def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {
'start_date': 20150101,
'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()
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status == '停牌'
dv.append_df(mask_sus, 'suspended', is_quarterly=False)
dv.add_formula('not_index_member', '!index_member', is_quarterly=False)
dv.add_formula('limit_reached',
'Abs((open - Delay(close, 1)) / Delay(close, 1)) > 0.095',
is_quarterly=False)
dv.save_dataview(dataview_folder)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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 save_data():
"""
This function fetches data from remote server and stores them locally.
Then we can use local data to do back-test.
"""
dataview_props = {# Start and end date of back-test
'start_date': 20170101, 'end_date': 20171030,
# Investment universe and performance benchmark
'universe': UNIVERSE, 'benchmark': '000300.SH',
# Data fields that we need
'fields': 'total_mv,turnover',
# freq = 1 means we use daily data. Please do not change this.
'freq': 1}
# 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()
dv.save_dataview(folder_path=dataview_store_folder)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {
'start_date': 20160101,
'end_date': 20171001,
'universe': '000300.SH',
'fields': 'volume,turnover',
'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('mask_limit_reached',
'limit_reached > 0',
is_quarterly=False)
dv.add_formula('mask_index_member',
'!(index_member > 0)',
is_quarterly=False)
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status == u'停牌'
dv.append_df(mask_sus, 'mask_sus', is_quarterly=False)
# dv.add_formula('size', '', is_quarterly=False)
dv.save_dataview(dataview_folder)
def test_write():
ds = RemoteDataService()
ds.init_from_config(data_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_data():
"""
This function fetches data from remote server and stores them locally.
Then we can use local data to do back-test.
"""
dataview_props = {'start_date': 20170101, # Start and end date of back-test
'end_date': 20171030,
'universe': UNIVERSE, # Investment universe and performance benchmark
'benchmark': '000905.SH',
'fields': 'high,low,close', # Data fields that we need
'freq': 1 # freq = 1 means we use daily data. Please do not change this.
}
# 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()
# 以9日为周期的KD线为例。首先须计算出最近9日的RSV值,即未成熟随机值,
# 计算公式为
# 9日RSV=(C-L9)÷(H9-L9)×100
# 式中,C为第9日的收盘价;L9为9日内的最低价;H9为9日内的最高价。
# K值=2/3×前一日K值+1/3×当日RSV
# D值=2/3×前一日K值+1/3×当日RSV
# J指标的计算公式为: J=3D—2K
factor_formula = '2/3*50 + (close-Ts_Min(low，5))/(Ts_Max(high，5)-Ts_Min(low，5)*100)'
dv.add_formula()
dv.save_dataview(folder_path=dataview_store_folder)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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 test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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(data_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 save_data():
"""
This function fetches data from remote server and stores them locally.
Then we can use local data to do back-test.
"""
dataview_props = {
'start_date': 20170101, # Start and end date of back-test
'end_date': 20171030,
'universe': UNIVERSE, # Investment universe and performance benchmark
'benchmark': '000300.SH',
'fields': 'total_mv,turnover', # Data fields that we need
'freq':
1 # freq = 1 means we use daily data. Please do not change this.
}
# 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()
dv.save_dataview(folder_path=dataview_store_folder)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {
'start_date': 20150101,
'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 save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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()
props = {'start_date': 20160101, 'end_date': 20171001, 'universe': '000300.SH',
'fields': 'volume,turnover',
'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('mask_limit_reached', 'limit_reached > 0', is_quarterly=False)
dv.add_formula('mask_index_member', '!(index_member > 0)', is_quarterly=False)
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status == u'停牌'
dv.append_df(mask_sus, 'mask_sus', is_quarterly=False)
# dv.add_formula('size', '', is_quarterly=False)
dv.save_dataview(dataview_folder)
def add(formula, name):
dv = DataView()
dv.load_dataview(folder_path=dataview_dir_path)
dv.add_formula(name,
formula,
is_quarterly=False,
formula_func_name_style='lower')
dv.save_dataview(folder_path=dataview_dir_path)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
print(DataView)
props = {'start_date': 20170501, 'end_date': 20171001, 'universe': '000016.SH',
'fields': 'volume,pb,pe,ps,float_mv,sw1',
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.save_dataview(dataview_folder)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {'start_date': 20160101, 'end_date': 20171001, 'universe': '000300.SH',
'fields': 'volume,turnover',
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.save_dataview(dataview_folder)
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]
jutil.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_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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 test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {'start_date': 20170901, 'end_date': 20171129, 'universe': BENCHMARK,
'fields': 'close,volume,sw1',
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('ret', 'Return(close_adj, 20)', is_quarterly=False)
dv.add_formula('rank_ret', 'Rank(ret)', is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def download_data():
dataview_props = {
'start_date': 20080101,
'end_date': 20180731,
'universe': '000016.SH',
'fields': 'open,close,high,low',
'freq': 1
}
ds = RemoteDataService()
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()
dv.save_dataview(folder_path=dataview_store_folder)
def save_data(self):
"""
This function fetches data from remote server and stores them locally.
Then we can use local data to do back-test.
"""
# RemoteDataService communicates with a remote server to fetch data
ds = RemoteDataService()
# Use username and password in data_config to login
ds.init_from_config(self.data_config)
# DataView utilizes RemoteDataService to get various data and store them
dv = DataView()
dv.init_from_config(self.dataview_props, ds)
dv.prepare_data()
dv.save_dataview(folder_path=self.dataview_store_folder)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {'start_date': start_date, 'end_date': end_date, 'universe': universe,
'fields': 'roe_yearly,roa_yearly',
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('roe_cond', 'roe_yearly >= 20', is_quarterly=True)
dv.add_formula('roa_cond', 'roa_yearly >= 5', is_quarterly=True)
dv.add_formula('cond', 'roe_cond && roa_cond', is_quarterly=True)
dv.save_dataview(folder_path=dataview_folder)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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 test_q():
ds = RemoteDataService()
ds.init_from_config(data_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():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {'start_date': start_date, 'end_date': end_date,
'fields': 'sw1',
'symbol': my_symbols,
'freq': 1}
dv.init_from_config(props, ds)
dv.prepare_data()
# set the benchmark
res, _ = ds.daily(benchmark, start_date=dv.start_date, end_date=dv.end_date)
dv._data_benchmark = res.set_index('trade_date').loc[:, ['close']]
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]
jutil.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_save_dataview(sub_folder='test_dataview'):
ds = RemoteDataService()
ds.init_from_config(data_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)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {
'start_date': 20170901,
'end_date': 20171129,
'universe': BENCHMARK,
'fields': 'close,volume,sw1',
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('ret', 'Return(close_adj, 20)', is_quarterly=False)
dv.add_formula('rank_ret', 'Rank(ret)', is_quarterly=False)
dv.save_dataview(folder_path=dataview_dir_path)
def save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {'start_date': 20150101, '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()
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status == '停牌'
dv.append_df(mask_sus, 'suspended', is_quarterly=False)
dv.add_formula('not_index_member', '!index_member', is_quarterly=False)
dv.add_formula('limit_reached', 'Abs((open - Delay(close, 1)) / Delay(close, 1)) > 0.095', is_quarterly=False)
dv.save_dataview(dataview_folder)
def download_data():
dataview_props = {
'start_date': 20120101,
'end_date': 20181231,
'universe': '000905.SH',
# 'symbol':'600030.SH,600104.SH',
'fields': 'open,close,high,low,close_adj,volume',
'freq': 1
}
ds = RemoteDataService()
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()
factor_formula = 'Delay(Return(close_adj, 2, 0), -2)'
dv.add_formula('future_return_2',
factor_formula,
is_quarterly=False,
is_factor=False)
factor_formula = 'Delay(Return(close_adj, 3, 0), -3)'
dv.add_formula('future_return_3',
factor_formula,
is_quarterly=False,
is_factor=False)
factor_formula = 'Delay(Return(close_adj, 4, 0), -4)'
dv.add_formula('future_return_4',
factor_formula,
is_quarterly=False,
is_factor=False)
factor_formula = 'Delay(Return(close_adj, 5, 0), -5)'
dv.add_formula('future_return_5',
factor_formula,
is_quarterly=False,
is_factor=False)
dv.save_dataview(folder_path=dataview_store_folder)
def test_write():
ds = RemoteDataService()
ds.init_from_config(data_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 test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_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 test_q():
ds = RemoteDataService()
ds.init_from_config(data_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(data_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)
def test_save_dataview():
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
#dataview参数选择
props = {
'start_date': 20080527,
'end_date': 20180807,
'universe': '000002.SH,399107.SZ',
"benchmark": "000905.SH,000905.SH",
'fields': ('open,close,volume,vwap,high,low,turnover'),
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
#因子
factor_formula = 'rank(volume)*(ts_sum(close, 5)/5)*(vwap-close)/(high-low)'
dv.add_formula('alpha',
factor_formula,
is_quarterly=False,
formula_func_name_style='lower')
dv.save_dataview(folder_path=dataview_dir_path)
print(dv.get_ts('roe_pb').head()) #这里用get_ts的方法输入新的名称即可
#5_从数据服务添加新数据至本地
#先设置Config
data_config = {
"remote.data.address":
"tcp://data.tushare.org:8910", #地址统一,暂不做修改
"remote.data.username":
"******", #quantos账号(手机号码)
#quantos账号的API令牌号码
"remote.data.password":
"******"
}
ds = RemoteDataService() #DataService启动
ds.init_from_config(data_config) #data_config启动
dv.add_field('eps_basic', ds) #添加新数据(eps_basic)至本地(ds)
print(dv.get_ts('eps_basic').head())
A = dv.get_ts('eps_basic').head() #get_ts为数据获取
dv.remove_field('eps_basic') #删除数据(eps_basic)
dv.add_field('volume', ds) #添加新数据至本地(ds)
A = dv.get_ts('volume').head()
dv.save_dataview('G:/data/hs300') #保存
dv.save_dataview('G:/data/hs300_1') #这相当于另存为
print(dv.fields) #查看dv中取得的数据
dv.add_field('roe', ds) #添加新数据至本地(ds)
"remote.trade.username":
"******",
"remote.trade.password":
"******"
}
dataview_dir_path = '***' #dataview存储路径
backtest_result_dir_path = '***' #回测结果存储路径
api = DataApi(addr='tcp://data.quantos.org:8910')
api.login("phone", "token")
dv = DataView()
dv.load_dataview(folder_path=dataview_dir_path)
dv.add_field('turnover_ratio', ds)
dv.save_dataview(folder_path=dataview_dir_path)
dv.update_snapshot()
#在已经保存dataview之后，需要添加某项指标(dataview.py里面可以找这些指标，不是因子！)，如turnover_ratio，使用这段代码，添加完之后下一次运行就可以注释掉
def my_selector(context, user_options=None):
#筛选僵尸股和ST股
df = context.dataview.data_inst['name']
result = pd.DataFrame(df, columns=['ST'], index=df.index, dtype='bool')
selector_volume = context.snapshot[
'mean_turnover'] > 50000000 #这里要先add('ts_mean(turnover, 5)', 'mean_turnover')
names = list(df)
for i in range(len(df)):
if 'ST' in names[i]:
result['ST'][i] = False
dv.append_df(alpha195_.run_formula(dv),'alpha195_')
dv.append_df(alpha42_.run_formula(dv),'alpha42_')
dv.append_df(alpha62_.run_formula(dv),'alpha62_')
dv.append_df(alpha64_.run_formula(dv),'alpha64_')
dv.append_df(alpha197_.run_formula(dv),'alpha197_')
dv.append_df(alpha211_.run_formula(dv),'alpha211_')
dv.append_df(alpha56_.run_formula(dv),'alpha56_')
factor_lis = ['alpha32_','alpha42_','alpha56_','alpha62_','alpha64_','alpha194','alpha195','alpha197','alpha211','pb','pe','roa','roe','pm','ETOP']
for each in factor_lis:
assert(each in dv.fields)
factors = {name:dv.get_ts(name) for name in factor_lis}
dv.save_dataview('muti_factor/')
# In[87]:
import pandas as pd
id_zz500 = dp.daily_index_cons(api, "000300.SH", start, end)
id_hs300 = dp.daily_index_cons(api, "000905.SH", start, end)
columns_500 = list(set(id_zz500.columns)-set(id_hs300.columns))
def limit_up_down():
trade_status = dv.get_ts('trade_status').fillna(0)
mask_sus = trade_status == 0
# 涨停
