对数回归二分类

import numpy as np
import matplotlib.pyplot as plt

# 定义数据集，X为特征，y为标签（1代表好瓜，0代表坏瓜）
X = np.array([[0.697, 0.460],
              [0.774, 0.376],
              [0.634, 0.264],
              [0.608, 0.318],
              [0.556, 0.215],
              [0.403, 0.237],
              [0.481, 0.149],
              [0.437, 0.211],
              [0.666, 0.091],
              [0.243, 0.267],
              [0.245, 0.057],
              [0.343, 0.099],
              [0.639, 0.161],
              [0.657, 0.198],
              [0.360, 0.370],
              [0.593, 0.042],
              [0.719, 0.103]])

y = np.array([1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0])

# 增加偏置项，通过在X矩阵左侧添加一列全为1的向量，方便矩阵运算
X_with_bias = np.c_[np.ones((X.shape[0], 1)), X]


# 定义sigmoid函数
def sigmoid(z):
    return 1 / (1 + np.exp(-z))


# 定义损失函数
def compute_loss(X, y, theta):
    m = len(y)
    h = sigmoid(X.dot(theta))
    epsilon = 1e-5  # 避免log(0)的情况
    loss = -1 / m * np.sum(y * np.log(h + epsilon) + (1 - y) * np.log(1 - h + epsilon))
    return loss


# 定义梯度下降函数,以最小化损失函数来更新模型参数
def gradient_descent(X, y, learning_rate=0.01, epochs=10000):
    m, n = X.shape
    theta = np.zeros(n)
    loss_history = []

    for epoch in range(epochs):
        h = sigmoid(X.dot(theta))
        gradient = 1 / m * X.T.dot(h - y)
        theta -= learning_rate * gradient
        loss = compute_loss(X, y, theta)
        loss_history.append(loss)

    return theta, loss_history


# 进行梯度下降训练
theta, loss_history = gradient_descent(X_with_bias, y)

# 可视化数据和决策边界
plt.figure()
plt.scatter(X[:, 0], X[:, 1], c=y, cmap='viridis', marker='o', edgecolor='k')
plt.xlabel("密度")
plt.ylabel("含糖率")

# 绘制决策边界
x_values = [np.min(X[:, 0]), np.max(X[:, 0])]
y_values = [-(theta[0] + theta[1] * x) / theta[2] for x in x_values]
plt.plot(x_values, y_values, color='red', linestyle='dashed', linewidth=2)
plt.title("Decision Boundary")
plt.show()