feat:添加alpha模块
This commit is contained in:
@@ -0,0 +1,254 @@
|
||||
"""
|
||||
策略模块 — 信号生成、权重分配、组合构建
|
||||
"""
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Dict, List, Optional, Set, Tuple
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 信号生成器
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class SignalGenerator(ABC):
|
||||
"""信号生成器基类 — 将因子值转换为交易信号"""
|
||||
|
||||
@abstractmethod
|
||||
def generate(self, factor_df: pd.DataFrame, **kwargs) -> pd.DataFrame:
|
||||
"""
|
||||
factor_df: DataFrame, index=date, columns=stock_codes, values=factor值
|
||||
返回信号 DataFrame，同结构，1=做多, 0=平仓, -1=做空
|
||||
"""
|
||||
...
|
||||
|
||||
|
||||
class QuantileSignal(SignalGenerator):
|
||||
"""基于因子分位数的信号生成器"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
n_quantiles: int = 5,
|
||||
long_quantile: int = 5,
|
||||
short_quantile: int = 1,
|
||||
min_stocks: int = 10,
|
||||
):
|
||||
self.n_quantiles = n_quantiles
|
||||
self.long_quantile = long_quantile
|
||||
self.short_quantile = short_quantile
|
||||
self.min_stocks = min_stocks
|
||||
|
||||
def generate(self, factor_df: pd.DataFrame, **kwargs) -> pd.DataFrame:
|
||||
"""
|
||||
逐截面按因子值分组：
|
||||
long_quantile 档 → +1
|
||||
short_quantile 档 → -1
|
||||
其余 → 0
|
||||
"""
|
||||
signal = pd.DataFrame(0, index=factor_df.index, columns=factor_df.columns)
|
||||
|
||||
for date in factor_df.index:
|
||||
row = factor_df.loc[date].dropna()
|
||||
if len(row) < self.min_stocks:
|
||||
continue
|
||||
try:
|
||||
bins = pd.qcut(
|
||||
row, self.n_quantiles, labels=False, duplicates="drop"
|
||||
)
|
||||
except ValueError:
|
||||
continue
|
||||
signal.loc[date, bins == self.long_quantile - 1] = 1
|
||||
signal.loc[date, bins == self.short_quantile - 1] = -1
|
||||
|
||||
return signal
|
||||
|
||||
|
||||
class ZScoreSignal(SignalGenerator):
|
||||
"""基于 Z-Score 阈值的信号生成器"""
|
||||
|
||||
def __init__(self, entry_z: float = 1.0, exit_z: float = 0.5):
|
||||
self.entry_z = entry_z
|
||||
self.exit_z = exit_z
|
||||
|
||||
def generate(self, factor_df: pd.DataFrame, **kwargs) -> pd.DataFrame:
|
||||
"""
|
||||
因子截面标准化（Z-Score）:
|
||||
> entry_z → +1
|
||||
< -entry_z → -1
|
||||
其余 → 0
|
||||
"""
|
||||
signal = pd.DataFrame(0, index=factor_df.index, columns=factor_df.columns)
|
||||
for date in factor_df.index:
|
||||
row = factor_df.loc[date]
|
||||
valid = row.notna()
|
||||
if valid.sum() < 3:
|
||||
continue
|
||||
z = (row - row[valid].mean()) / (row[valid].std() + 1e-12)
|
||||
signal.loc[date, z > self.entry_z] = 1
|
||||
signal.loc[date, z < -self.entry_z] = -1
|
||||
return signal
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 权重分配器
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class WeightAllocator(ABC):
|
||||
"""权重分配器基类"""
|
||||
|
||||
@abstractmethod
|
||||
def allocate(
|
||||
self,
|
||||
signals: pd.DataFrame,
|
||||
prices: pd.DataFrame,
|
||||
cash: float,
|
||||
positions: Dict[str, int],
|
||||
**kwargs,
|
||||
) -> Dict[str, float]:
|
||||
"""
|
||||
返回目标权重字典 {stock_code: weight}
|
||||
weight 为目标持仓市值占比 (0~1)
|
||||
"""
|
||||
...
|
||||
|
||||
|
||||
class EqualWeightAllocator(WeightAllocator):
|
||||
"""等权分配器"""
|
||||
|
||||
def __init__(self, max_positions: int = 30):
|
||||
self.max_positions = max_positions
|
||||
|
||||
def allocate(
|
||||
self,
|
||||
signals: pd.DataFrame,
|
||||
prices: pd.DataFrame,
|
||||
cash: float,
|
||||
positions: Dict[str, int],
|
||||
**kwargs,
|
||||
) -> Dict[str, float]:
|
||||
latest_signal = signals.iloc[-1] if len(signals) > 0 else pd.Series(dtype=float)
|
||||
long_stocks = latest_signal[latest_signal > 0].index.tolist()
|
||||
|
||||
if not long_stocks:
|
||||
return {}
|
||||
|
||||
# 限制持仓数
|
||||
long_stocks = long_stocks[: self.max_positions]
|
||||
weight = 1.0 / len(long_stocks)
|
||||
return {s: weight for s in long_stocks}
|
||||
|
||||
|
||||
class FactorWeightAllocator(WeightAllocator):
|
||||
"""因子值加权分配器 — 因子越大权重越大"""
|
||||
|
||||
def __init__(self, max_positions: int = 30, min_weight: float = 0.005):
|
||||
self.max_positions = max_positions
|
||||
self.min_weight = min_weight
|
||||
|
||||
def allocate(
|
||||
self,
|
||||
signals: pd.DataFrame,
|
||||
prices: pd.DataFrame,
|
||||
cash: float,
|
||||
positions: Dict[str, int],
|
||||
factor_df: Optional[pd.DataFrame] = None,
|
||||
**kwargs,
|
||||
) -> Dict[str, float]:
|
||||
if factor_df is None:
|
||||
return EqualWeightAllocator(self.max_positions).allocate(
|
||||
signals, prices, cash, positions
|
||||
)
|
||||
|
||||
latest_signal = signals.iloc[-1] if len(signals) > 0 else pd.Series(dtype=float)
|
||||
latest_factor = factor_df.iloc[-1] if len(factor_df) > 0 else pd.Series(dtype=float)
|
||||
|
||||
long_stocks = latest_signal[latest_signal > 0].index
|
||||
# 按因子值排序
|
||||
valid = latest_factor[long_stocks].dropna().sort_values(ascending=False)
|
||||
selected = valid.head(self.max_positions)
|
||||
if selected.empty:
|
||||
return {}
|
||||
|
||||
raw_w = selected.values / (selected.values.sum() + 1e-12)
|
||||
raw_w = np.clip(raw_w, self.min_weight, 1.0)
|
||||
raw_w = raw_w / raw_w.sum()
|
||||
return dict(zip(selected.index.tolist(), raw_w.tolist()))
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 策略上下文
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@dataclass
|
||||
class Strategy:
|
||||
"""
|
||||
量化策略 — 组合因子、信号生成器、权重分配器，定义一个完整策略。
|
||||
"""
|
||||
|
||||
name: str
|
||||
factors: List # 因子对象列表
|
||||
signal_generator: SignalGenerator
|
||||
weight_allocator: WeightAllocator
|
||||
factor_weights: Optional[Dict[str, float]] = None # 因子合成权重
|
||||
filter_universe: Optional[Set[str]] = None # 可选股票池
|
||||
description: str = ""
|
||||
|
||||
def compute_composite_factor(self, factor_data: Dict[str, pd.DataFrame]) -> pd.DataFrame:
|
||||
"""
|
||||
合成多因子值。
|
||||
factor_data: {factor_name: DataFrame(index=date, columns=stocks)}
|
||||
"""
|
||||
if not factor_data:
|
||||
raise ValueError("factor_data 为空")
|
||||
|
||||
# 统一列（股票池）合并
|
||||
all_stocks = sorted(
|
||||
set().union(*[set(df.columns) for df in factor_data.values()])
|
||||
)
|
||||
all_dates = sorted(
|
||||
set().union(*[set(df.index) for df in factor_data.values()])
|
||||
)
|
||||
|
||||
composite = pd.DataFrame(0.0, index=all_dates, columns=all_stocks)
|
||||
n_factors = len(factor_data)
|
||||
|
||||
for name, df in factor_data.items():
|
||||
w = (
|
||||
self.factor_weights.get(name, 1.0 / n_factors)
|
||||
if self.factor_weights
|
||||
else 1.0 / n_factors
|
||||
)
|
||||
aligned = df.reindex(index=all_dates, columns=all_stocks)
|
||||
# 截面标准化
|
||||
z = aligned.sub(aligned.mean(axis=1), axis=0).div(
|
||||
aligned.std(axis=1) + 1e-12, axis=0
|
||||
)
|
||||
composite += w * z
|
||||
|
||||
return composite
|
||||
|
||||
def run_step(
|
||||
self,
|
||||
date: pd.Timestamp,
|
||||
factor_data: Dict[str, pd.DataFrame],
|
||||
prices: pd.DataFrame,
|
||||
cash: float,
|
||||
positions: Dict[str, int],
|
||||
) -> Dict[str, float]:
|
||||
"""
|
||||
单步执行：生成信号 → 分配权重 → 返回目标持仓权重。
|
||||
"""
|
||||
composite = self.compute_composite_factor(factor_data)
|
||||
# 仅取当前日期截面
|
||||
if date in composite.index:
|
||||
current_slice = composite.loc[[date]]
|
||||
else:
|
||||
current_slice = composite.iloc[-1:]
|
||||
|
||||
signals = self.signal_generator.generate(current_slice)
|
||||
weights = self.weight_allocator.allocate(
|
||||
signals, prices, cash, positions, factor_df=composite
|
||||
)
|
||||
return weights
|
||||
Reference in New Issue
Block a user