如何将深度学习梯度下降方程转换为python

import numpy as np

def gradient_descent(X, y, learning_rate, num_iterations):
    num_samples, num_features = X.shape
    weights = np.zeros(num_features)
    bias = 0
    
    for i in range(num_iterations):
        # 计算预测值
        y_pred = np.dot(X, weights) + bias
        
        # 计算损失函数
        loss = np.mean((y_pred - y) ** 2)
        
        # 计算梯度
        d_weights = (1/num_samples) * np.dot(X.T, (y_pred - y))
        d_bias = (1/num_samples) * np.sum(y_pred - y)
        
        # 更新参数
        weights -= learning_rate * d_weights
        bias -= learning_rate * d_bias
    
    return weights, bias

X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
y = np.array([4, 7, 10])

learning_rate = 0.01
num_iterations = 1000

weights, bias = gradient_descent(X, y, learning_rate, num_iterations)