liaozhaorun/ProStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 修正回归训练中的未来收益率计算公式

Browse Source 
- 修复 Label 公式从过去收益率改为未来收益率
This commit is contained in:
liaozhaorun
2026-03-06 20:56:24 +08:00
parent 7b935b0fa3
commit 555cb00276
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/experiment/regression.py
View File

@@ -1,7 +1,7 @@
"""LightGBM 回归训练示例 - 使用因子字符串表达式 """LightGBM 回归训练示例 - 使用因子字符串表达式
使用字符串表达式定义因子，训练 LightGBM 回归模型预测未来5日收益率。 使用字符串表达式定义因子，训练 LightGBM 回归模型预测未来5日收益率。
Label: return_5 = (close / ts_delay(close, 5)) - 1 Label: return_5 = (ts_delay(close, -5) / close) - 1 # 未来5日收益率
""" """
import os import os
@@ -19,7 +19,8 @@ from src.training import (
StockFilterConfig, StockFilterConfig,
StockPoolManager, StockPoolManager,
Trainer, Trainer,
Winsorizer, NullFiller, Winsorizer,
NullFiller,
) )
from src.training.config import TrainingConfig from src.training.config import TrainingConfig
@@ -56,7 +57,7 @@ FACTOR_DEFINITIONS = {
# Label 因子定义（不参与训练，用于计算目标） # Label 因子定义（不参与训练，用于计算目标）
LABEL_FACTOR = { LABEL_FACTOR = {
"return_5": "(close / ts_delay(close, 5)) - 1", "return_5": "(ts_delay(close, -5) / close) - 1", # 未来5日收益率
} }
# ============================================================================= # =============================================================================