feat(training): 新增 TabM 模型支持及数据质量优化

- 添加 TabMModel、TabPFNModel 深度学习模型实现
- 新增 DataQualityAnalyzer 进行训练前数据质量诊断
- 改进数据处理器 NaN/null 双重处理,增强数据鲁棒性
- 支持 train_skip_days 参数跳过训练初期数据不足期
- Pipeline 自动清理标签为 NaN 的样本
This commit is contained in:
2026-03-31 23:11:21 +08:00
parent 9e0114c745
commit 36a3ccbcc8
22 changed files with 4421 additions and 204 deletions

View File

@@ -37,6 +37,7 @@ from src.experiment.common import (
get_model_save_path,
save_model_with_factors,
TOP_N,
TRAIN_SKIP_DAYS,
)
# 训练类型标识
@@ -155,6 +156,7 @@ def main():
filters=[STFilter(data_router=engine.router)],
stock_pool_filter_func=stock_pool_filter,
stock_pool_required_columns=STOCK_FILTER_REQUIRED_COLUMNS,
train_skip_days=TRAIN_SKIP_DAYS,
)
# 4. 创建 RankTask