression | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| np.random.seed(45) | |
| number_of_instances = 100 | |
| X = np.random.randn(number_of_instances,1) | |
| Y = 4 + 3 * X + np.random.randn(number_of_instances, 1) | |
| plt.scatter(X, Y) | |
| linear_regression = LinearRegression.LinearRegression() | |
| regressor = linear_regression.fit(X, Y) | |
| print(f"coaf: {linear_regression.coaf_}") | |
| print(f"intercept: {linear_regression.intercept_}") | |
| plt.plot(X, X @ regressor.coaf_ + regressor.intercept_, color='red') | |
| print(f"predict: {linear_regression.predict([0])}") | |
| print(f"score: {linear_regression.score([0], [4.07535703])}") | |
| plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment