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

resolved conflicts

Browse Source
This commit is contained in:
jbsch 2024-10-23 21:01:03 +05:30
parent c76784e708
commit 544a38b016
1 changed files with 19 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
machine_learning/ridge_regression/model.py
View File

@ -3,22 +3,21 @@ import pandas as pd
class RidgeRegression: class RidgeRegression:
def __init__( def __init__(self,
self, alpha: float = 0.001,
alpha: float = 0.001, regularization_param: float = 0.1,
regularization_param: float = 0.1, num_iterations: int = 1000,
num_iterations: int = 1000, ) -> None:
) -> None:
self.alpha: float = alpha self.alpha: float = alpha
self.regularization_param: float = regularization_param self.regularization_param: float = regularization_param
self.num_iterations: int = num_iterations self.num_iterations: int = num_iterations
self.theta: np.ndarray = None self.theta: np.ndarray = None
def feature_scaling( def feature_scaling(
self, X: np.ndarray self, x: np.ndarray
) -> tuple[np.ndarray, np.ndarray, np.ndarray]: ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
mean = np.mean(X, axis=0) mean = np.mean(x, axis=0)
std = np.std(X, axis=0) std = np.std(x, axis=0)
# avoid division by zero for constant features (std = 0) # avoid division by zero for constant features (std = 0)
std[std == 0] = 1 # set std=1 for constant features to avoid NaN std[std == 0] = 1 # set std=1 for constant features to avoid NaN
@ -31,7 +30,7 @@ class RidgeRegression:
m, n = x_scaled.shape m, n = x_scaled.shape
self.theta = np.zeros(n) # initializing weights to zeros self.theta = np.zeros(n) # initializing weights to zeros
for i in range(self.num_iterations): for _ in range(self.num_iterations):
predictions = x_scaled.dot(self.theta) predictions = x_scaled.dot(self.theta)
error = predictions - y error = predictions - y
@ -41,18 +40,19 @@ class RidgeRegression:
) / m ) / 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)
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)
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) + ( cost = (
self.regularization_param / (2 * m) 1 / (2 * m)) * np.sum((predictions - y) ** 2) + (
) * np.sum(self.theta**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:
@ -61,9 +61,9 @@ class RidgeRegression:
# Example usage # Example usage
if __name__ == "__main__": if __name__ == "__main__":
df = pd.read_csv("ADRvsRating.csv") data = pd.read_csv("ADRvsRating.csv")
x = df[["Rating"]].values x = data[["Rating"]].to_numpy()
y = df["ADR"].values y = data["ADR"].to_numpy()
y = (y - np.mean(y)) / np.std(y) y = (y - np.mean(y)) / np.std(y)
# added bias term to the feature matrix # added bias term to the feature matrix