def test_cache_keys_are_distinct_for_pytz_vs_dateutil(tz_name):
if tz_name == 'UTC':
# skip utc as it's a special case in dateutil
return
tz_p = timezones.maybe_get_tz(tz_name)
tz_d = timezones.maybe_get_tz('dateutil/' + tz_name)
if tz_d is None:
# skip timezones that dateutil doesn't know about.
return
assert timezones._p_tz_cache_key(tz_p) != timezones._p_tz_cache_key(tz_d)
def test_cache_keys_are_distinct_for_pytz_vs_dateutil(tz_name):
if tz_name == "UTC":
pytest.skip("UTC: special case in dateutil")
tz_p = timezones.maybe_get_tz(tz_name)
tz_d = timezones.maybe_get_tz("dateutil/" + tz_name)
if tz_d is None:
pytest.skip(tz_name + ": dateutil does not know about this one")
assert timezones._p_tz_cache_key(tz_p) != timezones._p_tz_cache_key(tz_d)
def test_tz_convert_utc_with_system_utc(self):
from pandas._libs.tslibs.timezones import maybe_get_tz
# from system utc to real utc
ts = Timestamp('2001-01-05 11:56', tz=maybe_get_tz('dateutil/UTC'))
# check that the time hasn't changed.
assert ts == ts.tz_convert(dateutil.tz.tzutc())
# from system utc to real utc
ts = Timestamp('2001-01-05 11:56', tz=maybe_get_tz('dateutil/UTC'))
# check that the time hasn't changed.
assert ts == ts.tz_convert(dateutil.tz.tzutc())
def tz(self, tz):
"""
Construct a dateutil timezone.
Use tslib.maybe_get_tz so that we get the filename on the tz right
on windows. See #7337.
"""
return timezones.maybe_get_tz('dateutil/' + tz)
def __init__(self, unit="ns", tz=None):
if isinstance(unit, DatetimeTZDtype):
unit, tz = unit.unit, unit.tz
if unit != 'ns':
if isinstance(unit, str) and tz is None:
# maybe a string like datetime64[ns, tz], which we support for
# now.
result = type(self).construct_from_string(unit)
unit = result.unit
tz = result.tz
msg = (
"Passing a dtype alias like 'datetime64[ns, {tz}]' "
"to DatetimeTZDtype is deprecated. Use "
"'DatetimeTZDtype.construct_from_string()' instead."
)
warnings.warn(msg.format(tz=tz), FutureWarning, stacklevel=2)
else:
raise ValueError("DatetimeTZDtype only supports ns units")
if tz:
tz = timezones.maybe_get_tz(tz)
tz = timezones.tz_standardize(tz)
elif tz is not None:
raise pytz.UnknownTimeZoneError(tz)
elif tz is None:
raise TypeError("A 'tz' is required.")
self._unit = unit
self._tz = tz
def test_dti_tz_convert_utc_to_local_no_modify(self, tz):
rng = date_range('3/11/2012', '3/12/2012', freq='H', tz='utc')
rng_eastern = rng.tz_convert(tz)
# Values are unmodified
tm.assert_numpy_array_equal(rng.asi8, rng_eastern.asi8)
assert timezones.tz_compare(rng_eastern.tz, timezones.maybe_get_tz(tz))
def test_tslib_tz_convert(self):
def compare_utc_to_local(tz_didx, utc_didx):
f = lambda x: conversion.tz_convert_single(x, 'UTC', tz_didx.tz)
result = conversion.tz_convert(tz_didx.asi8, 'UTC', tz_didx.tz)
result_single = np.vectorize(f)(tz_didx.asi8)
tm.assert_numpy_array_equal(result, result_single)
def compare_local_to_utc(tz_didx, utc_didx):
f = lambda x: conversion.tz_convert_single(x, tz_didx.tz, 'UTC')
result = conversion.tz_convert(utc_didx.asi8, tz_didx.tz, 'UTC')
result_single = np.vectorize(f)(utc_didx.asi8)
tm.assert_numpy_array_equal(result, result_single)
for tz in ['UTC', 'Asia/Tokyo', 'US/Eastern', 'Europe/Moscow']:
# US: 2014-03-09 - 2014-11-11
# MOSCOW: 2014-10-26 / 2014-12-31
tz_didx = date_range('2014-03-01', '2015-01-10', freq='H', tz=tz)
utc_didx = date_range('2014-03-01', '2015-01-10', freq='H')
compare_utc_to_local(tz_didx, utc_didx)
# local tz to UTC can be differ in hourly (or higher) freqs because
# of DST
compare_local_to_utc(tz_didx, utc_didx)
tz_didx = date_range('2000-01-01', '2020-01-01', freq='D', tz=tz)
utc_didx = date_range('2000-01-01', '2020-01-01', freq='D')
compare_utc_to_local(tz_didx, utc_didx)
compare_local_to_utc(tz_didx, utc_didx)
tz_didx = date_range('2000-01-01', '2100-01-01', freq='A', tz=tz)
utc_didx = date_range('2000-01-01', '2100-01-01', freq='A')
compare_utc_to_local(tz_didx, utc_didx)
compare_local_to_utc(tz_didx, utc_didx)
# Check empty array
result = conversion.tz_convert(np.array([], dtype=np.int64),
timezones.maybe_get_tz('US/Eastern'),
timezones.maybe_get_tz('Asia/Tokyo'))
tm.assert_numpy_array_equal(result, np.array([], dtype=np.int64))
# Check all-NaT array
result = conversion.tz_convert(np.array([tslib.iNaT], dtype=np.int64),
timezones.maybe_get_tz('US/Eastern'),
timezones.maybe_get_tz('Asia/Tokyo'))
tm.assert_numpy_array_equal(result, np.array(
[tslib.iNaT], dtype=np.int64))
def test_series_tz_localize_empty(self, tzstr):
# GH#2248
ser = Series()
ser2 = ser.tz_localize('utc')
assert ser2.index.tz == pytz.utc
ser2 = ser.tz_localize(tzstr)
timezones.tz_compare(ser2.index.tz, timezones.maybe_get_tz(tzstr))
def test_timestamp_tz_arg_dateutil(self):
from pandas._libs.tslibs.timezones import dateutil_gettz
from pandas._libs.tslibs.timezones import maybe_get_tz
for case in ['dateutil/Europe/Brussels', 'dateutil/Asia/Tokyo',
'dateutil/US/Pacific']:
p = Period('1/1/2005', freq='M').to_timestamp(
tz=maybe_get_tz(case))
exp = Timestamp('1/1/2005', tz='UTC').tz_convert(case)
assert p == exp
assert p.tz == dateutil_gettz(case.split('/', 1)[1])
assert p.tz == exp.tz
p = Period('1/1/2005',
freq='M').to_timestamp(freq='3H', tz=maybe_get_tz(case))
exp = Timestamp('1/1/2005', tz='UTC').tz_convert(case)
assert p == exp
assert p.tz == dateutil_gettz(case.split('/', 1)[1])
assert p.tz == exp.tz
def test_timetz_accessor(self, tz_naive_fixture):
# GH21358
tz = timezones.maybe_get_tz(tz_naive_fixture)
expected = np.array([time(10, 20, 30, tzinfo=tz), pd.NaT])
index = DatetimeIndex(['2018-06-04 10:20:30', pd.NaT], tz=tz)
result = index.timetz
tm.assert_numpy_array_equal(result, expected)
def __init__(self, unit="ns", tz=None):
"""
An ExtensionDtype for timezone-aware datetime data.
Parameters
----------
unit : str, default "ns"
The precision of the datetime data. Currently limited
to ``"ns"``.
tz : str, int, or datetime.tzinfo
The timezone.
Raises
------
pytz.UnknownTimeZoneError
When the requested timezone cannot be found.
Examples
--------
>>> pd.core.dtypes.dtypes.DatetimeTZDtype(tz='UTC')
datetime64[ns, UTC]
>>> pd.core.dtypes.dtypes.DatetimeTZDtype(tz='dateutil/US/Central')
datetime64[ns, tzfile('/usr/share/zoneinfo/US/Central')]
"""
if isinstance(unit, DatetimeTZDtype):
unit, tz = unit.unit, unit.tz
if unit != 'ns':
if isinstance(unit, compat.string_types) and tz is None:
# maybe a string like datetime64[ns, tz], which we support for
# now.
result = type(self).construct_from_string(unit)
unit = result.unit
tz = result.tz
msg = (
"Passing a dtype alias like 'datetime64[ns, {tz}]' "
"to DatetimeTZDtype is deprecated. Use "
"'DatetimeTZDtype.construct_from_string()' instead."
)
warnings.warn(msg.format(tz=tz), FutureWarning, stacklevel=2)
else:
raise ValueError("DatetimeTZDtype only supports ns units")
if tz:
tz = timezones.maybe_get_tz(tz)
tz = timezones.tz_standardize(tz)
elif tz is not None:
raise pytz.UnknownTimeZoneError(tz)
elif tz is None:
raise TypeError("A 'tz' is required.")
self._unit = unit
self._tz = tz
def test_dt_timetz_accessor(self, tz_naive_fixture):
# GH21358
tz = maybe_get_tz(tz_naive_fixture)
dtindex = pd.DatetimeIndex(['2014-04-04 23:56', '2014-07-18 21:24',
'2015-11-22 22:14'], tz=tz)
s = Series(dtindex)
expected = Series([time(23, 56, tzinfo=tz), time(21, 24, tzinfo=tz),
time(22, 14, tzinfo=tz)])
result = s.dt.timetz
tm.assert_series_equal(result, expected)
def test_getitem_pydatetime_tz(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
index = date_range(start='2012-12-24 16:00', end='2012-12-24 18:00',
freq='H', tz=tzstr)
ts = Series(index=index, data=index.hour)
time_pandas = Timestamp('2012-12-24 17:00', tz=tzstr)
dt = datetime(2012, 12, 24, 17, 0)
time_datetime = conversion.localize_pydatetime(dt, tz)
assert ts[time_pandas] == ts[time_datetime]
def test_tzlocal(self):
# GH 13583
ts = Timestamp('2011-01-01', tz=dateutil.tz.tzlocal())
assert ts.tz == dateutil.tz.tzlocal()
assert "tz='tzlocal()')" in repr(ts)
tz = timezones.maybe_get_tz('tzlocal()')
assert tz == dateutil.tz.tzlocal()
# get offset using normal datetime for test
offset = dateutil.tz.tzlocal().utcoffset(datetime(2011, 1, 1))
offset = offset.total_seconds() * 1000000000
assert ts.value + offset == Timestamp('2011-01-01').value
def test_timestamp_timetz_equivalent_with_datetime_tz(self,
tz_naive_fixture):
# GH21358
tz = timezones.maybe_get_tz(tz_naive_fixture)
stamp = Timestamp('2018-06-04 10:20:30', tz=tz)
_datetime = datetime(2018, 6, 4, hour=10,
minute=20, second=30, tzinfo=tz)
result = stamp.timetz()
expected = _datetime.timetz()
assert result == expected
def _infer_tz_from_endpoints(start, end, tz):
"""
If a timezone is not explicitly given via `tz`, see if one can
be inferred from the `start` and `end` endpoints. If more than one
of these inputs provides a timezone, require that they all agree.
Parameters
----------
start : Timestamp
end : Timestamp
tz : tzinfo or None
Returns
-------
tz : tzinfo or None
inferred_tz : tzinfo or None
Raises
------
TypeError : if start and end timezones do not agree
"""
try:
inferred_tz = timezones.infer_tzinfo(start, end)
except Exception:
raise TypeError('Start and end cannot both be tz-aware with '
'different timezones')
inferred_tz = timezones.maybe_get_tz(inferred_tz)
tz = timezones.maybe_get_tz(tz)
if tz is not None and inferred_tz is not None:
if not timezones.tz_compare(inferred_tz, tz):
raise AssertionError("Inferred time zone not equal to passed "
"time zone")
elif inferred_tz is not None:
tz = inferred_tz
return tz, inferred_tz
def test_timestamp_timetz_equivalent_with_datetime_tz(
self, tz_naive_fixture):
# GH21358
tz = timezones.maybe_get_tz(tz_naive_fixture)
stamp = Timestamp("2018-06-04 10:20:30", tz=tz)
_datetime = datetime(2018,
6,
4,
hour=10,
minute=20,
second=30,
tzinfo=tz)
result = stamp.timetz()
expected = _datetime.timetz()
assert result == expected
def test_localized_at_time_between_time(self, tzstr):
from datetime import time
tz = timezones.maybe_get_tz(tzstr)
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(tzstr)
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_utc_box_timestamp_and_localize(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
rng = date_range("3/11/2012", "3/12/2012", freq="H", tz="utc")
rng_eastern = rng.tz_convert(tzstr)
expected = rng[-1].astimezone(tz)
stamp = rng_eastern[-1]
assert stamp == expected
assert stamp.tzinfo == expected.tzinfo
# right tzinfo
rng = date_range("3/13/2012", "3/14/2012", freq="H", tz="utc")
rng_eastern = rng.tz_convert(tzstr)
# test not valid for dateutil timezones.
# assert 'EDT' in repr(rng_eastern[0].tzinfo)
assert "EDT" in repr(rng_eastern[0].tzinfo) or "tzfile" in repr(
rng_eastern[0].tzinfo)
def test_localized_at_time_between_time(self, tzstr):
from datetime import time
tz = timezones.maybe_get_tz(tzstr)
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(tzstr)
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_utc_box_timestamp_and_localize(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
rng = date_range('3/11/2012', '3/12/2012', freq='H', tz='utc')
rng_eastern = rng.tz_convert(tzstr)
expected = rng[-1].astimezone(tz)
stamp = rng_eastern[-1]
assert stamp == expected
assert stamp.tzinfo == expected.tzinfo
# right tzinfo
rng = date_range('3/13/2012', '3/14/2012', freq='H', tz='utc')
rng_eastern = rng.tz_convert(tzstr)
# test not valid for dateutil timezones.
# assert 'EDT' in repr(rng_eastern[0].tzinfo)
assert ('EDT' in repr(rng_eastern[0].tzinfo) or
'tzfile' in repr(rng_eastern[0].tzinfo))
def _simple_new(cls, values, freq=None, tz=None, **kwargs):
"""
we require the we have a dtype compat for the values
if we are passed a non-dtype compat, then coerce using the constructor
"""
if getattr(values, 'dtype', None) is None:
# empty, but with dtype compat
if values is None:
values = np.empty(0, dtype=_NS_DTYPE)
return cls(values, freq=freq, tz=tz, **kwargs)
values = np.array(values, copy=False)
if not is_datetime64_dtype(values):
values = ensure_int64(values).view(_NS_DTYPE)
result = object.__new__(cls)
result._data = values
result._freq = freq
tz = timezones.maybe_get_tz(tz)
result._tz = timezones.tz_standardize(tz)
return result
def _simple_new(cls, values, freq=None, tz=None, **kwargs):
"""
we require the we have a dtype compat for the values
if we are passed a non-dtype compat, then coerce using the constructor
"""
if getattr(values, 'dtype', None) is None:
# empty, but with dtype compat
if values is None:
values = np.empty(0, dtype=_NS_DTYPE)
return cls(values, freq=freq, tz=tz, **kwargs)
values = np.array(values, copy=False)
if not is_datetime64_dtype(values):
values = _ensure_int64(values).view(_NS_DTYPE)
result = object.__new__(cls)
result._data = values
result._freq = freq
tz = timezones.maybe_get_tz(tz)
result._tz = timezones.tz_standardize(tz)
return result
def test_range_tz_dateutil(self):
# see gh-2906
# Use maybe_get_tz to fix filename in tz under dateutil.
from pandas._libs.tslibs.timezones import maybe_get_tz
tz = lambda x: maybe_get_tz('dateutil/' + x)
start = datetime(2011, 1, 1, tzinfo=tz('US/Eastern'))
end = datetime(2011, 1, 3, tzinfo=tz('US/Eastern'))
dr = date_range(start=start, periods=3)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
dr = date_range(end=end, periods=3)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
dr = date_range(start=start, end=end)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
def test_range_tz_dateutil(self):
# see gh-2906
# Use maybe_get_tz to fix filename in tz under dateutil.
from pandas._libs.tslibs.timezones import maybe_get_tz
tz = lambda x: maybe_get_tz('dateutil/' + x)
start = datetime(2011, 1, 1, tzinfo=tz('US/Eastern'))
end = datetime(2011, 1, 3, tzinfo=tz('US/Eastern'))
dr = date_range(start=start, periods=3)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
dr = date_range(end=end, periods=3)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
dr = date_range(start=start, end=end)
assert dr.tz == tz('US/Eastern')
assert dr[0] == start
assert dr[2] == end
def test_tz_compare_utc(utc_fixture, utc_fixture2):
tz = timezones.maybe_get_tz(utc_fixture)
tz2 = timezones.maybe_get_tz(utc_fixture2)
assert timezones.tz_compare(tz, tz2)
def test_tz_convert_corner(self, arr):
result = conversion.tz_convert(arr,
timezones.maybe_get_tz('US/Eastern'),
timezones.maybe_get_tz('Asia/Tokyo'))
tm.assert_numpy_array_equal(result, arr)
def test_tzlocal_maybe_get_tz():
# see gh-13583
tz = timezones.maybe_get_tz("tzlocal()")
assert tz == dateutil.tz.tzlocal()
def tz_localize(self, tz, ambiguous='raise', errors='raise'):
"""
Localize tz-naive Datetime Array/Index to tz-aware
Datetime Array/Index.
This method takes a time zone (tz) naive Datetime Array/Index object
and makes this time zone aware. It does not move the time to another
time zone.
Time zone localization helps to switch from time zone aware to time
zone unaware objects.
Parameters
----------
tz : string, pytz.timezone, dateutil.tz.tzfile or None
Time zone to convert timestamps to. Passing ``None`` will
remove the time zone information preserving local time.
ambiguous : str {'infer', 'NaT', 'raise'} or bool array,
default 'raise'
- 'infer' will attempt to infer fall dst-transition hours based on
order
- bool-ndarray where True signifies a DST time, False signifies a
non-DST time (note that this flag is only applicable for
ambiguous times)
- 'NaT' will return NaT where there are ambiguous times
- 'raise' will raise an AmbiguousTimeError if there are ambiguous
times
errors : {'raise', 'coerce'}, default 'raise'
- 'raise' will raise a NonExistentTimeError if a timestamp is not
valid in the specified time zone (e.g. due to a transition from
or to DST time)
- 'coerce' will return NaT if the timestamp can not be converted
to the specified time zone
.. versionadded:: 0.19.0
Returns
-------
result : same type as self
Array/Index converted to the specified time zone.
Raises
------
TypeError
If the Datetime Array/Index is tz-aware and tz is not None.
See Also
--------
DatetimeIndex.tz_convert : Convert tz-aware DatetimeIndex from
one time zone to another.
Examples
--------
>>> tz_naive = pd.date_range('2018-03-01 09:00', periods=3)
>>> tz_naive
DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
'2018-03-03 09:00:00'],
dtype='datetime64[ns]', freq='D')
Localize DatetimeIndex in US/Eastern time zone:
>>> tz_aware = tz_naive.tz_localize(tz='US/Eastern')
>>> tz_aware
DatetimeIndex(['2018-03-01 09:00:00-05:00',
'2018-03-02 09:00:00-05:00',
'2018-03-03 09:00:00-05:00'],
dtype='datetime64[ns, US/Eastern]', freq='D')
With the ``tz=None``, we can remove the time zone information
while keeping the local time (not converted to UTC):
>>> tz_aware.tz_localize(None)
DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
'2018-03-03 09:00:00'],
dtype='datetime64[ns]', freq='D')
"""
if self.tz is not None:
if tz is None:
new_dates = conversion.tz_convert(self.asi8, 'UTC', self.tz)
else:
raise TypeError("Already tz-aware, use tz_convert to convert.")
else:
tz = timezones.maybe_get_tz(tz)
# Convert to UTC
new_dates = conversion.tz_localize_to_utc(self.asi8, tz,
ambiguous=ambiguous,
errors=errors)
new_dates = new_dates.view(_NS_DTYPE)
return self._shallow_copy(new_dates, tz=tz)
def _convert_listlike_datetimes(
arg,
format: str | None,
name: Hashable = None,
tz: Timezone | None = None,
unit: str | None = None,
errors: str = "raise",
infer_datetime_format: bool = False,
dayfirst: bool | None = None,
yearfirst: bool | None = None,
exact: bool = True,
):
"""
Helper function for to_datetime. Performs the conversions of 1D listlike
of dates
Parameters
----------
arg : list, tuple, ndarray, Series, Index
date to be parsed
name : object
None or string for the Index name
tz : object
None or 'utc'
unit : str
None or string of the frequency of the passed data
errors : str
error handing behaviors from to_datetime, 'raise', 'coerce', 'ignore'
infer_datetime_format : bool, default False
inferring format behavior from to_datetime
dayfirst : bool
dayfirst parsing behavior from to_datetime
yearfirst : bool
yearfirst parsing behavior from to_datetime
exact : bool, default True
exact format matching behavior from to_datetime
Returns
-------
Index-like of parsed dates
"""
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype="O")
arg_dtype = getattr(arg, "dtype", None)
# these are shortcutable
if is_datetime64tz_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
return DatetimeIndex(arg, tz=tz, name=name)
if tz == "utc":
arg = arg.tz_convert(None).tz_localize(tz)
return arg
elif is_datetime64_ns_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
elif tz:
# DatetimeArray, DatetimeIndex
return arg.tz_localize(tz)
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
return _to_datetime_with_unit(arg, unit, name, tz, errors)
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, datetime, list, tuple, 1-d array, or Series"
)
# warn if passing timedelta64, raise for PeriodDtype
# NB: this must come after unit transformation
orig_arg = arg
try:
arg, _ = maybe_convert_dtype(arg,
copy=False,
tz=timezones.maybe_get_tz(tz))
except TypeError:
if errors == "coerce":
npvalues = np.array(["NaT"],
dtype="datetime64[ns]").repeat(len(arg))
return DatetimeIndex(npvalues, name=name)
elif errors == "ignore":
idx = Index(arg, name=name)
return idx
raise
arg = ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
if format is not None:
res = _to_datetime_with_format(arg, orig_arg, name, tz, format, exact,
errors, infer_datetime_format)
if res is not None:
return res
assert format is None or infer_datetime_format
utc = tz == "utc"
result, tz_parsed = objects_to_datetime64ns(
arg,
dayfirst=dayfirst,
yearfirst=yearfirst,
utc=utc,
errors=errors,
require_iso8601=require_iso8601,
allow_object=True,
)
if tz_parsed is not None:
# We can take a shortcut since the datetime64 numpy array
# is in UTC
dta = DatetimeArray(result, dtype=tz_to_dtype(tz_parsed))
return DatetimeIndex._simple_new(dta, name=name)
utc = tz == "utc"
return _box_as_indexlike(result, utc=utc, name=name)
def test_tz_convert_corner(arr):
result = conversion.tz_convert(arr,
timezones.maybe_get_tz("US/Eastern"),
timezones.maybe_get_tz("Asia/Tokyo"))
tm.assert_numpy_array_equal(result, arr)
def tz_localize(self, tz, ambiguous='raise', errors='raise'):
"""
Localize tz-naive Datetime Array/Index to tz-aware
Datetime Array/Index.
This method takes a time zone (tz) naive Datetime Array/Index object
and makes this time zone aware. It does not move the time to another
time zone.
Time zone localization helps to switch from time zone aware to time
zone unaware objects.
Parameters
----------
tz : string, pytz.timezone, dateutil.tz.tzfile or None
Time zone to convert timestamps to. Passing ``None`` will
remove the time zone information preserving local time.
ambiguous : str {'infer', 'NaT', 'raise'} or bool array,
default 'raise'
- 'infer' will attempt to infer fall dst-transition hours based on
order
- bool-ndarray where True signifies a DST time, False signifies a
non-DST time (note that this flag is only applicable for
ambiguous times)
- 'NaT' will return NaT where there are ambiguous times
- 'raise' will raise an AmbiguousTimeError if there are ambiguous
times
errors : {'raise', 'coerce'}, default 'raise'
- 'raise' will raise a NonExistentTimeError if a timestamp is not
valid in the specified time zone (e.g. due to a transition from
or to DST time)
- 'coerce' will return NaT if the timestamp can not be converted
to the specified time zone
.. versionadded:: 0.19.0
Returns
-------
result : same type as self
Array/Index converted to the specified time zone.
Raises
------
TypeError
If the Datetime Array/Index is tz-aware and tz is not None.
See Also
--------
DatetimeIndex.tz_convert : Convert tz-aware DatetimeIndex from
one time zone to another.
Examples
--------
>>> tz_naive = pd.date_range('2018-03-01 09:00', periods=3)
>>> tz_naive
DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
'2018-03-03 09:00:00'],
dtype='datetime64[ns]', freq='D')
Localize DatetimeIndex in US/Eastern time zone:
>>> tz_aware = tz_naive.tz_localize(tz='US/Eastern')
>>> tz_aware
DatetimeIndex(['2018-03-01 09:00:00-05:00',
'2018-03-02 09:00:00-05:00',
'2018-03-03 09:00:00-05:00'],
dtype='datetime64[ns, US/Eastern]', freq='D')
With the ``tz=None``, we can remove the time zone information
while keeping the local time (not converted to UTC):
>>> tz_aware.tz_localize(None)
DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
'2018-03-03 09:00:00'],
dtype='datetime64[ns]', freq='D')
"""
if self.tz is not None:
if tz is None:
new_dates = conversion.tz_convert(self.asi8, 'UTC', self.tz)
else:
raise TypeError("Already tz-aware, use tz_convert to convert.")
else:
tz = timezones.maybe_get_tz(tz)
# Convert to UTC
new_dates = conversion.tz_localize_to_utc(self.asi8,
tz,
ambiguous=ambiguous,
errors=errors)
new_dates = new_dates.view(_NS_DTYPE)
return self._shallow_copy(new_dates, tz=tz)
def test_append_with_timezones_dateutil(setup_path):
from datetime import timedelta
# use maybe_get_tz instead of dateutil.tz.gettz to handle the windows
# filename issues.
from pandas._libs.tslibs.timezones import maybe_get_tz
gettz = lambda x: maybe_get_tz("dateutil/" + x)
# as columns
with ensure_clean_store(setup_path) as store:
_maybe_remove(store, "df_tz")
df = DataFrame(
dict(A=[
Timestamp("20130102 2:00:00", tz=gettz("US/Eastern")) +
timedelta(hours=1) * i for i in range(5)
]))
store.append("df_tz", df, data_columns=["A"])
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
# select with tz aware
expected = df[df.A >= df.A[3]]
result = store.select("df_tz", where="A>=df.A[3]")
_compare_with_tz(result, expected)
# ensure we include dates in DST and STD time here.
_maybe_remove(store, "df_tz")
df = DataFrame(
dict(
A=Timestamp("20130102", tz=gettz("US/Eastern")),
B=Timestamp("20130603", tz=gettz("US/Eastern")),
),
index=range(5),
)
store.append("df_tz", df)
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
df = DataFrame(
dict(
A=Timestamp("20130102", tz=gettz("US/Eastern")),
B=Timestamp("20130102", tz=gettz("EET")),
),
index=range(5),
)
with pytest.raises(ValueError):
store.append("df_tz", df)
# this is ok
_maybe_remove(store, "df_tz")
store.append("df_tz", df, data_columns=["A", "B"])
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
# can't append with diff timezone
df = DataFrame(
dict(
A=Timestamp("20130102", tz=gettz("US/Eastern")),
B=Timestamp("20130102", tz=gettz("CET")),
),
index=range(5),
)
with pytest.raises(ValueError):
store.append("df_tz", df)
# as index
with ensure_clean_store(setup_path) as store:
# GH 4098 example
df = DataFrame(
dict(A=Series(
range(3),
index=date_range(
"2000-1-1", periods=3, freq="H", tz=gettz("US/Eastern")),
)))
_maybe_remove(store, "df")
store.put("df", df)
result = store.select("df")
tm.assert_frame_equal(result, df)
_maybe_remove(store, "df")
store.append("df", df)
result = store.select("df")
tm.assert_frame_equal(result, df)
def test_tz_convert_corner(arr):
result = tzconversion.tz_convert_from_utc(
arr, timezones.maybe_get_tz("Asia/Tokyo"))
tm.assert_numpy_array_equal(result, arr)
def test_append_with_timezones_dateutil(setup_path):
from datetime import timedelta
# use maybe_get_tz instead of dateutil.tz.gettz to handle the windows
# filename issues.
from pandas._libs.tslibs.timezones import maybe_get_tz
gettz = lambda x: maybe_get_tz("dateutil/" + x)
# as columns
with ensure_clean_store(setup_path) as store:
_maybe_remove(store, "df_tz")
df = DataFrame(
{
"A": [
Timestamp("20130102 2:00:00", tz=gettz("US/Eastern"))
+ timedelta(hours=1) * i
for i in range(5)
]
}
)
store.append("df_tz", df, data_columns=["A"])
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
# select with tz aware
expected = df[df.A >= df.A[3]]
result = store.select("df_tz", where="A>=df.A[3]")
_compare_with_tz(result, expected)
# ensure we include dates in DST and STD time here.
_maybe_remove(store, "df_tz")
df = DataFrame(
{
"A": Timestamp("20130102", tz=gettz("US/Eastern")),
"B": Timestamp("20130603", tz=gettz("US/Eastern")),
},
index=range(5),
)
store.append("df_tz", df)
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
df = DataFrame(
{
"A": Timestamp("20130102", tz=gettz("US/Eastern")),
"B": Timestamp("20130102", tz=gettz("EET")),
},
index=range(5),
)
msg = (
r"invalid info for \[values_block_1\] for \[tz\], "
r"existing_value \[dateutil/.*US/Eastern\] "
r"conflicts with new value \[dateutil/.*EET\]"
)
with pytest.raises(ValueError, match=msg):
store.append("df_tz", df)
# this is ok
_maybe_remove(store, "df_tz")
store.append("df_tz", df, data_columns=["A", "B"])
result = store["df_tz"]
_compare_with_tz(result, df)
tm.assert_frame_equal(result, df)
# can't append with diff timezone
df = DataFrame(
{
"A": Timestamp("20130102", tz=gettz("US/Eastern")),
"B": Timestamp("20130102", tz=gettz("CET")),
},
index=range(5),
)
msg = (
r"invalid info for \[B\] for \[tz\], "
r"existing_value \[dateutil/.*EET\] "
r"conflicts with new value \[dateutil/.*CET\]"
)
with pytest.raises(ValueError, match=msg):
store.append("df_tz", df)
# as index
with ensure_clean_store(setup_path) as store:
dti = date_range("2000-1-1", periods=3, freq="H", tz=gettz("US/Eastern"))
dti = dti._with_freq(None) # freq doesnt round-trip
# GH 4098 example
df = DataFrame({"A": Series(range(3), index=dti)})
_maybe_remove(store, "df")
store.put("df", df)
result = store.select("df")
tm.assert_frame_equal(result, df)
_maybe_remove(store, "df")
store.append("df", df)
result = store.select("df")
tm.assert_frame_equal(result, df)
def test_tzlocal_maybe_get_tz():
# see gh-13583
tz = timezones.maybe_get_tz('tzlocal()')
assert tz == dateutil.tz.tzlocal()
def test_date_range_timezone_str_argument(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
result = date_range('1/1/2000', periods=10, tz=tzstr)
expected = date_range('1/1/2000', periods=10, tz=tz)
tm.assert_index_equal(result, expected)
def test_tz_convert_corner(arr):
result = conversion.tz_convert(arr, timezones.maybe_get_tz("US/Eastern"),
timezones.maybe_get_tz("Asia/Tokyo"))
tm.assert_numpy_array_equal(result, arr)
def _compare_with_tz(a, b):
tm.assert_frame_equal(a, b)
# compare the zones on each element
for c in a.columns:
for i in a.index:
a_e = a.loc[i, c]
b_e = b.loc[i, c]
if not (a_e == b_e and a_e.tz == b_e.tz):
raise AssertionError(f"invalid tz comparison [{a_e}] [{b_e}]")
# use maybe_get_tz instead of dateutil.tz.gettz to handle the windows
# filename issues.
gettz_dateutil = lambda x: maybe_get_tz("dateutil/" + x)
gettz_pytz = lambda x: x
@pytest.mark.parametrize("gettz", [gettz_dateutil, gettz_pytz])
def test_append_with_timezones(setup_path, gettz):
# as columns
# Single-tzinfo, no DST transition
df_est = DataFrame(
{
"A": [
Timestamp("20130102 2:00:00", tz=gettz("US/Eastern"))
+ timedelta(hours=1) * i
for i in range(5)
]
def tz_convert(self, tz):
"""
Convert tz-aware Datetime Array/Index from one time zone to another.
Parameters
----------
tz : string, pytz.timezone, dateutil.tz.tzfile or None
Time zone for time. Corresponding timestamps would be converted
to this time zone of the Datetime Array/Index. A `tz` of None will
convert to UTC and remove the timezone information.
Returns
-------
normalized : same type as self
Raises
------
TypeError
If Datetime Array/Index is tz-naive.
See Also
--------
DatetimeIndex.tz : A timezone that has a variable offset from UTC
DatetimeIndex.tz_localize : Localize tz-naive DatetimeIndex to a
given time zone, or remove timezone from a tz-aware DatetimeIndex.
Examples
--------
With the `tz` parameter, we can change the DatetimeIndex
to other time zones:
>>> dti = pd.DatetimeIndex(start='2014-08-01 09:00',
... freq='H', periods=3, tz='Europe/Berlin')
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='H')
>>> dti.tz_convert('US/Central')
DatetimeIndex(['2014-08-01 02:00:00-05:00',
'2014-08-01 03:00:00-05:00',
'2014-08-01 04:00:00-05:00'],
dtype='datetime64[ns, US/Central]', freq='H')
With the ``tz=None``, we can remove the timezone (after converting
to UTC if necessary):
>>> dti = pd.DatetimeIndex(start='2014-08-01 09:00',freq='H',
... periods=3, tz='Europe/Berlin')
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='H')
>>> dti.tz_convert(None)
DatetimeIndex(['2014-08-01 07:00:00',
'2014-08-01 08:00:00',
'2014-08-01 09:00:00'],
dtype='datetime64[ns]', freq='H')
"""
tz = timezones.maybe_get_tz(tz)
if self.tz is None:
# tz naive, use tz_localize
raise TypeError('Cannot convert tz-naive timestamps, use '
'tz_localize to localize')
# No conversion since timestamps are all UTC to begin with
return self._shallow_copy(tz=tz)
def ts_tz(self, ts, tz_aware_fixture):
tz = maybe_get_tz(tz_aware_fixture)
return Timestamp._from_value_and_reso(ts.value, ts._reso, tz)
def test_is_utc(utc_fixture):
tz = timezones.maybe_get_tz(utc_fixture)
assert timezones.is_utc(tz)
def tz_convert(self, tz):
"""
Convert tz-aware Datetime Array/Index from one time zone to another.
Parameters
----------
tz : string, pytz.timezone, dateutil.tz.tzfile or None
Time zone for time. Corresponding timestamps would be converted
to this time zone of the Datetime Array/Index. A `tz` of None will
convert to UTC and remove the timezone information.
Returns
-------
normalized : same type as self
Raises
------
TypeError
If Datetime Array/Index is tz-naive.
See Also
--------
DatetimeIndex.tz : A timezone that has a variable offset from UTC
DatetimeIndex.tz_localize : Localize tz-naive DatetimeIndex to a
given time zone, or remove timezone from a tz-aware DatetimeIndex.
Examples
--------
With the `tz` parameter, we can change the DatetimeIndex
to other time zones:
>>> dti = pd.DatetimeIndex(start='2014-08-01 09:00',
... freq='H', periods=3, tz='Europe/Berlin')
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='H')
>>> dti.tz_convert('US/Central')
DatetimeIndex(['2014-08-01 02:00:00-05:00',
'2014-08-01 03:00:00-05:00',
'2014-08-01 04:00:00-05:00'],
dtype='datetime64[ns, US/Central]', freq='H')
With the ``tz=None``, we can remove the timezone (after converting
to UTC if necessary):
>>> dti = pd.DatetimeIndex(start='2014-08-01 09:00',freq='H',
... periods=3, tz='Europe/Berlin')
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='H')
>>> dti.tz_convert(None)
DatetimeIndex(['2014-08-01 07:00:00',
'2014-08-01 08:00:00',
'2014-08-01 09:00:00'],
dtype='datetime64[ns]', freq='H')
"""
tz = timezones.maybe_get_tz(tz)
if self.tz is None:
# tz naive, use tz_localize
raise TypeError('Cannot convert tz-naive timestamps, use '
'tz_localize to localize')
# No conversion since timestamps are all UTC to begin with
return self._shallow_copy(tz=tz)
def test_tz_convert_corner(self, arr):
result = conversion.tz_convert(arr,
timezones.maybe_get_tz('US/Eastern'),
timezones.maybe_get_tz('Asia/Tokyo'))
tm.assert_numpy_array_equal(result, arr)
def _check_offsetfunc_works(self,
offset,
funcname,
dt,
expected,
normalize=False):
if normalize and issubclass(offset, Tick):
# normalize=True disallowed for Tick subclasses GH#21427
return
offset_s = self._get_offset(offset, normalize=normalize)
func = getattr(offset_s, funcname)
result = func(dt)
assert isinstance(result, Timestamp)
assert result == expected
result = func(Timestamp(dt))
assert isinstance(result, Timestamp)
assert result == expected
# see gh-14101
exp_warning = None
ts = Timestamp(dt) + Nano(5)
if (type(offset_s).__name__ == "DateOffset"
and (funcname in ["apply", "_apply"] or normalize)
and ts.nanosecond > 0):
exp_warning = UserWarning
# test nanosecond is preserved
with tm.assert_produces_warning(exp_warning):
result = func(ts)
if exp_warning is None and funcname == "_apply":
# GH#44522
# Check in this particular case to avoid headaches with
# testing for multiple warnings produced by the same call.
with tm.assert_produces_warning(FutureWarning,
match="apply is deprecated"):
res2 = offset_s.apply(ts)
assert type(res2) is type(result)
assert res2 == result
assert isinstance(result, Timestamp)
if normalize is False:
assert result == expected + Nano(5)
else:
assert result == expected
if isinstance(dt, np.datetime64):
# test tz when input is datetime or Timestamp
return
for tz in self.timezones:
expected_localize = expected.tz_localize(tz)
tz_obj = timezones.maybe_get_tz(tz)
dt_tz = conversion.localize_pydatetime(dt, tz_obj)
result = func(dt_tz)
assert isinstance(result, Timestamp)
assert result == expected_localize
result = func(Timestamp(dt, tz=tz))
assert isinstance(result, Timestamp)
assert result == expected_localize
# see gh-14101
exp_warning = None
ts = Timestamp(dt, tz=tz) + Nano(5)
if (type(offset_s).__name__ == "DateOffset"
and (funcname in ["apply", "_apply"] or normalize)
and ts.nanosecond > 0):
exp_warning = UserWarning
# test nanosecond is preserved
with tm.assert_produces_warning(exp_warning):
result = func(ts)
assert isinstance(result, Timestamp)
if normalize is False:
assert result == expected_localize + Nano(5)
else:
assert result == expected_localize
def _check_offsetfunc_works(self,
offset,
funcname,
dt,
expected,
normalize=False):
if normalize and issubclass(offset, Tick):
# normalize=True disallowed for Tick subclasses GH#21427
return
offset_s = self._get_offset(offset, normalize=normalize)
func = getattr(offset_s, funcname)
result = func(dt)
assert isinstance(result, Timestamp)
assert result == expected
result = func(Timestamp(dt))
assert isinstance(result, Timestamp)
assert result == expected
# see gh-14101
exp_warning = None
ts = Timestamp(dt) + Nano(5)
if (type(offset_s).__name__ == "DateOffset"
and (funcname == "apply" or normalize) and ts.nanosecond > 0):
exp_warning = UserWarning
# test nanosecond is preserved
with tm.assert_produces_warning(exp_warning):
result = func(ts)
assert isinstance(result, Timestamp)
if normalize is False:
assert result == expected + Nano(5)
else:
assert result == expected
if isinstance(dt, np.datetime64):
# test tz when input is datetime or Timestamp
return
for tz in self.timezones:
expected_localize = expected.tz_localize(tz)
tz_obj = timezones.maybe_get_tz(tz)
dt_tz = conversion.localize_pydatetime(dt, tz_obj)
result = func(dt_tz)
assert isinstance(result, Timestamp)
assert result == expected_localize
result = func(Timestamp(dt, tz=tz))
assert isinstance(result, Timestamp)
assert result == expected_localize
# see gh-14101
exp_warning = None
ts = Timestamp(dt, tz=tz) + Nano(5)
if (type(offset_s).__name__ == "DateOffset"
and (funcname == "apply" or normalize)
and ts.nanosecond > 0):
exp_warning = UserWarning
# test nanosecond is preserved
with tm.assert_produces_warning(exp_warning):
result = func(ts)
assert isinstance(result, Timestamp)
if normalize is False:
assert result == expected_localize + Nano(5)
else:
assert result == expected_localize
def test_date_range_timezone_str_argument(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
result = date_range("1/1/2000", periods=10, tz=tzstr)
expected = date_range("1/1/2000", periods=10, tz=tz)
tm.assert_index_equal(result, expected)
