def calculate(time_s, time_e):
try:
tasks = pre.generate_tasks(time_s, time_e, freq="w", processes=7, conn=engine_rd)
tasks = {k: v for k, v in tasks.items() if k >= dt.date(2015, 1, 1)}
print(time_e, len(tasks))
except ValueError as e:
print(time_e, e)
for statistic_date, ids_used in sorted(tasks.items(), key=lambda x: x[0]):
print("UPDATE TIME:{ut}: STATISTIC DATE:{sd}, LENGTH:{l}".format(ut=time_e, sd=statistic_date, l=len(ids_used)))
result_return = []
result_risk = []
result_sub = []
data = pre.ProcessedData(statistic_date, list(ids_used), _freq)
bms = {index_name: cal.Benchmark(attr_dict, index_name) for index_name, attr_dict in data.index.items()}
tbond = cal.Tbond(data.index["y1_treasury_rate"], "y1_treasury_rate")
for fid, attrs in data.funds.items():
fund = cal.Fund(attrs)
res_return, cols_return_sorted = cal.calculate(_funcs_return, _intervals, _bms_used, _freq, statistic_date, fund, bms, tbond, with_func_names=True)
res_risk, cols_risk_sorted = cal.calculate(_funcs_risk, _intervals, _bms_used, _freq, statistic_date, fund, bms, tbond, with_func_names=True)
res_sub, cols_sub_sorted = cal.calculate(_funcs_sub, _intervals, _bms_used, _freq, statistic_date, fund, bms, tbond, with_func_names=True)
result_return.extend(res_return)
result_risk.extend(res_risk)
result_sub.extend(res_sub)
df_return = pd.DataFrame(result_return)
df_risk = pd.DataFrame(result_risk)
df_sub = pd.DataFrame(result_sub)
cols_return = cal.format_cols(
cols_return_sorted, _freq, prefix=["fund_id", "fund_name", "statistic_date", "benchmark"]
)
cols_risk = cal.format_cols(
cols_risk_sorted, _freq, prefix=["fund_id", "fund_name", "statistic_date", "benchmark"]
)
cols_sub = cal.format_cols(
cols_sub_sorted, _freq, prefix=["fund_id", "fund_name", "statistic_date", "benchmark"]
)
df_return.columns = cols_return
df_risk.columns = cols_risk
df_sub.columns = cols_sub
try:
io.to_sql("fund_weekly_return", conn=engine_rd, dataframe=df_return, chunksize=5000)
io.to_sql("fund_weekly_risk", conn=engine_rd, dataframe=df_risk, chunksize=5000)
io.to_sql("fund_subsidiary_weekly_index", conn=engine_rd, dataframe=df_sub, chunksize=5000)
except Exception as e:
time.sleep(10)
io.to_sql("fund_weekly_return", conn=engine_rd, dataframe=df_return, chunksize=5000)
io.to_sql("fund_weekly_risk", conn=engine_rd, dataframe=df_risk, chunksize=5000)
io.to_sql("fund_subsidiary_weekly_index", conn=engine_rd, dataframe=df_sub, chunksize=5000)
print("TASK DONE: {ut}".format(ut=time_e))
def generate_tasks(update_time_l, update_time_r):
try:
tasks = pre.generate_tasks(update_time_l,
update_time_r,
freq="w",
processes=7,
conn=engine_rd)
tasks = {k: v for k, v in tasks.items() if k >= dt.date(2015, 1, 1)}
print("{l}->{r}".format(l=update_time_l, r=update_time_r), len(tasks))
except ValueError as e:
print("{l}->{r}".format(l=update_time_l, r=update_time_r), e)
return tasks
"ability_security",
"tracking_error_a",
"p_earning_periods",
"n_earning_periods",
"min_return",
"max_return",
"skewness",
"kurtosis",
]
_bms_used = ["hs300", "csi500", "sse50", "cbi", "nfi"]
for update_time in [UPDATE_TIME]:
try:
tasks = pre.generate_tasks(update_time -
relativedelta(hours=35, minutes=5),
update_time,
freq=_freq,
processes=7,
conn=engine_rd)
tasks = {k: v for k, v in tasks.items() if k >= dt.date(2015, 1, 1)}
print(update_time, len(tasks))
except ValueError as e:
print(update_time, e)
continue
for statistic_date, ids_used in sorted(tasks.items(), key=lambda x: x[0]):
if statistic_date != dt.date(2017, 9, 21): continue
print("UPDATE TIME:{ut}: STATISTIC DATE:{sd}, LENGTH:{l}".format(
ut=update_time, sd=statistic_date, l=len(ids_used)))
result_return = []
result_risk = []
result_sub = []
prefix=["fund_id", "fund_name", "statistic_date", "benchmark"])
cols_risk = cal.format_cols(
_funcs_risk,
_freq,
prefix=["fund_id", "fund_name", "statistic_date", "benchmark"])
cols_sub = cal.format_cols(
_funcs_sub,
_freq,
prefix=["fund_id", "fund_name", "statistic_date", "benchmark"])
_bms_used = ["hs300", "csi500", "sse50", "cbi", "strategy", "FI01", "nfi"]
try:
tasks = pre.generate_tasks(last_month - dt.timedelta(last_month.day - 1),
last_month + dt.timedelta(0, 86399),
freq=_freq,
processes=7,
conn=engine_rd)
tasks = {
k: v
for k, v in tasks.items()
if (k >= dt.date(2015, 1, 1)
and k < dt.date(UPDATE_TIME.year, UPDATE_TIME.month, 1))
}
print(UPDATE_TIME, len(tasks))
except ValueError as e:
print(UPDATE_TIME, e)
for statistic_date, ids_used in sorted(tasks.items(), key=lambda x: x[0]):
print("UPDATE TIME:{ut}: STATISTIC DATE:{sd}, LENGTH:{l}".format(
ut=UPDATE_TIME, sd=statistic_date, l=len(ids_used)))
