# FactorList = [] #输入因子合成阶段要使用的因子
from jaqs_fxdayu.research.signaldigger import process
dv.add_field('sw1')
factor_dict = dict()
index_member = ~mask
for name in FactorList:
print(name)
signal = -1 * dv.get_ts(name) # 调整符号
signal = process.winsorize(factor_df=signal, alpha=0.05, index_member=index_member) # 去极值
# 行业中性化
signal = process.neutralize(signal,
group=dv.get_ts("sw1"), # 行业分类标准
)
signal = process.standardize(signal, index_member) # z-score标准化 保留排序信息和分布信息
# signal = process.rank_standardize(signal,index_member) #因子在截面排序并归一化到0-1(只保留排序信息)
print('OK!')
factor_dict[name] = signal
# 因子间存在较强同质性时，使用施密特正交化方法对因子做正交化处理，用得到的正交化残差作为因子
new_factors = multi_factor.orthogonalize(factors_dict=factor_dict,
standardize_type="z_score",#输入因子标准化方法，有"rank"（排序标准化）,"z_score"(z-score标准化)两种（"rank"/"z_score"）
winsorization=False,#是否对输入因子去极值
index_member=index_member) # 是否只处理指数成分股
# rollback_period代表滚动窗口所用到的天数,即用前多少期的数据来计算现阶段的因子权重。 通常建议设置时间在半年以上,可以获得相对稳定的预期结果
return can_enter, can_exit
can_enter, can_exit = limit_up_down()
import numpy as np
price = dv.get_ts('close_adj')
sw1 = sw1_name
enter = can_enter
exit = can_exit
mask = mask
from jaqs_fxdayu.research.signaldigger.process import neutralize
neutralize_dict = {}
i = 0
for a in alpha_signal:
neutralize_dict[a] = neutralize(factor_df=dv.get_ts(a),
group=dv.get_ts("sw1")) #行业中性化处理
i = i + 1
print('处理进度%s' % (i / len(alpha_signal)))
print('总体进度%s' % (i / (3 * len(alpha_signal))))
# except:
# print(str(a)+'异常')
import matplotlib.pyplot as plt
from jaqs_fxdayu.research import SignalDigger
from jaqs_fxdayu.research.signaldigger import analysis
def cal_obj(signal, name, period, quantile):
# price_bench = dv.data_benchmark
obj = SignalDigger(output_folder="FACTORS/%s" % name, output_format='pdf')
obj.process_signal_before_analysis(signal,
def test_multi_factor():
from jaqs_fxdayu.research.signaldigger import multi_factor, process
dv = DataView()
dv.load_dataview(dataview_folder)
dv.add_formula("momentum",
"Return(close_adj, 20)",
is_quarterly=False,
add_data=True)
mask = mask_index_member(dv)
can_enter, can_exit = limit_up_down(dv)
ic = dict()
factors_dict = {
signal: dv.get_ts(signal)
for signal in ["pb", "pe", "ps", "momentum"]
}
for period in [5, 15]:
ic[period] = multi_factor.get_factors_ic_df(
factors_dict,
price=dv.get_ts("close_adj"),
high=dv.get_ts("high_adj"), # 可为空
low=dv.get_ts("low_adj"), # 可为空
n_quantiles=5, # quantile分类数
mask=mask, # 过滤条件
can_enter=can_enter, # 是否能进场
can_exit=can_exit, # 是否能出场
period=period, # 持有期
benchmark_price=dv.
data_benchmark, # 基准价格 可不传入，持有期收益（return）计算为绝对收益
commission=0.0008,
)
factor_dict = dict()
index_member = dv.get_ts("index_member")
for name in ["pb", "pe", "ps", "momentum"]:
signal = -1 * dv.get_ts(name) # 调整符号
process.winsorize(factor_df=signal,
alpha=0.05,
index_member=index_member) # 去极值
signal = process.rank_standardize(
signal, index_member) # 因子在截面排序并归一化到0-1(只保留排序信息)
signal = process.standardize(signal,
index_member) # z-score标准化 保留排序信息和分布信息
# 行业市值中性化
signal = process.neutralize(
signal,
group=dv.get_ts("sw1"),
float_mv=dv.get_ts("float_mv"),
index_member=index_member, # 是否只处理时只考虑指数成份股
)
factor_dict[name] = signal
# 因子间存在较强同质性时，使用施密特正交化方法对因子做正交化处理，用得到的正交化残差作为因子
new_factors = multi_factor.orthogonalize(
factors_dict=factor_dict,
standardize_type="rank",
# 输入因子标准化方法，有"rank"（排序标准化）,"z_score"(z-score标准化)两种（"rank"/"z_score"）
winsorization=False, # 是否对输入因子去极值
index_member=index_member) # 是否只处理指数成分股
# 多因子组合-动态加权参数配置
props = {
'price': dv.get_ts("close_adj"),
'high': dv.get_ts("high_adj"), # 可为空
'low': dv.get_ts("low_adj"), # 可为空
'ret_type':
'return', # 可选参数还有upside_ret/downside_ret 则组合因子将以优化潜在上行、下行空间为目标
'benchmark_price': dv.data_benchmark, # 为空计算的是绝对收益 不为空计算相对收益
'period': 30, # 30天的持有期
'mask': mask,
'can_enter': can_enter,
'can_exit': can_exit,
'forward': True,
'commission': 0.0008,
"covariance_type": "shrink", # 协方差矩阵估算方法 还可以为"simple"
"rollback_period": 120
} # 滚动窗口天数
comb_factors = dict()
for method in [
"equal_weight", "ic_weight", "ir_weight", "max_IR", "max_IC",
"factors_ret_weight"
]:
comb_factors[method] = multi_factor.combine_factors(
factor_dict,
standardize_type="rank",
winsorization=False,
weighted_method=method,
props=props)
return can_enter, can_exit
can_enter, can_exit = limit_up_down()
alpha_signal = [
'gainvariance120', 'alpha46', 'alpha48', 'alpha85', "vema12", "ir60",
'adminiexpenserate', 'ssctol'
]
price = dv.get_ts('close_adj')
sw1 = sw1_name
enter = can_enter
exit = can_exit
mask = mask
from jaqs_fxdayu.research.signaldigger.process import neutralize
neutralize_dict = {
a: neutralize(factor_df=dv.get_ts(a), group=dv.get_ts("sw1"))
for a in alpha_signal
}
#分析因子所在行业特点
import matplotlib.pyplot as plt
from jaqs_fxdayu.research import SignalDigger
from jaqs_fxdayu.research.signaldigger import analysis
def cal_obj(signal, name, period, quantile):
# price_bench = dv.data_benchmark
obj = SignalDigger(output_folder="hs300/%s" % name, output_format='pdf')
obj.process_signal_before_analysis(signal,
price=price,
n_quantiles=quantile,
id_zz800 = dp.daily_index_cons(api, "000906.SH", start, end)
import pandas as pd
id_zz800 = dp.daily_index_cons(api, "000906.SH", start, end)
index_member = pd.concat([id_zz800],axis=1)
dv.add_field('float_mv')
for name in ["alpha1","alpha2","alpha3","alpha4","alpha5","alpha6","alpha7"]:
signal = dv.get_ts(name)
process.winsorize(factor_df=signal, alpha=0.05, index_member=index_member) # 去极值
#signal = process.standardize(signal, index_member) # z-score标准化 保留排序信息和分布信息
# signal = process.rank_standardize(signal,index_member) #因子在截面排序并归一化到0-1(只保留排序信息)
# 行业市值中性化
signal = process.neutralize(factor_df=signal,
group=dv.get_ts("sw1"),# 行业分类标准
float_mv = dv.get_ts("float_mv"), #流通市值 可为None 则不进行市值中性化
index_member=index_member,# 是否只处理时只考虑指数成份股
)
factor_dict[name] = signal
new_factors = multi_factor.orthogonalize(factors_dict=factor_dict,
standardize_type="rank",#输入因子标准化方法，有"rank"（排序标准化）,"z_score"(z-score标准化)两种（"rank"/"z_score"）
winsorization=False,#是否对输入因子去极值
index_member=index_member) # 是否只处理指数成分股
props = {
'price':dv.get_ts("close_adj"),
'high':dv.get_ts("high_adj"), # 可为空
'low':dv.get_ts("low_adj"),# 可为空
'ret_type': 'return',#可选参数还有upside_ret/downside_ret 则组合因子将以优化潜在上行、下行空间为目标
'benchmark_price': dv.data_benchmark, # 为空计算的是绝对收益 不为空计算相对收益