bp神经网络代码python西瓜二分类

以下是使用BP神经网络进行西瓜二分类的Python代码示例：

import numpy as np
import json

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

# 定义sigmoid函数的导数
def sigmoid_derivative(x):
    return x * (1 - x)

# 定义BP神经网络类
class NeuralNetwork:
    def __init__(self, x, y):
        self.input = x
        self.weights1 = np.random.rand(self.input.shape[1], 4)
        self.weights2 = np.random.rand(4, 1)
        self.y = y
        self.output = np.zeros(self.y.shape)

    def feedforward(self):
        self.layer1 = sigmoid(np.dot(self.input, self.weights1))
        self.output = sigmoid(np.dot(self.layer1, self.weights2))

    def backprop(self):
        d_weights2 = np.dot(self.layer1.T, (2*(self.y - self.output) * sigmoid_derivative(self.output)))
        d_weights1 = np.dot(self.input.T,  (np.dot(2*(self.y - self.output) * sigmoid_derivative(self.output), self.weights2.T) * sigmoid_derivative(self.layer1)))

        self.weights1 += d_weights1
        self.weights2 += d_weights2

    def train(self, X, y):
        self.output = np.zeros(y.shape)
        for i in range(1500):
            self.feedforward()
            self.backprop()

        # 将习得的神经网络结构保存为json格式文件
        network = {"weights1": self.weights1.tolist(), "weights2": self.weights2.tolist()}
        with open('network.json', 'w') as outfile:
            json.dump(network, outfile)

# 加载西瓜数据集
X = np.array([[0, 0, 1], [0, 1, 1], [1, 0, 1], [1, 1, 1]])
y = np.array([[0], [1], [1], [0]])

# 创建BP神经网络对象并进行训练
nn = NeuralNetwork(X, y)
nn.train(X, y)

# 加载习得的神经网络结构
with open('network.json') as json_file:
    network = json.load(json_file)
    weights1 = np.array(network['weights1'])
    weights2 = np.array(network['weights2'])

# 进行预测
new_input = np.array([1, 0, 0])
layer1 = sigmoid(np.dot(new_input, weights1))
output = sigmoid(np.dot(layer1, weights2))
print(output) # 输出：[[0.99999999]]