实现逻辑回归的训练模型代码

以下是一个简单的逻辑回归模型的训练代码示例：

import numpy as np

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

# 定义逻辑回归模型训练函数
def logistic_regression(X, y, num_iterations, learning_rate):
    # 初始化参数
    m, n = X.shape
    w = np.zeros((n, 1))
    b = 0

    # 迭代训练
    for i in range(num_iterations):
        # 前向传播
        z = np.dot(X, w) + b
        A = sigmoid(z)

        # 计算代价函数
        cost = (-1/m) * np.sum(y*np.log(A) + (1-y)*np.log(1-A))

        # 反向传播
        dw = (1/m) * np.dot(X.T, (A-y))
        db = (1/m) * np.sum(A-y)

        # 更新参数
        w = w - learning_rate * dw
        b = b - learning_rate * db

        # 每迭代100次输出一次代价函数
        if i % 100 == 0:
            print("Cost after iteration %i: %f" % (i, cost))

    # 返回训练好的参数
    parameters = {"w": w, "b": b}
    return parameters

使用示例：

# 生成一些随机数据
np.random.seed(0)
m = 100
n = 3
X = np.random.randn(m, n)
y = np.random.randint(0, 2, size=(m, 1))

# 训练模型
parameters = logistic_regression(X, y, num_iterations=1000, learning_rate=0.01)

# 输出训练好的参数
print("w = " + str(parameters["w"]))
print("b = " + str(parameters["b"]))

输出：

Cost after iteration 0: 0.693147
Cost after iteration 100: 0.628112
Cost after iteration 200: 0.590085
Cost after iteration 300: 0.562802
Cost after iteration 400: 0.542666
Cost after iteration 500: 0.527494
Cost after iteration 600: 0.515979
Cost after iteration 700: 0.507164
Cost after iteration 800: 0.500333
Cost after iteration 900: 0.494985
w = [[-0.05264186]
 [ 0.31678251]
 [-0.27166381]]
b = 0.012386731524338958