crpto_predictor/train_full_data.py

"""方案A：使用2020-2025年BTC全部数据训练 - 准备实盘使用"""

import sys
import os
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from data.fetcher import BinanceDataFetcher
from data.preprocessor import CryptoPreprocessor, split_data
from data.dataset import create_dataloaders
from models.dlinear.model import DLinear, DLinearConfig
from training.trainer import Trainer
from training.config import TrainingConfig
import json
import numpy as np

def main():
    print("="*80)
    print("方案A：BTC全量数据训练 (2020-2025)")
    print("训练集：95% | 验证集：5%（仅用于early stopping）| 测试集：无")
    print("="*80)

    # ========== 步骤1: 获取全部BTC数据 ==========
    print("\n[1/7] 获取BTC 2020-2025年全部数据...")
    fetcher = BinanceDataFetcher()
    df = fetcher.fetch_ohlcv(
        symbol='BTC',
        timeframe='1h',
        start_date='2020-01-01',
        end_date='2025-12-31',
        use_cache=True
    )

    print(f"✓ 已获取 {len(df):,} 行数据（约{len(df)/8760:.1f}年）")
    print(f"✓ 时间范围：{df['timestamp'].min()} 至 {df['timestamp'].max()}")
    print(f"✓ 价格范围：${df['close'].iloc[0]:,.2f} → ${df['close'].iloc[-1]:,.2f}")
    total_return = (df['close'].iloc[-1] - df['close'].iloc[0]) / df['close'].iloc[0]
    print(f"✓ 总收益率：{total_return*100:+.2f}%")

    # 市场周期分析
    df['year'] = df['timestamp'].dt.year
    print(f"\n✓ 市场周期覆盖：")
    for year in sorted(df['year'].unique()):
        year_df = df[df['year'] == year]
        if len(year_df) > 100:
            year_return = (year_df['close'].iloc[-1] - year_df['close'].iloc[0]) / year_df['close'].iloc[0]
            trend = "🚀 牛市" if year_return > 0.3 else ("🔴 熊市" if year_return < -0.3 else "📊 震荡")
            print(f"    {year}年: {year_return*100:+7.2f}%  {trend}")

    # ========== 步骤2: 数据预处理 ==========
    print("\n[2/7] 数据预处理（回归任务）...")
    preprocessor = CryptoPreprocessor(
        lookback=168,           # 输入：过去7天
        forecast_horizon=1,     # 预测：未来1小时
        price_change_threshold=0.0
    )
    X, y, processed_df = preprocessor.preprocess_pipeline(df, task='regression', fit=True)

    print(f"✓ 序列数量：{len(X):,}")
    print(f"✓ 序列形状：{X.shape}")
    print(f"✓ 特征数量：{X.shape[-1]}")

    print(f"\n✓ 标签统计（收益率）：")
    print(f"    最小值: {y.min()*100:.4f}%")
    print(f"    最大值: {y.max()*100:.4f}%")
    print(f"    均值:   {y.mean()*100:.4f}%")
    print(f"    标准差: {y.std()*100:.4f}%")
    print(f"    中位数: {np.median(y)*100:.4f}%")

    n_positive = (y > 0).sum()
    n_negative = (y <= 0).sum()
    print(f"\n✓ 方向分布：")
    print(f"    上涨: {n_positive:,} ({n_positive/len(y)*100:.1f}%)")
    print(f"    下跌: {n_negative:,} ({n_negative/len(y)*100:.1f}%)")

    # ========== 步骤3: 划分数据集（95% 训练 + 5% 验证）==========
    print("\n[3/7] 划分数据集（95%训练 + 5%验证）...")
    print("⚠️  注意：此次训练使用几乎全部数据，无独立测试集")
    print("    验证集仅用于early stopping防止过拟合")

    n = len(X)
    train_end = int(n * 0.95)

    X_train = X[:train_end]
    y_train = y[:train_end]
    X_val = X[train_end:]
    y_val = y[train_end:]

    print(f"\n  训练集：{len(X_train):,} 样本 ({len(X_train)/n*100:.1f}%)")
    print(f"    收益率范围: {y_train.min()*100:.4f}% ~ {y_train.max()*100:.4f}%")

    print(f"  验证集：{len(X_val):,} 样本 ({len(X_val)/n*100:.1f}%)")
    print(f"    收益率范围: {y_val.min()*100:.4f}% ~ {y_val.max()*100:.4f}%")

    # 时间范围分析
    lookback = 168
    train_df = processed_df.iloc[lookback:train_end+lookback]
    val_df = processed_df.iloc[train_end+lookback:]

    print(f"\n  时间范围：")
    print(f"    训练集: {train_df['timestamp'].min()} 至 {train_df['timestamp'].max()}")
    train_return = (train_df['close'].iloc[-1] - train_df['close'].iloc[0]) / train_df['close'].iloc[0]
    print(f"            ${train_df['close'].iloc[0]:,.0f} → ${train_df['close'].iloc[-1]:,.0f} ({train_return*100:+.1f}%)")

    print(f"    验证集: {val_df['timestamp'].min()} 至 {val_df['timestamp'].max()}")
    val_return = (val_df['close'].iloc[-1] - val_df['close'].iloc[0]) / val_df['close'].iloc[0]
    print(f"            ${val_df['close'].iloc[0]:,.0f} → ${val_df['close'].iloc[-1]:,.0f} ({val_return*100:+.1f}%)")

    # ========== 步骤4: 创建数据加载器 ==========
    print("\n[4/7] 创建数据加载器...")
    train_loader, val_loader, _ = create_dataloaders(
        (X_train, y_train),
        (X_val, y_val),
        (X_val, y_val),  # 测试集用验证集替代（不使用）
        task='regression',
        batch_size=64
    )

    # ========== 步骤5: 创建模型 ==========
    print("\n[5/7] 创建DLinear回归模型...")
    model_config = DLinearConfig(
        input_dim=X.shape[-1],
        lookback=168,
        task='regression',
        hidden_dim=512,
        dropout=0.1,
        moving_avg_kernel=25
    )
    model = DLinear(model_config)
    print(f"✓ 模型参数：{model.count_parameters():,} 个")
    print(f"✓ 任务类型：回归（预测未来1小时收益率）")
    print(f"✓ 损失函数：MSELoss")

    # ========== 步骤6: 训练模型 ==========
    print("\n[6/7] 开始全量数据训练...")
    print(f"✓ 训练样本：{len(X_train):,} （使用了{len(X_train)/len(X)*100:.1f}%的数据）")
    print(f"✓ 对比之前：之前训练集36,645样本，现在{len(X_train):,}样本（+{(len(X_train)-36645)/36645*100:.1f}%）")

    train_config = TrainingConfig(
        batch_size=64,
        max_epochs=50,
        learning_rate=0.001,
        early_stopping_patience=15,  # 增加patience，允许更充分训练
        lr_scheduler='plateau',
        save_best=True,
        checkpoint_dir='./models/checkpoints/dlinear_btc_full_data'
    )

    trainer = Trainer(model, train_config, task='regression')
    history = trainer.fit(train_loader, val_loader)

    # ========== 步骤7: 保存最终模型 ==========
    print("\n[7/7] 保存最终模型...")

    # 在验证集上快速评估
    print("\n在验证集上进行sanity check...")
    val_metrics = trainer.evaluate(val_loader)

    results_path = './models/checkpoints/dlinear_btc_full_data/final_metrics.json'
    with open(results_path, 'w') as f:
        json.dump(val_metrics, f, indent=2)
    print(f"✓ 结果保存至：{results_path}")

    # 同时保存预处理器（实盘使用时需要）
    import pickle
    preprocessor_path = './models/checkpoints/dlinear_btc_full_data/preprocessor.pkl'
    with open(preprocessor_path, 'wb') as f:
        pickle.dump(preprocessor, f)
    print(f"✓ 预处理器保存至：{preprocessor_path}")

    # ========== 最终报告 ==========
    print("\n" + "="*80)
    print("全量数据训练完成 - 最终报告")
    print("="*80)

    print(f"\n📊 训练概况：")
    print(f"  数据时间范围：2020-01-01 至 2025-12-31 (6年)")
    print(f"  训练样本数量：{len(X_train):,} (95%)")
    print(f"  验证样本数量：{len(X_val):,} (5%)")
    print(f"  特征数量：{X.shape[-1]}")
    print(f"  模型参数：{model.count_parameters():,}")

    print(f"\n📈 验证集性能（仅供参考，非独立测试）：")
    print(f"  RMSE:        {val_metrics.get('rmse', 0)*100:.4f}%")
    print(f"  MAE:         {val_metrics.get('mae', 0)*100:.4f}%")
    print(f"  方向准确率:   {val_metrics.get('directional_accuracy', 0)*100:.2f}%")

    print(f"\n💰 验证集回测（仅供参考）：")
    print(f"  总收益率:    {val_metrics.get('backtest_total_return', 0)*100:.2f}%")
    print(f"  夏普比率:    {val_metrics.get('backtest_sharpe_ratio', 0):.4f}")
    max_dd = val_metrics.get('backtest_max_drawdown', 0)
    if not np.isnan(max_dd):
        print(f"  最大回撤:    {max_dd*100:.2f}%")
    print(f"  胜率:        {val_metrics.get('backtest_win_rate', 0)*100:.2f}%")

    print("\n" + "="*80)
    print("🎯 全量训练 vs 之前训练对比")
    print("="*80)

    print("\n之前训练（70/15/15分割）：")
    print("  训练样本: 36,645")
    print("  时间范围: 2020-01 至 2024-03")
    print("  测试集方向准确率: 50.67%")
    print("  测试集回测收益: -16.71%")

    print(f"\n当前全量训练（95/5分割）：")
    print(f"  训练样本: {len(X_train):,} (+{(len(X_train)-36645)/36645*100:.1f}%)")
    print(f"  时间范围: 2020-01 至 {train_df['timestamp'].max().strftime('%Y-%m')}")
    print(f"  验证集方向准确率: {val_metrics.get('directional_accuracy', 0)*100:.2f}%")
    print(f"  验证集回测收益: {val_metrics.get('backtest_total_return', 0)*100:.2f}%")

    print("\n" + "="*80)
    print("⚠️  重要说明")
    print("="*80)
    print("\n1. 此模型使用了95%的历史数据训练")
    print("2. 验证集仅占5%，性能指标仅供参考，不代表真实泛化能力")
    print("3. 模型已针对2020-2025年市场环境充分优化")
    print("4. 适用场景：")
    print("   ✅ 用于2026年未来数据的预测")
    print("   ✅ 用于实盘交易（假设未来市场特征与历史相似）")
    print("   ❌ 不适合评估在未见过数据上的泛化性能")

    print("\n💡 下一步建议：")
    print("  1. 使用此模型预测2026年1月的BTC价格")
    print("  2. 在实盘中小仓位测试策略")
    print("  3. 定期（每月/季度）用新数据重新训练模型")
    print("  4. 监控实盘性能，如果偏差大说明市场环境变化")

    print("\n" + "="*80)
    print("✓ 训练完成！模型已保存到 ./models/checkpoints/dlinear_btc_full_data/")
    print("="*80)

if __name__ == "__main__":
    main()