def _get_hour_starts(dt_ranges: Sequence[DateTimeRange]) -> Iterator[datetime]:
min_starts_at = _find_earliest_start(dt_ranges)
max_ends_at = _find_latest_end(dt_ranges)
hour_starts_arrow = Arrow.range('hour', min_starts_at, max_ends_at)
return _to_datetimes_without_tzinfo(hour_starts_arrow)
def view(party_id):
"""List orga presence and task time slots for that party."""
party = Party.query.get_or_404(party_id)
presences = Presence.query \
.for_party(party) \
.options(db.joinedload('orga')) \
.all()
tasks = Task.query.for_party(party).all()
time_slots = [party] + tasks
min_starts_at = find_earliest_time_slot_start(time_slots)
max_ends_at = find_latest_time_slot_end(time_slots)
hour_starts_arrow = Arrow.range('hour', min_starts_at, max_ends_at)
hour_starts = [hour_start.datetime.replace(tzinfo=None)
for hour_start in hour_starts_arrow]
hour_ranges = list(map(DateTimeRange._make, pairwise(hour_starts)))
days = [(day, len(list(hour_starts))) for day, hour_starts
in groupby(hour_starts, key=lambda hour: hour.date())]
return {
'party': party,
'days': days,
'hour_ranges': hour_ranges,
'presences': presences,
'tasks': tasks,
}
def _get_hour_starts(dt_ranges):
min_starts_at = _find_earliest_start(dt_ranges)
max_ends_at = _find_latest_end(dt_ranges)
hour_starts_arrow = Arrow.range('hour', min_starts_at, max_ends_at)
return _to_datetimes_without_tzinfo(hour_starts_arrow)
def create_array_with_zeroes(data_frame: DataFrame, beg: Arrow, end: Arrow) -> List[float]:
arr = []
for day in Arrow.range('day', beg, end):
try:
value = data_frame.loc[day.date()].values[0]
except KeyError:
value = 0.0
arr.append(value)
return arr
def run(self, task_define):
Arrow.now().date()
start_dt = arrow.get(task_define['last_crawl_day']) # .strftime('%Y%m%d')
end_dt = arrow.get(task_define['cur_dt'])
for r_dt in Arrow.range('day', start_dt, end_dt):
logger.info('Start to crawl data of task: %s, dt: %s' % (self.__class__.__name__, r_dt))
t_dt = r_dt.strftime('%Y%m%d')
daily_records = self.ts_client.query(API_NAME, trade_date=t_dt)
self.write_db_with_df('stock_daily_basic', daily_records)
def get_mean_forecast(data_frame: DataFrame, now: Arrow,
for_date: Arrow) -> Series:
tomorrow = now.shift(days=1)
beg = now.shift(days=-6)
arr = []
for day in Arrow.range('day', beg, now):
try:
value = data_frame.loc[day.date()].values[0]
except KeyError:
value = 0.0
arr.append([day.date(), value])
init_df = create_df_indexed_by_date(create_df(arr))
df = create_df_with_zeroes(init_df, beg, for_date)
for day in Arrow.range('day', tomorrow, for_date):
yesterday = day.shift(days=-1)
past_week = df[yesterday.shift(days=-6).date():yesterday.date()]
df.loc[day.date()] = past_week.mean()
return df['quantity'][tomorrow.date():for_date.date()]
def timeloop(start=datetime.now() + timedelta(days=-1),
end=datetime.now() + timedelta(days=0)):
"生成一个字符串格式为YYYY-MM-DD形式的数组."
if (type(start) is str) or (type(end) is str):
start = start if type(
start) is datetime else datetime.strptime(start, '%Y-%m-%d')
end = datetime.now()
# TODO:检查时间是否为字符串，如果是则转换为时间。
rond = []
for r_time in Arrow.range('day', start, end):
rond.append(r_time.format('YYYY-MM-DD'))
return rond
def create_df_with_zeroes(data_frame: DataFrame,
beg: Arrow,
end: Arrow,
date_selector: Union[Callable, None] = None
) -> DataFrame:
arr = []
for day in Arrow.range('day', beg, end):
dt = date_selector(day) if date_selector else day
try:
value = data_frame.loc[dt.date()].values[0]
except KeyError:
value = 0.0
arr.append([day.date(), value])
return create_df_indexed_by_date(create_df(arr))
def export_hourly2day(self, target_day: arrow.Arrow):
"""
将一天拆成小时查询并合并
:param vins: 需要查询的vin
:param target_day: 需要查询的精确到天的时间
:return: 查询的vin的目标日的数据
"""
day_hours = list(
target_day.range('hour', target_day, target_day.shift(days=1)))
target_time_bucket = []
for i in range(len(day_hours) - 1):
target_time_bucket.append((day_hours[i], day_hours[i + 1]))
# 查询数据
df = pandas.DataFrame()
for t_t, d_t in target_time_bucket:
dd, err_list = self.export(t_t, d_t)
df = df.append(dd)
if len(err_list) > 0:
self.record_err(t_t.format('YYY-MM-DD_HH'))
return df
def export_daily2month(self, vins: list, target_month: arrow.Arrow):
"""
将目标vin号的一个月拆分为单天查询后组合返回
:param vins: 需要查询的vin
:param target_month: 需要查询的精确到月的时间
:return: 查询的vin的目标月的数据
"""
# 拼装一个月的单日时间范围
month_days = list(
target_month.range('day', target_month,
target_month.shift(months=1)))
target_time_bucket = []
for i in range(len(month_days) - 1):
target_time_bucket.append((month_days[i], month_days[i + 1]))
# 查询数据
df = pandas.DataFrame()
for t_t, d_t in target_time_bucket:
dd, err_list = self.export(vins, [(t_t, d_t)])
df = df.append(dd)
if len(err_list) > 0:
df = df.append(self.export_hourly2day(err_list, t_t))
return df
def modify_df(beg: Arrow, end: Arrow, modifier: Callable):
arr = []
for day in Arrow.range('day', beg, end):
arr.append([day.date(), modifier(day)])
return create_df_indexed_by_date(create_df(arr))
def _calendar_tasks(tdb: TaskDB, date: Arrow, period) -> List[Tuple[Arrow, TaskDB]]:
start, end = _calendar_range(date, period)
tasks = [] # type: List[Tuple[Arrow, TaskDB]]
for date in Arrow.range("day", start, end):
tasks.append((date, tdb.filter(lambda t: filters.due_on(t, date))))
return tasks
