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_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_load(): dv = DataView() folder_path = '../output/prepared/20160601_20170601_freq=1D' dv.load_dataview(folder=folder_path) assert dv.start_date == 20160601 and set(dv.symbol) == set('000001.SZ,600030.SH,000063.SZ'.split(',')) # test get_snapshot snap1 = dv.get_snapshot(20170504, symbol='600030.SH,000063.SZ', fields='close,pb') assert snap1.shape == (2, 2) assert set(snap1.columns.values) == {'close', 'pb'} assert set(snap1.index.values) == {'600030.SH', '000063.SZ'} # test get_ts ts1 = dv.get_ts('close', symbol='600030.SH,000063.SZ', start_date=20170101, end_date=20170302) assert ts1.shape == (38, 2) assert set(ts1.columns.values) == {'600030.SH', '000063.SZ'} assert ts1.index.values[-1] == 20170302
for index in indexList: # 设置DataView props = { 'start_date': startdate, 'end_date': enddate, 'universe': index, 'fields': 'close_adj', 'freq': 1 } dv.init_from_config(props, data_api=ds) dv.prepare_data() print(index) # 取出板块指数,版块成份股日收盘价及是否为成分股的信息 closeData = dv.get_ts('close_adj') closeData['trade_date'] = closeData.index closeData['trade_date'] = closeData['trade_date'].apply(lambda x: str(x)) closeData['trade_y'] = closeData['trade_date'].apply(lambda x: x[:4]) benchmarkData = dv.data_benchmark benchmarkData['trade_date'] = benchmarkData.index benchmarkData['trade_date'] = benchmarkData['trade_date'].apply( lambda x: str(x)) benchmarkData['trade_y'] = benchmarkData['trade_date'].apply( lambda x: x[:4]) isIndexMember = dv.get_ts('index_member') == 1 isIndexMember['trade_date'] = isIndexMember.index isIndexMember['trade_date'] = isIndexMember['trade_date'].apply( lambda x: str(x))