98 lines
3.5 KiB
Python
98 lines
3.5 KiB
Python
"""
|
||
大盘独立性特征 (3维) — calculate_independence_features(df)
|
||
使用 HS300(000300) 作为 benchmark，最近 20 个交易日 OLS 回归。
|
||
"""
|
||
import numpy as np
|
||
import pandas as pd
|
||
from core.scoring.config import WINDOW_20D
|
||
from core.scoring.features.v3_2_features import _ols_slope
|
||
|
||
|
||
def calculate_independence_features(ctx) -> pd.DataFrame:
|
||
"""计算大盘独立性特征 (3维)"""
|
||
kline = ctx.kline.copy()
|
||
hs300 = ctx.hs300_kline.copy() if ctx.hs300_kline is not None else pd.DataFrame()
|
||
|
||
if kline.empty or hs300.empty:
|
||
return pd.DataFrame()
|
||
|
||
# 准备 HS300 收益率序列
|
||
hs300 = hs300.sort_values('trade_date')
|
||
hs300['market_return'] = hs300['close'].pct_change()
|
||
hs300['market_amplitude'] = (hs300['high'] - hs300['low']) / hs300['open']
|
||
hs300 = hs300.dropna(subset=['market_return', 'market_amplitude'])
|
||
|
||
# 对齐日期
|
||
hs300_dates = set(hs300['trade_date'].dt.date
|
||
if hasattr(hs300['trade_date'], 'dt') else hs300['trade_date'])
|
||
|
||
kline = kline.sort_values(['stock_code', 'trade_date'])
|
||
kline['trade_date_dt'] = (kline['trade_date'].dt.date
|
||
if hasattr(kline['trade_date'], 'dt')
|
||
else pd.to_datetime(kline['trade_date']).dt.date)
|
||
|
||
candidates = ctx.candidates
|
||
|
||
# 计算 HS300 最近20日平均振幅
|
||
hs300_tail = hs300.tail(WINDOW_20D)
|
||
hs300_avg_amp = hs300_tail['market_amplitude'].mean() if len(hs300_tail) > 0 else 0
|
||
|
||
features = {}
|
||
grouped = kline.groupby('stock_code')
|
||
|
||
for code, group in grouped:
|
||
if code not in candidates:
|
||
continue
|
||
if len(group) < 20:
|
||
continue
|
||
|
||
g = group.sort_values('trade_date').tail(120)
|
||
closes = g['close'].values
|
||
|
||
# 计算个股日收益率
|
||
stock_rets = np.diff(closes) / np.where(closes[:-1] > 0, closes[:-1], 1)
|
||
|
||
# 对齐 HS300 收益率 (取对应日期)
|
||
# 简化: 取最近 N 个交易日的数据点
|
||
n = min(WINDOW_20D, len(stock_rets))
|
||
|
||
# 获取 HS300 最近 n 天的 market_return
|
||
market_rets = hs300['market_return'].tail(n + 1).values
|
||
if len(market_rets) < n:
|
||
market_rets = hs300['market_return'].values[-n - 1:]
|
||
|
||
# 对齐长度
|
||
min_len = min(n, len(market_rets) - 1, len(stock_rets))
|
||
if min_len < 5: # 至少需要5个数据点做回归
|
||
continue
|
||
|
||
stock_ret_window = stock_rets[-min_len:]
|
||
market_ret_window = market_rets[-min_len:]
|
||
|
||
feat = {}
|
||
|
||
# OLS 回归: stock_ret ~ market_return
|
||
try:
|
||
slope, r_value = _ols_slope(market_ret_window, stock_ret_window)
|
||
residuals = stock_ret_window - slope * market_ret_window
|
||
|
||
# 58. market_residual_volatility_20d: std(residuals) × √252
|
||
feat['market_residual_volatility_20d'] = np.std(residuals, ddof=1) * np.sqrt(252)
|
||
|
||
# 59. market_independence_ratio_20d: 1 - R²
|
||
feat['market_independence_ratio_20d'] = 1 - r_value ** 2
|
||
|
||
except Exception:
|
||
feat['market_residual_volatility_20d'] = 0
|
||
feat['market_independence_ratio_20d'] = 1
|
||
|
||
# 60. market_amplitude_deviation_20d: 个股平均振幅 - HS300 平均振幅
|
||
g_amps = (g['high'].values[-20:] - g['low'].values[-20:]) / np.where(
|
||
g['open'].values[-20:] > 0, g['open'].values[-20:], 1
|
||
)
|
||
feat['market_amplitude_deviation_20d'] = np.mean(g_amps) - hs300_avg_amp
|
||
|
||
features[code] = feat
|
||
|
||
return pd.DataFrame.from_dict(features, orient='index')
|