def __init__(self, *codes, start="20200101", end=yesterday(), col="close"):
"""
:param codes: Union[str, tuple], 格式与 :func:`xalpha.universal.get_daily` 相同，若需要汇率转换，需要用 tuple，第二个元素形如 "USD"
:param start: %Y%m%d
:param end: %Y%m%d, default yesterday
"""
totdf = pd.DataFrame()
codelist = []
for c in codes:
if isinstance(c, tuple):
code = c[0]
currency = c[1]
else:
code = c
currency = "CNY" # 标的不做汇率调整
codelist.append(code)
df = xu.get_daily(code, start=start, end=end)
df = df[df.date.isin(opendate)]
currency_code = _get_currency_code(currency)
if currency_code:
cdf = xu.get_daily(currency_code, start=start, end=end)
cdf = cdf[cdf["date"].isin(opendate)]
df = df.merge(right=cdf, on="date", suffixes=("_x", "_y"))
df[col] = df[col + "_x"] * df[col + "_y"]
df[code] = df[col] / df.iloc[0][col]
df = df.reset_index()
df = df[["date", code]]
if "date" not in totdf.columns:
totdf = df
else:
totdf = totdf.merge(on="date", right=df)
self.totdf = totdf
self.codes = codelist
def daily_increment(code, date, lastday=None, _check=False):
"""
单一标的 date 日（若 date 日无数据则取之前的最晚有数据日，但该日必须大于 _check 对应的日期）较上一日或 lastday 的倍数，
lastday 支持不完整，且不能离 date 太远
:param code:
:param date:
:param lastday: 如果用默认 None，则表示和前一日的涨跌
:param _check: 数据必须已更新到 date 日，除非之前每天都是节假日
:return:
"""
try:
tds = xu.get_daily(code=code, end=date, prev=30)
except Exception as e: # 只能笼统 catch 了，因为抓取失败的异常是什么都能遇到。。。
code = get_alt(code)
if code:
tds = xu.get_daily(code=code, end=date, prev=30)
else:
raise e
tds = tds[tds["date"] <= date]
if _check:
date = date.replace("-", "").replace("/", "")
date_obj = dt.datetime.strptime(date, "%Y%m%d")
while tds.iloc[-1]["date"] < date_obj:
# in case data is not up to date
# 但是存在日本市场休市时间不一致的情况，估计美股也存在
if not is_on(
date_obj.strftime("%Y%m%d"),
get_market(code),
no_trading_days=no_trading_days,
) or (date_obj.strftime("%Y-%m-%d") in gap_info.get(code, [])):
print("%s is closed on %s" % (code, date))
if not lastday:
return 1 # 当日没有涨跌，这里暂时为考虑 _check 和 lastday 相同的的情形
date_obj -= dt.timedelta(days=1)
else:
raise DateMismatch(
code,
reason="%s has no data newer than %s" %
(code, date_obj.strftime("%Y-%m-%d")),
)
if not lastday:
ratio = tds.iloc[-1]["close"] / tds.iloc[-2]["close"]
else:
tds2 = tds[tds["date"] <= lastday]
# 未考虑连 lastday 的数据数据源都没更新的情形，这种可能极小
ratio = tds.iloc[-1]["close"] / tds2.iloc[-1]["close"]
return ratio
def __init__(self, code, status, name=None):
"""
:param code: str. 代码格式与 :func:`xalpha.universal.get_daily` 要求相同
:param status: 记账单或 irecord 类。
:param name: Optional[str]. 可提供标的名称。
"""
self.code = code
if isinstance(status, irecord):
self.status = status.filter(code)
else:
self.status = status[status.code == code]
# self.cftable = pd.DataFrame([], columns=["date", "cash", "share"])
try:
self.price = xu.get_daily(
self.code,
start=self.status.iloc[0]["date"].strftime("%Y-%m-%d"))
self.price["netvalue"] = self.price["close"]
except Exception as e:
logger.warning("%s when trade trying to get daily price of %s" %
(e, self.code))
self.price = None
self._arrange()
if not name:
try:
self.name = get_rt(code)["name"]
except:
self.name = code
self.type_ = None
def xirrcal(cftable, trades, date, guess=0.1):
"""
calculate the xirr rate
:param cftable: cftable (pd.Dateframe) with date and cash column
:param trades: list [trade1, ...], every item is an trade object,
whose shares would be sold out virtually
:param date: string of date or datetime object,
the date when virtually all holding positions being sold
:param guess: floating number, a guess at the xirr rate solution to be used
as a starting point for the numerical solution
:returns: the IRR as a single floating number
"""
date = convert_date(date)
partcftb = cftable[cftable["date"] <= date]
if len(partcftb) == 0:
return 0
cashflow = [(row["date"], row["cash"]) for i, row in partcftb.iterrows()]
rede = 0
for fund in trades:
if not isinstance(fund, itrade):
rede += fund.aim.shuhui(
fund.briefdailyreport(date).get("currentshare", 0),
date,
fund.remtable[fund.remtable["date"] <= date].iloc[-1].rem,
)[1]
else: # 场内交易
pricedf = get_daily(fund.code, end=date.strftime("%Y%m%d"), prev=20)
price = pricedf[pricedf.date <= date].iloc[-1]["close"]
rede += fund.cftable.share.sum() * price
cashflow.append((date, rede))
return xirr(cashflow, guess)
def __init__(self, code, start=None, end=None):
"""
:param code: str. 形式可以是 399971.XSHE 或者 SH000931
:param start: Optional[str]. %Y-%m-%d, 估值历史计算的起始日。
:param end: Dont use, only for debug
"""
yesterday_str = (dt.datetime.now() -
dt.timedelta(days=1)).strftime("%Y-%m-%d")
if len(code.split(".")) == 2:
self.code = code
self.scode = _convert_code(code)
else:
self.scode = code
self.code = _inverse_convert_code(self.scode)
if self.code in self.indexs:
self.name = self.indexs[self.code][0]
if not start:
start = self.indexs[self.code][1]
else:
try:
self.name = get_rt(self.scode)["name"]
except:
self.name = self.scode
if not start:
start = "2012-01-01" # 可能会出问题，对应指数还未有数据
self.start = start
if not end:
end = yesterday_str
self.df = xu.get_daily("peb-" + self.scode, start=self.start, end=end)
self.ratio = None
self.title = "指数"
self._gen_percentile()
def __init__(self, code, start=None, end=None, prev=None):
"""
:param code: str. eg SH501018, SZ160416
:param start: date range format is the same as xa.get_daily
:param end:
:param prev:
"""
self.code = code
df1 = xu.get_daily("F" + self.code[2:],
start=start,
end=end,
prev=prev)
df2 = xu.get_daily(self.code, start=start, end=end, prev=prev)
df1 = df1.merge(df2, on="date", suffixes=("_F", "_" + code[:2]))
df1["diff_rate"] = ((df1["close_" + code[:2]] - df1["close_F"]) /
df1["close_F"] * 100)
self.df = df1
def fluctuation(self):
if not self.ratio:
d = self.df.iloc[-1]["date"]
oprice = xu.get_daily(code=self.scode,
end=d.strftime("%Y%m%d"),
prev=20).iloc[-1]["close"]
nprice = get_rt(self.scode)["current"]
self.ratio = nprice / oprice
return self.ratio
def get_portfolio(self, date=yesterdayobj()):
"""
获取基金组合底层资产大类配置的具体值
:param date:
:return: Dict[str, float]. stock，bond，cash 对应总值的字典
"""
d = {"stock": 0, "bond": 0, "cash": 0}
date = convert_date(date)
for f in self.fundtradeobj:
value = f.briefdailyreport(date).get("currentvalue", 0)
if value > 0:
if isinstance(f, itrade):
if f.get_type() == "股票":
d["stock"] += value
continue
elif f.get_type() in ["可转债", "债券"]:
d["bond"] += value
continue
elif f.get_type() == "货币基金":
d["cash"] += value
continue
elif f.get_type() == "场内基金":
code = f.code[2:]
else:
continue
else:
code = f.code
if code == "mf":
d["cash"] += value
continue
if get_fund_type(code) == "货币基金":
d["cash"] += value
continue
df = xu.get_daily("pt-F" + code, end=date.strftime("%Y%m%d"))
if df is None or len(df) == 0:
logger.warning("empty portfolio info for %s" % code)
row = df.iloc[-1]
if row["bond_ratio"] + row["stock_ratio"] < 10: # 联接基金
d["stock"] += (
(100 - row["bond_ratio"] - row["cash_ratio"]) * value / 100
)
d["bond"] += row["bond_ratio"] * value / 100
d["cash"] += row["cash_ratio"] * value / 100
else:
d["stock"] += row["stock_ratio"] * value / 100
d["bond"] += row["bond_ratio"] * value / 100
d["cash"] += row["cash_ratio"] * value / 100
return d
def __init__(self, code, start=None, end=None):
self.code = code
self.scode = code
if not end:
end = (dt.datetime.now() -
dt.timedelta(days=1)).strftime("%Y-%m-%d")
if not start:
start = "2016-01-01" # 基金历史通常比较短
self.start = start
self.df = xu.get_daily("peb-" + code, start=start, end=end)
self.name = get_rt(code)["name"]
self.title = "基金"
self.ratio = None
self._gen_percentile()
def get_t0(self, return_date=True, percent=False):
last_value, last_date = self.get_t1()
last_date_obj = dt.datetime.strptime(last_date, "%Y-%m-%d")
cday = last_onday(self.today)
while last_date_obj < cday: # 昨天净值数据还没更新
# 是否存在部分部分基金可能有 gap？
if cday.strftime("%Y-%m-%d") not in gap_info[self.fcode]:
self.t1_type = "昨日未出"
raise DateMismatch(
self.code,
reason="%s netvalue has not been updated to yesterday" %
self.code,
)
else:
cday = last_onday(cday)
# 经过这个没报错，就表示数据源是最新的
if last_date_obj >= self.today: # 今天数据已出，不需要再预测了
print("no need to predict net value since it has been out for %s" %
self.code)
self.t1_type = "今日已出"
if not return_date:
return last_value
else:
return last_value, last_date
t = 0
n = 0
today_str = self.today.strftime("%Y%m%d")
for k, v in self.t0dict.items():
w = v
t += w
r = get_rt(k)
# k should support get_rt, investing pid doesn't support this!
if percent:
c = w / 100 * (1 + r["percent"] / 100) # 直接取标的当日涨跌幅
else:
df = xu.get_daily(k)
basev = df[df["date"] <= last_date].iloc[-1]["close"]
c = w / 100 * r["current"] / basev
currency_code = get_currency_code(k)
if currency_code:
c = c * daily_increment(currency_code, today_str)
n += c
n += (100 - t) / 100
t0value = n * last_value
self.t0_delta = n
if not return_date:
return t0value
else:
return t0value, self.today.strftime("%Y-%m-%d")
def _base_value(self, code, shift):
if not shift:
funddf = xu.get_daily(code) ## 获取股指现货日线
return funddf[funddf["date"] < self.today.strftime(
"%Y-%m-%d")].iloc[-1]["close"] # 日期是按当地时间
# TODO: check it is indeed date of last_on(today)
else:
if code not in self.bar_cache:
funddf = get_bar(code, prev=48, interval="3600") ## 获取小时线
if self.now.hour > 6: # 昨日美国市场收盘才正常，才缓存参考小时线
self.bar_cache[code] = funddf
else:
funddf = self.bar_cache[code]
return funddf[funddf["date"] <= self.today +
dt.timedelta(hours=shift)].iloc[-1][
"close"] # 时间是按北京时间, 小时线只能手动缓存，日线不需要是因为自带透明缓存器
def __init__(self, code, start=None, end=None):
"""
:param code: str. 指数代码，eg. SH000016
:param start:
:param end:
"""
df = xu.get_daily("teb-" + code, start=start, end=end)
df["e"] = pd.to_numeric(df["e"])
df["b"] = pd.to_numeric(df["b"])
df["lnb"] = df["b"].apply(lambda s: np.log(s))
df["lne"] = df["e"].apply(lambda s: np.log(s))
df["roe"] = df["e"] / df["b"] * 100
df["date_count"] = (df["date"] -
df["date"].iloc[0]).apply(lambda s: int(s.days))
self.df = df
self.fit(verbose=False)
def get_netvalue(self, date=yesterdayobj()):
# 若使用请务必配合带 precached 的缓存策略！！
if not getattr(self, "fetchonly", None):
self.fetchonly = False
prestart = self.status.iloc[0]["date"]
df = xu.get_daily(
self.code,
end=date.strftime("%Y%m%d"),
prev=20,
fetchonly=self.fetchonly,
precached=prestart.strftime("%Y%m%d"),
)
self.fetchonly = True # 这么做防止数据空白时期的反复抓取
if len(df) > 0:
return df.iloc[-1].close
else:
return 0
def _base_value(self, code, shift):
if not shift:
funddf = xu.get_daily(code) ## 获取股指现货日线
return funddf[funddf["date"] <= last_onday(self.today)].iloc[-1][
"close"] # 日期是按当地时间
# TODO: check it is indeed date of last_on(today)
else:
if code not in self.bar_cache:
funddf = get_bar(code, prev=168, interval="3600") ## 获取小时线
## 注意对于国内超长假期，prev 可能还不够
if self.now.hour > 6: # 昨日美国市场收盘才正常，才缓存参考小时线
self.bar_cache[code] = funddf
else:
funddf = self.bar_cache[code]
refdate = last_onday(self.today) + dt.timedelta(days=1) # 按北京时间校准
return funddf[funddf["date"] <= refdate +
dt.timedelta(hours=shift)].iloc[-1][
"close"] # 时间是按北京时间, 小时线只能手动缓存，日线不需要是因为自带透明缓存器
def __init__(self, code, start=None, end=None):
"""
:param code: 801180 申万行业指数
:param start:
:param end:
"""
self.code = code
self.scode = code
if not end:
end = (dt.datetime.now() -
dt.timedelta(days=1)).strftime("%Y-%m-%d")
if not start:
start = "2012-01-01"
self.start = start
self.df = xu.get_daily("sw-" + code, start=start, end=end)
self.name = self.df.iloc[0]["name"]
self.ratio = 1
self.title = "申万行业指数"
self._gen_percentile()
def _arrange(self):
d = {"date": [], "cash": [], "share": []}
for _, r in self.status.iterrows():
d["date"].append(r.date)
if r.share == 0:
d["cash"].append(-r.value)
d["share"].append(0)
else:
if r.value < 0:
r.value = xu.get_daily(
self.code, end=r.date.strftime("%Y-%m-%d"), prev=15
).iloc[-1]["close"]
if r.value == 0:
d["cash"].append(0)
d["share"].append(r.share) # 直接记录总的应增加+或减少的份额数
else:
d["cash"].append(-r.value * r.share - abs(r.fee)) # 手续费总是正的，和买入同号
d["share"].append(r.share)
self.cftable = pd.DataFrame(d)
def get_netvalue(self, date=yesterdayobj()):
return get_daily(self.code, end=date.strftime("%Y%m%d"), prev=20).iloc[-1].close
def _is_on(code, date):
df = xu.get_daily(code, prev=20, end=date)
if len(df[df["date"] == date]) == 0:
return False
return True
def process_byday(self, date):
if not date:
self.date_obj = dt.datetime.today()
else:
self.date_obj = dt.datetime.strptime(
date.replace("-", "").replace("/", ""), "%Y%m%d")
if not date:
rt = get_rt(self.code)
self.name = rt["name"]
self.cbp = rt["current"] # 转债价
self.stockp = get_rt(self.scode)["current"] # 股票价
else:
try:
if not self.name:
rt = get_rt(self.code)
self.name = rt["name"]
except:
self.name = "unknown"
df = xu.get_daily(self.code,
prev=100,
end=self.date_obj.strftime("%Y%m%d"))
self.cbp = df.iloc[-1]["close"]
df = xu.get_daily(self.scode,
prev=100,
end=self.date_obj.strftime("%Y%m%d"))
self.stockp = df.iloc[-1]["close"]
df = xu.get_daily(self.scode,
prev=360,
end=self.date_obj.strftime("%Y%m%d"))
self.history_volatility = np.std(
np.log(df["close"] / df.shift(1)["close"])) * np.sqrt(244)
if not self.refvolatility:
self.volatility = 0.17
if self.rating in ["A", "A+", "AA-"]:
self.volatility = 0.19
elif self.rating in ["AA"]:
self.volatility = 0.18
if self.history_volatility < 0.25:
self.volatility -= 0.01
elif self.history_volatility > 0.65:
self.volatility += 0.02
elif self.history_volatility > 0.45:
self.volatility += 0.01
self.years = len(self.rlist) - 1
syear = int(self.enddate.split("-")[0]) - self.years
self.issuedate = str(syear) + self.enddate[4:]
self.days = (dt.datetime.strptime(self.enddate, "%Y-%m-%d") -
self.date_obj).days
if not self.refbondrate:
ratestable = get_bond_rates(self.rating,
self.date_obj.strftime("%Y-%m-%d"))
if self.rating in ["A", "A+", "AA-"]:
## AA 到 AA- 似乎是利率跳高的一个坎
cutoff = 2
else:
cutoff = 4
if self.days / 365 > cutoff:
# 过长久期的到期收益率，容易造成估值偏离，虽然理论上是对的
# 考虑到国内可转债市场信用风险较低，不应过分低估低信用债的债券价值
self.bondrate = (
ratestable[ratestable["year"] <= cutoff].iloc[-1]["rate"] /
100)
else:
self.bondrate = (ratestable[ratestable["year"] >= self.days /
365].iloc[0]["rate"] / 100)
if not self.refriskfreerate:
ratestable = get_bond_rates("N",
self.date_obj.strftime("%Y-%m-%d"))
if self.days / 365 > 5:
self.riskfreerate = (
ratestable[ratestable["year"] <= 5].iloc[-1]["rate"] / 100)
else:
self.riskfreerate = (
ratestable[ratestable["year"] >= self.days /
365].iloc[0]["rate"] / 100)
def get_t1(self, date=None, return_date=True):
"""
预测 date 日的净值，基于 date-1 日的净值和 date 日的外盘数据，数据自动缓存，不会重复计算
:param date: str. %Y-%m-%d. 注意若是 date 日为昨天，即今日预测昨日的净值，date 取默认值 None。
:param return_date: bool, default True. return tuple, the second one is date in the format %Y%m%d
:return: float, (str).
:raises NonAccurate: 由于外盘数据还未及时更新，而 raise，可在调用程序中用 except 捕获再处理。
"""
if date is None:
yesterday = last_onday(self.today)
datekey = yesterday.strftime("%Y%m%d")
else:
datekey = date.replace("/", "").replace("-", "")
if datekey not in self.t1value_cache:
if self.positions:
current_pos = self.get_position(datekey, return_date=False)
hdict = scale_dict(self.t1dict.copy(), aim=current_pos * 100)
else:
hdict = self.t1dict.copy()
if date is None: # 此时预测上个交易日净值
yesterday_str = datekey
last_value, last_date = self.get_t2()
last_date_obj = dt.datetime.strptime(last_date, "%Y-%m-%d")
cday = last_onday(last_onday(self.today))
while last_date_obj < cday: # 前天净值数据还没更新
# 是否存在部分 QDII 在 A 股交易日，美股休市日不更新净值的情形？
if (cday.strftime("%Y-%m-%d")
not in gap_info[self.fcode]) and is_on(
cday, "US", no_trading_days):
# 这里检查比较宽松，只要当天美股休市，就可以认为确实基金数据不存在而非未更新
self.t1_type = "前日未出"
raise DateMismatch(
self.code,
reason=
"%s netvalue has not been updated to the day before yesterday"
% self.code,
)
else:
cday = last_onday(cday)
# 经过这个没报错，就表示数据源是最新的
if last_date_obj >= last_onday(self.today): # 昨天数据已出，不需要再预测了
print(
"no need to predict t-1 value since it has been out for %s"
% self.code)
self.t1_type = "昨日已出"
self.t1value_cache = {
last_date.replace("-", ""): last_value
}
if not return_date:
return last_value
else:
return last_value, last_date
else:
yesterday_str = datekey
fund_price = xu.get_daily(self.fcode) # 获取国内基金净值
fund_last = fund_price[fund_price["date"] < date].iloc[-1]
# 注意实时更新应用 date=None 传入，否则此处无法保证此数据是前天的而不是大前天的，因为没做校验
# 事实上这里计算的预测是针对 date 之前的最晚数据和之前一日的预测
last_value = fund_last["close"]
last_date = fund_last["date"].strftime("%Y-%m-%d")
self.t1_delta = (1 + evaluate_fluctuation(
hdict, yesterday_str, lastday=last_date, _check=True) / 100)
net = last_value * self.t1_delta
self.t1value_cache[datekey] = net
self.t1_type = "已计算"
if not return_date:
return self.t1value_cache[datekey]
else:
return (
self.t1value_cache[datekey],
datekey[:4] + "-" + datekey[4:6] + "-" + datekey[6:8],
)
