def update_index_class(self, industry_class_name, industry_class_dict):
with MongoConnect(self.database):
index_members_data = AShareIndexMembers.objects(
index_code__in=industry_class_dict.keys()).as_pymongo()
field_list = ['index_code', 'security_code', 'in_date', 'out_date']
self.index_members_df = pd.DataFrame(
list(index_members_data)).reindex(columns=field_list)
self.index_members_df = self.index_members_df.fillna(
datetime.now()).reset_index(drop=True)
get_collection_list = GetCollectionList()
a_share_list = get_collection_list.get_a_share_list()
calendar_obj = GetCalendar()
calendar_SH = calendar_obj.get_calendar('SH')
self.index_class = pd.DataFrame(columns=a_share_list,
index=calendar_SH)
def industry_history(x, index_members_df):
industry_in_out_date = index_members_df[
index_members_df.security_code == x.name]
for index, row in industry_in_out_date.iterrows():
x[row['in_date']:row['out_date']] = row['index_code']
return x
self.index_class = self.index_class.apply(
industry_history, args=(self.index_members_df, ), axis=0)
self.index_class = self.index_class.fillna(method='pad').fillna(
method='backfill')
folder_name = LocalDataFolderName.INDUSTRY_CLASS.value
path = LocalDataPath.path + folder_name + '/'
data_name = industry_class_name
save_data_to_hdf5(path, data_name, self.index_class)
def save_a_share_adj_factor_right(self):
"""
取当日收盘价，作为转、送的股价，
再计算复权因子更新到AShareExRightDividend, 复权因子adj_factor
比例 = 送股比例 + 转增比例 + 缩减比例
单次复权因子 = 股权登记日收盘价 * (1 + 比例 + 配股比例 + 增发比例) /
(股权登记日收盘价 - 派息比例 + 股权登记日收盘价 * 比例 + 配股价格 * 配股比例 + 增发价格 * 增发比例)
:return:
"""
kline_object = GetKlineData()
all_market_data = kline_object.cache_all_stock_data()
with MongoConnect(self.database):
self.data = pd.DataFrame(
AShareExRightDividend.objects.as_pymongo())
self.data['close'] = self.data.apply(
lambda x: self.get_adj_day_close(x['security_code'], x[
'ex_date'], all_market_data),
axis=1)
self.data = self.data.fillna(0)
ratio = self.data['bonus_share_ratio'] + self.data[
'conversed_ratio'] + self.data['consolidate_split_ratio']
self.data['adj_factor'] = self.data['close'] * (
1 + ratio + self.data['rightsissue_ratio'] +
self.data['seo_ratio']
) / (self.data['close'] - self.data['cash_dividend_ratio'] +
self.data['close'] * ratio + self.data['rightsissue_price'] *
self.data['rightsissue_ratio'] +
self.data['seo_price'] * self.data['seo_ratio'])
folder_name = LocalDataFolderName.ADJ_FACTOR.value
path = LocalDataPath.path + folder_name + '/'
self.data = self.data.reindex(
columns=['security_code', 'ex_date', 'adj_factor'])
self.data.set_index(["ex_date"], inplace=True)
self.data.sort_index(inplace=True)
calendar_obj = GetCalendar()
calendar = calendar_obj.get_calendar('SZ')
backward_factor = pd.DataFrame(index=calendar)
adj_factor = pd.DataFrame(index=calendar)
data_dict = dict(
list(self.data.groupby(self.data['security_code'])))
for security_code, adj_data in data_dict.items():
backward_factor[security_code] = self.cal_backward_factor(
adj_data['adj_factor'])
adj_factor[security_code] = adj_data['adj_factor']
backward_factor.replace([np.inf, 0], np.nan, inplace=True)
backward_factor.fillna(method='ffill', inplace=True)
backward_factor.fillna(1, inplace=True)
backward_factor = backward_factor.reindex(
columns=all_market_data['close'].columns, fill_value=1)
save_data_to_hdf5(path, AdjustmentFactor.BACKWARD_ADJ_FACTOR.value,
backward_factor)
save_data_to_hdf5(path, AdjustmentFactor.FROWARD_ADJ_FACTOR.value,
backward_factor.div(backward_factor.iloc[-1]))
def get_all_market_data(self, security_list, end=datetime.now()):
"""
:param security_list:
:param end:
:return:
"""
calendar_obj = GetCalendar()
self.calendar_SZ = calendar_obj.get_calendar('SZ')
self.end = end
database = DatabaseName.A_SHARE_KLINE_DAILY.value
process_num = cpu_count() + 2
process_stock_num = int(len(security_list) / process_num) + 1
security_list_split = []
for i in range(int(len(security_list) / process_stock_num)):
if i < int(len(security_list) / process_stock_num) - 1:
security_list_split.append(
security_list[i * process_stock_num:(i + 1) *
process_stock_num])
else:
security_list_split.append(security_list[i *
process_stock_num:])
with Manager() as manager:
process_pool = Pool(process_num)
process_manager_dict = manager.dict()
for security_list_i in range(len(security_list_split)):
process_pool.apply_async(
self._get_data_with_process_pool,
args=(database, security_list_split[security_list_i],
process_manager_dict, security_list_i))
process_pool.close()
process_pool.join()
process_dict = dict(process_manager_dict)
stock_data_dict = {}
for single_stock_data in process_dict.values():
stock_data_dict.update(single_stock_data)
field_data_dict = {}
for i in self.field:
if i != 'time_tag':
field_data_pd = pd.DataFrame({
key: value[i]
for key, value in stock_data_dict.items()
})
# 原始数据的开高低收除以10000
if i in ['open', 'high', 'low', 'close']:
field_data_dict[i] = field_data_pd.div(10000)
else:
field_data_dict[i] = field_data_pd
return field_data_dict