def get_(folder):
# step 2 因子数据预处理
# 加载dataview数据集
dv = DataView()
dataview_folder = folder
dv.load_dataview(dataview_folder)
# 定义信号过滤条件-非指数成分
# df_index_member = dv.get_ts('index_member')
signal = dv.get_ts("pb")
price = dv.get_ts("close_adj")
group = dv.get_ts("sw1")
# mask
mask = dv.get_ts('index_member') == 0 # 定义信号过滤条件-非指数成分
# 定义可买入卖出条件——未停牌、未涨跌停
trade_status = dv.get_ts('trade_status')
can_trade = trade_status == 1 # 可以交易
# 涨停
up_limit = dv.add_formula(
'up_limit',
'(open - Delay(close, 1)) / Delay(close, 1) > 0.095',
is_quarterly=False)
# 跌停
down_limit = dv.add_formula(
'down_limit',
'(open - Delay(close, 1)) / Delay(close, 1) < -0.095',
is_quarterly=False)
can_enter = np.logical_and(up_limit < 1, can_trade) # 未涨停未停牌
can_exit = np.logical_and(down_limit < 1, can_trade) # 未跌停未停牌
benchmark = dv.data_benchmark
return signal, price, mask, group, can_enter, can_exit, benchmark
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, add_data=True)
assert dv.data_d.shape == (nrows, ncols + 1 * n_securities)
formula2 = 'myvar1 - close'
dv.add_formula('myvar2', formula2, is_quarterly=False, add_data=True)
assert dv.data_d.shape == (nrows, ncols + 2 * n_securities)
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, add_data=True)
df1 = dv.get_ts('myvar1')
assert not df1.empty
formula2 = 'Delta(oper_exp * myvar1 - open, 3)'
dv.add_formula('myvar2', formula2, is_quarterly=False, add_data=True)
df2 = dv.get_ts('myvar2')
assert not df2.empty
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, 36)
import pandas as pd
from datetime import datetime
def change_time(df):
df.index = pd.Index(
map(lambda x: datetime.strptime(str(x), "%Y%m%d"), df.index))
return df
EMA = dv.get_ts('close').ewm(span=5, adjust=False).mean()
EMA2 = EMA.ewm(span=5, adjust=False).mean()
EMA3 = EMA2.ewm(span=5, adjust=False).mean()
dv.append_df(EMA3, 'EMA3')
dv.add_formula('a',
'close/Delay(close,1)-1',
is_quarterly=False,
add_data=True)
dv.add_formula('b',
'(close/Delay(EMA3,19))^(1/20)-1',
is_quarterly=False,
add_data=True)
Factor1 = dv.add_formula(
'Factor1',
'-Log((Ts_Sum(If(a>b,1,0),20)-1)*Ts_Sum(If(a<b,(a-b)^2,0),20)/(Ts_Sum(If(a<b,1,0),20))*Ts_Sum(If(a>b,(a-b)^2,0),20))',
is_quarterly=False,
add_data=True)
EMA = dv.get_ts('close').ewm(span=60, adjust=False).mean()
dv.append_df(EMA, 'EMA')
Factor2 = dv.add_formula('Factor2', '-ps', is_quarterly=False, add_data=True)
#1_初始化
from jaqs_fxdayu.data import DataView
import warnings
warnings.filterwarnings("ignore")
dataview_folder = 'G:/data/hs300_2'
dv = DataView()
dv.load_dataview(dataview_folder)
dv.add_formula("momentum",
"Return(close_adj, 20)",
is_quarterly=False,
add_data=True) #直接使用内置的函数,添加新因子,可能之前已经添加过了
dv.get_ts("momentum").head()
print(dv.fields) #查看dv中取得的数据
import numpy as np
#定义过滤条件
def mask_index_member():
df_index_member = dv.get_ts('index_member')
mask_index_member = ~(df_index_member > 0) #定义信号过滤条件-非指数成分
return mask_index_member
def limit_up_down():
# 定义可买卖条件——未停牌、未涨跌停
trade_status = dv.get_ts('trade_status')
mask_sus = trade_status == u'停牌'
# 涨停
dv.add_formula('up_limit',
dv.add_field('close',ds)
dv.add_field('high',ds)
dv.add_field('low',ds)
dv.add_field('turnover',ds)
dv.add_field('turnover_ratio',ds)
dv.add_field('price_div_dps',ds)
dv.add_field('oper_rev',ds)
dv.add_field('roa',ds)
dv.add_field('total_share',ds)
dv.add_field('pe_ttm',ds)
dv.add_field('roe',ds)
dv.add_field('roa',ds)
#alpha1= dv.add_formula('alpha1', "-1*Delta(close,200)/Delay(close,200)", is_quarterly=False, add_data=True)
dv.add_formula('DP01',"close-Delay(Ts_Mean(close,20),11)",is_quarterly=False,add_data=True)
alpha1=dv.add_formula('alpha1','-Ts_Mean(DP01,6)',is_quarterly=False,add_data=True)
alpha2 = dv.add_formula('alpha2',
"-Log(total_share*close)"
, is_quarterly=False, add_data=True)
#alpha3 = dv.add_formula('alpha3',
# "roa"
# , is_quarterly=False, add_data=True)
#alpha4 = dv.add_formula('alpha4',
# "roe"
# , is_quarterly=False, add_data=True)
#alpha5 = dv.add_formula('alpha5',
# "-1*price_div_dps", is_quarterly=False, add_data=True)
from jaqs_fxdayu.data import DataView
import warnings
warnings.filterwarnings("ignore")
dataview_folder = '../Factor'
dv = DataView()
dv.load_dataview(dataview_folder)
dv.add_formula("Divert", "Corr(volume,close_adj,20)",
is_quarterly=False).head()
# 添加到数据集dv里，则计算结果之后可以反复调用
dv.add_formula("Divert",
"Corr(volume,close_adj,20)",
is_quarterly=False,
add_data=True)
dv.get_ts("Divert").head()