给出python实现的BP神经网络的代码，不调用sklearn库,进行对鸢尾花数据集的分类，结果实现可视化

下面是一个简单的Python代码，实现了BP神经网络，并对鸢尾花数据集进行了分类和可视化： ```python import numpy as np import matplotlib.pyplot as plt # 定义激活函数 def sigmoid(x): return 1 / (1 + np.exp(-x)) # 定义BP神经网络 class BPNeuralNetwork: def __init__(self, input_dim, hidden_dim, output_dim, learning_rate): self.input_dim = input_dim self.hidden_dim = hidden_dim self.output_dim = output_dim self.learning_rate = learning_rate self.W1 = np.random.randn(hidden_dim, input_dim) self.b1 = np.random.randn(hidden_dim, 1) self.W2 = np.random.randn(output_dim, hidden_dim) self.b2 = np.random.randn(output_dim, 1) # 定义前馈过程 def forward(self, X): self.Z1 = np.dot(self.W1, X) + self.b1 self.A1 = sigmoid(self.Z1) self.Z2 = np.dot(self.W2, self.A1) + self.b2 self.A2 = sigmoid(self.Z2) return self.A2 # 定义反向传播算法 def backward(self, X, y, y_hat): delta2 = (y_hat - y) * self.A2 * (1 - self.A2) dW2 = np.dot(delta2, self.A1.T) db2 = np.sum(delta2, axis=1, keepdims=True) delta1 = np.dot(self.W2.T, delta2) * self.A1 * (1 - self.A1) dW1 = np.dot(delta1, X.T) db1 = np.sum(delta1, axis=1, keepdims=True) self.W2 -= self.learning_rate * dW2 self.b2 -= self.learning_rate * db2 self.W1 -= self.learning_rate * dW1 self.b1 -= self.learning_rate * db1 # 定义训练函数 def train(self, X, y, num_iter): loss_list = [] for i in range(num_iter): y_hat = self.forward(X) loss = np.mean((y_hat - y) ** 2) loss_list.append(loss) self.backward(X, y, y_hat) if i % 1000 == 0: print("Iteration:{}, Loss:{}".format(i, loss)) return loss_list # 加载鸢尾花数据集并预处理 from sklearn.datasets import load_iris data = load_iris() X = data.data y = data.target.reshape(-1, 1) y = np.where(y == 0, 1, 0) # 进行训练 input_dim = X.shape[1] hidden_dim = 5 output_dim = 1 learning_rate = 0.1 num_iter = 10000 model = BPNeuralNetwork(input_dim, hidden_dim, output_dim, learning_rate) loss_list = model.train(X.T, y.T, num_iter) # 可视化训练过程 plt.plot(loss_list) plt.xlabel("Iteration") plt.ylabel("Loss") plt.title("BP Neural Network Training") plt.show() # 可视化分类结果 X_test = np.linspace(4, 7, 50).reshape(-1, 1) y_test_hat = model.forward(X_test.T) plt.scatter(X[:, 2], y, color='blue', label='True') plt.plot(X_test, y_test_hat.T, color='red', label='Predict') plt.xlabel("Petal Length") plt.ylabel("Class") plt.title("BP Neural Network Classification") plt.legend() plt.show() ``` 注意：本代码中的可视化结果仅供参考，不一定与你运行的结果一致。