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

feat: 完善 QMT 交易模块文档和配置展示功能

Browse Source 
- 优化前端仪表盘界面
- 添加配置文件可视化展示
- 编写 QMT 模块配置文档
- 完善项目规则体系（KiloCode）
This commit is contained in:
liaozhaorun
2026-01-27 00:52:35 +08:00
parent 50ee1a5a0a
commit 4607555eaf
31 changed files with 5248 additions and 8621 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
main/factor/__init__.py
View File

@@ -78,88 +78,6 @@ from .momentum_factors import (
VolatilityFactor,
MomentumFactor,
MomentumAcceleration,
TrendEfficiency
TrendEfficiency,
SimpleVolatilityFactor
)
# 导入统一因子计算模块
from .all_factors import calculate_all_factors, compute_factors
# 导入算子框架
from .operator_framework import StockWiseFactor, DateWiseFactor, FactorGraph
# 定义所有因子类的列表，便于统一管理
ALL_STOCK_FACTORS = [
SMAFactor,
EMAFactor,
ATRFactor,
OBVFactor,
MACDFactor,
RSI_Factor,
LGFlowFactor,
FlowIntensityFactor,
FlowDivergenceFactor,
FlowStructureFactor,
FlowAccelerationFactor,
ChipConcentrationFactor,
ChipSkewnessFactor,
FloatingChipFactor,
CostSupportFactor,
WinnerPriceZoneFactor,
SentimentPanicGreedFactor,
SentimentBreadthFactor,
SentimentReversalFactor,
PriceDeductionFactor,
PriceDeductionRatioFactor,
CashflowToEVFactor,
BookToPriceFactor,
DebtToEquityFactor,
ProfitMarginFactor,
LimitFactor,
VolumeRatioFactor,
BBI_RATIO_FACTOR,
VolatilitySlopeFactor,
PriceVolumeTrendFactor
]
ALL_DATE_FACTORS = [
CrossSectionalRankFactor,
IndustryMomentumFactor,
MarketBreadthFactor,
SectorRotationFactor
]
__all__ = [
# 技术指标因子
'SMAFactor', 'EMAFactor', 'ATRFactor', 'OBVFactor', 'MACDFactor', 'RSI_Factor',
# 资金流因子
'LGFlowFactor', 'FlowIntensityFactor', 'FlowDivergenceFactor',
'FlowStructureFactor', 'FlowAccelerationFactor',
# 筹码分布因子
'ChipConcentrationFactor', 'ChipSkewnessFactor', 'FloatingChipFactor',
'CostSupportFactor', 'WinnerPriceZoneFactor',
# 市场情绪因子
'SentimentPanicGreedFactor', 'SentimentBreadthFactor', 'SentimentReversalFactor',
'PriceDeductionFactor', 'PriceDeductionRatioFactor',
# 行业/横截面因子
'CrossSectionalRankFactor', 'IndustryMomentumFactor', 'MarketBreadthFactor',
'SectorRotationFactor',
# 财务因子
'CashflowToEVFactor', 'BookToPriceFactor', 'ROEFactor', 'DebtToEquityFactor',
'ProfitMarginFactor',
# 特殊因子
'LimitFactor', 'VolumeRatioFactor', 'BBI_RATIO_FACTOR',
'VolatilitySlopeFactor', 'PriceVolumeTrendFactor',
# 统一因子计算
'calculate_all_factors', 'compute_factors', 'get_available_stock_factors', 'get_available_date_factors',
# # 算子框架
# 'StockWiseFactor', 'DateWiseFactor'
]

5
main/factor/all_factors.py
View File

@@ -65,6 +65,7 @@ from main.factor import (
BBI_RATIO_FACTOR,
VolatilitySlopeFactor,
PriceVolumeTrendFactor,
SimpleVolatilityFactor
)
@@ -168,6 +169,10 @@ def calculate_all_factors(
"class": CrossSectionalRankFactor,
"params": {"column": "circ_mv", "name": "size_rank"},
},
{
"class": SimpleVolatilityFactor,
"params": {"high", "low", "vol"}
}
]
if date_factor_configs is None:

85
main/factor/momentum_factors.py
View File

@@ -122,53 +122,38 @@ class TrendEfficiency(StockWiseFactor):
return efficiency_ratio
# -------------------- 统一计算函数 --------------------
def calculate_momentum_factors(df: pl.DataFrame) -> pl.DataFrame:
"""
统一计算动量因子的函数
Parameters:
df (pl.DataFrame): 输入的股票数据表，必须包含以下列：
ts_code, trade_date, close, pct_chg, high, low, vol
Returns:
pl.DataFrame: 包含所有动量因子的DataFrame
"""
# 初始化结果DataFrame
result_df = df.clone()
# 定义要计算的因子列表
# 先计算股票截面因子（时间序列因子）
stock_operators = [
ReturnFactor(5),
ReturnFactor(20),
VolatilityFactor(10),
VolatilityFactor(30),
MomentumFactor(10),
MomentumFactor(30),
RSI_Factor(14)
]
# 依次应用股票截面因子算子
for operator in stock_operators:
try:
result_df = operator.apply(result_df)
except Exception as e:
print(f"计算股票截面因子 {operator.factor_id} 时出错: {e}")
# 再计算日期截面因子（横截面排序因子）
date_operators = [
CrossSectionalRanking("return_5d"),
CrossSectionalRanking("return_20d"),
CrossSectionalRanking("volatility_10d"),
CrossSectionalRanking("momentum_10d")
]
# 依次应用日期截面因子算子
for operator in date_operators:
try:
result_df = operator.apply(result_df)
except Exception as e:
print(f"计算日期截面因子 {operator.factor_id} 时出错: {e}")
return result_df
class SimpleVolatilityFactor(StockWiseFactor):
factor_id = "simple_volatility"
required_factor_ids = ["high", "low", "vol"]
def __init__(self):
super(SimpleVolatilityFactor, self).__init__(
name=self.factor_id,
parameters={},
required_factor_ids=self.required_factor_ids
)
def calc_factor(self, g: pl.DataFrame) -> pl.Series:
high = g["high"]
low = g["low"]
vol = g["vol"]
# Step 1: 计算 EM_i,t
# 注意：shift(1) 得到 t-1 的值
em = ((high + low) - (high.shift(1) + low.shift(1))) / 2.0
em = em.fill_null(0.0) # 第一天无前值，设为0
# Step 2: 计算 BR_i,t
# 避免除零：若 High == Low，设 BR = 0
range_ = high - low
br = vol / range_
br = br.fill_null(0.0).replace({float('inf'): 0.0, float('-inf'): 0.0})
# Step 3: 计算 MM_i,t = EM / BR
mm = em / br
mm = mm.fill_null(0.0).replace({float('inf'): 0.0, float('-inf'): 0.0})
# Step 4: 计算 239 日简单移动平均
emv = mm.rolling_mean(window_size=239, min_periods=1)
return emv.alias(self.factor_id)

15
main/factor/qlib_utils.py
View File

@@ -12,7 +12,6 @@ import pandas as pd
def prepare_data(
polars_df: pl.DataFrame,
label_horizon: int = 5,
open_col: str = "open",
date_col: str = "trade_date",
code_col: str = "ts_code",
@@ -24,13 +23,13 @@ def prepare_data(
df = polars_df.sort([code_col, date_col])
# 获取 T+1 日的开盘价（作为买入价）
df = df.with_columns([
pl.col(open_col).shift(-1).over(code_col).alias("__buy_price"),
pl.col(open_col).shift(-(1 + label_horizon)).over(code_col).alias("__sell_price"),
]).with_columns([
(pl.col("__sell_price") / pl.col("__buy_price") - 1).alias("label")
]).drop(["__buy_price", "__sell_price"])
# # 获取 T+1 日的开盘价（作为买入价）
# df = df.with_columns([
# pl.col(open_col).shift(-1).over(code_col).alias("__buy_price"),
# pl.col(open_col).shift(-(1 + label_horizon)).over(code_col).alias("__sell_price"),
# ]).with_columns([
# (pl.col("__sell_price") / pl.col("__buy_price") - 1).alias("label")
# ]).drop(["__buy_price", "__sell_price"])
# 转 pandas
df = df.to_pandas()