bp神经网络预测GDP代码

BP神经网络是一种常用的机器学习算法，可以用于预测GDP等连续值的问题。下面是一个简单的BP神经网络预测GDP的代码示例：

import numpy as np

# 定义BP神经网络类
class BPNeuralNetwork:
    def __init__(self, input_size, hidden_size, output_size):
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        
        # 初始化权重和偏置
        self.weights1 = np.random.randn(self.input_size, self.hidden_size)
        self.bias1 = np.random.randn(self.hidden_size)
        self.weights2 = np.random.randn(self.hidden_size, self.output_size)
        self.bias2 = np.random.randn(self.output_size)
        
    # 定义激活函数（sigmoid函数）
    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))
    
    # 定义激活函数的导数（sigmoid函数的导数）
    def sigmoid_derivative(self, x):
        return x * (1 - x)
    
    # 前向传播
    def forward(self, X):
        self.hidden_layer_output = self.sigmoid(np.dot(X, self.weights1) + self.bias1)
        self.predicted_output = self.sigmoid(np.dot(self.hidden_layer_output, self.weights2) + self.bias2)
        
    # 反向传播
    def backward(self, X, y, learning_rate):
        error = y - self.predicted_output
        delta_output = error * self.sigmoid_derivative(self.predicted_output)
        
        error_hidden = delta_output.dot(self.weights2.T)
        delta_hidden = error_hidden * self.sigmoid_derivative(self.hidden_layer_output)
        
        self.weights2 += self.hidden_layer_output.T.dot(delta_output) * learning_rate
        self.bias2 += np.sum(delta_output) * learning_rate
        
        self.weights1 += X.T.dot(delta_hidden) * learning_rate
        self.bias1 += np.sum(delta_hidden) * learning_rate
        
    # 训练模型
    def train(self, X, y, epochs, learning_rate):
        for epoch in range(epochs):
            self.forward(X)
            self.backward(X, y, learning_rate)
            
    # 预测
    def predict(self, X):
        self.forward(X)
        return self.predicted_output

# 创建BP神经网络对象
input_size = 10  # 输入层大小
hidden_size = 5  # 隐藏层大小
output_size = 1  # 输出层大小
bpnn = BPNeuralNetwork(input_size, hidden_size, output_size)

# 准备训练数据
X_train = np.random.randn(100, input_size)  # 输入数据
y_train = np.random.randn(100, output_size)  # 输出数据

# 训练模型
bpnn.train(X_train, y_train, epochs=1000, learning_rate=0.1)

# 准备测试数据
X_test = np.random.randn(10, input_size)  # 输入数据

# 预测
predictions = bpnn.predict(X_test)
print(predictions)

这段代码实现了一个简单的BP神经网络，包括前向传播、反向传播、训练和预测等功能。你可以根据自己的需求进行修改和扩展。