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 analyze_event():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
# --------------------------------------------------------------------------------
# Step.2 calculate mask (to mask those ill data points)
mask_limit_reached = dv.get_ts('mask_limit_reached')
mask_index_member = dv.get_ts('mask_index_member')
mask_sus = dv.get_ts('mask_sus')
mask_all = np.logical_or(
mask_sus, np.logical_or(mask_index_member, mask_limit_reached))
# --------------------------------------------------------------------------------
# Step.3 get signal, benchmark and price data
price = dv.get_ts('close_adj')
price_bench = dv.data_benchmark
dv.add_formula('in_',
'(Delay(index_weight, 1) == 0) && (index_weight > 0)',
is_quarterly=False)
signal = dv.get_ts('in_').shift(1, axis=0) # avoid look-ahead bias
# Step.4 analyze!
obj = SignalDigger(output_folder='../../output', output_format='pdf')
obj.create_binary_event_report(signal,
price,
mask_all,
price_bench,
periods=[20, 60, 121, 242],
group_by=None)
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_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 analyze_event():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
# --------------------------------------------------------------------------------
# Step.2 calculate mask (to mask those ill data points)
mask_limit_reached = dv.get_ts('mask_limit_reached')
mask_index_member = dv.get_ts('mask_index_member')
mask_sus = dv.get_ts('mask_sus')
mask_all = np.logical_or(mask_sus, np.logical_or(mask_index_member, mask_limit_reached))
# --------------------------------------------------------------------------------
# Step.3 get signal, benchmark and price data
price = dv.get_ts('close_adj')
price_bench = dv.data_benchmark
dv.add_formula('in_', '(Delay(index_weight, 1) == 0) && (index_weight > 0)', is_quarterly=False)
signal = dv.get_ts('in_').shift(1, axis=0) # avoid look-ahead bias
# Step.4 analyze!
obj = SignalDigger(output_folder='../../output', output_format='pdf')
obj.create_binary_event_report(signal, price, mask_all, price_bench, periods=[20, 60, 121, 242], group_by=None)
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_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 analyze_event():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
# --------------------------------------------------------------------------------
# Step.3 get signal, benchmark and price data
target_symbol = '600519.SH'
price = dv.get_ts('close_adj', symbol=target_symbol)
dv.add_formula('in_', 'open_adj / Delay(close_adj, 1)', is_quarterly=False)
signal = dv.get_ts('in_', symbol=target_symbol).shift(1, axis=0) # avoid look-ahead bias
# Step.4 analyze!
obj = SignalDigger(output_folder='../../output', output_format='pdf')
obj.create_single_signal_report(signal, price, [1, 5, 9, 21], 6, mask=None,
buy_condition={'cond1': {'column': 'quantile',
'filter': lambda x: x > 3,
'hold': 5},
'cond2': {'column': 'quantile',
'filter': lambda x: x > 5,
'hold': 5},
'cond3': {'column': 'quantile',
'filter': lambda x: x > 5,
'hold': 9},
})
def simple_test_signal():
dv = DataView()
dv.load_dataview(dataview_folder)
dv.add_formula('open_jump', 'open_adj / Delay(close_adj, 1)', is_quarterly=False) # good
analyze_signal(dv, 'open_jump', 'pdf')
print("Signal return & IC test finished.")
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_DIY_signal():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
# 方法1：add_formula 基于dataview里已有的字段,通过表达式定义因子
dv.add_formula("momentum",
"Return(close_adj, 20)",
is_quarterly=False,
add_data=True)
# 方法2: append_df 构造一个因子表格（pandas.Dataframe）,直接添加到dataview当中
import pandas as pd
import talib as ta
close = dv.get_ts("close_adj").dropna(how='all', axis=1)
slope_df = pd.DataFrame(
{
sec_symbol: -ta.LINEARREG_SLOPE(value.values, 10)
for sec_symbol, value in close.iteritems()
},
index=close.index)
dv.append_df(slope_df, 'slope')
dv.get_ts("slope")
# 定义事件
from jaqs_fxdayu.research.signaldigger import process
Open = dv.get_ts("open_adj")
High = dv.get_ts("high_adj")
Low = dv.get_ts("low_adj")
Close = dv.get_ts("close_adj")
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status != 1
# 剔除掉停牌期的数据 再计算指标
open_masked = process._mask_df(Open, mask=mask_sus)
high_masked = process._mask_df(High, mask=mask_sus)
low_masked = process._mask_df(Low, mask=mask_sus)
close_masked = process._mask_df(Close, mask=mask_sus)
from jaqs_fxdayu.data import signal_function_mod as sfm
MA5 = sfm.ta(ta_method='MA',
ta_column=0,
Open=open_masked,
High=high_masked,
Low=low_masked,
Close=close_masked,
Volume=None,
timeperiod=10)
MA10 = sfm.ta('MA', Close=close_masked, timeperiod=10)
dv.append_df(MA5, 'MA5')
dv.append_df(MA10, 'MA10')
dv.add_formula("Cross",
"(MA5>=MA10)&&(Delay(MA5<MA10, 1))",
is_quarterly=False,
add_data=True)
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(output_folder='../../output/test_signal',
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()
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_directly():
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',
'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, 39)
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(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 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(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_add_formula_directly():
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',
'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, 39)
def test_analyze_signal():
# --------------------------------------------------------------------------------
# Step.1 load dataview
dv = DataView()
dv.load_dataview(dataview_folder)
mask = mask_index_member(dv)
can_enter, can_exit = limit_up_down(dv)
# --------------------------------------------------------------------------------
# Step.3 get signal, benchmark and price data
dv.add_formula('divert',
'- Correlation(vwap_adj, volume, 10)',
is_quarterly=False,
add_data=True)
signal = dv.get_ts('divert')
price = dv.get_ts('close_adj')
price_bench = dv.data_benchmark
# Step.4 analyze!
my_period = 5
obj = SignalDigger(output_folder='../output/test_signal',
output_format='pdf')
obj.process_signal_before_analysis(
signal=signal,
price=price,
high=dv.get_ts("high_adj"), # 可为空
low=dv.get_ts("low_adj"), # 可为空
group=dv.get_ts("sw1"),
n_quantiles=5, # quantile分类数
mask=mask, # 过滤条件
can_enter=can_enter, # 是否能进场
can_exit=can_exit, # 是否能出场
period=my_period, # 持有期
benchmark_price=price_bench, # 基准价格 可不传入，持有期收益（return）计算为绝对收益
commission=0.0008,
)
signal_data = obj.signal_data
result = analysis(signal_data, is_event=False, period=my_period)
ic = pfm.calc_signal_ic(signal_data, by_group=True)
mean_ic_by_group = pfm.mean_information_coefficient(ic, by_group=True)
plotting.plot_ic_by_group(mean_ic_by_group)
res = obj.create_full_report()
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_ttm():
from jaqs.data import DataView
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
props = {
'start_date': 20120101,
'end_date': 20170601,
'universe': '000016.SH',
'fields': ('net_profit_incl_min_int_inc'),
'freq': 1
}
dv.init_from_config(props, ds)
dv.prepare_data()
dv.add_formula('single',
'TTM(net_profit_incl_min_int_inc)',
is_quarterly=True)
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 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': 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 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_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 analyze_event():
# --------------------------------------------------------------------------------
# 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('new_high',
'close_adj >= Ts_Max(close_adj, 300)',
is_quarterly=False)
dv.add_formula('new_high_delay',
'Delay(Ts_Max(new_high, 300), 1)',
is_quarterly=False)
dv.add_formula('sig', 'new_high && (! new_high_delay)', is_quarterly=False)
signal = dv.get_ts('sig').shift(0, axis=0) # avoid look-ahead bias
price = dv.get_ts('close_adj')
price_bench = dv.data_benchmark
# Step.4 analyze!
obj = SignalDigger(output_folder=jutil.join_relative_path('../output'),
output_format='pdf')
obj.create_binary_event_report(signal,
price,
mask_all,
5,
price_bench,
periods=[5, 20, 40])
def test_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'
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('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(output_folder='../output/test_signal', 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_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)
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 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': ('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)
dv.load_dataview(dataview_folder2)
dv.fields
# In[6]:
sw1 = dv.get_ts('sw1')
dict_classify = {'480000': '银行', '430000': '房地产', '460000': '休闲服务', '640000': '机械设备', '240000': '有色金属', '510000': '综合', '410000': '公用事业', '450000': '商业贸易', '730000': '通信', '330000': '家用电器', '720000': '传媒', '630000': '电气设备', '270000': '电子', '490000': '非银金融', '370000': '医药生物', '710000': '计算机', '280000': '汽车', '340000': '食品饮料', '220000': '化工', '210000': '采掘', '230000': '钢铁', '650000': '国防军工', '110000': '农林牧渔', '420000': '交通运输', '620000': '建筑装饰', '350000': '纺织服装', '610000': '建筑材料', '360000': '轻工制造'}
sw1_name = sw1.replace(dict_classify)
# In[76]:
pm = dv.add_formula('pm','tot_profit/float_mv',is_quarterly=False,add_data=True)
ETOP = dv.add_formula('ETOP','tot_profit/total_mv',is_quarterly=False,add_data=True)
roa = dv.add_formula('roa','roa',is_quarterly=True,add_data=True)
roe = dv.add_formula('roe','roe',is_quarterly=True,add_data=True)
import alpha32_,alpha194,alpha195,alpha42_,alpha62_,alpha64_,alpha197,alpha211,alpha56_
dv.append_df(alpha32_.run_formula(dv),'alpha32_')
dv.append_df(alpha194_.run_formula(dv),'alpha194_')
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_')
def test_multi_factor():
from jaqs_fxdayu.research.signaldigger import multi_factor, process
dv = DataView()
dv.load_dataview(dataview_folder)
dv.add_formula("momentum",
"Return(close_adj, 20)",
is_quarterly=False,
add_data=True)
mask = mask_index_member(dv)
can_enter, can_exit = limit_up_down(dv)
ic = dict()
factors_dict = {
signal: dv.get_ts(signal)
for signal in ["pb", "pe", "ps", "momentum"]
}
for period in [5, 15]:
ic[period] = multi_factor.get_factors_ic_df(
factors_dict,
price=dv.get_ts("close_adj"),
high=dv.get_ts("high_adj"), # 可为空
low=dv.get_ts("low_adj"), # 可为空
n_quantiles=5, # quantile分类数
mask=mask, # 过滤条件
can_enter=can_enter, # 是否能进场
can_exit=can_exit, # 是否能出场
period=period, # 持有期
benchmark_price=dv.
data_benchmark, # 基准价格 可不传入，持有期收益（return）计算为绝对收益
commission=0.0008,
)
factor_dict = dict()
index_member = dv.get_ts("index_member")
for name in ["pb", "pe", "ps", "momentum"]:
signal = -1 * dv.get_ts(name) # 调整符号
process.winsorize(factor_df=signal,
alpha=0.05,
index_member=index_member) # 去极值
signal = process.rank_standardize(
signal, index_member) # 因子在截面排序并归一化到0-1(只保留排序信息)
signal = process.standardize(signal,
index_member) # z-score标准化 保留排序信息和分布信息
# 行业市值中性化
signal = process.neutralize(
signal,
group=dv.get_ts("sw1"),
float_mv=dv.get_ts("float_mv"),
index_member=index_member, # 是否只处理时只考虑指数成份股
)
factor_dict[name] = signal
# 因子间存在较强同质性时，使用施密特正交化方法对因子做正交化处理，用得到的正交化残差作为因子
new_factors = multi_factor.orthogonalize(
factors_dict=factor_dict,
standardize_type="rank",
# 输入因子标准化方法，有"rank"（排序标准化）,"z_score"(z-score标准化)两种（"rank"/"z_score"）
winsorization=False, # 是否对输入因子去极值
index_member=index_member) # 是否只处理指数成分股
# 多因子组合-动态加权参数配置
props = {
'price': dv.get_ts("close_adj"),
'high': dv.get_ts("high_adj"), # 可为空
'low': dv.get_ts("low_adj"), # 可为空
'ret_type':
'return', # 可选参数还有upside_ret/downside_ret 则组合因子将以优化潜在上行、下行空间为目标
'benchmark_price': dv.data_benchmark, # 为空计算的是绝对收益 不为空计算相对收益
'period': 30, # 30天的持有期
'mask': mask,
'can_enter': can_enter,
'can_exit': can_exit,
'forward': True,
'commission': 0.0008,
"covariance_type": "shrink", # 协方差矩阵估算方法 还可以为"simple"
"rollback_period": 120
} # 滚动窗口天数
comb_factors = dict()
for method in [
"equal_weight", "ic_weight", "ir_weight", "max_IR", "max_IC",
"factors_ret_weight"
]:
comb_factors[method] = multi_factor.combine_factors(
factor_dict,
standardize_type="rank",
winsorization=False,
weighted_method=method,
props=props)
import time
import pandas as pd
from jaqs.data import RemoteDataService
from jaqs.data import DataView
import jaqs.util as jutil
from config_path import DATA_CONFIG_PATH, TRADE_CONFIG_PATH
data_config = jutil.read_json(DATA_CONFIG_PATH)
trade_config = jutil.read_json(TRADE_CONFIG_PATH)
dataview_dir_path = '../../output/canslim/dataview'
props = {
'start_date': 20170101,
'end_date': 20180516,
'universe': '000905.SH',
'fields': "",
'freq': 1
}
ds = RemoteDataService()
ds.init_from_config(data_config)
dv = DataView()
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)
dv.save_dataview(folder_path=dataview_dir_path)
{
name: value.dropna().rolling(120).std()**2
for name, value in pct_return.iteritems()
},
index=pct_return.index).fillna(method='ffill')
gainvariance120 = dv.append_df(temp, 'gainvariance120')
#alpha46
def mean(df, day):
return df.rolling(window=day, center=False).mean()
alpha46 = dv.add_formula(
'alpha46',
"(mean(close,3)+mean(close,6)+mean(close,12)+mean(close,24))/(4*close)",
is_quarterly=False,
add_data=True,
register_funcs={"mean": mean})
#alpha48
def sum_fxdayu(df, day):
return df.rolling(window=day, center=False).sum()
alpha48 = dv.add_formula(
'alpha48',
"(-1*((Rank(((Sign((close - Delay(close, 1))) + Sign((Delay(close, 1) - Delay(close, 2)))) +Sign((Delay(close, 2) - Delay(close, 3)))))) * SUM(volume, 5)) / SUM(volume, 20))",
is_quarterly=False,
add_data=True,
register_funcs={"SUM": sum_fxdayu})
