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

# 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  # 将标签从1-4转换为0-3

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, 4),  # 输出层，4个类别
        )

    def forward(self, x):
        return self.model(x)

# 使用5折交叉验证
skf = StratifiedKFold(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(skf.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).long().to(device))
    val_dataset = TensorDataset(torch.from_numpy(X_val).float().to(device), torch.from_numpy(y_val).long().to(device))

    train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
    val_loader = DataLoader(val_dataset, batch_size=32)

    model = MLP().to(device)
    criterion = nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(model.parameters())

    n_epochs = 120  # 增加到150个epoch
    train_losses, val_losses, train_accs, val_accs = [], [], [], []

    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)
            _, preds = torch.max(outputs, 1)
            corrects += torch.sum(preds == targets.data)

        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)
                _, preds = torch.max(outputs, 1)
                corrects += torch.sum(preds == targets.data)

        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}')

    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()