generated from LufsX/Experiment-LogReg
This commit is contained in:
+12
-9
@@ -1,31 +1,35 @@
|
||||
import numpy as np
|
||||
|
||||
id = "202210423213" # 请填写学号
|
||||
name = "熊浩燃" # 请填写姓名
|
||||
|
||||
def sigmoid(z):
|
||||
"""计算Sigmoid函数值"""
|
||||
return 1 / (1 + np.exp(-z))
|
||||
|
||||
def train_logreg(X, y, learning_rate=0.01, iterations=1000):
|
||||
def train_logreg(X, y, learning_rate=0.01, iterations=5000, reg_lambda=0.1):
|
||||
"""
|
||||
对率回归训练函数。
|
||||
对率回归训练函数,带正则化项。
|
||||
|
||||
Args:
|
||||
- X (numpy array): 特征数据。
|
||||
- y (numpy array): 标签数据。
|
||||
- learning_rate (float): 学习率,默认为0.01。
|
||||
- iterations (int): 梯度下降迭代次数,默认为1000。
|
||||
- iterations (int): 梯度下降迭代次数,默认为5000。
|
||||
- reg_lambda (float): L2正则化系数,默认为0.1。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
"""
|
||||
# 数据标准化
|
||||
X = (X - X.mean(axis=0)) / X.std(axis=0)
|
||||
|
||||
# 初始化权重
|
||||
weights = np.zeros(X.shape[1])
|
||||
|
||||
# 批量梯度下降
|
||||
for i in range(iterations):
|
||||
predictions = sigmoid(np.dot(X, weights))
|
||||
errors = y - predictions
|
||||
weights += learning_rate * np.dot(X.T, errors)
|
||||
# 更新权重,带L2正则化
|
||||
weights += learning_rate * (np.dot(X.T, errors) - reg_lambda * weights)
|
||||
|
||||
return weights
|
||||
|
||||
@@ -54,7 +58,6 @@ def load_data(filepath):
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
|
||||
data = np.genfromtxt(filepath, delimiter=" ", dtype=float, missing_values="?", filling_values=np.nan)
|
||||
|
||||
# 使用列均值填充缺失值
|
||||
@@ -74,7 +77,7 @@ if __name__ == "__main__":
|
||||
X_test, y_test = load_data("./data/horse-colic.test")
|
||||
|
||||
# 训练对率回归模型
|
||||
weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
|
||||
weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, reg_lambda=0.1)
|
||||
|
||||
# 测试单个数据
|
||||
y_pred = predict_logreg(X_test[11], weights)
|
||||
|
||||
Reference in New Issue
Block a user