def calculate():
df_whole = pd.DataFrame()
conn = engine_read.connect()
year = process_date.year
month = process_date.month
month_range = cld.monthrange(year, month)[1]
time_to_fill = sf.Time(dt.datetime(year, month, month_range))
# year, month = time_to_fill.year, time_to_fill.month
# month_range = time_to_fill.month_range
sql_bm = sf.SQL.market_index(time_to_fill.today) # Get benchmark prices
sql_pe = sf.SQL.pe_index(time_to_fill.today, freq="m") ###w->m
bm = pd.read_sql(sql_bm, engine_read)
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].fillna(method="backfill")
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].apply(su.annually2monthly)
bm["statistic_date"] = bm["statistic_date"].apply(su.date2tstp)
pe = pd.read_sql(sql_pe, engine_read)
pe["statistic_date"] = pe["statistic_date"].apply(su.date2tstp)
conn.close()
prices_bm = [
bm["hs300"].tolist(), bm["csi500"].tolist(), bm["sse50"].tolist(),
bm["cbi"].tolist(), bm["nfi"]
]
price_pe = pe["index_value"].tolist()
r_tbond = bm["y1_treasury_rate"].tolist()
t_bm = bm["statistic_date"].tolist()
t_pe = pe["statistic_date"].tolist()
intervals = table.intervals
intervals5 = [1, 2, 3, 4, 5, 6, 10, 11]
intervals6 = [2, 3, 4, 5, 6, 10, 11]
result = []
conn = engine_read.connect()
# Get Data
date_s = sf.Time(process_date -
dt.timedelta(process_date.day)) # Generate statistic_date
sql_fids_updated = sf.SQL.ids_updated_sd(date_s.today, "om")
ids_updated = tuple(
x[0]
for x in conn.execute(sql_fids_updated).fetchall()) # 找到当月净值有更新的基金
sql_o_updated = "SELECT DISTINCT fom.org_id FROM fund_org_mapping fom \
JOIN org_info oi ON fom.org_id = oi.org_id \
WHERE org_type_code = 1 AND oi.found_date <= '{0}' AND fund_id IN {1}".format(
date_s.today - relativedelta(months=3),
ids_updated) # 根据净值更新的基金确定需要计算的投顾
o_updated = tuple(x[0] for x in conn.execute(sql_o_updated).fetchall())
sql_fom = "SELECT fom.org_id, fom.fund_id, oi.found_date, oi.org_name FROM fund_org_mapping fom \
JOIN org_info oi ON fom.org_id = oi.org_id \
JOIN fund_info fi ON fom.fund_id = fi.fund_id \
WHERE fom.org_id IN {0} AND fom.org_type_code = 1 AND oi.found_date <= '{1}' AND fi.foundation_date <= '{2}'".format(
o_updated, date_s.today - relativedelta(months=3),
date_s.today - relativedelta(months=1))
fom = pd.read_sql(sql_fom, conn) # 根据需要计算的投顾找到其旗下管理的所有基金
fid_used = tuple(fom["fund_id"])
sql_fnd = sf.SQL.nav(fid_used)
fnd = pd.read_sql(sql_fnd, conn)
fnd = fnd.dropna()
fnd.index = range(len(fnd))
data = fom.merge(fnd, how="inner", on="fund_id")
data = data.sort_values(by=["org_id", "fund_id", "statistic_date"],
ascending=[True, True, False])
t_mins = data.groupby(["org_id"])["statistic_date"].min().tolist()
t_mins_tstp = [time.mktime(x.timetuple()) for x in t_mins]
data["statistic_date"] = data["statistic_date"].apply(
lambda x: time.mktime(x.timetuple()))
data.index = range(len(data))
ids_o = data["org_id"].drop_duplicates().tolist()
names_o = data.drop_duplicates(subset=["org_id"])["org_name"].tolist()
idx4slice_o = su.idx4slice(data, "org_id")
dfs = [
data[idx4slice_o[i]:idx4slice_o[i + 1]]
if i != len(idx4slice_o) - 1 else data[idx4slice_o[i]:]
for i in range(len(idx4slice_o) - 1)
]
# Proprocess
# 标准序列
t_stds = [
tu.timeseries_std(date_s.today,
interval,
periods_y=12,
use_lastday=True,
extend=1) for interval in intervals
]
t_std_y5 = t_stds[6]
t_stds_len = [len(x) - 1 for x in t_stds]
# 基金标准序列_成立以来
t_std_alls = [
tu.timeseries_std(date_s.today,
tu.periods_in_interval(date_s.today, t_min, 12),
periods_y=12,
use_lastday=True,
extend=6) for t_min in t_mins
] # 标准序列_成立以来
t_std_alls = [
t_std_all[:len([x for x in t_std_all if x >= t_min]) + 1]
for t_std_all, t_min in zip(t_std_alls, t_mins_tstp)
]
# 基准指数的标准序列_成立以来
matchs_bm = [
tu.outer_match4indicator_m(t_bm, t_std_all, False)
for t_std_all in t_std_alls
]
idx_matchs_bm = [x[1] for x in matchs_bm]
price_bm0_all = [[
prices_bm[0][ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_bm]
price_bm1_all = [[
prices_bm[1][ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_bm]
price_bm2_all = [[
prices_bm[2][ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_bm]
price_bm3_all = [[
prices_bm[3][ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_bm]
price_bm4_all = [[
prices_bm[4][ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_bm]
matchs_pe = [
tu.outer_match4indicator_m(t_pe, t_std_all, False)
for t_std_all in t_std_alls
]
idx_matchs_pe = [x[1] for x in matchs_pe]
price_pe_all = [[
price_pe[ix] if ix is not None else None for ix in idx.values()
] for idx in idx_matchs_pe]
# 基准指标的收益率_成立以来
r_bm0_all = [fi.gen_return_series(x) for x in price_bm0_all]
r_bm1_all = [fi.gen_return_series(x) for x in price_bm1_all]
r_bm2_all = [fi.gen_return_series(x) for x in price_bm2_all]
r_bm3_all = [fi.gen_return_series(x) for x in price_bm3_all]
r_bm4_all = [fi.gen_return_series(x) for x in price_bm4_all]
r_pe_all = [fi.gen_return_series(x) for x in price_pe_all]
tmp = [len(idx_matchs_bm[i]) for i in range(len(idx_matchs_bm))]
tmp_id = tmp.index(max(tmp))
tmp_list = [
r_tbond[ix] if ix is not None else None
for ix in idx_matchs_bm[tmp_id].values()
]
tmp = pd.DataFrame(tmp_list)[0].fillna(method="backfill").tolist()
r_f_all = [[
r_tbond[idx[k]] if idx[k] is not None else tmp[k] for k in idx.keys()
] for idx in idx_matchs_bm]
r_f_all = [x[1:] for x in r_f_all]
# 基准指标的收益率_不同频率
matchs_bm = tu.outer_match4indicator_m(t_bm, t_std_y5,
False) # 基准指数标准序列_成立以来
matchs_pe = tu.outer_match4indicator_m(t_pe, t_std_y5, False)
idx_matchs_bm = matchs_bm[1]
idx_matchs_pe = matchs_pe[1]
price_bm0_y5 = [
prices_bm[0][ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
price_bm1_y5 = [
prices_bm[1][ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
price_bm2_y5 = [
prices_bm[2][ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
price_bm3_y5 = [
prices_bm[3][ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
price_bm4_y5 = [
prices_bm[4][ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
price_pe_y5 = [
price_pe[ix] if ix is not None else None
for ix in idx_matchs_pe.values()
]
# 基准指标的收益率_不同频率
r_bm0_y5 = fi.gen_return_series(price_bm0_y5)
r_bm1_y5 = fi.gen_return_series(price_bm1_y5)
r_bm2_y5 = fi.gen_return_series(price_bm2_y5)
r_bm3_y5 = fi.gen_return_series(price_bm3_y5)
r_bm4_y5 = fi.gen_return_series(price_bm4_y5)
r_pe_y5 = fi.gen_return_series(price_pe_y5)
r_f_y5 = [
r_tbond[ix] if ix is not None else None
for ix in idx_matchs_bm.values()
]
r_f_y5 = r_f_y5[1:]
rs_bm0 = [r_bm0_y5[:length - 1] for length in t_stds_len]
rs_bm1 = [r_bm1_y5[:length - 1] for length in t_stds_len]
rs_bm2 = [r_bm2_y5[:length - 1] for length in t_stds_len]
rs_bm3 = [r_bm3_y5[:length - 1] for length in t_stds_len]
rs_bm4 = [r_bm4_y5[:length - 1] for length in t_stds_len]
rs_pe = [r_pe_y5[:length - 1] for length in t_stds_len]
rs_f = [r_f_y5[:length - 1] for length in t_stds_len]
benchmark = {
1: rs_bm0,
2: rs_bm1,
3: rs_bm2,
4: rs_pe,
6: rs_bm3,
7: rs_bm4
}
benchmark_all = {
1: r_bm0_all,
2: r_bm1_all,
3: r_bm2_all,
4: r_pe_all,
6: r_bm3_all,
7: r_bm4_all
}
for i in range(len(ids_o)):
df = dfs[i]
df.index = range(len(df))
idx4slice = su.idx4slice(df, "fund_id")
navs = su.slice(df, idx4slice, "nav")
t_reals = su.slice(df, idx4slice, "statistic_date")
matchs_all = [
tu.outer_match4indicator_m(t_real, t_std_alls[i], drop_none=False)
for t_real in t_reals
]
idx_matchs_all = [x[1] for x in matchs_all]
nav_matchs_all = [[
nav[ix] if ix is not None else np.NaN for ix in idx.values()
] for nav, idx in zip(navs, idx_matchs_all)]
nv_matrix = np.array(nav_matchs_all).T
r_total = np.nanmean((nv_matrix[:-1] / nv_matrix[1:] - 1), axis=1)
price_total = np.nancumprod(1 + r_total[::-1])[::-1].tolist()
price_total.append(1) # 定义基期伪价格为1
r_total = fi.gen_return_series(price_total)
prices = []
for j in range(7):
if t_mins[i] + relativedelta(months=intervals[j]) <= date_s.today:
length = min(len(price_total), t_stds_len[j])
prices.append(price_total[:length])
else:
prices.append(None)
for j in range(7, 11):
length = min(len(price_total), t_stds_len[j])
prices.append(price_total[:length])
prices.append(price_total)
navs2 = [prices[i] for i in intervals5]
navs3 = [prices[i] for i in intervals6]
rs2 = [fi.gen_return_series(x) for x in navs2]
rs3 = [fi.gen_return_series(x) for x in navs3]
rs_f_ = rs_f.copy()
rs_f_.append(r_f_all[i])
rs_f2_ = [rs_f_[i] for i in intervals5]
rs_f3_ = [rs_f_[i] for i in intervals6]
for k in benchmark.keys():
rs_bm_ = benchmark[k].copy() # 指定benchmark
rs_bm_.append(benchmark_all[k][i])
rs_bm2 = [rs_bm_[i] for i in intervals5]
rs_bm3 = [rs_bm_[i] for i in intervals6]
s_time = [
fi.competency_timing(r, r_bm, r_f)
for r, r_bm, r_f in zip(rs3, rs_bm3, rs_f3_)
]
s_security = [
fi.competency_stock(r, r_bm, r_f)
for r, r_bm, r_f in zip(rs3, rs_bm3, rs_f3_)
]
persistence = [
fi.persistence_er(r, r_bm) for r, r_bm in zip(rs2, rs_bm2)
]
odds = [fi.odds(r, r_bm) for r, r_bm in zip(rs2, rs_bm2)]
tmp = [odds, persistence, s_time, s_security]
result_i = [
ids_o[i], names_o[i], k, 1, 1, nv_matrix.shape[1], 60001,
"全产品", 6000101, "全产品", date_s.today
]
for x in tmp:
result_i.extend(x)
result.append(result_i)
df = pd.DataFrame(result)
df[list(range(11, 41))] = df[list(range(11, 41))].astype(np.float64)
df[list(range(11, 41))] = df[list(range(11,
41))].apply(lambda x: round(x, 6))
df.columns = columns
df_whole = df_whole.append(df)
return df_whole
engines = cfg.load_engine()
engine_rd = engines["2Gb"]
engine_wt = engines["2Gb"]
df_whole = pd.DataFrame()
for year in range(2017, 2018):
for month in range(2, 3):
conn = engine_rd.connect()
now = dt.datetime.now()
year, month = year, month
month_range = cld.monthrange(year, month)[1]
time_to_fill = sf.Time(dt.datetime(year, month, month_range))
year, month = time_to_fill.year, time_to_fill.month
month_range = time_to_fill.month_range
sql_bm = sf.SQL.market_index(time_to_fill.today) # Get benchmark prices
sql_pe = sf.SQL.pe_index(time_to_fill.today, freq="m") ###w->m
bm = pd.read_sql(sql_bm, engine_rd)
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].fillna(method="backfill")
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].apply(su.annually2monthly)
bm["statistic_date"] = bm["statistic_date"].apply(su.date2tstp)
pe = pd.read_sql(sql_pe, engine_rd)
pe["statistic_date"] = pe["statistic_date"].apply(su.date2tstp)
conn.close()
prices_bm = [bm["hs300"].tolist(), bm["csi500"].tolist(), bm["sse50"].tolist(), bm["cbi"].tolist(), bm["nfi"]]
def calculate():
conn = engine_rd.connect()
year, month = yesterday.year, yesterday.month
month_range = cld.monthrange(year, month)[1]
time_to_fill = sf.Time(dt.datetime(year, month, month_range))
year, month = time_to_fill.year, time_to_fill.month
bms_used = [
"hs300", "csi500", "sse50", "ssia", "cbi", "y1_treasury_rate", "nfi"
]
sql_bm = sf.SQL.market_index(date=time_to_fill.today,
benchmarks=bms_used,
whole=True) # Get benchmark prices
bm = pd.read_sql(sql_bm, conn)
# bm.loc[bm["statistic_date"] == dt.date(1995, 8, 16), "y1_treasury_rate"] = 2.35
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].fillna(method="backfill")
bm["y1_treasury_rate"] = bm["y1_treasury_rate"].apply(su.annually2weekly)
bm["statistic_date"] = bm["statistic_date"].apply(su.date2tstp)
prices_bm = [
bm.dropna(subset=[bm_name])[bm_name].tolist() for bm_name in bms_used
]
ts_bm = [
bm.dropna(subset=[bm_name])["statistic_date"].tolist()
for bm_name in bms_used
]
prices = prices_bm.copy()
ts = ts_bm.copy()
t_mins_pe_all = sf.PEIndex().firstmonday # 寻找指数中可被计算的
pesid_used = []
for k in t_mins_pe_all:
if t_mins_pe_all[k].year < year:
pesid_used.append(k)
elif t_mins_pe_all[k].year == year:
if t_mins_pe_all[k].month <= month:
pesid_used.append(k)
else:
continue
else:
continue
prices_pe = []
ts_pe = []
pes_used = []
for idx in pesid_used:
PE = sf.PEIndex(idx)
pes_used.append(PE.id)
sql_pe = sf.SQL.pe_index(time_to_fill.today, index_id=PE.id, freq="w")
pe = pd.read_sql(sql_pe, conn)
pe["statistic_date"] = pe["statistic_date"].apply(su.date2tstp)
prices_pe.append(pe["index_value"].tolist())
ts_pe.append(pe["statistic_date"].tolist())
conn.close()
prices.extend(prices_pe)
ts.extend(ts_pe)
t_mins_tstp = [min(x) for x in ts]
t_mins = tu.tr(t_mins_tstp)
intervals = table.intervals
intervals1 = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
intervals3 = [0, 1, 2, 3, 4, 5, 6, 10, 11]
index_used = bms_used.copy()
index_used.extend(pes_used)
index_name = {
"FI01": "私募全市场指数",
"FI02": "阳光私募指数",
"FI03": "私募FOF指数",
"FI04": "股票多头策略私募指数",
"FI05": "股票多空策略私募指数",
"FI06": "市场中性策略私募指数",
"FI07": "债券基金私募指数",
"FI08": "管理期货策略私募指数",
"FI09": "宏观策略私募指数",
"FI10": "事件驱动策略私募指数",
"FI11": "相对价值策略私募指数",
"FI12": "多策略私募指数",
"FI13": "组合投资策略私募指数",
"hs300": "沪深300指数",
"csi500": "中证500指数",
"sse50": "上证50指数",
"ssia": "上证A股指数",
"cbi": "中债指数",
"nfi": "南华商品指数",
"y1_treasury_rate": "y1_treasury_rate"
}
result = []
for mday in range(1, yesterday.day + 1):
print("Day {0}: {1}".format(mday, dt.datetime.now()))
date_s = sf.Time(dt.datetime(year, month,
mday)) # Generate statistic_date
#
t_stds = [
tu.timeseries_std(date_s.today, interval, 52, extend=1)
for interval in intervals
] # 标准序列
t_std_lens = [len(x) - 1 for x in t_stds] # 标准序列净值样本个数
t_std_week = tu.timeseries_std(date_s.today, "w", 52, 1) # 标准序列_本周
ts_std_total = [
tu.timeseries_std(date_s.today,
tu.periods_in_interval(date_s.today, t_min, 12),
extend=4) for t_min in t_mins
] # 标准序列_成立以来
ts_std_total = [
t_std_total[:len([x for x in t_std_total if x >= t_min]) + 1]
for t_std_total, t_min in zip(ts_std_total, t_mins_tstp)
]
# 基准指数的标准序列_成立以来
matchs = [
tu.outer_match4indicator_w(t, t_std_all, False)
for t, t_std_all in zip(ts, ts_std_total)
]
idx_matchs = [x[1] for x in matchs]
prices_total = [[
price[ix] if ix is not None else None for ix in idx.values()
] for price, idx in zip(prices, idx_matchs)]
# 基准指标的收益率_不同频率
rs_total = [
fi.gen_return_series(price_total) for price_total in prices_total
]
# 无风险国债的收益率
r_f_total = prices_total[5][
1:] # the list `y1_treasury_rate` in prices_total is not price, but return
r_f_total = pd.DataFrame(r_f_total).fillna(
method="backfill")[0].tolist()
r_f_all = [r_f_total[:length - 1] for length in t_std_lens]
r_f_all.append(r_f_total)
# for i in range(len(index_used)):
for i in range(len(index_used)):
if index_name[index_used[i]] == "y1_treasury_rate": continue
price_all = []
r_all = []
for j in range(7):
if dt.date.fromtimestamp(
(t_mins[i] + relativedelta(months=intervals[j])
).timestamp()) <= date_s.today:
price_all.append(prices_total[i][:t_std_lens[j]])
r_all.append(rs_total[i][:t_std_lens[j] - 1])
else:
price_all.append([])
r_all.append([])
for j in range(7, 11):
price_all.append(prices_total[i][:t_std_lens[j]])
if rs_total[i] is not None:
r_all.append(rs_total[i][:t_std_lens[j] - 1])
else:
r_all.append([])
price_all.append(prices_total[i])
r_all.append(rs_total[i])
price_all1 = [price_all[i] for i in intervals1]
price_all3 = [price_all[i] for i in intervals3]
r_all1 = [r_all[i] for i in intervals1]
r_all3 = [r_all[i] for i in intervals3]
r_f_all1 = [r_f_all[i] for i in intervals1][:-1]
r_f_all3 = [r_f_all[i] for i in intervals3][:-1]
r_f_all1.append(r_f_all[-1][:len(r_all[-1])])
r_f_all3.append(r_f_all[-1][:len(r_all[-1])])
ir = [fi.accumulative_return(price) for price in price_all1]
ir_a = [fi.return_a(r) for r in r_all1]
stdev_a = [fi.standard_deviation_a(r) for r in r_all3]
dd_a = [
fi.downside_deviation_a(r, r_f)
for r, r_f in zip(r_all3, r_f_all3)
]
mdd = [fi.max_drawdown(price)[0] for price in price_all3]
sharpe_a = [
fi.sharpe_a(r, r_f) for r, r_f in zip(r_all3, r_f_all3)
]
calmar_a = [
fi.calmar_a(price, r_f)
for price, r_f in zip(price_all3, r_f_all3)
]
sortino_a = [
fi.sortino_a(r, r_f) for r, r_f in zip(r_all3, r_f_all3)
]
p_earning_weeks = [fi.periods_positive_return(r) for r in r_all3]
n_earning_weeks = [fi.periods_npositive_return(r) for r in r_all3]
con_rise_weeks = [fi.periods_continuous_rise(r)[0] for r in r_all3]
con_fall_weeks = [fi.periods_continuous_fall(r)[0] for r in r_all3]
tmp = [
ir, ir_a, stdev_a, dd_a, mdd, sharpe_a, calmar_a, sortino_a,
p_earning_weeks, n_earning_weeks, con_rise_weeks,
con_fall_weeks
]
result_i = [index_used[i], index_name[index_used[i]], date_s.today]
for x in tmp:
result_i.extend(x)
result.append(result_i)
df = pd.DataFrame(result)
df[list(range(3, 117))] = df[list(range(3, 117))].astype(np.float64)
df[list(range(3, 117))] = df[list(range(3,
117))].apply(lambda x: round(x, 6))
df.columns = columns
df.index_id = df.index_id.apply(lambda x: x.upper())
return df