def get_opm_weight_individual(
signal=pd.DataFrame(),
start_date='2017-01-01',
end_date='2020-08-31',
out_path='E:/FT_Users/LihaiYang/Files/factor_comb_data/all_cluster_comb/1_pm.csv'
):
pm = po.Portfolio_Management(signal,
start_date=start_date,
end_date=end_date,
num_holdings=cfg.PARAMS_PM['num_holdings'],
style_neutral=False,
industry_neutral=True,
to_bound=cfg.PARAMS_PM['to_bound'])
tdays = query_data.get_trade_days('d',
from_trade_day=start_date,
to_trade_day=end_date)
newdf = pd.DataFrame()
w_b, expo = pm.solve(tdays[1])
newdf = newdf.append(w_b)
for tday in tdays[2:]:
print(tday)
w_b11, expo1 = pm.solve(tday, w_lastday=w_b)
w_b = w_b11.copy()
newdf = newdf.append(w_b)
newdf.index = tdays[1:]
newdf.to_csv(out_path)
print(w_b.head())
ic_sign = [
uc.sign(i['perf'][list(i['perf'].keys())[0]]['ic-mean'])
for i in mine_summary
]
print(len(ic_sign))
# 提取因子值
factor_value = fetch.fetch_factor(begin,
end,
fields=fac_name,
standard='clean1_alla',
codes=None,
df=False)
# 有些因子数据不足1009个,比较奇怪
factor_value = {
k: v
for k, v in factor_value.items() if len(v) == len(
query_data.get_trade_days('d', from_trade_day=begin, to_trade_day=end))
}
# 调整因子正负
factor_value_adj = {}
for summa in mine_summary:
if summa['factor_name'] in list(factor_value.keys()):
factor_value_adj[summa['factor_name']] = factor_value[summa['factor_name']] * \
uc.sign(summa['perf'][list(summa['perf'].keys())[0]]['ic-mean'])
f = open(
'E:/FT_Users/LihaiYang/Files/factor_comb_data/all_fac_li_20170101-20210228/all_fac_li_20170101-20210228.pkl',
'wb')
pickle.dump(factor_value_adj, f, -1)
f.close()
import pandas as pd
import pickle
from matplotlib import pyplot as plt
import statsmodels.api as sm
import numpy as np
import math
from ft_platform.utils import utils_calculation as uc
from utils_func import query_data
data_pat = 'E:/FT_Users/LihaiYang/Files/factor_comb_data/fac_meaning/all_cluster'
new_f = pd.read_pickle(data_pat + '/fac_reshape.pkl')
trade_days = query_data.get_trade_days('d', 'SSE', '2017-01-01',
'2021-02-28') # 记得修改
trade_days = [pd.to_datetime(i) for i in trade_days]
# 每天的截面回归估计因子暴露
coef = {}
R_sq = {}
for date in trade_days:
sub_data = new_f.loc[date, ]
model = sm.OLS(sub_data.iloc[:, -1],
sm.add_constant(sub_data.iloc[:, 0:-1]),
missing='drop').fit()
coef[date] = model.params
R_sq[date] = model.rsquared_adj
print(date)
coef_param = pd.concat(coef.values(), axis=1, keys=coef.keys())
coef_param = pd.DataFrame(coef_param.values.T,
index=coef_param.columns,
columns=coef_param.index) # 转置
r2_param = pd.DataFrame(R_sq.values(),
