def initialize(self):
globalVars.initialize()
loadedDataList = load_material_data()
# TODO:use logger latter
print('We now have {} in our globalVar now'.format(loadedDataList))
try:
shiftedReturn = globalVars.materialData['pctChange'].get_shifted(
-1)
except AttributeError as ae:
print(ae)
raise AttributeError('There\'s no pctChange in globalVars')
except Exception as e:
print(e)
raise
shiftedReturn.metadata.update({'shiftN': -1})
shiftedReturn.name = 'shiftedReturn'
self.allTradeDatetime = shiftedReturn.timestamp
self.dependents.update({'shiftedReturn': shiftedReturn})
# TODO: should load from some factor.json file latter
############ this part realy socks
############ to be modified latter
############ with nice designed globalVars
############ the factor in globalVars.factors is a dict
toLoadFactors = ['close', 'high', 'low', 'open']
for aFactor in toLoadFactors:
simple_load_factor(aFactor)
self.factorNameList.append(aFactor)
def run(self):
# initialize the globalVars
globalVars.initialize()
self.logger.info('globalVars is initialized')
# load material data
loadedDataList = load_material_data()
self.logger.info('material data {0} is loaded'.format(loadedDataList))
# load factors
# TODO: should load from some factor.json file latter rather than simply load from material data
# self.factorNameList
# # 给globalVars注册factors（dict）
# # key：factor的名字，value：generalData
if 'factors' not in globalVars.varList:
globalVars.register('factors', {})
# TODO: factorManager
for factorName in self.factorNameList:
globalVars.factors[factorName] = Factor(
factorName, globalVars.materialData[factorName])
print(factorName, 'is now in globalVars.factors')
self.logger.info("factor {0} is loaded".format(factorName))
self.logger.info("all factors are loaded")
# calculate the signal
# 设置计算factors的参数
# 可直接传pipeline
# maskList：mask的nameList
self.logger.info("start to generate signalGenerator")
self.signalGenerator = self.signalGeneratorClass(
model=CrossSectionalModelXGBoost, logger=self.logger)
signals = self.signalGenerator.generate_signals(**self.params)
return signals
for field in temp_fileds:
d = np.load(f'{cur_path}/tables/tempData/{field}.npy',
allow_pickle=True).item()
df[rename_dict[field]] = df['code'].map(d)
df['is_exist'] = (df['ipo_date'] <= df['datetime']) & (
df['delist_date'] >= df['datetime'])
# Todo: 'is_st' # 是否st
return df
if __name__ == '__main__':
from GetData.loadData import load_material_data
BacktestDatabase.get_all_trade_days()
globalVars.initialize()
load_material_data()
BacktestDatabase.get_daily_quote(['000300.SH'],
pd.to_datetime("2020-01-01"),
pd.to_datetime("2020-02-28"))
BacktestDatabase.get_daily_factor(['000001.SZ', '000002.SZ'],
["close", "open"],
pd.to_datetime("2020-01-01"),
pd.to_datetime("2020-02-28"))
BacktestDatabase.get_index_weight('沪深300', pd.to_datetime("2020-01-22"),
pd.to_datetime("2020-01-22"))
# start_date = pd.to_datetime('2016-01-01')
# end_date = pd.to_datetime('2021-01-05')
# all_trade_days = BacktestDatabase.get_all_trade_days()
# to_get_date_list = all_trade_days[(all_trade_days >= start_date) & (all_trade_days <= end_date)]
# for index_code in ['000300.SH', '000905.SH']:
factorTestDict[factor.name] = np.vstack(
(factor.get_data(testStart,
testEnd), factor.get_data(at=testEnd)))
if dependents is not None:
for name, dependent in dependents.items():
dependentTrainDict[name] = dependent.get_data(at=trainEnd)
dependentTestDict[name] = dependent.get_data(at=testEnd)
return factorTrainDict, factorTestDict, dependentTrainDict, dependentTestDict
#%% test
from Tool import globalVars
from GetData.loadData import load_material_data, simple_load_factor
globalVars.initialize()
loadedDataList = load_material_data()
#TODO:use logger latter
shiftedReturn = globalVars.materialData['pctChange'].get_shifted(-1)
# TODO: take the -1 as a para: the period we want to shift
shiftedReturn.metadata.update({'shiftN': -1})
shiftedReturn.name = 'shiftedReturn'
dependents = {}
factorNameList = []
allTradeDatetime = shiftedReturn.timestamp
dependents.update({'shiftedReturn': shiftedReturn})
toLoadFactors = ['close', 'high', 'low', 'open']
for aFactor in toLoadFactors:
simple_load_factor(aFactor)
factorNameList.append(aFactor)
def run(self):
# initialize the globalVars
globalVars.initialize()
self.logger.info('globalVars is initialized')
# load material data
loadedDataList = load_material_data()
self.logger.info('material data {0} is loaded'.format(loadedDataList))
# load factors
# TODO: should load from some factor.json file latter rather than simply load from material data
# self.factorNameList
# toLoadFactors = ['close',
# 'high',
# 'low',
# 'open',
# 'volume'
# ]
# # 给globalVars注册factors（dict）
# # key：factor的名字，value：generalData
if 'factors' not in globalVars.varList:
globalVars.register('factors', {})
globalVars.factors['{}_factor'.format(self.toTestFactor.name)] = Factor('{}_factor'.format(self.toTestFactor.name),self.toTestFactor)
self.factorNameList.append('{}_factor'.format(self.toTestFactor.name))
# TODO: factorManager
# for factorName in toLoadFactors:
# globalVars.factors[factorName] = Factor(factorName, globalVars.materialData[factorName])
# print(factorName, 'is now in globalVars.factors')
# self.factorNameList.append(factorName)
# self.logger.info("factor {0} is loaded".format(factorName))
# self.logger.info("all factors are loaded")
# calculate the signal
# 设置计算factors的参数
# 可直接传pipeline
# maskList：mask的nameList
params = {
"startDate": pd.to_datetime('2020-01-01'),
"endDate": pd.to_datetime('2020-10-31'),
"panelSize": 3,
"trainTestGap": 1,
"maskList": None,
"deExtremeMethod": DeExtremeMethod.MeanStd(),
"imputeMethod": ImputeMethod.JustMask(),
"standardizeMethod": StandardizeMethod.StandardScaler(),
"pipeline": None,
"factorNameList": self.factorNameList,
# params for XGBoost
"modelParams": {
"jsonPath": None,
"paraDict": {
"n_estimators": 50,
"random_state": 42,
"max_depth": 2}
},
# metric function for machine learning models
"metric_func": mean_squared_error,
# smoothing params
"smoothing_params": None
}
self.logger.info("start to generate signalGenerator")
self.signalGenerator = self.signalGeneratorClass(model=CrossSectionalModelXGBoost, logger=self.logger)
signals = self.signalGenerator.generate_signals(**params)
return signals