def slice_data(dataframe, slice_by, cols_used):
"""
Args:
dataframe:
slice_by:
cols_used:
Returns:
list<pandas.DataFrame>
"""
if dataframe is not None:
df_tmp = dataframe.copy()
bys = df_tmp[slice_by].drop_duplicates().tolist()
df_tmp.index = df_tmp[slice_by]
result = {}
idx4slice = su.idx4slice(dataframe, slice_by)
for col in cols_used:
tmp = su.slice(df_tmp, idx4slice, col)
result[col] = {by: value for by, value in zip(bys, tmp)}
result = _reverse_dict(result)
else:
result = None
return result
def is_daily(ids_to_update):
sql_fnds = "SELECT fund_id, statistic_date FROM fund_nv_data_standard WHERE statistic_date >= '19700101' \
AND fund_id IN {ids}".format(ids=sf.SQL.ids4sql(ids_to_update))
su.tic("Fetching get_data......")
fnds = pd.read_sql(sql_fnds, engine_rd)
fnds = fnds.dropna().sort_values(by=["fund_id", "statistic_date"],
ascending=[True, False])
fnds.index = range(len(fnds))
fnds["statistic_date"] = fnds["statistic_date"].apply(
lambda x: time.mktime(x.timetuple()))
su.tic("Calculating......")
ids4slice = su.idx4slice(fnds, slice_by="fund_id")
ids = fnds.drop_duplicates(subset=["fund_id"])["fund_id"].tolist()
t_reals = su.slice(fnds, ids4slice, "statistic_date")
match_ratio = [
(len(t_real) - 1) /
((t_real[0] - t_real[-1]) / 86400) if len(t_real) > 1 else None
for t_real in t_reals
]
matched = [
"日度" if (x is not None and x >= 0.5) else None for x in match_ratio
]
result = dict([x for x in list(zip(ids, matched)) if x[1] is not None])
return result
def is_monthly(ids_to_update):
su.tic("Fetching get_data......")
sql_std_m = "SELECT fund_id, statistic_date_std, statistic_date FROM fund_nv_standard_m \
WHERE fund_id IN {ids} \
AND fund_id IN (SELECT fund_id FROM (SELECT fund_id, COUNT(fund_id) cnt FROM fund_nv_standard_m \
GROUP BY fund_id HAVING cnt >= 3) T)".format(
ids=sf.SQL.ids4sql(ids_to_update))
d_std_m = pd.read_sql(sql_std_m, engine_rd)
ids4slice = su.idx4slice(d_std_m, slice_by="fund_id")
ids = d_std_m.drop_duplicates(subset=["fund_id"])["fund_id"].tolist()
t_reals = su.slice(d_std_m, ids4slice, "statistic_date")
t_stds = su.slice(d_std_m, ids4slice, "statistic_date_std")
match_ratio = [
len([x for x in t_real if x is not None]) / len(t_std)
for t_real, t_std in zip(t_reals, t_stds)
]
matched = [
"月度" if (x is not None and x >= 0.5) else None for x in match_ratio
]
result = dict([x for x in list(zip(ids, matched)) if x[1] is not None])
return result
ids_diff = list(set(ids_used) - set(ids_fdate))
sql_fnvdate = sf.SQL.firstnv_date(ids_diff)
fnvdate = pd.read_sql(sql_fnvdate, engine_rd)
ids_diff = fnvdate["fund_id"].tolist()
t_min = pd.merge(fdate, fnvdate, "outer")
print("Some foundation_date missed, use first nv date...", len(ids_diff), len(ids_fdate), len(t_min))
t_min = t_min.sort_values("fund_id", ascending=True) # Sort the df by fund id ASC
sql_nav = sf.SQL.nav(ids_used) # Get their navs
d = pd.read_sql(sf.SQL.nav(ids_used), engine_rd)
tic("Preproessing")
d["statistic_date"] = d["statistic_date"].apply(su.date2tstp)
tic("Grouping")
idx4slice = su.idx4slice(d, slice_by="fund_id") # Grouping the datas By fund_id
navs = su.slice(d, idx4slice, "nav")
t_reals = su.slice(d, idx4slice, "statistic_date")
t_mins = t_min["t_min"].tolist()
t_mins_tstp = [su.date2tstp(x) for x in t_mins]
print("length of Data: {0}".format(len(d)))
conn.close()
#
t_stds = [tu.timeseries_std(date_s.today, interval, periods_y=12, use_lastday=True, extend=1) for interval
in intervals] # 标准序列 ###w->m
t_std_y5 = t_stds[6]
t_stds_len = [len(x) - 1 for x in t_stds] # 标准序列净值样本个数
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
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
tmins = dict(
zip(d_fund_foundationdate["fund_id"],
d_fund_foundationdate["foundation_date"]))
for fid, fnvdate in zip(d_fund_firstnvdate["fund_id"],
d_fund_firstnvdate["first_nv_date"]):
tmins[fid] = fnvdate
d_fund_nv = pd.read_sql(sql_fund_nv, conn)
d_fund_nv = d_fund_nv.dropna()
d_fund_nv = d_fund_nv.drop(
d_fund_nv.loc[d_fund_nv["statistic_date"] < dt.date(1970, 1, 2)].index)
d_fund_nv["statistic_date"] = d_fund_nv["statistic_date"].apply(su.date2tstp)
d_fund_nv.index = range(len(d_fund_nv))
idxs = su.idx4slice(d_fund_nv, "fund_id")
navs = su.slice(d_fund_nv, idxs, "nav")
ts = su.slice(d_fund_nv, idxs, "statistic_date")
ids = d_fund_nv["fund_id"].drop_duplicates().tolist()
t_std_totals = []
for id_ in ids:
try:
t_std_total = tu.timeseries_std(date_s,
tu.periods_in_interval(
date_s, tmins[id_], 12),
periods_y=12,
extend=1,
use_last_day=True)
t_std_totals.append(t_std_total[:-1])
except Exception as e:
def cal_std(fund_ids=None, whole=False):
"""
每次计算一个基金
Args:
fund_ids: str
whole:
Returns:
"""
if whole is True:
sql_navs = "SELECT fund_id, nav, added_nav, swanav, statistic_date FROM fund_nv_data_standard"
else:
sql_navs = "SELECT fund_id, nav, added_nav, swanav, statistic_date FROM fund_nv_data_standard \
WHERE update_time >= {ut}".format(ut=yesterday)
if fund_ids:
if 'WHERE' in sql_navs:
sql_navs += " AND fund_id in ({})".format(fund_ids)
else:
sql_navs += " WHERE fund_id in ({})".format(fund_ids)
su.tic("Fetching nv Data......")
df_nav = pd.read_sql(sql_navs, conn)
criterias = [(df_nav["nav"] >= 0.2), (df_nav["added_nav"] >= 0.2),
(df_nav["statistic_date"] >= dt.date(1970, 1, 2)),
(df_nav["statistic_date"] <= dt.date.today())]
su.tic("Preprocessing......")
criteria = get_creterias(criterias)
df_nav = df_nav.loc[criteria].sort_values(["fund_id", "statistic_date"],
ascending=[True, False])
df_nav.index = range(len(df_nav))
ids = df_nav["fund_id"].drop_duplicates().tolist()
t_mins = list(df_nav.groupby("fund_id")["statistic_date"].min())
t_mins_tstp = [time.mktime(x.timetuple()) for x in t_mins]
t_maxs = list(df_nav.groupby("fund_id")["statistic_date"].max())
t_maxs_tstp = [time.mktime(x.timetuple()) for x in t_maxs]
idx4slice = su.idx4slice(df_nav, slice_by="fund_id")
navs = su.slice(df_nav, idx4slice, "nav")
added_navs = su.slice(df_nav, idx4slice, "added_nav")
swanavs = su.slice(df_nav, idx4slice, "swanav")
t_reals = su.slice(df_nav, idx4slice, "statistic_date")
t_reals_tstp = []
for t_real in t_reals:
t_reals_tstp.append([time.mktime(x.timetuple()) for x in t_real])
t_std_alls_w = [
tu.timeseries_std(friday,
tu.periods_in_interval(friday, t_min, 12),
extend=4) for t_min in t_mins
] # 标准序列_成立以来
t_std_alls_w = [
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_w, t_mins_tstp)
]
t_std_alls_w = [
t_std_all[-len([x for x in t_std_all if x < t_max]) - 1:]
for t_std_all, t_max in zip(t_std_alls_w, t_maxs_tstp)
]
t_std_alls_m = [
tu.timeseries_std(date,
tu.periods_in_interval(date, t_min, 12),
periods_y=12,
use_lastday=True,
extend=6) for date, t_min in zip(t_maxs, t_mins)
] # 标准序列_成立以来
t_std_alls_m = [
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_m, t_mins_tstp)
]
su.tic("Matching......")
matchs_w = [
tu.outer_match4indicator_w(t_real, t_std)
for t_real, t_std in zip(t_reals_tstp, t_std_alls_w)
]
idx_matchs_w = [x[1] for x in matchs_w]
nav_matchs_w = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(navs, idx_matchs_w)]
anav_matchs_w = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(added_navs, idx_matchs_w)]
swanav_matchs_w = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(swanavs, idx_matchs_w)]
t_matchs_w = [[
t_real[ix] if ix is not None else None for ix in idx.values()
] for t_real, idx in zip(t_reals, idx_matchs_w)]
t_matchs_std_w = [
tu.tr(x[:-1], "date") if x is not None else None for x in t_std_alls_w
]
matchs_m = [
tu.outer_match4indicator_m(t_real, t_std)
for t_real, t_std in zip(t_reals_tstp, t_std_alls_m)
]
idx_matchs_m = [x[1] for x in matchs_m]
nav_matchs_m = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(navs, idx_matchs_m)]
anav_matchs_m = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(added_navs, idx_matchs_m)]
swanav_matchs_m = [[
nav[ix] if ix is not None else None for ix in idx.values()
] for nav, idx in zip(swanavs, idx_matchs_m)]
t_matchs_m = [[
t_real[ix] if ix is not None else None for ix in idx.values()
] for t_real, idx in zip(t_reals, idx_matchs_m)]
t_matchs_std_m = [
tu.tr(x[:-1], "date") if x is not None else None for x in t_std_alls_m
]
result_w = {
"fund_id": ids,
"nav": nav_matchs_w,
"added_nav": anav_matchs_w,
"swanav": swanav_matchs_w,
"statistic_date": t_matchs_w,
"statistic_date_std": t_matchs_std_w
}
result_m = {
"fund_id": ids,
"nav": nav_matchs_m,
"added_nav": anav_matchs_m,
"swanav": swanav_matchs_m,
"statistic_date": t_matchs_m,
"statistic_date_std": t_matchs_std_m
}
su.tic("Merging Result......")
result = {}
result["w"] = pd.DataFrame.from_dict(merge_result(result_w, ids))
result["m"] = pd.DataFrame.from_dict(merge_result(result_m, ids))
return result
