def save_regression_analysis_result(self, factor_name):
with MongoConnect(DatabaseName.MULTI_FACTOR_DATA.value):
factor_return = self.factor_return.copy()
factor_t_value = self.factor_t_value.copy()
net_analysis_result = self.net_analysis_result
factor_return.index = factor_return.index.format()
factor_t_value.index = factor_t_value.index.format()
net_analysis_result['cumsum'][
'net_value_df'].index = net_analysis_result['cumsum'][
'net_value_df'].index.format()
net_analysis_result['cumprod'][
'net_value_df'].index = net_analysis_result['cumprod'][
'net_value_df'].index.format()
net_analysis_result['cumsum'][
'benchmark_df'].index = net_analysis_result['cumsum'][
'benchmark_df'].index.format()
net_analysis_result['cumprod'][
'benchmark_df'].index = net_analysis_result['cumprod'][
'benchmark_df'].index.format()
doc = FactorRegressionAnalysisResult(
factor_name=factor_name,
# 因子数据开始时间
begin_date=self.factor.index[0],
# 因子数据结束时间
end_date=self.factor.index[-1],
# 因子收益率的自相关系数acf和偏自相关系数pacf,默认1-10阶,结果list len=11，取1-10个数
acf_result=self.acf_result,
# 因子收益率，单利，复利, 日收益率
factor_return=factor_return,
# 单因子检测的T值, Series, index为时间
factor_t_value=factor_t_value,
# 单因子检测的T值的统计值，'t_value_mean': 绝对值均值, 't_value_greater_two':绝对值序列大于2的占比
factor_t_value_statistics=self.factor_t_value_statistics,
# 净值分析结果
net_analysis_result=self.net_analysis_result)
doc.save()
path = LocalDataPath.path + LocalDataFolderName.FACTOR.value + '/'
factor_data = {}
for factor_name in factor_list:
factor_single_data = get_local_data(path, factor_name + '.h5')
# 指数数据不全，需要删一部分因子数据
factor_data[factor_name] = factor_single_data[
factor_single_data.index < datetime(2020, 1, 1)]
with MongoConnect(DatabaseName.MULTI_FACTOR_DATA.value):
factor_ic = {}
factor_return = {}
for factor_name in factor_list:
factor_regression_analysis_result = FactorRegressionAnalysisResult.objects(factor_name=factor_name) \
.only('factor_name') \
.only('begin_date') \
.only('end_date') \
.only('factor_return') \
.as_pymongo()
factor_return[factor_name] = pd.DataFrame(
factor_regression_analysis_result[0]['factor_return'])
factor_return[factor_name].index = pd.DatetimeIndex(
factor_return[factor_name].index)
factor_ic_result = FactorIcAnalysisResult.objects(factor_name=factor_name) \
.only('factor_name') \
.only('begin_date') \
.only('end_date') \
.only('ic') \
.as_pymongo()
# print(factor_ic_result)
factor_ic[factor_name] = pd.DataFrame(factor_ic_result[0]['ic'])