ShopTRAINING/server/trainers/tcn_trainer.py

"""
药店销售预测系统 - TCN模型训练函数
"""

import os
import time
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
from tqdm import tqdm

from models.tcn_model import TCNForecaster
from utils.data_utils import create_dataset, PharmacyDataset
from utils.visualization import plot_loss_curve
from analysis.metrics import evaluate_model
from core.config import DEVICE, DEFAULT_MODEL_DIR, LOOK_BACK, FORECAST_HORIZON
from utils.training_progress import progress_manager

def save_checkpoint(checkpoint_data: dict, epoch_or_label, path_info: dict):
    """
    保存训练检查点
    
    Args:
        checkpoint_data: 检查点数据
        epoch_or_label: epoch编号或标签（如'best', 'final', 50）
        path_info (dict): 包含所有路径信息的字典
    """
    if epoch_or_label == 'best':
        # 使用由 ModelPathManager 直接提供的最佳检查点路径
        checkpoint_path = path_info['best_checkpoint_path']
    else:
        # 使用 epoch 检查点模板生成路径
        template = path_info.get('epoch_checkpoint_template')
        if not template:
            raise ValueError("路径信息 'path_info' 中缺少 'epoch_checkpoint_template'。")
        checkpoint_path = template.format(N=epoch_or_label)

    # 保存检查点
    torch.save(checkpoint_data, checkpoint_path)
    print(f"[TCN] 检查点已保存: {checkpoint_path}", flush=True)
    
    return checkpoint_path

def train_product_model_with_tcn(
    product_id,
    product_df=None,
    store_id=None,
    training_mode='product',
    aggregation_method='sum',
    epochs=50,
    model_dir=DEFAULT_MODEL_DIR, # 将被 path_info 替代
    version=None, # 将被 path_info 替代
    socketio=None,
    task_id=None,
    continue_training=False,
    path_info=None, # 新增参数
    **kwargs
):
    """
    使用TCN模型训练产品销售预测模型
    
    参数:
    product_id: 产品ID
    epochs: 训练轮次
    model_dir: 模型保存目录，默认使用配置中的DEFAULT_MODEL_DIR
    version: 指定版本号，如果为None则自动生成
    socketio: WebSocket对象，用于实时反馈
    task_id: 训练任务ID
    continue_training: 是否继续训练现有模型
    
    返回:
    model: 训练好的模型
    metrics: 模型评估指标
    version: 实际使用的版本号
    model_path: 模型文件路径
    """
    
    if not path_info:
        raise ValueError("train_product_model_with_tcn 需要 'path_info' 参数。")
    
    version = path_info['version']

    def emit_progress(message, progress=None, metrics=None):
        """发送训练进度到前端"""
        if socketio and task_id:
            data = {
                'task_id': task_id,
                'message': message,
                'timestamp': time.time()
            }
            if progress is not None:
                data['progress'] = progress
            if metrics is not None:
                data['metrics'] = metrics
            socketio.emit('training_progress', data, namespace='/training')
    
    emit_progress(f"开始训练 TCN 模型版本 v{version}")
    
    # 如果没有传入product_df，则根据训练模式加载数据
    if product_df is None:
        from utils.multi_store_data_utils import load_multi_store_data, get_store_product_sales_data, aggregate_multi_store_data
        
        try:
            if training_mode == 'store' and store_id:
                # 加载特定店铺的数据
                product_df = get_store_product_sales_data(
                    store_id,
                    product_id,
                    'pharmacy_sales_multi_store.csv'
                )
                training_scope = f"店铺 {store_id}"
            elif training_mode == 'global':
                # 聚合所有店铺的数据
                product_df = aggregate_multi_store_data(
                    product_id,
                    aggregation_method=aggregation_method,
                    file_path='pharmacy_sales_multi_store.csv'
                )
                training_scope = f"全局聚合({aggregation_method})"
            else:
                # 默认：加载所有店铺的产品数据
                product_df = load_multi_store_data('pharmacy_sales_multi_store.csv', product_id=product_id)
                training_scope = "所有店铺"
        except Exception as e:
            print(f"多店铺数据加载失败: {e}")
            # 后备方案：尝试原始数据
            df = pd.read_excel('pharmacy_sales.xlsx')
            product_df = df[df['product_id'] == product_id].sort_values('date')
            training_scope = "原始数据"
    else:
        # 如果传入了product_df，直接使用
        if training_mode == 'store' and store_id:
            training_scope = f"店铺 {store_id}"
        elif training_mode == 'global':
            training_scope = f"全局聚合({aggregation_method})"
        else:
            training_scope = "所有店铺"
    
    if product_df.empty:
        raise ValueError(f"产品 {product_id} 没有可用的销售数据")
    
    # 数据量检查
    min_required_samples = LOOK_BACK + FORECAST_HORIZON
    if len(product_df) < min_required_samples:
        error_msg = (
            f"❌ 训练数据不足错误\n"
            f"当前配置需要: {min_required_samples} 天数据 (LOOK_BACK={LOOK_BACK} + FORECAST_HORIZON={FORECAST_HORIZON})\n"
            f"实际数据量: {len(product_df)} 天\n"
            f"产品ID: {product_id}, 训练模式: {training_mode}\n"
            f"建议解决方案:\n"
            f"1. 生成更多数据: uv run generate_multi_store_data.py\n"
            f"2. 调整配置参数: 减小 LOOK_BACK 或 FORECAST_HORIZON\n"
            f"3. 使用全局训练模式聚合更多数据"
        )
        print(error_msg)
        emit_progress(f"训练失败：数据不足 ({len(product_df)}/{min_required_samples} 天)")
        raise ValueError(error_msg)
    
    product_df = product_df.sort_values('date')
    product_name = product_df['product_name'].iloc[0]
    
    print(f"使用TCN模型训练产品 '{product_name}' (ID: {product_id}) 的销售预测模型")
    print(f"训练范围: {training_scope}")
    print(f"版本: v{version}")
    print(f"使用设备: {DEVICE}")
    print(f"模型将保存到: {path_info['base_dir']}")
    
    emit_progress(f"训练产品: {product_name} (ID: {product_id})")
    
    # 创建特征和目标变量
    features = ['sales', 'weekday', 'month', 'is_holiday', 'is_weekend', 'is_promotion', 'temperature']
    
    # 预处理数据
    X = product_df[features].values
    y = product_df[['sales']].values  # 保持为二维数组
    
    # 设置数据预处理阶段
    progress_manager.set_stage("data_preprocessing", 0)
    emit_progress("数据预处理中...")
    
    # 归一化数据
    scaler_X = MinMaxScaler(feature_range=(0, 1))
    scaler_y = MinMaxScaler(feature_range=(0, 1))
    
    X_scaled = scaler_X.fit_transform(X)
    y_scaled = scaler_y.fit_transform(y)
    
    # 划分训练集和测试集（80% 训练，20% 测试）
    train_size = int(len(X_scaled) * 0.8)
    X_train, X_test = X_scaled[:train_size], X_scaled[train_size:]
    y_train, y_test = y_scaled[:train_size], y_scaled[train_size:]
    
    progress_manager.set_stage("data_preprocessing", 50)
    
    # 创建时间序列数据
    trainX, trainY = create_dataset(X_train, y_train, LOOK_BACK, FORECAST_HORIZON)
    testX, testY = create_dataset(X_test, y_test, LOOK_BACK, FORECAST_HORIZON)
    
    # 转换为PyTorch的Tensor
    trainX_tensor = torch.Tensor(trainX)
    trainY_tensor = torch.Tensor(trainY)
    testX_tensor = torch.Tensor(testX)
    testY_tensor = torch.Tensor(testY)
    
    # 创建数据加载器
    train_dataset = PharmacyDataset(trainX_tensor, trainY_tensor)
    test_dataset = PharmacyDataset(testX_tensor, testY_tensor)
    
    batch_size = 32
    train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
    test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
    
    # 更新进度管理器的批次信息
    total_batches = len(train_loader)
    total_samples = len(train_dataset)
    progress_manager.total_batches_per_epoch = total_batches
    progress_manager.batch_size = batch_size
    progress_manager.total_samples = total_samples
    
    progress_manager.set_stage("data_preprocessing", 100)
    
    # 初始化TCN模型
    input_dim = X_train.shape[1]
    output_dim = FORECAST_HORIZON
    hidden_size = 64
    num_layers = 3
    kernel_size = 3
    dropout_rate = 0.2
    
    model = TCNForecaster(
        num_features=input_dim,
        output_sequence_length=output_dim,
        num_channels=[hidden_size] * num_layers,
        kernel_size=kernel_size,
        dropout=dropout_rate
    )
    
    # 如果是继续训练，加载现有模型
    if continue_training:
        # TODO: 继续训练的逻辑需要调整以适应新的路径结构
        emit_progress("继续训练功能待适配新路径结构，暂时作为新训练开始。")
    
    # 将模型移动到设备上
    model = model.to(DEVICE)
    
    criterion = nn.MSELoss()
    optimizer = optim.Adam(model.parameters(), lr=0.001)
    
    emit_progress("开始模型训练...")
    
    # 训练模型
    train_losses = []
    test_losses = []
    start_time = time.time()
    
    # 配置检查点保存
    checkpoint_interval = max(1, epochs // 10)  # 每10%进度保存一次，最少每1个epoch
    best_loss = float('inf')
    
    progress_manager.set_stage("model_training", 0)
    emit_progress(f"开始训练 - 总epoch: {epochs}, 检查点间隔: {checkpoint_interval}")
    
    for epoch in range(epochs):
        # 开始新的轮次
        progress_manager.start_epoch(epoch)
        
        model.train()
        epoch_loss = 0
        
        for batch_idx, (X_batch, y_batch) in enumerate(train_loader):
            X_batch, y_batch = X_batch.to(DEVICE), y_batch.to(DEVICE)
            
            # 确保目标张量有正确的形状 (batch_size, forecast_horizon, 1)
            if y_batch.dim() == 2:
                y_batch = y_batch.unsqueeze(-1)
            
            # 前向传播
            outputs = model(X_batch)
            
            # 确保输出和目标形状匹配
            loss = criterion(outputs, y_batch)
            
            # 反向传播和优化
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            epoch_loss += loss.item()
            
            # 更新批次进度（每10个批次更新一次）
            if batch_idx % 10 == 0 or batch_idx == len(train_loader) - 1:
                current_lr = optimizer.param_groups[0]['lr']
                progress_manager.update_batch(batch_idx, loss.item(), current_lr)
        
        # 计算训练损失
        train_loss = epoch_loss / len(train_loader)
        train_losses.append(train_loss)
        
        # 设置验证阶段
        progress_manager.set_stage("validation", 0)
        
        # 在测试集上评估
        model.eval()
        test_loss = 0
        with torch.no_grad():
            for batch_idx, (X_batch, y_batch) in enumerate(test_loader):
                X_batch, y_batch = X_batch.to(DEVICE), y_batch.to(DEVICE)
                
                # 确保目标张量有正确的形状
                if y_batch.dim() == 2:
                    y_batch = y_batch.unsqueeze(-1)
                
                outputs = model(X_batch)
                loss = criterion(outputs, y_batch)
                test_loss += loss.item()
                
                # 更新验证进度
                if batch_idx % 5 == 0 or batch_idx == len(test_loader) - 1:
                    val_progress = (batch_idx / len(test_loader)) * 100
                    progress_manager.set_stage("validation", val_progress)
        
        test_loss = test_loss / len(test_loader)
        test_losses.append(test_loss)
        
        # 完成当前轮次
        progress_manager.finish_epoch(train_loss, test_loss)
        
        # 发送训练进度（保持与旧系统的兼容性）
        if (epoch + 1) % 5 == 0 or epoch == epochs - 1:
            progress = ((epoch + 1) / epochs) * 100
            current_metrics = {
                'train_loss': train_loss,
                'test_loss': test_loss,
                'epoch': epoch + 1,
                'total_epochs': epochs
            }
            emit_progress(f"Epoch {epoch+1}/{epochs}, Train Loss: {train_loss:.4f}, Test Loss: {test_loss:.4f}", 
                         progress=progress, metrics=current_metrics)
        
        # 定期保存检查点
        if (epoch + 1) % checkpoint_interval == 0 or epoch == epochs - 1:
            checkpoint_data = {
                'epoch': epoch + 1,
                'model_state_dict': model.state_dict(),
                'optimizer_state_dict': optimizer.state_dict(),
                'train_loss': train_loss,
                'test_loss': test_loss,
                'train_losses': train_losses,
                'test_losses': test_losses,
                'scaler_X': scaler_X,
                'scaler_y': scaler_y,
                'config': {
                    'input_dim': input_dim,
                    'output_dim': output_dim,
                    'hidden_size': hidden_size,
                    'num_layers': num_layers,
                    'dropout': dropout_rate,
                    'kernel_size': kernel_size,
                    'sequence_length': LOOK_BACK,
                    'forecast_horizon': FORECAST_HORIZON,
                    'model_type': 'tcn'
                },
                'training_info': {
                    'product_id': product_id,
                    'product_name': product_name,
                    'training_mode': training_mode,
                    'store_id': store_id,
                    'aggregation_method': aggregation_method,
                    'timestamp': time.time()
                }
            }
            
            # 保存检查点
            save_checkpoint(checkpoint_data, epoch + 1, path_info)
            
            # 如果是最佳模型，额外保存一份
            if test_loss < best_loss:
                best_loss = test_loss
                save_checkpoint(checkpoint_data, 'best', path_info)
                emit_progress(f"💾 保存最佳模型检查点 (epoch {epoch+1}, test_loss: {test_loss:.4f})")
            
            emit_progress(f"💾 保存训练检查点 epoch_{epoch+1}")
        
        if (epoch + 1) % 10 == 0:
            print(f"Epoch {epoch+1}/{epochs}, Train Loss: {train_loss:.4f}, Test Loss: {test_loss:.4f}")
    
    # 计算训练时间
    training_time = time.time() - start_time
    
    # 设置模型保存阶段
    progress_manager.set_stage("model_saving", 0)
    emit_progress("训练完成，正在保存模型...")
    
    # 绘制损失曲线并保存到模型目录
    loss_curve_path = path_info['loss_curve_path']
    plot_loss_curve(
        train_losses,
        test_losses,
        product_name,
        'TCN',
        save_path=loss_curve_path
    )
    print(f"损失曲线已保存到: {loss_curve_path}")
    
    # 评估模型
    model.eval()
    with torch.no_grad():
        # 确保测试数据的形状正确
        test_pred = model(testX_tensor.to(DEVICE))
        # 将输出转换为二维数组 [samples, forecast_horizon]
        test_pred = test_pred.squeeze(-1).cpu().numpy()
        
    # 反归一化预测结果和真实值
    test_pred_inv = scaler_y.inverse_transform(test_pred.reshape(-1, 1)).flatten()
    test_true_inv = scaler_y.inverse_transform(testY.reshape(-1, 1)).flatten()
    
    # 计算评估指标
    metrics = evaluate_model(test_true_inv, test_pred_inv)
    metrics['training_time'] = training_time
    
    # 打印评估指标
    print("\n模型评估指标:")
    print(f"MSE: {metrics['mse']:.4f}")
    print(f"RMSE: {metrics['rmse']:.4f}")
    print(f"MAE: {metrics['mae']:.4f}")
    print(f"R²: {metrics['r2']:.4f}")
    print(f"MAPE: {metrics['mape']:.2f}%")
    print(f"训练时间: {training_time:.2f}秒")
    
    # 保存最终训练完成的模型（基于最终epoch）
    final_model_data = {
        'epoch': epochs,  # 最终epoch
        'model_state_dict': model.state_dict(),
        'optimizer_state_dict': optimizer.state_dict(),
        'train_loss': train_losses[-1],
        'test_loss': test_losses[-1],
        'train_losses': train_losses,
        'test_losses': test_losses,
        'scaler_X': scaler_X,
        'scaler_y': scaler_y,
        'config': {
            'input_dim': input_dim,
            'output_dim': output_dim,
            'hidden_size': hidden_size,
            'num_layers': num_layers,
            'dropout': dropout_rate,
            'kernel_size': kernel_size,
            'sequence_length': LOOK_BACK,
            'forecast_horizon': FORECAST_HORIZON,
            'model_type': 'tcn'
        },
        'metrics': metrics,
        'loss_curve_path': loss_curve_path,
        'training_info': {
            'product_id': product_id,
            'product_name': product_name,
            'training_mode': training_mode,
            'store_id': store_id,
            'aggregation_method': aggregation_method,
            'timestamp': time.time(),
            'training_completed': True
        }
    }
    
    progress_manager.set_stage("model_saving", 50)
    
    # 检查模型性能是否达标
    # 移除R2检查，始终保存模型
    if metrics:
        # 保存最终模型
        final_model_path = path_info['model_path']
        torch.save(final_model_data, final_model_path)
        print(f"[TCN] 最终模型已保存: {final_model_path}", flush=True)
        progress_manager.set_stage("model_saving", 100)
    else:
        final_model_path = None
        print(f"[TCN] 训练过程中未生成评估指标，不保存最终模型。", flush=True)
    
    final_metrics = {
        'mse': metrics['mse'],
        'rmse': metrics['rmse'],
        'mae': metrics['mae'],
        'r2': metrics['r2'],
        'mape': metrics['mape'],
        'training_time': training_time,
        'final_epoch': epochs
    }
    
    if final_model_path:
        emit_progress(f"模型训练完成！最终epoch: {epochs}", progress=100, metrics=final_metrics)
    else:
        emit_progress(f"❌ TCN模型训练失败：性能不达标", progress=100, metrics={'error': '模型性能不佳'})
    
    return model, metrics, epochs, final_model_path