Initial commit: BTC 1h prediction model (53.10% accuracy)

🎯 项目成果： - 准确率: 53.10% (2026年测试集) - 任务类型: 二分类 (预测涨/跌) - 特征: OHLCV + RSI + MACD (9个特征) - 训练数据: 2020-2025年BTC小时数据 (52,351序列) - 测试数据: 2026年1-29日 (484序列) 📊 性能指标： - 精确率: 51.79% - 召回率: 49.36% - F1分数: 0.5054 - 预测分布: 非常平衡 (偏差仅-11个) 🔬 实验历史： - 尝试了5种方案 (回归/分类, 不同数据划分) - 分类任务优于回归任务 (53.10% vs 49.5%) - 全量训练避免了过拟合问题 📦 主要模型文件： - models/checkpoints/dlinear_classification_2026/ - best_model.pt (最佳模型) - preprocessor.pkl (预处理器) - test_2026_results.json (测试结果) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-29 21:27:15 +08:00
commit 9bbdc8d42b
@@ -0,0 +1,258 @@
+"""使用回归任务训练DLinear模型 - 预测未来1小时的实际价格变化百分比"""
+
+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("DLinear回归模型训练 - 预测未来1小时价格变化百分比")
+    print("="*80)
+
+    # 步骤1: 获取2020-2025年完整数据
+    print("\n[1/8] 从Binance获取BTC 2020-2025年完整数据...")
+    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()}")
+
+    # 分析数据覆盖的市场周期
+    print(f"\n✓ 价格变化分析：")
+    print(f"  起始价格: ${df['close'].iloc[0]:,.2f} (2020年)")
+    print(f"  结束价格: ${df['close'].iloc[-1]:,.2f} (2025年)")
+    total_return = (df['close'].iloc[-1] - df['close'].iloc[0]) / df['close'].iloc[0]
+    print(f"  总收益率: {total_return*100:+.2f}%")
+
+    # 按年分析
+    df['year'] = df['timestamp'].dt.year
+    print(f"\n✓ 年度表现分析（确保包含牛熊周期）：")
+    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（回归任务）
+    print("\n[2/8] 数据预处理（回归任务 - 预测未来1小时的收益率）...")
+    preprocessor = CryptoPreprocessor(
+        lookback=168,           # 输入：过去168小时（7天）
+        forecast_horizon=1,     # 预测：未来1小时
+        price_change_threshold=0.0  # 回归任务不使用阈值
+    )
+    X, y, processed_df = preprocessor.preprocess_pipeline(df, task='regression', fit=True)
+    print(f"✓ 已创建序列：X形状 = {X.shape}, y形状 = {y.shape}")
+    print(f"✓ 特征数量：{X.shape[-1]}")
+
+    # 分析标签分布（收益率）
+    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}%")
+
+    # 方向统计
+    n_positive = (y > 0).sum()
+    n_negative = (y <= 0).sum()
+    print(f"\n✓ 方向分布：")
+    print(f"  正收益（上涨）: {n_positive} ({n_positive/len(y)*100:.1f}%)")
+    print(f"  负收益（下跌）: {n_negative} ({n_negative/len(y)*100:.1f}%)")
+
+    # 步骤3: 划分数据集
+    print("\n[3/8] 划分训练/验证/测试集 (70/15/15)...")
+    train_data, val_data, test_data = split_data(X, y, train_split=0.7, val_split=0.15)
+
+    print(f"  训练集：{len(train_data[0])} 样本")
+    print(f"    收益率范围: {train_data[1].min()*100:.4f}% ~ {train_data[1].max()*100:.4f}%")
+    print(f"    均值: {train_data[1].mean()*100:.4f}%")
+
+    print(f"  验证集：{len(val_data[0])} 样本")
+    print(f"    收益率范围: {val_data[1].min()*100:.4f}% ~ {val_data[1].max()*100:.4f}%")
+    print(f"    均值: {val_data[1].mean()*100:.4f}%")
+
+    print(f"  测试集：{len(test_data[0])} 样本")
+    print(f"    收益率范围: {test_data[1].min()*100:.4f}% ~ {test_data[1].max()*100:.4f}%")
+    print(f"    均值: {test_data[1].mean()*100:.4f}%")
+
+    # 分析各数据集对应的时间范围
+    lookback = 168
+    train_end_idx = int(len(processed_df) * 0.7) - lookback
+    val_end_idx = int(len(processed_df) * 0.85) - lookback
+
+    train_df = processed_df.iloc[lookback:train_end_idx+lookback]
+    val_df = processed_df.iloc[train_end_idx+lookback:val_end_idx+lookback]
+    test_df = processed_df.iloc[val_end_idx+lookback:]
+
+    print(f"\n  训练集时间范围: {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"    价格: ${train_df['close'].iloc[0]:,.0f} → ${train_df['close'].iloc[-1]:,.0f} ({train_return*100:+.1f}%)")
+
+    print(f"  验证集时间范围: {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"    价格: ${val_df['close'].iloc[0]:,.0f} → ${val_df['close'].iloc[-1]:,.0f} ({val_return*100:+.1f}%)")
+
+    print(f"  测试集时间范围: {test_df['timestamp'].min()} 至 {test_df['timestamp'].max()}")
+    test_return = (test_df['close'].iloc[-1] - test_df['close'].iloc[0]) / test_df['close'].iloc[0]
+    print(f"    价格: ${test_df['close'].iloc[0]:,.0f} → ${test_df['close'].iloc[-1]:,.0f} ({test_return*100:+.1f}%)")
+
+    # 步骤4: 创建数据加载器
+    print("\n[4/8] 创建PyTorch数据加载器...")
+    train_loader, val_loader, test_loader = create_dataloaders(
+        train_data, val_data, test_data,
+        task='regression',  # 回归任务
+        batch_size=64
+    )
+
+    # 步骤5: 创建模型
+    print("\n[5/8] 创建DLinear回归模型...")
+    model_config = DLinearConfig(
+        input_dim=X.shape[-1],
+        lookback=168,
+        task='regression',  # 回归任务
+        hidden_dim=512,
+        dropout=0.1,
+        moving_avg_kernel=25
+    )
+    model = DLinear(model_config)
+    print(f"✓ 模型已创建，可训练参数：{model.count_parameters():,} 个")
+    print(f"✓ 任务类型：回归（预测收益率百分比）")
+    print(f"✓ 损失函数：MSELoss")
+
+    # 步骤6: 训练模型
+    print("\n[6/8] 开始训练回归模型...")
+    train_config = TrainingConfig(
+        batch_size=64,
+        max_epochs=50,
+        learning_rate=0.001,
+        early_stopping_patience=10,
+        lr_scheduler='plateau',
+        save_best=True,
+        checkpoint_dir='./models/checkpoints/dlinear_btc_regression'
+    )
+
+    trainer = Trainer(
+        model,
+        train_config,
+        task='regression'  # 回归任务，不需要pos_weight
+    )
+
+    print(f"✓ 训练数据规模：{len(train_data[0]):,} 样本")
+    history = trainer.fit(train_loader, val_loader)
+
+    # 步骤7: 评估模型
+    print("\n[7/8] 在测试集上评估模型...")
+    metrics = trainer.evaluate(test_loader)
+
+    # 保存评估结果
+    results_path = './models/checkpoints/dlinear_btc_regression/test_metrics.json'
+    with open(results_path, 'w') as f:
+        json.dump(metrics, f, indent=2)
+
+    print(f"\n✓ 评估结果已保存至：{results_path}")
+
+    # 步骤8: 结果分析
+    print("\n[8/8] 回归模型性能分析...")
+    print("\n" + "="*80)
+    print("训练完成 - 回归模型测试结果")
+    print("="*80)
+
+    print(f"\n📊 回归指标:")
+    print(f"  RMSE (均方根误差):  {metrics.get('rmse', 0):.6f} ({metrics.get('rmse', 0)*100:.4f}%)")
+    print(f"  MAE (平均绝对误差):  {metrics.get('mae', 0):.6f} ({metrics.get('mae', 0)*100:.4f}%)")
+    print(f"  MAPE (平均绝对百分比误差): {metrics.get('mape', 0):.2f}%")
+    print(f"  方向准确率:         {metrics.get('directional_accuracy', 0)*100:.2f}%")
+
+    print(f"\n💰 回测结果:")
+    print(f"  总收益率:    {metrics.get('backtest_total_return', 0)*100:.2f}%")
+    print(f"  最终资金:    ${metrics.get('backtest_final_capital', 0):,.2f}")
+    print(f"  夏普比率:    {metrics.get('backtest_sharpe_ratio', 0):.4f}")
+    max_dd = metrics.get('backtest_max_drawdown', 0)
+    if not np.isnan(max_dd):
+        print(f"  最大回撤:    {max_dd*100:.2f}%")
+    else:
+        print(f"  最大回撤:    N/A")
+    print(f"  胜率:        {metrics.get('backtest_win_rate', 0)*100:.2f}%")
+    print(f"  交易次数:    {metrics.get('backtest_num_trades', 0)}")
+
+    # 与分类任务对比
+    print("\n" + "="*80)
+    print("📊 回归 vs 分类任务对比")
+    print("="*80)
+
+    print(f"\n二分类模型（之前的结果）:")
+    print(f"  准确率: 49.76%")
+    print(f"  F1分数: 0.3898")
+    print(f"  预测偏差: 68.1%预测下跌（过度悲观）")
+    print(f"  回测收益: -3.29%")
+
+    print(f"\n回归模型（当前结果）:")
+    print(f"  方向准确率: {metrics.get('directional_accuracy', 0)*100:.2f}%")
+    print(f"  RMSE: {metrics.get('rmse', 0)*100:.4f}%")
+    print(f"  MAE: {metrics.get('mae', 0)*100:.4f}%")
+    print(f"  回测收益: {metrics.get('backtest_total_return', 0)*100:.2f}%")
+
+    # 性能评估
+    print(f"\n🎯 回归模型性能评估:")
+
+    dir_acc = metrics.get('directional_accuracy', 0)
+    if dir_acc > 0.55:
+        print(f"  ✅ 方向准确率 {dir_acc*100:.1f}% > 55%，模型有预测能力")
+    elif dir_acc > 0.50:
+        print(f"  ⚠️  方向准确率 {dir_acc*100:.1f}% 略优于随机，预测能力较弱")
+    else:
+        print(f"  ❌ 方向准确率 {dir_acc*100:.1f}% ≤ 50%，方向预测能力不足")
+
+    rmse = metrics.get('rmse', 0)
+    mae = metrics.get('mae', 0)
+    print(f"\n  误差分析:")
+    print(f"    RMSE = {rmse*100:.4f}% - 平均预测误差的平方根")
+    print(f"    MAE = {mae*100:.4f}% - 平均绝对误差")
+    if rmse < 0.01:  # 小于1%
+        print(f"    ✅ RMSE < 1%，预测精度较高")
+    elif rmse < 0.02:  # 小于2%
+        print(f"    ⚠️  RMSE在1-2%之间，预测精度中等")
+    else:
+        print(f"    ❌ RMSE > 2%，预测误差较大")
+
+    total_return = metrics.get('backtest_total_return', 0)
+    if total_return > 0.05:
+        print(f"\n  ✅ 回测收益 {total_return*100:.2f}% > 5%，策略有盈利潜力")
+    elif total_return > 0:
+        print(f"\n  ⚠️  回测收益 {total_return*100:.2f}% > 0，策略微弱盈利")
+    else:
+        print(f"\n  ❌ 回测收益 {total_return*100:.2f}% ≤ 0，策略亏损")
+
+    print("\n💡 回归任务的优势:")
+    print("  ✅ 提供预测幅度信息（可用于动态仓位管理）")
+    print("  ✅ 评估风险收益比")
+    print("  ✅ 更适合量化交易策略")
+
+    print("\n💡 回归任务的挑战:")
+    print("  ❌ 预测具体数值比预测方向更难")
+    print("  ❌ 对异常值敏感")
+    print("  ❌ 需要更多训练数据才能稳定")
+
+    print("\n" + "="*80)
+    print("✓ 回归模型训练完成！")
+    print("="*80)
+
+if __name__ == "__main__":
+    main()