zhangyiss/python-by-example-150-challenges
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

8th day of python challenges 111-117

Browse Source
This commit is contained in:
abd.shallal
2019-08-04 15:26:35 +03:00
parent b04c1b055f
commit 627802c383
3215 changed files with 760227 additions and 491 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
venv/lib/python3.6/site-packages/pandas/tseries/__init__.py Normal file
View File

8
venv/lib/python3.6/site-packages/pandas/tseries/api.py Normal file
View File

@@ -0,0 +1,8 @@
"""
Timeseries API
"""
# flake8: noqa
from pandas.tseries.frequencies import infer_freq
import pandas.tseries.offsets as offsets

32
venv/lib/python3.6/site-packages/pandas/tseries/converter.py Normal file
View File

@@ -0,0 +1,32 @@
# flake8: noqa
import warnings
# TODO `_matplotlib` module should be private, so the plotting backend
# can be change. Decide whether all these should be public and exponsed
# in `pandas.plotting`, or remove from here (I guess they are here for
# legacy reasons
from pandas.plotting._matplotlib.converter import (
DatetimeConverter,
MilliSecondLocator,
PandasAutoDateFormatter,
PandasAutoDateLocator,
PeriodConverter,
TimeConverter,
TimeFormatter,
TimeSeries_DateFormatter,
TimeSeries_DateLocator,
get_datevalue,
get_finder,
time2num,
)
def register():
from pandas.plotting import register_matplotlib_converters
msg = (
"'pandas.tseries.converter.register' has been moved and renamed to "
"'pandas.plotting.register_matplotlib_converters'. "
)
warnings.warn(msg, FutureWarning, stacklevel=2)
register_matplotlib_converters()

514
venv/lib/python3.6/site-packages/pandas/tseries/frequencies.py Normal file
View File

@@ -0,0 +1,514 @@
from datetime import timedelta
import re
from typing import Dict
import numpy as np
from pytz import AmbiguousTimeError
from pandas._libs.algos import unique_deltas
from pandas._libs.tslibs import Timedelta, Timestamp
from pandas._libs.tslibs.ccalendar import MONTH_ALIASES, int_to_weekday
from pandas._libs.tslibs.fields import build_field_sarray
import pandas._libs.tslibs.frequencies as libfreqs
from pandas._libs.tslibs.offsets import _offset_to_period_map
import pandas._libs.tslibs.resolution as libresolution
from pandas._libs.tslibs.resolution import Resolution
from pandas._libs.tslibs.timezones import UTC
from pandas._libs.tslibs.tzconversion import tz_convert
from pandas.util._decorators import cache_readonly
from pandas.core.dtypes.common import (
is_datetime64_dtype,
is_period_arraylike,
is_timedelta64_dtype,
)
from pandas.core.dtypes.generic import ABCSeries
from pandas.core.algorithms import unique
from pandas.tseries.offsets import (
DateOffset,
Day,
Hour,
Micro,
Milli,
Minute,
Nano,
Second,
prefix_mapping,
)
_ONE_MICRO = 1000
_ONE_MILLI = _ONE_MICRO * 1000
_ONE_SECOND = _ONE_MILLI * 1000
_ONE_MINUTE = 60 * _ONE_SECOND
_ONE_HOUR = 60 * _ONE_MINUTE
_ONE_DAY = 24 * _ONE_HOUR
# ---------------------------------------------------------------------
# Offset names ("time rules") and related functions
#: cache of previously seen offsets
_offset_map = {} # type: Dict[str, DateOffset]
def get_period_alias(offset_str):
""" alias to closest period strings BQ->Q etc"""
return _offset_to_period_map.get(offset_str, None)
_name_to_offset_map = {
"days": Day(1),
"hours": Hour(1),
"minutes": Minute(1),
"seconds": Second(1),
"milliseconds": Milli(1),
"microseconds": Micro(1),
"nanoseconds": Nano(1),
}
def to_offset(freq):
"""
Return DateOffset object from string or tuple representation
or datetime.timedelta object
Parameters
----------
freq : str, tuple, datetime.timedelta, DateOffset or None
Returns
-------
DateOffset
None if freq is None.
Raises
------
ValueError
If freq is an invalid frequency
See Also
--------
DateOffset
Examples
--------
>>> to_offset('5min')
<5 * Minutes>
>>> to_offset('1D1H')
<25 * Hours>
>>> to_offset(('W', 2))
<2 * Weeks: weekday=6>
>>> to_offset((2, 'B'))
<2 * BusinessDays>
>>> to_offset(datetime.timedelta(days=1))
<Day>
>>> to_offset(Hour())
<Hour>
"""
if freq is None:
return None
if isinstance(freq, DateOffset):
return freq
if isinstance(freq, tuple):
name = freq[0]
stride = freq[1]
if isinstance(stride, str):
name, stride = stride, name
name, _ = libfreqs._base_and_stride(name)
delta = get_offset(name) * stride
elif isinstance(freq, timedelta):
delta = None
freq = Timedelta(freq)
try:
for name in freq.components._fields:
offset = _name_to_offset_map[name]
stride = getattr(freq.components, name)
if stride != 0:
offset = stride * offset
if delta is None:
delta = offset
else:
delta = delta + offset
except Exception:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
else:
delta = None
stride_sign = None
try:
splitted = re.split(libfreqs.opattern, freq)
if splitted[-1] != "" and not splitted[-1].isspace():
# the last element must be blank
raise ValueError("last element must be blank")
for sep, stride, name in zip(
splitted[0::4], splitted[1::4], splitted[2::4]
):
if sep != "" and not sep.isspace():
raise ValueError("separator must be spaces")
prefix = libfreqs._lite_rule_alias.get(name) or name
if stride_sign is None:
stride_sign = -1 if stride.startswith("-") else 1
if not stride:
stride = 1
if prefix in Resolution._reso_str_bump_map.keys():
stride, name = Resolution.get_stride_from_decimal(
float(stride), prefix
)
stride = int(stride)
offset = get_offset(name)
offset = offset * int(np.fabs(stride) * stride_sign)
if delta is None:
delta = offset
else:
delta = delta + offset
except Exception:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
if delta is None:
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(freq))
return delta
def get_offset(name):
"""
Return DateOffset object associated with rule name
Examples
--------
get_offset('EOM') --> BMonthEnd(1)
"""
if name not in libfreqs._dont_uppercase:
name = name.upper()
name = libfreqs._lite_rule_alias.get(name, name)
name = libfreqs._lite_rule_alias.get(name.lower(), name)
else:
name = libfreqs._lite_rule_alias.get(name, name)
if name not in _offset_map:
try:
split = name.split("-")
klass = prefix_mapping[split[0]]
# handles case where there's no suffix (and will TypeError if too
# many '-')
offset = klass._from_name(*split[1:])
except (ValueError, TypeError, KeyError):
# bad prefix or suffix
raise ValueError(libfreqs.INVALID_FREQ_ERR_MSG.format(name))
# cache
_offset_map[name] = offset
return _offset_map[name]
# ---------------------------------------------------------------------
# Period codes
def infer_freq(index, warn=True):
"""
Infer the most likely frequency given the input index. If the frequency is
uncertain, a warning will be printed.
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
if passed a Series will use the values of the series (NOT THE INDEX)
warn : boolean, default True
Returns
-------
str or None
None if no discernible frequency
TypeError if the index is not datetime-like
ValueError if there are less than three values.
"""
import pandas as pd
if isinstance(index, ABCSeries):
values = index._values
if not (
is_datetime64_dtype(values)
or is_timedelta64_dtype(values)
or values.dtype == object
):
raise TypeError(
"cannot infer freq from a non-convertible dtype "
"on a Series of {dtype}".format(dtype=index.dtype)
)
index = values
if is_period_arraylike(index):
raise TypeError(
"PeriodIndex given. Check the `freq` attribute "
"instead of using infer_freq."
)
elif is_timedelta64_dtype(index):
# Allow TimedeltaIndex and TimedeltaArray
inferer = _TimedeltaFrequencyInferer(index, warn=warn)
return inferer.get_freq()
if isinstance(index, pd.Index) and not isinstance(index, pd.DatetimeIndex):
if isinstance(index, (pd.Int64Index, pd.Float64Index)):
raise TypeError(
"cannot infer freq from a non-convertible index "
"type {type}".format(type=type(index))
)
index = index.values
if not isinstance(index, pd.DatetimeIndex):
try:
index = pd.DatetimeIndex(index)
except AmbiguousTimeError:
index = pd.DatetimeIndex(index.asi8)
inferer = _FrequencyInferer(index, warn=warn)
return inferer.get_freq()
class _FrequencyInferer:
"""
Not sure if I can avoid the state machine here
"""
def __init__(self, index, warn=True):
self.index = index
self.values = index.asi8
# This moves the values, which are implicitly in UTC, to the
# the timezone so they are in local time
if hasattr(index, "tz"):
if index.tz is not None:
self.values = tz_convert(self.values, UTC, index.tz)
self.warn = warn
if len(index) < 3:
raise ValueError("Need at least 3 dates to infer frequency")
self.is_monotonic = (
self.index._is_monotonic_increasing or self.index._is_monotonic_decreasing
)
@cache_readonly
def deltas(self):
return unique_deltas(self.values)
@cache_readonly
def deltas_asi8(self):
return unique_deltas(self.index.asi8)
@cache_readonly
def is_unique(self):
return len(self.deltas) == 1
@cache_readonly
def is_unique_asi8(self):
return len(self.deltas_asi8) == 1
def get_freq(self):
"""
Find the appropriate frequency string to describe the inferred
frequency of self.values
Returns
-------
str or None
"""
if not self.is_monotonic or not self.index._is_unique:
return None
delta = self.deltas[0]
if _is_multiple(delta, _ONE_DAY):
return self._infer_daily_rule()
# Business hourly, maybe. 17: one day / 65: one weekend
if self.hour_deltas in ([1, 17], [1, 65], [1, 17, 65]):
return "BH"
# Possibly intraday frequency. Here we use the
# original .asi8 values as the modified values
# will not work around DST transitions. See #8772
elif not self.is_unique_asi8:
return None
delta = self.deltas_asi8[0]
if _is_multiple(delta, _ONE_HOUR):
# Hours
return _maybe_add_count("H", delta / _ONE_HOUR)
elif _is_multiple(delta, _ONE_MINUTE):
# Minutes
return _maybe_add_count("T", delta / _ONE_MINUTE)
elif _is_multiple(delta, _ONE_SECOND):
# Seconds
return _maybe_add_count("S", delta / _ONE_SECOND)
elif _is_multiple(delta, _ONE_MILLI):
# Milliseconds
return _maybe_add_count("L", delta / _ONE_MILLI)
elif _is_multiple(delta, _ONE_MICRO):
# Microseconds
return _maybe_add_count("U", delta / _ONE_MICRO)
else:
# Nanoseconds
return _maybe_add_count("N", delta)
@cache_readonly
def day_deltas(self):
return [x / _ONE_DAY for x in self.deltas]
@cache_readonly
def hour_deltas(self):
return [x / _ONE_HOUR for x in self.deltas]
@cache_readonly
def fields(self):
return build_field_sarray(self.values)
@cache_readonly
def rep_stamp(self):
return Timestamp(self.values[0])
def month_position_check(self):
return libresolution.month_position_check(self.fields, self.index.dayofweek)
@cache_readonly
def mdiffs(self):
nmonths = self.fields["Y"] * 12 + self.fields["M"]
return unique_deltas(nmonths.astype("i8"))
@cache_readonly
def ydiffs(self):
return unique_deltas(self.fields["Y"].astype("i8"))
def _infer_daily_rule(self):
annual_rule = self._get_annual_rule()
if annual_rule:
nyears = self.ydiffs[0]
month = MONTH_ALIASES[self.rep_stamp.month]
alias = "{prefix}-{month}".format(prefix=annual_rule, month=month)
return _maybe_add_count(alias, nyears)
quarterly_rule = self._get_quarterly_rule()
if quarterly_rule:
nquarters = self.mdiffs[0] / 3
mod_dict = {0: 12, 2: 11, 1: 10}
month = MONTH_ALIASES[mod_dict[self.rep_stamp.month % 3]]
alias = "{prefix}-{month}".format(prefix=quarterly_rule, month=month)
return _maybe_add_count(alias, nquarters)
monthly_rule = self._get_monthly_rule()
if monthly_rule:
return _maybe_add_count(monthly_rule, self.mdiffs[0])
if self.is_unique:
days = self.deltas[0] / _ONE_DAY
if days % 7 == 0:
# Weekly
day = int_to_weekday[self.rep_stamp.weekday()]
return _maybe_add_count("W-{day}".format(day=day), days / 7)
else:
return _maybe_add_count("D", days)
if self._is_business_daily():
return "B"
wom_rule = self._get_wom_rule()
if wom_rule:
return wom_rule
def _get_annual_rule(self):
if len(self.ydiffs) > 1:
return None
if len(unique(self.fields["M"])) > 1:
return None
pos_check = self.month_position_check()
return {"cs": "AS", "bs": "BAS", "ce": "A", "be": "BA"}.get(pos_check)
def _get_quarterly_rule(self):
if len(self.mdiffs) > 1:
return None
if not self.mdiffs[0] % 3 == 0:
return None
pos_check = self.month_position_check()
return {"cs": "QS", "bs": "BQS", "ce": "Q", "be": "BQ"}.get(pos_check)
def _get_monthly_rule(self):
if len(self.mdiffs) > 1:
return None
pos_check = self.month_position_check()
return {"cs": "MS", "bs": "BMS", "ce": "M", "be": "BM"}.get(pos_check)
def _is_business_daily(self):
# quick check: cannot be business daily
if self.day_deltas != [1, 3]:
return False
# probably business daily, but need to confirm
first_weekday = self.index[0].weekday()
shifts = np.diff(self.index.asi8)
shifts = np.floor_divide(shifts, _ONE_DAY)
weekdays = np.mod(first_weekday + np.cumsum(shifts), 7)
return np.all(
((weekdays == 0) & (shifts == 3))
| ((weekdays > 0) & (weekdays <= 4) & (shifts == 1))
)
def _get_wom_rule(self):
# wdiffs = unique(np.diff(self.index.week))
# We also need -47, -49, -48 to catch index spanning year boundary
# if not lib.ismember(wdiffs, set([4, 5, -47, -49, -48])).all():
# return None
weekdays = unique(self.index.weekday)
if len(weekdays) > 1:
return None
week_of_months = unique((self.index.day - 1) // 7)
# Only attempt to infer up to WOM-4. See #9425
week_of_months = week_of_months[week_of_months < 4]
if len(week_of_months) == 0 or len(week_of_months) > 1:
return None
# get which week
week = week_of_months[0] + 1
wd = int_to_weekday[weekdays[0]]
return "WOM-{week}{weekday}".format(week=week, weekday=wd)
class _TimedeltaFrequencyInferer(_FrequencyInferer):
def _infer_daily_rule(self):
if self.is_unique:
days = self.deltas[0] / _ONE_DAY
if days % 7 == 0:
# Weekly
wd = int_to_weekday[self.rep_stamp.weekday()]
alias = "W-{weekday}".format(weekday=wd)
return _maybe_add_count(alias, days / 7)
else:
return _maybe_add_count("D", days)
def _is_multiple(us, mult):
return us % mult == 0
def _maybe_add_count(base, count):
if count != 1:
assert count == int(count)
count = int(count)
return "{count}{base}".format(count=count, base=base)
else:
return base

535
venv/lib/python3.6/site-packages/pandas/tseries/holiday.py Normal file
View File

@@ -0,0 +1,535 @@
from datetime import datetime, timedelta
from typing import List
import warnings
from dateutil.relativedelta import FR, MO, SA, SU, TH, TU, WE # noqa
import numpy as np
from pandas.errors import PerformanceWarning
from pandas import DateOffset, Series, Timestamp, date_range
from pandas.tseries.offsets import Day, Easter
def next_monday(dt):
"""
If holiday falls on Saturday, use following Monday instead;
if holiday falls on Sunday, use Monday instead
"""
if dt.weekday() == 5:
return dt + timedelta(2)
elif dt.weekday() == 6:
return dt + timedelta(1)
return dt
def next_monday_or_tuesday(dt):
"""
For second holiday of two adjacent ones!
If holiday falls on Saturday, use following Monday instead;
if holiday falls on Sunday or Monday, use following Tuesday instead
(because Monday is already taken by adjacent holiday on the day before)
"""
dow = dt.weekday()
if dow == 5 or dow == 6:
return dt + timedelta(2)
elif dow == 0:
return dt + timedelta(1)
return dt
def previous_friday(dt):
"""
If holiday falls on Saturday or Sunday, use previous Friday instead.
"""
if dt.weekday() == 5:
return dt - timedelta(1)
elif dt.weekday() == 6:
return dt - timedelta(2)
return dt
def sunday_to_monday(dt):
"""
If holiday falls on Sunday, use day thereafter (Monday) instead.
"""
if dt.weekday() == 6:
return dt + timedelta(1)
return dt
def weekend_to_monday(dt):
"""
If holiday falls on Sunday or Saturday,
use day thereafter (Monday) instead.
Needed for holidays such as Christmas observation in Europe
"""
if dt.weekday() == 6:
return dt + timedelta(1)
elif dt.weekday() == 5:
return dt + timedelta(2)
return dt
def nearest_workday(dt):
"""
If holiday falls on Saturday, use day before (Friday) instead;
if holiday falls on Sunday, use day thereafter (Monday) instead.
"""
if dt.weekday() == 5:
return dt - timedelta(1)
elif dt.weekday() == 6:
return dt + timedelta(1)
return dt
def next_workday(dt):
"""
returns next weekday used for observances
"""
dt += timedelta(days=1)
while dt.weekday() > 4:
# Mon-Fri are 0-4
dt += timedelta(days=1)
return dt
def previous_workday(dt):
"""
returns previous weekday used for observances
"""
dt -= timedelta(days=1)
while dt.weekday() > 4:
# Mon-Fri are 0-4
dt -= timedelta(days=1)
return dt
def before_nearest_workday(dt):
"""
returns previous workday after nearest workday
"""
return previous_workday(nearest_workday(dt))
def after_nearest_workday(dt):
"""
returns next workday after nearest workday
needed for Boxing day or multiple holidays in a series
"""
return next_workday(nearest_workday(dt))
class Holiday:
"""
Class that defines a holiday with start/end dates and rules
for observance.
"""
def __init__(
self,
name,
year=None,
month=None,
day=None,
offset=None,
observance=None,
start_date=None,
end_date=None,
days_of_week=None,
):
"""
Parameters
----------
name : str
Name of the holiday , defaults to class name
offset : array of pandas.tseries.offsets or
class from pandas.tseries.offsets
computes offset from date
observance: function
computes when holiday is given a pandas Timestamp
days_of_week:
provide a tuple of days e.g (0,1,2,3,) for Monday Through Thursday
Monday=0,..,Sunday=6
Examples
--------
>>> from pandas.tseries.holiday import Holiday, nearest_workday
>>> from dateutil.relativedelta import MO
>>> USMemorialDay = Holiday('Memorial Day', month=5, day=31,
offset=pd.DateOffset(weekday=MO(-1)))
>>> USLaborDay = Holiday('Labor Day', month=9, day=1,
offset=pd.DateOffset(weekday=MO(1)))
>>> July3rd = Holiday('July 3rd', month=7, day=3,)
>>> NewYears = Holiday('New Years Day', month=1, day=1,
observance=nearest_workday),
>>> July3rd = Holiday('July 3rd', month=7, day=3,
days_of_week=(0, 1, 2, 3))
"""
if offset is not None and observance is not None:
raise NotImplementedError("Cannot use both offset and observance.")
self.name = name
self.year = year
self.month = month
self.day = day
self.offset = offset
self.start_date = (
Timestamp(start_date) if start_date is not None else start_date
)
self.end_date = Timestamp(end_date) if end_date is not None else end_date
self.observance = observance
assert days_of_week is None or type(days_of_week) == tuple
self.days_of_week = days_of_week
def __repr__(self):
info = ""
if self.year is not None:
info += "year={year}, ".format(year=self.year)
info += "month={mon}, day={day}, ".format(mon=self.month, day=self.day)
if self.offset is not None:
info += "offset={offset}".format(offset=self.offset)
if self.observance is not None:
info += "observance={obs}".format(obs=self.observance)
repr = "Holiday: {name} ({info})".format(name=self.name, info=info)
return repr
def dates(self, start_date, end_date, return_name=False):
"""
Calculate holidays observed between start date and end date
Parameters
----------
start_date : starting date, datetime-like, optional
end_date : ending date, datetime-like, optional
return_name : bool, optional, default=False
If True, return a series that has dates and holiday names.
False will only return dates.
"""
start_date = Timestamp(start_date)
end_date = Timestamp(end_date)
filter_start_date = start_date
filter_end_date = end_date
if self.year is not None:
dt = Timestamp(datetime(self.year, self.month, self.day))
if return_name:
return Series(self.name, index=[dt])
else:
return [dt]
dates = self._reference_dates(start_date, end_date)
holiday_dates = self._apply_rule(dates)
if self.days_of_week is not None:
holiday_dates = holiday_dates[
np.in1d(holiday_dates.dayofweek, self.days_of_week)
]
if self.start_date is not None:
filter_start_date = max(
self.start_date.tz_localize(filter_start_date.tz), filter_start_date
)
if self.end_date is not None:
filter_end_date = min(
self.end_date.tz_localize(filter_end_date.tz), filter_end_date
)
holiday_dates = holiday_dates[
(holiday_dates >= filter_start_date) & (holiday_dates <= filter_end_date)
]
if return_name:
return Series(self.name, index=holiday_dates)
return holiday_dates
def _reference_dates(self, start_date, end_date):
"""
Get reference dates for the holiday.
Return reference dates for the holiday also returning the year
prior to the start_date and year following the end_date. This ensures
that any offsets to be applied will yield the holidays within
the passed in dates.
"""
if self.start_date is not None:
start_date = self.start_date.tz_localize(start_date.tz)
if self.end_date is not None:
end_date = self.end_date.tz_localize(start_date.tz)
year_offset = DateOffset(years=1)
reference_start_date = Timestamp(
datetime(start_date.year - 1, self.month, self.day)
)
reference_end_date = Timestamp(
datetime(end_date.year + 1, self.month, self.day)
)
# Don't process unnecessary holidays
dates = date_range(
start=reference_start_date,
end=reference_end_date,
freq=year_offset,
tz=start_date.tz,
)
return dates
def _apply_rule(self, dates):
"""
Apply the given offset/observance to a DatetimeIndex of dates.
Parameters
----------
dates : DatetimeIndex
Dates to apply the given offset/observance rule
Returns
-------
Dates with rules applied
"""
if self.observance is not None:
return dates.map(lambda d: self.observance(d))
if self.offset is not None:
if not isinstance(self.offset, list):
offsets = [self.offset]
else:
offsets = self.offset
for offset in offsets:
# if we are adding a non-vectorized value
# ignore the PerformanceWarnings:
with warnings.catch_warnings():
warnings.simplefilter("ignore", PerformanceWarning)
dates += offset
return dates
holiday_calendars = {}
def register(cls):
try:
name = cls.name
except AttributeError:
name = cls.__name__
holiday_calendars[name] = cls
def get_calendar(name):
"""
Return an instance of a calendar based on its name.
Parameters
----------
name : str
Calendar name to return an instance of
"""
return holiday_calendars[name]()
class HolidayCalendarMetaClass(type):
def __new__(cls, clsname, bases, attrs):
calendar_class = super().__new__(cls, clsname, bases, attrs)
register(calendar_class)
return calendar_class
class AbstractHolidayCalendar(metaclass=HolidayCalendarMetaClass):
"""
Abstract interface to create holidays following certain rules.
"""
rules = [] # type: List[Holiday]
start_date = Timestamp(datetime(1970, 1, 1))
end_date = Timestamp(datetime(2030, 12, 31))
_cache = None
def __init__(self, name=None, rules=None):
"""
Initializes holiday object with a given set a rules. Normally
classes just have the rules defined within them.
Parameters
----------
name : str
Name of the holiday calendar, defaults to class name
rules : array of Holiday objects
A set of rules used to create the holidays.
"""
super().__init__()
if name is None:
name = self.__class__.__name__
self.name = name
if rules is not None:
self.rules = rules
def rule_from_name(self, name):
for rule in self.rules:
if rule.name == name:
return rule
return None
def holidays(self, start=None, end=None, return_name=False):
"""
Returns a curve with holidays between start_date and end_date
Parameters
----------
start : starting date, datetime-like, optional
end : ending date, datetime-like, optional
return_name : bool, optional
If True, return a series that has dates and holiday names.
False will only return a DatetimeIndex of dates.
Returns
-------
DatetimeIndex of holidays
"""
if self.rules is None:
raise Exception(
"Holiday Calendar {name} does not have any "
"rules specified".format(name=self.name)
)
if start is None:
start = AbstractHolidayCalendar.start_date
if end is None:
end = AbstractHolidayCalendar.end_date
start = Timestamp(start)
end = Timestamp(end)
holidays = None
# If we don't have a cache or the dates are outside the prior cache, we
# get them again
if self._cache is None or start < self._cache[0] or end > self._cache[1]:
for rule in self.rules:
rule_holidays = rule.dates(start, end, return_name=True)
if holidays is None:
holidays = rule_holidays
else:
holidays = holidays.append(rule_holidays)
self._cache = (start, end, holidays.sort_index())
holidays = self._cache[2]
holidays = holidays[start:end]
if return_name:
return holidays
else:
return holidays.index
@staticmethod
def merge_class(base, other):
"""
Merge holiday calendars together. The base calendar
will take precedence to other. The merge will be done
based on each holiday's name.
Parameters
----------
base : AbstractHolidayCalendar
instance/subclass or array of Holiday objects
other : AbstractHolidayCalendar
instance/subclass or array of Holiday objects
"""
try:
other = other.rules
except AttributeError:
pass
if not isinstance(other, list):
other = [other]
other_holidays = {holiday.name: holiday for holiday in other}
try:
base = base.rules
except AttributeError:
pass
if not isinstance(base, list):
base = [base]
base_holidays = {holiday.name: holiday for holiday in base}
other_holidays.update(base_holidays)
return list(other_holidays.values())
def merge(self, other, inplace=False):
"""
Merge holiday calendars together. The caller's class
rules take precedence. The merge will be done
based on each holiday's name.
Parameters
----------
other : holiday calendar
inplace : bool (default=False)
If True set rule_table to holidays, else return array of Holidays
"""
holidays = self.merge_class(self, other)
if inplace:
self.rules = holidays
else:
return holidays
USMemorialDay = Holiday(
"Memorial Day", month=5, day=31, offset=DateOffset(weekday=MO(-1))
)
USLaborDay = Holiday("Labor Day", month=9, day=1, offset=DateOffset(weekday=MO(1)))
USColumbusDay = Holiday(
"Columbus Day", month=10, day=1, offset=DateOffset(weekday=MO(2))
)
USThanksgivingDay = Holiday(
"Thanksgiving", month=11, day=1, offset=DateOffset(weekday=TH(4))
)
USMartinLutherKingJr = Holiday(
"Martin Luther King Jr. Day",
start_date=datetime(1986, 1, 1),
month=1,
day=1,
offset=DateOffset(weekday=MO(3)),
)
USPresidentsDay = Holiday(
"Presidents Day", month=2, day=1, offset=DateOffset(weekday=MO(3))
)
GoodFriday = Holiday("Good Friday", month=1, day=1, offset=[Easter(), Day(-2)])
EasterMonday = Holiday("Easter Monday", month=1, day=1, offset=[Easter(), Day(1)])
class USFederalHolidayCalendar(AbstractHolidayCalendar):
"""
US Federal Government Holiday Calendar based on rules specified by:
https://www.opm.gov/policy-data-oversight/
snow-dismissal-procedures/federal-holidays/
"""
rules = [
Holiday("New Years Day", month=1, day=1, observance=nearest_workday),
USMartinLutherKingJr,
USPresidentsDay,
USMemorialDay,
Holiday("July 4th", month=7, day=4, observance=nearest_workday),
USLaborDay,
USColumbusDay,
Holiday("Veterans Day", month=11, day=11, observance=nearest_workday),
USThanksgivingDay,
Holiday("Christmas", month=12, day=25, observance=nearest_workday),
]
def HolidayCalendarFactory(name, base, other, base_class=AbstractHolidayCalendar):
rules = AbstractHolidayCalendar.merge_class(base, other)
calendar_class = type(name, (base_class,), {"rules": rules, "name": name})
return calendar_class

2816
venv/lib/python3.6/site-packages/pandas/tseries/offsets.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
venv/lib/python3.6/site-packages/pandas/tseries/plotting.py Normal file
View File

@@ -0,0 +1,3 @@
# flake8: noqa
from pandas.plotting._matplotlib.timeseries import tsplot