基于神经网络的鸢尾花分类代码

您好，以下是一个基于神经网络的鸢尾花分类代码，供您参考：

import numpy as np

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

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

# 定义神经网络类
class NeuralNetwork:
    def __init__(self, input_shape, output_shape, hidden_shape=4):
        self.input_shape = input_shape
        self.hidden_shape = hidden_shape
        self.output_shape = output_shape
        
        # 权重初始化为随机值
        self.weights1 = np.random.randn(self.input_shape, self.hidden_shape)
        self.weights2 = np.random.randn(self.hidden_shape, self.output_shape)

    # 前向传播
    def feed_forward(self, X):
        # 输入层到隐藏层
        self.hidden_layer = sigmoid(np.dot(X, self.weights1))
        
        # 隐藏层到输出层
        self.output_layer = sigmoid(np.dot(self.hidden_layer, self.weights2))
    
    # 反向传播
    def backpropagation(self, X, y, learning_rate):
        # 计算输出层误差
        output_error = y - self.output_layer
        output_delta = output_error * sigmoid_derivative(self.output_layer)
        
        # 计算隐藏层误差
        hidden_error = np.dot(output_delta, self.weights2.T)
        hidden_delta = hidden_error * sigmoid_derivative(self.hidden_layer)
        
        # 更新权重
        self.weights2 += learning_rate * np.dot(self.hidden_layer.T, output_delta)
        self.weights1 += learning_rate * np.dot(X.T, hidden_delta)

    # 训练模型
    def train(self, X, y, learning_rate, num_epochs):
        for i in range(num_epochs):
            self.feed_forward(X)
            self.backpropagation(X, y, learning_rate)
    
    # 预测结果
    def predict(self, X):
        self.feed_forward(X)
        return self.output_layer

希望以上代码对您有帮助！