def get_torate(universe, start_time, end_time):
'''
获取换手率，使用当天交易量/流通股数来计算
'''
volume = query('TO_VOLUME', (start_time, end_time))
float_shares = query('FLOAT_SHARE', (start_time, end_time))
res = volume / float_shares
res = res.loc[:, sorted(universe)]
assert checkdata_completeness(res, start_time, end_time), "Error, data missed!"
return res
def inner(universe, start_time, end_time):
adj_factor = query('ADJ_FACTOR', (start_time, end_time))
data = query(price_type, (start_time, end_time))
assert len(adj_factor) == len(data), "Error, basic data length does not match! " + \
"adj_factor data = {sd_len}, while close data = {cd_len}".format(sd_len=len(adj_factor),
cd_len=len(data))
res = adj_factor * data
res = res.loc[:, sorted(universe)]
assert checkdata_completeness(res, start_time, end_time), "Error, data missed!"
return res
def _inner(universe, start_time, end_time):
share_data = query(share_factor_name, (start_time, end_time))
close_data = query('CLOSE', (start_time, end_time))
assert len(share_data) == len(close_data), "Error, basic data length does not match! " + \
"share data = {sd_len}, while close data = {cd_len}".format(sd_len=len(share_data),
cd_len=len(close_data))
res = share_data * close_data
res = res.loc[:, sorted(universe)]
assert checkdata_completeness(res, start_time, end_time), "Error, data missed!"
return res
def get_valid_mask(start_time, end_time):
'''
获取给定期间内（包含起始时间）数据是否有效的掩码。
Parameter
---------
start_time: datetime like
开始时间
end_time: datetime like
结束时间
Return
------
out: pd.DataFrame
index为时间，columns为股票代码
Notes
-----
数据是否有效是根据当前股票是否退市或者终止上市来判断的，凡是LIST_STATUS为退市或者终止上市（3和4）
状态的股票均被视作为无效数据，即False
'''
from fmanager.factors.query import query
ls_status = query('LIST_STATUS', (start_time, end_time))
valid_mask = np.logical_or(ls_status == 1, ls_status == 2)
return valid_mask
def get_lntotalmktv(universe, start_time, end_time):
'''
对数总市值
'''
tmktv = query('TOTAL_MKTVALUE', (start_time, end_time))
data = np.log(tmktv)
data = data.loc[:, sorted(universe)]
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
def get_lnfloatmktv(universe, start_time, end_time):
'''
对数流通市值
'''
fmktv = query('FLOAT_MKTVALUE', (start_time, end_time))
data = np.log(fmktv)
data = data.loc[:, sorted(universe)]
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
def get_dailyret(universe, start_time, end_time):
'''
获取日收益率，使用后复权收盘价计算
'''
new_start = pd.to_datetime(start_time) - pd.Timedelta('30 day')
data = query('ADJ_CLOSE', (new_start, end_time))
data = data.pct_change()
mask = data.index >= start_time
data = data.loc[mask, sorted(universe)]
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
def get_avgtorate(universe, start_time, end_time):
'''
指过去20个交易日平均换手率
'''
start_time = pd.to_datetime(start_time)
new_start = start_time - pd.Timedelta('60 day')
daily_torate = query('TO_RATE', (new_start, end_time))
data = daily_torate.rolling(20, min_periods=20).mean().dropna(how='all')
mask = (data.index >= start_time) & (data.index <= end_time)
data = data.loc[mask, sorted(universe)]
if start_time > pd.to_datetime(START_TIME): # 第一次更新从START_TIME开始，必然会有缺失数据
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
def inner(universe, start_time, end_time):
start_time = pd.to_datetime(start_time)
threshold = 10e-6
new_start = dateshandle.tds_shift(start_time, offset)
daily_torate = query('TO_RATE', (new_start, end_time))
data = daily_torate.rolling(offset, min_periods=offset).sum().dropna(how='all')
data[data <= threshold] = np.NaN
data = data / month_num
data = np.log(data)
mask = (data.index >= start_time) & (data.index <= end_time)
data = data.loc[mask, sorted(universe)]
if start_time > pd.to_datetime(START_TIME): # 第一次更新从START_TIME开始，必然会有缺失数据
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
def get_nonlinearmktv(universe, start_time, end_time):
'''
非线性市值，并不针对市值数据进行正交化
'''
lnmktv = query('LN_TMKV', (start_time, end_time))
# def get_nlsize(df):
# # 市值3次方然后通过OLS来获取与市值正交的残差
# raw_index = df.index
# df = df.dropna()
# nonlsize = np.power(df, 3)
# mod = OLS(nonlsize, add_constant(df))
# mod_res = mod.fit()
# return mod_res.resid.reindex(raw_index)
# data = lnmktv.apply(get_nlsize, axis=1)
data = np.power(lnmktv, 3)
data = data.loc[:, sorted(universe)]
assert checkdata_completeness(data, start_time, end_time), "Error, data missed!"
return data
