用python语言编写一个程序，使用logistic回归实现梯度下降算法，决定迭代次数，计算每次迭代并绘制结果。数据集通过txt文件输入且x和y的数据集彼此独立。不使用sklearn库的LogisticRegression模型

为了使用Python编写一个简单的逻辑回归模型，并实现梯度下降算法，我们可以创建一个包含sigmoid函数、代价函数、梯度函数以及更新步骤的类。首先，你需要安装numpy库，因为我们将使用它来进行数值计算。

import numpy as np

class LogisticRegression:
    def __init__(self, learning_rate=0.01, num_iterations=1000):
        self.lr = learning_rate
        self.num_iterations = num_iterations
        self.weights = None
        self.bias = None
        
    def sigmoid(self, z):
        return 1 / (1 + np.exp(-z))
        
    def cost_function(self, X, y, weights, bias):
        m = len(y)
        z = np.dot(X, weights) + bias
        h = self.sigmoid(z)
        J = (-1/m) * (np.sum(y * np.log(h)) + np.sum((1 - y) * np.log(1 - h)))
        return J
    
    def gradient_descent(self, X, y):
        m = X.shape[0]
        dw = (1/m) * np.dot(X.T, (h - y))
        db = (1/m) * np.sum(h - y)
        self.weights -= self.lr * dw
        self.bias -= self.lr * db
        
    def fit(self, X, y):
        X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
        self.weights = np.zeros(X.shape[1])
        self.bias = 0
        for _ in range(self.num_iterations):
            z = np.dot(X, self.weights) + self.bias
            h = self.sigmoid(z)
            self.gradient_descent(X, y)

def read_data_from_file(filename):
    with open(filename, 'r') as file:
        data = [line.strip().split(',') for line in file.readlines()]
    X = np.array([list(map(float, row[:-1])) for row in data], dtype=np.float64)
    y = np.array([float(row[-1]) for row in data])
    return X, y

# 使用数据集
X, y = read_data_from_file('data.txt')
model = LogisticRegression()
model.fit(X, y)

# 每次迭代后的决策边界可视化（假设你可以用matplotlib）
# 这里由于代码限制，我们简化了绘图部分
# 实际上，你可能需要保存每个迭代点的权重，然后用它们画出线或曲线
# plot_interpolating_line(X, model.weights, model.bias, i+1)

# 结果
print("Weights after {} iterations:".format(model.num_iterations), model.weights)
print("Bias after {} iterations:".format(model.num_iterations), model.bias)