Files
etf/rotation/experiments/debug_clf_2022.py
aszerW 6a5ae8efbf fix: generate_report now uses actual position_weights from daily_records
Previously hardcoded equal weight (1/select_num), ignoring config weight type.
Now reads position_weights from last daily_record, correctly showing rank-based weights.
2026-06-07 23:29:27 +08:00

129 lines
4.6 KiB
Python

"""分析 2022年4月底~5月初 CL=F 入选原因"""
import os, sys, math
from pathlib import Path
import numpy as np
import pandas as pd
PROJECT_ROOT = Path(__file__).parent.parent.parent
sys.path.insert(0, str(PROJECT_ROOT))
from rotation.simple_rotation import SimpleRotationStrategy, slope_r2_score
if 'FLASK_API_URL' not in os.environ:
os.environ['FLASK_API_URL'] = 'https://k3s.tokenpluse.xyz'
strategy = SimpleRotationStrategy()
strategy._preload_data()
# 分析日期范围
start = pd.Timestamp('2022-04-15')
end = pd.Timestamp('2022-05-10')
n_days = strategy.config.factor.n_days # 25
print("=" * 80)
print(f" 分析 CL=F 动量信号 ({start.date()} ~ {end.date()})")
print(f" 窗口长度: {n_days}")
print("=" * 80)
# 获取所有 signal_codes 的 score
signal_codes = strategy.signal_codes
date_range = pd.bdate_range(start, end)
for date in date_range:
scores = {}
for code in signal_codes:
if code not in strategy.index_data:
continue
df = strategy.index_data[code]
mask = df.index <= date
recent = df.loc[mask]
if len(recent) < n_days:
continue
prices = recent['close'].values[-n_days:]
score = slope_r2_score(prices)
scores[code] = (score, prices[-1])
if not scores:
continue
# 排序
ranked = sorted(scores.items(), key=lambda x: x[1][0], reverse=True)
cl_rank = None
for i, (code, (score, price)) in enumerate(ranked):
if code == 'CL=F':
cl_rank = i + 1
break
cl_score = scores.get('CL=F', (None, None))[0]
cl_price = scores.get('CL=F', (None, None))[1]
print(f"\n{date.strftime('%Y-%m-%d')} | CL=F score={cl_score:.4f}, price={cl_price:.2f}, rank={cl_rank}/{len(ranked)}")
print(f" Top 5:")
for i, (code, (score, price)) in enumerate(ranked[:5]):
marker = " <<<" if code == 'CL=F' else ""
print(f" #{i+1} {code:<15} score={score:>10.4f} price={price:.2f}{marker}")
# 详细分析 CL=F 价格走势
print(f"\n{'='*80}")
print(f" CL=F 价格走势 (2022年3月~5月)")
print(f"{'='*80}")
df_cl = strategy.index_data['CL=F']
mask = (df_cl.index >= '2022-03-01') & (df_cl.index <= '2022-05-15')
cl_prices = df_cl.loc[mask, 'close']
for date, price in cl_prices.items():
# 计算25天窗口的score
mask2 = df_cl.index <= date
recent = df_cl.loc[mask2]
if len(recent) < n_days:
continue
prices = recent['close'].values[-n_days:]
score = slope_r2_score(prices)
normalized = prices / prices[0]
slope, intercept = np.polyfit(np.arange(len(normalized)), normalized, 1)
y_pred = slope * np.arange(len(normalized)) + intercept
ss_res = np.sum((normalized - y_pred) ** 2)
ss_tot = np.sum((normalized - np.mean(normalized)) ** 2)
r2 = 1 - ss_res / ss_tot if ss_tot > 0 else 0
flag = ""
if date.strftime('%Y-%m-%d') in ('2022-04-29', '2022-05-05'):
flag = " <<< 入选日"
print(f" {date.strftime('%Y-%m-%d')} price={price:>8.2f} score={score:>10.4f} "
f"slope={slope:>8.5f} R²={r2:.4f}{flag}")
# 分析 CL=F 的组内竞争
print(f"\n{'='*80}")
print(f" CL=F 所在组: 查看组内竞争")
print(f"{'='*80}")
groups = strategy.config.asset_pools.by_group
for group_name, assets in groups.items():
group_codes = [a.signal_source for a in assets.values()]
if 'CL=F' in group_codes:
print(f" 组名: {group_name}")
print(f" 组成员: {group_codes}")
# 4/29 和 5/5 的组内得分
for target_date_str in ['2022-04-29', '2022-05-05']:
target_date = pd.Timestamp(target_date_str)
print(f"\n {target_date_str} 组内得分:")
for code in group_codes:
if code not in strategy.index_data:
continue
df = strategy.index_data[code]
mask = df.index <= target_date
recent = df.loc[mask]
if len(recent) < n_days:
print(f" {code:<15} 数据不足")
continue
prices = recent['close'].values[-n_days:]
score = slope_r2_score(prices)
marker = " <<< TOP1" if score == max(
slope_r2_score(strategy.index_data[c].loc[strategy.index_data[c].index <= target_date]['close'].values[-n_days:])
for c in group_codes if c in strategy.index_data and len(strategy.index_data[c].loc[strategy.index_data[c].index <= target_date]) >= n_days
) else ""
print(f" {code:<15} score={score:>10.4f}{marker}")