def factor_analysis(f_name):
from alphamind.api import SqlEngine, Universe, alpha_logger
engine = SqlEngine()
universe = Universe('custom', ['zz800'])
base1 = LAST('Alpha60')
base2 = CSRes('roe_q', base1)
base3 = CSRes(CSRes('ep_q', base1), base2)
factor = CSRes(CSRes(CSRes(LAST(f_name), base1), base2), base3)
res = factor_residue_analysis('2010-01-01', '2018-01-26', f_name, factor,
'10b', universe, engine)
alpha_logger.info('{0} is done'.format(f_name))
return f_name, res
def worker_func_negative(factor_name):
from alphamind.api import SqlEngine, Universe
neutralize_factors = ['roe_q', 'ep_q']
engine = SqlEngine()
benchmark_code = 905
universe_name = ['zz500']
universe = Universe('custom', universe_name)
return factor_analysis(engine,
factor_name,
universe,
benchmark_code,
positive=False,
neutralize_factors=neutralize_factors)
factor = CSRes(CSRes(CSRes(LAST(f_name), base1), base2), base3)
res = factor_residue_analysis('2010-01-01', '2018-01-26', f_name, factor,
'10b', universe, engine)
alpha_logger.info('{0} is done'.format(f_name))
return f_name, res
if __name__ == '__main__':
from dask.distributed import Client
client = Client('10.63.6.176:8786')
engine = SqlEngine()
df = engine.fetch_factor_coverage()
df = df[df.universe == 'zz800'].groupby('factor').mean()
df = df[df.coverage >= 0.98]
universe = Universe('custom', ['zz800'])
factor_df = pd.DataFrame()
tasks = client.map(factor_analysis, df.index.tolist())
res = client.gather(tasks)
for f_name, df in res:
factor_df[f_name] = df['$top1 - bottom1$']
# for i, f_name in enumerate(df.index):
# base1 = LAST('Alpha60')
# base2 = CSRes('roe_q', base1)
# base3 = CSRes(CSRes('ep_q', base1), base2)
# factor = CSRes(CSRes(CSRes(LAST(f_name), base1), base2), base3)
# res = factor_residue_analysis('2010-01-01',
from alphamind.api import industry_list
from alphamind.api import winsorize_normal
from alphamind.api import standardize
from matplotlib import pyplot as plt
from matplotlib.pylab import mpl
plt.style.use('seaborn-whitegrid')
mpl.rcParams['font.sans-serif'] = ['SimHei']
mpl.rcParams['axes.unicode_minus'] = False
start_date = '2017-01-01'
end_date = '2018-05-17'
freq = '10b'
neutralized_risk = None
universe = Universe('zz800')
dask_client = Client('10.63.6.176:8786')
alpha_factors = {
'f1':
CSQuantiles(LAST('ILLIQUIDITY') * LAST('NegMktValue'),
groups='sw1_adj'),
'f2':
CSQuantiles('con_pe', groups='sw1_adj')
}
weights = {'f1': 1., 'f2': 0.}
# alpha_model = XGBTrainer(objective='reg:linear',
# booster='gbtree',
# n_estimators=300,
from matplotlib import pyplot as plt
from PyFin.api import *
from dask.distributed import Client
from alphamind.api import Universe
from alphamind.api import ConstLinearModel
from alphamind.api import XGBTrainer
from alphamind.api import DataMeta
from alphamind.api import industry_list
from alphamind.api import winsorize_normal
from alphamind.api import standardize
start_date = '2011-01-01'
end_date = '2018-05-04'
freq = '20b'
neutralized_risk = None
universe = Universe("custom", ['zz800'])
dask_client = Client('10.63.6.176:8786')
factor = CSQuantiles(LAST('NetProfitRatio'), groups='sw1_adj')
alpha_factors = {
str(factor): factor,
}
weights = {str(factor): 1.}
# alpha_model = XGBTrainer(objective='reg:linear',
# booster='gbtree',
# n_estimators=300,
# eval_sample=0.25,
# features=alpha_factors)
from alphamind.api import industry_list
from alphamind.api import winsorize_normal
from alphamind.api import standardize
from matplotlib import pyplot as plt
from matplotlib.pylab import mpl
plt.style.use('seaborn-whitegrid')
mpl.rcParams['font.sans-serif'] = ['SimHei']
mpl.rcParams['axes.unicode_minus'] = False
"""
Back test parameter settings
"""
benchmark_code = 905
universe = Universe('zz800') + Universe('cyb')
start_date = '2011-01-01'
end_date = '2011-05-04'
freq = '10b'
neutralized_risk = None
alpha_factors = {'ep_q_cs': CSQuantiles(LAST('ep_q'), groups='sw1_adj')}
weights = dict(ep_q_cs=1.)
alpha_model = ConstLinearModel(features=alpha_factors, weights=weights)
data_meta = DataMeta(freq=freq,
universe=universe,
batch=1,
industry_matrix = engine.fetch_industry_matrix(ref_date, codes, 'sw_adj',
1)
dx_returns = engine.fetch_dx_return(ref_date,
codes,
horizon=horizon,
offset=1)
return cs_impl(ref_date, factor_data, factor_name, risk_exposure,
constraint_risk, industry_matrix, dx_returns)
if __name__ == '__main__':
from alphamind.api import SqlEngine, Universe, risk_styles, industry_styles
factor_name = 'SIZE'
data_source = 'postgres+psycopg2://postgres:[email protected]/alpha'
engine = SqlEngine(data_source)
risk_names = list(set(risk_styles).difference({factor_name}))
industry_names = list(set(industry_styles).difference({factor_name}))
constraint_risk = risk_names + industry_names
universe = Universe('custom', ['ashare_ex'])
horizon = 9
x = cross_section_analysis('2018-02-08',
factor_name,
universe,
horizon,
constraint_risk,
engine=engine)
print(x)