def create_information_report(self):
"""
Creates a tear sheet for information analysis of a signal.
"""
ic = pfm.calc_signal_ic(self.signal_data)
ic.index = pd.to_datetime(ic.index, format="%Y%m%d")
monthly_ic = pfm.mean_information_coefficient(ic, "M")
self.ic_report_data = {'daily_ic': ic, 'monthly_ic': monthly_ic}
def test_analyze_signal():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
mask = mask_index_member(dv)
can_enter, can_exit = limit_up_down(dv)
# --------------------------------------------------------------------------------
# Step.3 get signal, benchmark and price data
dv.add_formula('divert',
'- Correlation(vwap_adj, volume, 10)',
is_quarterly=False,
add_data=True)
signal = dv.get_ts('divert')
price = dv.get_ts('close_adj')
price_bench = dv.data_benchmark
# Step.4 analyze!
my_period = 5
obj = SignalDigger(output_folder='../output/test_signal',
output_format='pdf')
obj.process_signal_before_analysis(
signal=signal,
price=price,
high=dv.get_ts("high_adj"), # 可为空
low=dv.get_ts("low_adj"), # 可为空
group=dv.get_ts("sw1"),
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=my_period, # 持有期
benchmark_price=price_bench, # 基准价格 可不传入，持有期收益（return）计算为绝对收益
commission=0.0008,
)
signal_data = obj.signal_data
result = analysis(signal_data, is_event=False, period=my_period)
ic = pfm.calc_signal_ic(signal_data, by_group=True)
mean_ic_by_group = pfm.mean_information_coefficient(ic, by_group=True)
plotting.plot_ic_by_group(mean_ic_by_group)
res = obj.create_full_report()
signal_dict = {
alpha: signal_data(dv.get_ts(alpha), alpha, period=20, quantile=5)
for alpha in good_alpha.index
}
def ic_length(signal, days=750):
return signal.loc[signal.index.levels[0][-days]:]
from jaqs.research.signaldigger import performance as pfm
performance_dict = {}
for alpha in good_alpha.index:
ic = pfm.calc_signal_ic(ic_length(signal_dict[alpha]), by_group=True)
mean_ic_by_group = pfm.mean_information_coefficient(ic, by_group=True)
performance_dict[alpha] = round(mean_ic_by_group, 2)
ic_industry = pd.Panel(performance_dict).minor_xs('ic')
High_IC_Industry = pd.DataFrame([
ic_industry[ic_industry >= 0.05][alpha].dropna(how='all')
for alpha in good_alpha.index
]).T
#输出 八个因子，好因子就剩下一个alpha46
alpha46 = pd.Series({
'name': 'alpha46',
'data': ['close'],
'IC': good_alpha_dict['alpha46'],
'type': '191因子',