import torch import torch.nn as nn import pandas as pd import matplotlib.pyplot as plt from sklearn.metrics import roc_curve, auc

读取训练数据

data = pd.read_excel('C:\Users\lenovo\Desktop\HIV\DNN神经网络测试\output_data.xlsx') x = data.iloc[:, 1:].values y = data.iloc[:, 0].values

数据归一化

x = (x - x.mean()) / x.std()

将numpy数组转换为张量

x = torch.Tensor(x) y = torch.Tensor(y)

定义模型

class DNN(nn.Module): def init(self, input_size, hidden_size, num_classes): super(DNN, self).init() self.fc1 = nn.Linear(input_size, hidden_size) self.fc2 = nn.Linear(hidden_size, hidden_size) self.fc3 = nn.Linear(hidden_size, hidden_size) self.out = nn.Linear(hidden_size, num_classes) self.dropout = nn.Dropout(p=0.5) self.attention = nn.Sequential( nn.Linear(hidden_size, 1), nn.Tanh(), nn.Softmax(dim=1) )

def forward(self, x):
    out = torch.relu(self.fc1(x))
    out = self.dropout(out)
    out = torch.relu(self.fc2(out))
    out = self.dropout(out)
    out = torch.relu(self.fc3(out))
    out = self.dropout(out)
    attention_weights = self.attention(out)
    out = attention_weights * out
    out = self.out(out)
    return out

定义超参数

input_size = 16 hidden_size = 128 num_classes = 2 learning_rate = 0.001 num_epochs = 100

初始化模型

model = DNN(input_size, hidden_size, num_classes)

定义损失函数和优化器

criterion = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

训练模型

train_loss = [] train_accuracy = [] for epoch in range(num_epochs): # 前向传播和反向传播 outputs = model(x) loss = criterion(outputs, y.long()) optimizer.zero_grad() loss.backward() optimizer.step()

# 计算准确率
_, predicted = torch.max(outputs.data, 1)
total = y.size(0)
correct = (predicted == y.long()).sum().item()
accuracy = correct / total
train_accuracy.append(accuracy)
train_loss.append(loss.item())

# 输出训练信息
print('Epoch [{}/{}], Loss: {:.4f}, Accuracy: {:.2f}%'
      .format(epoch + 1, num_epochs, loss.item(), accuracy * 100))

输出每个样本的概率

prob = torch.softmax(outputs, dim=1)[:, 1] print('每个样本的概率:', prob.detach().numpy().reshape(-1, 1))

绘制准确率变化的图

plt.plot(train_accuracy) plt.title('Accuracy') plt.xlabel('Epoch') plt.ylabel('Accuracy') plt.show()

绘制损失变化的图

plt.plot(train_loss) plt.title('Loss') plt.xlabel('Epoch') plt.ylabel('Loss') plt.show()

绘制ROC图

fpr, tpr, threshold = roc_curve(y, prob.detach().numpy()) roc_auc = auc(fpr, tpr) plt.title('ROC Curve') plt.plot(fpr, tpr, 'b', label='AUC = %0.2f' % roc_auc) plt.legend(loc='lower right') plt.plot([0, 1], [0, 1], 'r--') plt.xlim([0, 1]) plt.ylim([0, 1]) plt.ylabel('True Positive Rate') plt.xlabel('False Positive Rate') plt.show()

读取验证集数据

val_data = pd.read_excel('C:\Users\lenovo\Desktop\HIV\DNN神经网络测试\validation_data.xlsx') val_x = val_data.iloc[:, 1:].values val_y = val_data.iloc[:, 0].values

数据归一化

val_x = (val_x - x.mean()) / x.std()

将numpy数组转换为张量

val_x = torch.Tensor(val_x) val_y = torch.Tensor(val_y)

验证模型

model.eval() val_outputs = model(val_x) val_loss = criterion(val_outputs, val_y.long())

计算准确率

_, val_predicted = torch.max(val_outputs.data, 1) val_total = val_y.size(0) val_correct = (val_predicted == val_y.long()).sum().item() val_accuracy = val_correct / val_total print('Validation Loss: {:.4f}, Accuracy: {:.2f}%'.format(val_loss.item(), val_accuracy * 100))

输出验证集每个样本的概率

val_prob = torch.softmax(val_outputs, dim=1)[:, 1] print('Validation每个样本的概率:', val_prob.detach().numpy().reshape(-1, 1))

绘制验证集ROC图

val_fpr, val_tpr, val_threshold = roc_curve(val_y, val_prob.detach().numpy()) val_roc_auc = auc(val_fpr, val_tpr) plt.title('Validation ROC Curve') plt.plot(val_fpr, val_tpr, 'b', label='AUC = %0.2f' % val_roc_auc) plt.legend(loc='lower right') plt.plot([0, 1], [0, 1], 'r--') plt.xlim([0, 1]) plt.ylim([0, 1]) plt.ylabel('True Positive Rate') plt.xlabel('False Positive Rate') plt.show()