def save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {
'start_date': 20140101,
'end_date': 20171001,
'universe': '000300.SH',
'fields': 'volume,turnover,float_mv,pb,total_mv',
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
# for convenience to check limit reachers
dv.add_formula('limit_reached',
'Abs((open - Delay(close, 1)) / Delay(close, 1)) > 0.095',
is_quarterly=False)
dv.add_formula('random', 'StdDev(volume, 20)', is_quarterly=False)
dv.add_formula('momentum', 'Return(close_adj, 20)', is_quarterly=False)
# dv.add_formula('size', '', is_quarterly=False)
dv.save_dataview(dataview_folder)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {
'start_date': 20170101,
'end_date': 20171001,
'universe': '000300.SH',
'fields': ('float_mv,pb,pe_ttm,sw2'),
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'GroupQuantile(-float_mv, sw2, 10)'
dv.add_formula('rank_mv', factor_formula, is_quarterly=False)
factor_formula = 'GroupQuantile(If(pb >= 0.2, pb, 100), sw2, 10)'
dv.add_formula('rank_pb', factor_formula, is_quarterly=False)
factor_formula = 'GroupQuantile(If(pe_ttm >= 3, pe_ttm, 9999.0), sw2, 10)'
dv.add_formula('rank_pe', factor_formula, is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {'start_date': 20150101, 'end_date': 20170930, 'universe': '000905.SH',
'fields': ('turnover,float_mv,close_adj,pe,pb'),
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'Cutoff(Standardize(turnover / 10000 / float_mv), 2)'
dv.add_formula('TO', factor_formula, is_quarterly=False)
factor_formula = 'Cutoff(Standardize(1/pb), 2)'
dv.add_formula('BP', factor_formula, is_quarterly=False)
factor_formula = 'Cutoff(Standardize(Return(close_adj, 20)), 2)'
dv.add_formula('REVS20', factor_formula, is_quarterly=False)
factor_formula = 'Cutoff(Standardize(Log(float_mv)), 2)'
dv.add_formula('float_mv_factor', factor_formula, is_quarterly=False)
factor_formula = 'Delay(Return(close_adj, 1), -1)'
dv.add_formula('NextRet', factor_formula, is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def test_write():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
secs = '600030.SH,000063.SZ,000001.SZ'
props = {
'start_date': 20160601,
'end_date': 20170601,
'symbol': secs,
'fields': 'open,close,high,low,volume,pb,net_assets,pcf_ncf',
'freq': 1
}
dv.init_from_config(props, data_api=ds)
dv.prepare_data()
assert dv.data_d.shape == (281, 48)
assert dv.dates.shape == (281, )
# TODO
"""
PerformanceWarning:
your performance may suffer as PyTables will pickle object types that it cannot
map directly to c-types [inferred_type->mixed,key->block1_values] [items->[('000001.SZ', 'int_income'), ('000001.SZ', 'less_handling_chrg_comm_exp'), ('000001.SZ', 'net_int_income'), ('000001.SZ', 'oper_exp'), ('000001.SZ', 'symbol'), ('000063.SZ', 'int_income'), ('000063.SZ', 'less_handling_chrg_comm_exp'), ('000063.SZ', 'net_int_income'), ('000063.SZ', 'oper_exp'), ('000063.SZ', 'symbol'), ('600030.SH', 'int_income'), ('600030.SH', 'less_handling_chrg_comm_exp'), ('600030.SH', 'net_int_income'), ('600030.SH', 'oper_exp'), ('600030.SH', 'symbol')]]
"""
dv.save_dataview(folder_path=daily_path)
def save_dataview(sub_folder='test_dataview'):
ds = RemoteDataService()
dv = DataView()
props = {
'start_date':
20141114,
'end_date':
20160327,
'universe':
'000300.SH',
'fields': (
'open,high,low,close,vwap,volume,turnover,'
# + 'pb,net_assets,'
+ 's_fa_eps_basic,oper_exp,tot_profit,int_income'),
'freq':
1
}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'close > Ts_Max(close, 20)' # 20 days new high
factor_name = 'new_high'
dv.add_formula(factor_name, factor_formula, is_quarterly=False)
dv.save_dataview(
folder_path=fileio.join_relative_path('../output/prepared'),
sub_folder=sub_folder)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {'start_date': 20150101, 'end_date': 20170930, 'universe': '000905.SH',
'fields': ('tot_cur_assets,tot_cur_liab,inventories,pre_pay,deferred_exp,'
'eps_basic,ebit,pe,pb,float_mv,sw1'),
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'pe < 30'
dv.add_formula('pe_condition', factor_formula, is_quarterly=False)
factor_formula = 'pb < 3'
dv.add_formula('pb_condition', factor_formula, is_quarterly=False)
factor_formula = 'Return(eps_basic, 4) > 0'
dv.add_formula('eps_condition', factor_formula, is_quarterly=True)
factor_formula = 'Return(ebit, 4) > 0'
dv.add_formula('ebit_condition', factor_formula, is_quarterly=True)
factor_formula = 'tot_cur_assets/tot_cur_liab > 2'
dv.add_formula('current_condition', factor_formula, is_quarterly=True)
factor_formula = '(tot_cur_assets - inventories - pre_pay - deferred_exp)/tot_cur_liab > 1'
dv.add_formula('quick_condition', factor_formula, is_quarterly=True)
dv.add_formula('mv_rank', 'Rank(float_mv)', is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {
'start_date':
20170101,
'end_date':
20171030,
'universe':
'000300.SH',
'fields': (
'open,high,low,close,vwap,volume,turnover,sw1,'
# + 'pb,net_assets,'
+ 'eps_basic,total_mv,tot_profit,int_income'),
'freq':
1
}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'close >= Delay(Ts_Max(close, 20), 1)' # 20 days new high
factor_name = 'new_high'
dv.add_formula(factor_name, factor_formula, is_quarterly=False)
dv.add_formula('total_profit_growth',
formula='Return(tot_profit, 4)',
is_quarterly=True)
dv.save_dataview(folder_path=dataview_dir_path)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
start_date = get_index_basic_information()[2]
end_date = get_index_basic_information()[3]
props = {
'universe': index,
'start_date': start_date,
'end_date': end_date,
'fields': fields,
'freq': 1
}
dv.init_from_config(props, data_api=ds)
dv.prepare_data()
dv.save_dataview(folder_path=dataview_dir_path)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {'start_date': 20170201, 'end_date': 20171001, 'universe': '000300.SH',
'fields': ('float_mv,sw2,sw1'),
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'GroupQuantile(float_mv, sw1, 10)'
dv.add_formula('gq30', factor_formula, is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def store_ic_weight():
"""
Calculate IC weight and save it to file
"""
dv = DataView()
dv.load_dataview(folder_path=dataview_dir_path)
factorList = ['TO', 'BP', 'REVS20', 'float_mv_factor']
orthFactor_dic = {}
for factor in factorList:
orthFactor_dic[factor] = {}
# add the orthogonalized factor to dataview
for trade_date in dv.dates:
snapshot = dv.get_snapshot(trade_date)
factorPanel = snapshot[factorList]
factorPanel = factorPanel.dropna()
if len(factorPanel) != 0:
orthfactorPanel = Schmidt(factorPanel)
orthfactorPanel.columns = [x + '_adj' for x in factorList]
snapshot = pd.merge(left=snapshot, right=orthfactorPanel,
left_index=True, right_index=True, how='left')
for factor in factorList:
orthFactor_dic[factor][trade_date] = snapshot[factor]
for factor in factorList:
dv.append_df(pd.DataFrame(orthFactor_dic[factor]).T, field_name=factor + '_adj', is_quarterly=False)
dv.save_dataview(dataview_dir_path)
factorList_adj = [x + '_adj' for x in factorList]
fileio.save_json(factorList_adj, custom_data_path)
w = get_ic_weight(dv)
store = pd.HDFStore(ic_weight_hd5_path)
store['ic_weight'] = w
store.close()
def test_q():
from jaqs.data.dataservice import RemoteDataService
ds = RemoteDataService()
dv = DataView()
secs = '600030.SH,000063.SZ,000001.SZ'
props = {'start_date': 20160609, 'end_date': 20170601, 'universe': '000300.SH', 'symbol': secs,
'fields': ('open,close,'
+ 'pb,net_assets,'
+ 'total_oper_rev,oper_exp,'
+ 'cash_paid_invest,'
+ 'capital_stk,'
+ 'roe'), 'freq': 1}
dv.init_from_config(props, data_api=ds)
dv.prepare_data()
folder_path = '../output/prepared'
dv.save_dataview(folder_path=folder_path)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {
'start_date': 20170101,
'end_date': 20171001,
'universe': '000300.SH',
'fields': 'pe_ttm,net_profit_incl_min_int_inc',
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'Return(net_profit_incl_min_int_inc, 4)'
factor_name = 'net_profit_growth'
dv.add_formula(factor_name, factor_formula, is_quarterly=True)
dv.save_dataview(folder_path=dataview_dir_path)
def save_dataview():
# total 130 seconds
ds = RemoteDataService()
dv = DataView()
props = {'start_date': 20141114, 'end_date': 20170327, 'universe': '000300.SH',
# 'symbol': 'rb1710.SHF,rb1801.SHF',
'fields': ('open,high,low,close,vwap,volume,turnover,'
# + 'pb,net_assets,'
+ 's_fa_eps_basic,oper_exp,tot_profit,int_income'
),
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('eps_ret', 'Return(s_fa_eps_basic, 3)', is_quarterly=True)
dv.add_formula('ret20', 'Delay(Return(close_adj, 20), -20)', is_quarterly=False)
dv.save_dataview(folder_path=fileio.join_relative_path('../output/prepared'))
def build_stock_selection_factor():
ds = RemoteDataService()
dv = DataView()
props = {'start_date': 20120101, 'end_date': 20170901, 'universe': '000300.SH',
# 'symbol': 'rb1710.SHF,rb1801.SHF',
'fields': ('open,high,low,close,vwap,volume,turnover,'
# + 'pb,net_assets,'
+ 's_fa_eps_basic,oper_exp,tot_profit,int_income'
),
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('eps_ret', 'Return(s_fa_eps_basic, 4)', is_quarterly=True)
dv.add_formula('rule1', '(eps_ret > 0.2) && (Delay(eps_ret, 1) > 0.2)', is_quarterly=True)
dv.add_formula('rule2', 'close > Ts_Max(close, 120)', is_quarterly=False)
# dv.add_formula('ytan', 'rule1 && rule2', is_quarterly=False)
dv.add_formula('ret20', 'Delay(Return(close_adj, 20), -20)', is_quarterly=False)
dv.save_dataview(folder_path=fileio.join_relative_path('../output/prepared'))
def test_q():
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
secs = '600030.SH,000063.SZ,000001.SZ'
props = {
'start_date':
20160609,
'end_date':
20170601,
'symbol':
secs,
'fields':
('open,close,' + 'pb,net_assets,' + 'total_oper_rev,oper_exp,' +
'cash_paid_invest,' + 'capital_stk,' + 'roe'),
'freq':
1
}
dv.init_from_config(props, data_api=ds)
dv.prepare_data()
dv.save_dataview(folder_path=quarterly_path)
def test_save_dataview(sub_folder='test_dataview'):
ds = RemoteDataService()
ds.init_from_config()
dv = DataView()
props = {
'start_date': 20150101,
'end_date': 20170930,
'universe': '000905.SH',
'fields':
('float_mv,tot_shrhldr_eqy_excl_min_int,deferred_tax_assets,sw2'),
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
factor_formula = 'Quantile(-float_mv,5)'
dv.add_formula('rank_mv', factor_formula, is_quarterly=False)
factor_formula = 'Quantile(float_mv/(tot_shrhldr_eqy_excl_min_int+deferred_tax_assets), 5)'
dv.add_formula('rank_pb', factor_formula, is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
# RemoteDataService communicates with a remote server to fetch data
ds = RemoteDataService()
# Use username and password in data_config to login
ds.init_from_config(data_config)
# DataView utilizes RemoteDataService to get various data and store them
dv = DataView()
dv.init_from_config(dataview_props, ds)
dv.prepare_data()
# In[35]:
type(dv)
# In[ ]:
props = {
'start_date': 20150101,
'end_date': 20170901,
'universe': '000300.SH',
'fields': ('open,high,low,close,vwap,volume,turnover,eps_basic,roe,sw2'),
'freq': 1
}
dv.init_from_config(props, ds)
# In[12]:
dv.prepare_data()
dv.save_dataview('save_folder')