mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-01-19 00:37:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

added ridge regression

Browse Source
This commit is contained in:
jbsch 2024-10-23 19:49:44 +05:30
commit 6fc134d96c
1 changed files with 29 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
machine_learning/ridge_regression/model.py
View File

@ -1,6 +1,7 @@
import numpy as np import numpy as np
import pandas as pd import pandas as pd
class RidgeRegression: class RidgeRegression:
def __init__(self, alpha:float=0.001, regularization_param:float=0.1, num_iterations:int=1000) -> None: def __init__(self, alpha:float=0.001, regularization_param:float=0.1, num_iterations:int=1000) -> None:
self.alpha:float = alpha self.alpha:float = alpha
@ -8,8 +9,12 @@ class RidgeRegression:
self.num_iterations:int = num_iterations self.num_iterations:int = num_iterations
self.theta:np.ndarray = None self.theta:np.ndarray = None
<<<<<<< HEAD
def feature_scaling(self, X:np.ndarray) -> tuple[np.ndarray, np.ndarray, np.ndarray]: def feature_scaling(self, X:np.ndarray) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
=======
def feature_scaling(self, X):
>>>>>>> d4fc2bf852ec4a023380f4ef367edefa88fd6881
mean = np.mean(X, axis=0) mean = np.mean(X, axis=0)
std = np.std(X, axis=0) std = np.std(X, axis=0)
@ -19,7 +24,6 @@ class RidgeRegression:
X_scaled = (X - mean) / std X_scaled = (X - mean) / std
return X_scaled, mean, std return X_scaled, mean, std
def fit(self, X:np.ndarray, y:np.ndarray) -> None: def fit(self, X:np.ndarray, y:np.ndarray) -> None:
X_scaled, mean, std = self.feature_scaling(X) X_scaled, mean, std = self.feature_scaling(X)
m, n = X_scaled.shape m, n = X_scaled.shape
@ -30,24 +34,30 @@ class RidgeRegression:
error = predictions - y error = predictions - y
# computing gradient with L2 regularization # computing gradient with L2 regularization
gradient = (X_scaled.T.dot(error) + self.regularization_param * self.theta) / m gradient = (
X_scaled.T.dot(error) + self.regularization_param * self.theta
) / m
self.theta -= self.alpha * gradient # updating weights self.theta -= self.alpha * gradient # updating weights
def predict(self, X:np.ndarray) -> np.ndarray: def predict(self, X:np.ndarray) -> np.ndarray:
X_scaled, _, _ = self.feature_scaling(X) X_scaled, _, _ = self.feature_scaling(X)
return X_scaled.dot(self.theta) return X_scaled.dot(self.theta)
<<<<<<< HEAD
def compute_cost(self, X:np.ndarray, y:np.ndarray) -> float: def compute_cost(self, X:np.ndarray, y:np.ndarray) -> float:
X_scaled, _, _ = self.feature_scaling(X) X_scaled, _, _ = self.feature_scaling(X)
=======
def compute_cost(self, X, y):
X_scaled, _, _ = self.feature_scaling(X)
>>>>>>> d4fc2bf852ec4a023380f4ef367edefa88fd6881
m = len(y) m = len(y)
predictions = X_scaled.dot(self.theta) predictions = X_scaled.dot(self.theta)
cost = (1 / (2 * m)) * np.sum((predictions - y) ** 2) + (self.regularization_param / (2 * m)) * np.sum(self.theta**2) cost = (1 / (2 * m)) * np.sum((predictions - y) ** 2) + (
self.regularization_param / (2 * m)
) * np.sum(self.theta**2)
return cost return cost
def mean_absolute_error(self, y_true:np.ndarray, y_pred:np.ndarray) -> float: def mean_absolute_error(self, y_true:np.ndarray, y_pred:np.ndarray) -> float:
return np.mean(np.abs(y_true - y_pred)) return np.mean(np.abs(y_true - y_pred))
@ -59,8 +69,13 @@ if __name__ == "__main__":
y = df["ADR"].values y = df["ADR"].values
y = (y - np.mean(y)) / np.std(y) y = (y - np.mean(y)) / np.std(y)
<<<<<<< HEAD
# added bias term to the feature matrix # added bias term to the feature matrix
X = np.c_[np.ones(X.shape[0]), X] X = np.c_[np.ones(X.shape[0]), X]
=======
# Add bias term (intercept) to the feature matrix
X = np.c_[np.ones(X.shape[0]), X]
>>>>>>> d4fc2bf852ec4a023380f4ef367edefa88fd6881
# initialize and train the ridge regression model # initialize and train the ridge regression model
model = RidgeRegression(alpha=0.01, regularization_param=0.1, num_iterations=1000) model = RidgeRegression(alpha=0.01, regularization_param=0.1, num_iterations=1000)