|
|
"""
|
|
|
文件名: detect_num.py
|
|
|
|
|
|
训练部分代码
|
|
|
|
|
|
作者: 王春林
|
|
|
创建日期: 2023年7月13日
|
|
|
最后修改日期: 2023年7月18日
|
|
|
版本号: 1.0.0
|
|
|
|
|
|
"""
|
|
|
import pandas as pd
|
|
|
import numpy as np
|
|
|
from sklearn.preprocessing import MinMaxScaler
|
|
|
from sklearn.model_selection import StratifiedKFold
|
|
|
import torch
|
|
|
from torch import nn
|
|
|
from torch.utils.data import DataLoader, TensorDataset
|
|
|
import matplotlib.pyplot as plt
|
|
|
from sklearn.model_selection import KFold
|
|
|
from torchsummary import summary
|
|
|
|
|
|
# 检查GPU是否可用
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
|
|
# 读取特征和标签
|
|
|
data = pd.read_excel('feature_label.xlsx')
|
|
|
|
|
|
# 以下是你的特征名
|
|
|
feature_names = ["躯体化", "强迫症状", "人际关系敏感", "抑郁", "焦虑", "敌对", "恐怖", "偏执", "精神病性", "其他", "父亲教养方式数字化", "母亲教养方式数字化", "自评家庭经济条件数字化", "有无心理治疗（咨询）史数字化", "出勤情况数字化", "学业情况数字化", "权重数字化值"]
|
|
|
|
|
|
# 将特征和标签分开，并做归一化处理
|
|
|
X = data[feature_names].values
|
|
|
y = (data['label'].values - 1) / 3 # 将标签从1-4转换为0-1
|
|
|
|
|
|
scaler = MinMaxScaler()
|
|
|
X = scaler.fit_transform(X)
|
|
|
|
|
|
# 定义 MLP 网络
|
|
|
class MLP(nn.Module):
|
|
|
def __init__(self):
|
|
|
super(MLP, self).__init__()
|
|
|
self.model = nn.Sequential(
|
|
|
nn.Linear(17, 32), # 输入层
|
|
|
nn.ReLU(), # 激活函数
|
|
|
nn.Linear(32, 128), # 隐藏层
|
|
|
nn.ReLU(), # 激活函数
|
|
|
nn.Linear(128, 32), # 隐藏层
|
|
|
nn.ReLU(), # 激活函数
|
|
|
nn.Linear(32, 1), # 输出层，1个类别
|
|
|
)
|
|
|
|
|
|
def forward(self, x):
|
|
|
return self.model(x).squeeze() # 去除多余的维度
|
|
|
|
|
|
# 使用KFold而非StratifiedKFold
|
|
|
kfold = KFold(n_splits=5, shuffle=True)
|
|
|
|
|
|
# 用于存储所有折的损失和准确率
|
|
|
all_train_losses, all_val_losses, all_train_accs, all_val_accs = [], [], [], []
|
|
|
|
|
|
for fold, (train_index, test_index) in enumerate(kfold.split(X, y)):
|
|
|
X_train, X_val = X[train_index], X[test_index]
|
|
|
y_train, y_val = y[train_index], y[test_index]
|
|
|
|
|
|
train_dataset = TensorDataset(torch.from_numpy(X_train).float().to(device), torch.from_numpy(y_train).float().to(device))
|
|
|
val_dataset = TensorDataset(torch.from_numpy(X_val).float().to(device), torch.from_numpy(y_val).float().to(device))
|
|
|
|
|
|
|
|
|
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
|
|
|
val_loader = DataLoader(val_dataset, batch_size=32)
|
|
|
|
|
|
model = MLP().to(device)
|
|
|
# 查看模型网络结构
|
|
|
# print(model)
|
|
|
summary(model.to(torch.device("cuda:0")), (1,17))
|
|
|
criterion = nn.MSELoss()
|
|
|
optimizer = torch.optim.Adam(model.parameters())
|
|
|
|
|
|
n_epochs = 120 # 增加到150个epoch
|
|
|
train_losses, val_losses, train_accs, val_accs = [], [], [], []
|
|
|
|
|
|
# 存储每一折的模型和对应的验证准确率
|
|
|
best_val_acc = 0.0
|
|
|
best_model = None
|
|
|
|
|
|
for epoch in range(n_epochs):
|
|
|
model.train()
|
|
|
running_loss, corrects = 0, 0
|
|
|
for inputs, targets in train_loader:
|
|
|
optimizer.zero_grad()
|
|
|
outputs = model(inputs)
|
|
|
loss = criterion(outputs, targets)
|
|
|
loss.backward()
|
|
|
optimizer.step()
|
|
|
running_loss += loss.item() * inputs.size(0)
|
|
|
# 使用阈值判断类别
|
|
|
thresholds = [1/6, 1/2, 5/6]
|
|
|
preds = torch.tensor([sum(o.item() > t for t in thresholds) for o in outputs]).to(device)
|
|
|
corrects += torch.sum(preds == (targets.data*3).long())
|
|
|
|
|
|
epoch_loss = running_loss / len(train_loader.dataset)
|
|
|
epoch_acc = corrects.double().cpu() / len(train_loader.dataset)
|
|
|
train_losses.append(epoch_loss)
|
|
|
train_accs.append(epoch_acc)
|
|
|
|
|
|
print(f'Fold {fold+1}, Epoch {epoch+1} | Train Loss: {epoch_loss:.4f} | Train Accuracy: {epoch_acc:.4f}')
|
|
|
|
|
|
model.eval()
|
|
|
running_loss, corrects = 0, 0
|
|
|
with torch.no_grad():
|
|
|
for inputs, targets in val_loader:
|
|
|
outputs = model(inputs)
|
|
|
loss = criterion(outputs, targets)
|
|
|
running_loss += loss.item() * inputs.size(0)
|
|
|
# 使用阈值判断类别
|
|
|
thresholds = [1/6, 1/2, 5/6]
|
|
|
preds = torch.tensor([sum(o.item() > t for t in thresholds) for o in torch.flatten(outputs)]).to(device)
|
|
|
corrects += torch.sum(preds == (targets.data*3).long())
|
|
|
|
|
|
epoch_loss = running_loss / len(val_loader.dataset)
|
|
|
epoch_acc = corrects.double().cpu() / len(val_loader.dataset)
|
|
|
val_losses.append(epoch_loss)
|
|
|
val_accs.append(epoch_acc)
|
|
|
|
|
|
print(f'Fold {fold+1}, Epoch {epoch+1} | Validation Loss: {epoch_loss:.4f} | Validation Accuracy: {epoch_acc:.4f}')
|
|
|
|
|
|
# 保存最佳模型
|
|
|
if epoch_acc > best_val_acc:
|
|
|
best_val_acc = epoch_acc
|
|
|
best_model = model.state_dict()
|
|
|
|
|
|
# 保存每一折的最佳模型
|
|
|
torch.save(best_model, f'model_fold{fold+1}.pth')
|
|
|
|
|
|
all_train_losses.append(train_losses)
|
|
|
all_val_losses.append(val_losses)
|
|
|
all_train_accs.append(train_accs)
|
|
|
all_val_accs.append(val_accs)
|
|
|
|
|
|
# 绘制所有折的平均损失和准确率曲线
|
|
|
plt.figure(figsize=(12, 4))
|
|
|
plt.subplot(1, 2, 1)
|
|
|
plt.plot(range(n_epochs), np.mean(all_train_losses, axis=0), label='Train Loss')
|
|
|
plt.plot(range(n_epochs), np.mean(all_val_losses, axis=0), label='Validation Loss')
|
|
|
plt.legend()
|
|
|
plt.title('Loss')
|
|
|
|
|
|
plt.subplot(1, 2, 2)
|
|
|
plt.plot(range(n_epochs), np.mean(all_train_accs, axis=0), label='Train Accuracy')
|
|
|
plt.plot(range(n_epochs), np.mean(all_val_accs, axis=0), label='Validation Accuracy')
|
|
|
plt.legend()
|
|
|
plt.title('Accuracy')
|
|
|
|
|
|
print(f'All Fold Average | Train Loss: {np.mean(all_train_losses, axis=0)[-1].item():.4f} | Train Accuracy: {np.mean(all_train_accs, axis=0)[-1].item():.4f} | Validation Loss: {np.mean(all_val_losses, axis=0)[-1].item():.4f} | Validation Accuracy: {np.mean(all_val_accs, axis=0)[-1].item():.4f}')
|
|
|
|
|
|
plt.show()
|