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() 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_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 analyze_signal(): # -------------------------------------------------------------------------------- # Step.1 load dataview dv = DataView() dv.load_dataview(dataview_folder) # -------------------------------------------------------------------------------- # Step.2 calculate mask (to mask those ill data points) trade_status = dv.get_ts('trade_status') mask_sus = trade_status == u'停牌'.encode('utf-8') df_index_member = dv.get_ts('index_member') mask_index_member = ~(df_index_member > 0) dv.add_formula('limit_reached', 'Abs((open - Delay(close, 1)) / Delay(close, 1)) > 0.095', is_quarterly=False) df_limit_reached = dv.get_ts('limit_reached') mask_limit_reached = df_limit_reached > 0 mask_all = np.logical_or( mask_sus, np.logical_or(mask_index_member, mask_limit_reached)) # -------------------------------------------------------------------------------- # Step.3 get signal, benchmark and price data # dv.add_formula('illi_daily', '(high - low) * 1000000000 / turnover', is_quarterly=False) # dv.add_formula('illi', 'Ewma(illi_daily, 11)', is_quarterly=False) # dv.add_formula('size', 'Log(float_mv)', is_quarterly=False) # dv.add_formula('value', '-1.0/pb', is_quarterly=False) # dv.add_formula('liquidity', 'Ts_Mean(volume, 22) / float_mv', is_quarterly=False) dv.add_formula('divert', '- Correlation(vwap_adj, volume, 10)', is_quarterly=False) signal = dv.get_ts('divert').shift(1, axis=0) # avoid look-ahead bias price = dv.get_ts('close_adj') price_bench = dv.data_benchmark # Step.4 analyze! my_period = 5 obj = signaldigger.digger.SignalDigger( output_folder=jutil.join_relative_path('../output'), output_format='pdf') obj.process_signal_before_analysis( signal, price=price, mask=mask_all, n_quantiles=5, period=my_period, benchmark_price=price_bench, ) res = obj.create_full_report()
def test_add_formula(): dv = DataView() dv.load_dataview(folder_path=daily_path) nrows, ncols = dv.data_d.shape n_securities = len(dv.data_d.columns.levels[0]) formula = 'Delta(high - close, 1)' dv.add_formula('myvar1', formula, is_quarterly=False) assert dv.data_d.shape == (nrows, ncols + 1 * n_securities) formula2 = 'myvar1 - close' dv.add_formula('myvar2', formula2, is_quarterly=False) assert dv.data_d.shape == (nrows, ncols + 2 * n_securities)
def test_add_formula(): dv = DataView() folder_path = '../output/prepared/20160601_20170601_freq=1D' dv.load_dataview(folder=folder_path) nrows, ncols = dv.data_d.shape n_securities = len(dv.data_d.columns.levels[0]) formula = 'Delta(high - close, 1)' dv.add_formula('myvar1', formula, is_quarterly=False) assert dv.data_d.shape == (nrows, ncols + 1 * n_securities) formula2 = 'myvar1 - close' dv.add_formula('myvar2', formula2, is_quarterly=False) assert dv.data_d.shape == (nrows, ncols + 2 * n_securities)
def test_add_formula_directly(): from jaqs.data.dataservice import RemoteDataService ds = RemoteDataService() dv = DataView() secs = '600030.SH,000063.SZ,000001.SZ' props = {'start_date': 20160601, 'end_date': 20170601, 'symbol': secs, 'fields': 'open,close', 'freq': 1} dv.init_from_config(props, data_api=ds) dv.prepare_data() dv.add_formula("myfactor", 'close / open', is_quarterly=False) assert dv.data_d.shape == (281, 33)
def test_q_add_formula(): dv = DataView() folder_path = '../output/prepared/20160609_20170601_freq=1D' dv.load_dataview(folder_path=quarterly_path) nrows, ncols = dv.data_d.shape n_securities = len(dv.data_d.columns.levels[0]) formula = 'total_oper_rev / close' dv.add_formula('myvar1', formula, is_quarterly=False) df1 = dv.get_ts('myvar1') assert not df1.empty formula2 = 'Delta(oper_exp * myvar1 - open, 3)' dv.add_formula('myvar2', formula2, is_quarterly=False) df2 = dv.get_ts('myvar2') assert not df2.empty
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 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(): 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(): # 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 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)
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_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)