def get_holdings_dict(code, aim=95):
"""
通过天天基金的股票持仓数据来生成实时预测所需的持仓字典，不保证稳定性和可靠性以及 API 的连续性，慎用
:param code:
:param aim:
:return:
"""
df = get_fund_holdings(code)
if df.ratio.sum() < 60:
d = dt.datetime.now()
if d.month > 3 and d.month < 8:
year = d.year - 1
season = 4
elif d.month <= 3:
year = d.year - 1
season = 2
else:
year = d.year
season = 2
# season 只选 2，4, 具有更详细的持仓信息
df = get_fund_holdings(code, year, season)
if df is None:
if season == 4:
season = 2
else:
year -= 1
season = 4
df = get_fund_holdings(code, year, season)
df["scode"] = df["code"].apply(ttjjcode)
d = pd.Series(df.ratio.values, index=df.scode).to_dict()
d = scale_dict(d, aim=aim)
return d
def benchmark_test(self, start, end, **kws):
"""
对该净值预测模型回测
:param start: str. 起始日期
:param end: str. 终止日期
:param kws: 可选仓位估计的超参。
:return: pd.DataFrame. real 列为真实涨跌幅，est 列为估计涨跌幅，diff 列为两者之差。
"""
compare_data = {
"date": [],
}
l = kws.get("window", 4)
q = kws.get("decay", 0.8)
c = kws.get("pos", self.position_zero)
s = kws.get("smooth", _smooth_pos)
real_holdings = {self.fcode: 100}
full_holdings = scale_dict(self.t1dict.copy(), aim=100)
compare_data["est"] = []
compare_data["real"] = []
compare_data["estpos3"] = []
compare_data["estpos1"] = []
fq = deque([c / 100] * l, maxlen=l)
current_pos = c / 100
dl = pd.Series(pd.date_range(start=start, end=end))
dl = dl[dl.isin(opendate)]
for j, d in enumerate(dl):
if j == 0:
continue
dstr = d.strftime("%Y%m%d")
lstdstr = dl.iloc[j - 1].strftime("%Y%m%d")
compare_data["date"].append(d)
fullestf = evaluate_fluctuation(full_holdings, dstr, lstdstr)
realf = evaluate_fluctuation(real_holdings, dstr, lstdstr)
estf = fullestf * current_pos
compare_data["est"].append(estf)
compare_data["estpos3"].append(current_pos)
compare_data["estpos1"].append(fq[-1])
compare_data["real"].append(realf)
pos = s(realf, fullestf, fq[-1])
fq.append(pos)
fq[0] = c / 100 ## 模拟实际的无状态仓位分析
if self.positions:
current_pos = sum([q**i * fq[l - i - 1] for i in range(l)
]) / sum([q**i for i in range(l)])
if current_pos > 1:
current_pos = 1
cpdf = pd.DataFrame(compare_data)
cpdf["diff"] = cpdf["est"] - cpdf["real"]
self.cpdf = cpdf
return cpdf
def get_position(self, date=None, refresh=False, return_date=True, **kws):
"""
基于 date 日之前的净值数据，对 date 预估需要的仓位进行计算。
:param date: str. %Y-%m-%d
:param refresh: bool, default False. 若为 True，则刷新缓存，重新计算仓位。
:param return_date: bool, default True. return tuple, the second one is date in the format %Y%m%d
:param kws: 一些预估仓位可能的超参。包括 window，预估所需的时间窗口，decay 加权平均的权重衰减，smooth 每日仓位处理的平滑函数。以上参数均可保持默认即可获得较好效果。
:return: float. 0-100. 100 代表满仓。
"""
if not date:
date = last_onday(self.today).strftime("%Y%m%d")
else:
date = date.replace("/", "").replace("-", "")
if date not in self.position_cache or refresh:
fdict = scale_dict(self.t1dict.copy(), aim=100)
l = kws.get("window", 4)
q = kws.get("decay", 0.8)
s = kws.get("smooth", _smooth_pos)
d = dt.datetime.strptime(date, "%Y%m%d")
posl = [sum([v for _, v in self.t1dict.items()]) / 100]
for _ in range(l):
d = last_onday(d)
for _ in range(l - 1):
d = next_onday(d)
pred = evaluate_fluctuation(
fdict,
d.strftime("%Y-%m-%d"),
lastday=last_onday(d).strftime("%Y-%m-%d"),
)
real = evaluate_fluctuation(
{self.fcode: 100},
d.strftime("%Y-%m-%d"),
lastday=last_onday(d).strftime("%Y-%m-%d"),
)
posl.append(s(real, pred, posl[-1]))
current_pos = sum([q**i * posl[l - i - 1] for i in range(l)
]) / sum([q**i for i in range(l)])
self.position_cache[date] = current_pos
if not return_date:
return self.position_cache[date]
else:
return (
self.position_cache[date],
date[:4] + "-" + date[4:6] + "-" + date[6:8],
)
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],
)
