class TimestampOps(object):
goal_time = 0.2
def setup(self):
self.ts = Timestamp('2017-08-25 08:16:14')
self.ts_tz = Timestamp('2017-08-25 08:16:14', tz='US/Eastern')
dt = datetime.datetime(2016, 3, 27, 1)
self.tzinfo = pytz.timezone('CET').localize(dt, is_dst=False).tzinfo
self.ts2 = Timestamp(dt)
def time_replace_tz(self):
self.ts.replace(tzinfo=pytz.timezone('US/Eastern'))
def time_replace_across_dst(self):
self.ts2.replace(tzinfo=self.tzinfo)
def time_replace_None(self):
self.ts_tz.replace(tzinfo=None)
def time_to_pydatetime(self):
self.ts.to_pydatetime()
def time_to_pydatetime_tz(self):
self.ts_tz.to_pydatetime()
def test_timestamp_tz_localize_nonexistent_raise(self, tz):
# GH 8917
ts = Timestamp('2015-03-29 02:20:00')
with pytest.raises(pytz.NonExistentTimeError):
ts.tz_localize(tz, nonexistent='raise')
with pytest.raises(ValueError):
ts.tz_localize(tz, nonexistent='foo')
def test_datetime_name_accessors(self, time_locale):
# Test Monday -> Sunday and January -> December, in that sequence
if time_locale is None:
# If the time_locale is None, day-name and month_name should
# return the english attributes
expected_days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday',
'Friday', 'Saturday', 'Sunday']
expected_months = ['January', 'February', 'March', 'April', 'May',
'June', 'July', 'August', 'September',
'October', 'November', 'December']
else:
with tm.set_locale(time_locale, locale.LC_TIME):
expected_days = calendar.day_name[:]
expected_months = calendar.month_name[1:]
# GH#11128
dti = pd.date_range(freq='D', start=datetime(1998, 1, 1),
periods=365)
english_days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday',
'Friday', 'Saturday', 'Sunday']
for day, name, eng_name in zip(range(4, 11),
expected_days,
english_days):
name = name.capitalize()
assert dti.weekday_name[day] == eng_name
assert dti.day_name(locale=time_locale)[day] == name
ts = Timestamp(datetime(2016, 4, day))
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
assert ts.weekday_name == eng_name
assert ts.day_name(locale=time_locale) == name
dti = dti.append(DatetimeIndex([pd.NaT]))
assert np.isnan(dti.day_name(locale=time_locale)[-1])
ts = Timestamp(pd.NaT)
assert np.isnan(ts.day_name(locale=time_locale))
# GH#12805
dti = pd.date_range(freq='M', start='2012', end='2013')
result = dti.month_name(locale=time_locale)
expected = Index([month.capitalize() for month in expected_months])
# work around different normalization schemes
# https://github.com/pandas-dev/pandas/issues/22342
if not compat.PY2:
result = result.str.normalize("NFD")
expected = expected.str.normalize("NFD")
tm.assert_index_equal(result, expected)
for date, expected in zip(dti, expected_months):
result = date.month_name(locale=time_locale)
expected = expected.capitalize()
if not compat.PY2:
result = unicodedata.normalize("NFD", result)
expected = unicodedata.normalize("NFD", result)
assert result == expected
dti = dti.append(DatetimeIndex([pd.NaT]))
assert np.isnan(dti.month_name(locale=time_locale)[-1])
class TimestampProperties:
_tzs = [None, pytz.timezone('Europe/Amsterdam'), pytz.UTC,
dateutil.tz.tzutc()]
_freqs = [None, 'B']
params = [_tzs, _freqs]
param_names = ['tz', 'freq']
def setup(self, tz, freq):
self.ts = Timestamp('2017-08-25 08:16:14', tzinfo=tz, freq=freq)
def time_tz(self, tz, freq):
self.ts.tz
def time_dayofweek(self, tz, freq):
self.ts.dayofweek
def time_weekday_name(self, tz, freq):
self.ts.day_name
def time_dayofyear(self, tz, freq):
self.ts.dayofyear
def time_week(self, tz, freq):
self.ts.week
def time_quarter(self, tz, freq):
self.ts.quarter
def time_days_in_month(self, tz, freq):
self.ts.days_in_month
def time_freqstr(self, tz, freq):
self.ts.freqstr
def time_is_month_start(self, tz, freq):
self.ts.is_month_start
def time_is_month_end(self, tz, freq):
self.ts.is_month_end
def time_is_quarter_start(self, tz, freq):
self.ts.is_quarter_start
def time_is_quarter_end(self, tz, freq):
self.ts.is_quarter_end
def time_is_year_start(self, tz, freq):
self.ts.is_year_start
def time_is_year_end(self, tz, freq):
self.ts.is_year_end
def time_is_leap_year(self, tz, freq):
self.ts.is_leap_year
def time_microsecond(self, tz, freq):
self.ts.microsecond
def time_month_name(self, tz, freq):
self.ts.month_name()
def test_timestamp_tz_localize(self, tz):
stamp = Timestamp('3/11/2012 04:00')
result = stamp.tz_localize(tz)
expected = Timestamp('3/11/2012 04:00', tz=tz)
assert result.hour == expected.hour
assert result == expected
def test_replace_preserves_nanos(self, tz_aware_fixture):
tz = tz_aware_fixture
# GH#14621, GH#7825
ts = Timestamp('2016-01-01 09:00:00.000000123', tz=tz)
result = ts.replace(hour=0)
expected = Timestamp('2016-01-01 00:00:00.000000123', tz=tz)
assert result == expected
def test_timestamp_to_datetime_tzoffset(self):
#tzoffset
from dateutil.tz import tzoffset
tzinfo = tzoffset(None, 7200)
expected = Timestamp('3/11/2012 04:00', tz=tzinfo)
result = Timestamp(expected.to_datetime())
self.assertEquals(expected, result)
def setup(self):
self.ts = Timestamp('2017-08-25 08:16:14')
self.ts_tz = Timestamp('2017-08-25 08:16:14', tz='US/Eastern')
dt = datetime.datetime(2016, 3, 27, 1)
self.tzinfo = pytz.timezone('CET').localize(dt, is_dst=False).tzinfo
self.ts2 = Timestamp(dt)
def test_tz_localize_errors_invalid_arg(self):
# GH 22644
tz = 'Europe/Warsaw'
ts = Timestamp('2015-03-29 02:00:00')
with pytest.raises(ValueError):
with tm.assert_produces_warning(FutureWarning):
ts.tz_localize(tz, errors='foo')
def test_constructor_strptime(self):
# GH25016
# Test support for Timestamp.strptime
fmt = '%Y%m%d-%H%M%S-%f%z'
ts = '20190129-235348-000001+0000'
with pytest.raises(NotImplementedError):
Timestamp.strptime(ts, fmt)
def test_replace_aware(self, tz):
# GH#14621, GH#7825
# replacing datetime components with and w/o presence of a timezone
ts = Timestamp('2016-01-01 09:00:00', tz=tz)
result = ts.replace(hour=0)
expected = Timestamp('2016-01-01 00:00:00', tz=tz)
assert result == expected
def test_names(self, data, time_locale):
# GH 17354
# Test .weekday_name, .day_name(), .month_name
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
assert data.weekday_name == 'Monday'
if time_locale is None:
expected_day = 'Monday'
expected_month = 'August'
else:
with tm.set_locale(time_locale, locale.LC_TIME):
expected_day = calendar.day_name[0].capitalize()
expected_month = calendar.month_name[8].capitalize()
result_day = data.day_name(time_locale)
result_month = data.month_name(time_locale)
# Work around https://github.com/pandas-dev/pandas/issues/22342
# different normalizations
if not PY2:
expected_day = unicodedata.normalize("NFD", expected_day)
expected_month = unicodedata.normalize("NFD", expected_month)
result_day = unicodedata.normalize("NFD", result_day,)
result_month = unicodedata.normalize("NFD", result_month)
assert result_day == expected_day
assert result_month == expected_month
# Test NaT
nan_ts = Timestamp(NaT)
assert np.isnan(nan_ts.day_name(time_locale))
assert np.isnan(nan_ts.month_name(time_locale))
def test_to_period_tz_warning(self):
# GH#21333 make sure a warning is issued when timezone
# info is lost
ts = Timestamp('2009-04-15 16:17:18', tz='US/Eastern')
with tm.assert_produces_warning(UserWarning):
# warning that timezone info will be lost
ts.to_period('D')
def test_timestamp_tz_localize_explicit(self):
stamp = Timestamp("3/11/2012 04:00")
result = stamp.tz_localize(self.tz("US/Eastern"))
expected = Timestamp("3/11/2012 04:00", tz=self.tz("US/Eastern"))
self.assertEqual(result.hour, expected.hour)
self.assertEqual(result, expected)
def test_cant_compare_tz_naive_w_aware(self, utc_fixture):
# see GH#1404
a = Timestamp('3/12/2012')
b = Timestamp('3/12/2012', tz=utc_fixture)
with pytest.raises(TypeError):
a == b
with pytest.raises(TypeError):
a != b
with pytest.raises(TypeError):
a < b
with pytest.raises(TypeError):
a <= b
with pytest.raises(TypeError):
a > b
with pytest.raises(TypeError):
a >= b
with pytest.raises(TypeError):
b == a
with pytest.raises(TypeError):
b != a
with pytest.raises(TypeError):
b < a
with pytest.raises(TypeError):
b <= a
with pytest.raises(TypeError):
b > a
with pytest.raises(TypeError):
b >= a
assert not a == b.to_pydatetime()
assert not a.to_pydatetime() == b
def test_timestamp_tz_localize(self):
stamp = Timestamp('3/11/2012 04:00')
result = stamp.tz_localize('US/Eastern')
expected = Timestamp('3/11/2012 04:00', tz='US/Eastern')
self.assertEquals(result.hour, expected.hour)
self.assertEquals(result, expected)
class TimestampAcrossDst:
def setup(self):
dt = datetime.datetime(2016, 3, 27, 1)
self.tzinfo = pytz.timezone('CET').localize(dt, is_dst=False).tzinfo
self.ts2 = Timestamp(dt)
def time_replace_across_dst(self):
self.ts2.replace(tzinfo=self.tzinfo)
def test_tz_convert_roundtrip(self, stamp, tz):
ts = Timestamp(stamp, tz='UTC')
converted = ts.tz_convert(tz)
reset = converted.tz_convert(None)
assert reset == Timestamp(stamp)
assert reset.tzinfo is None
assert reset == converted.tz_convert('UTC').tz_localize(None)
def test_astimezone(self, tzstr):
# astimezone is an alias for tz_convert, so keep it with
# the tz_convert tests
utcdate = Timestamp('3/11/2012 22:00', tz='UTC')
expected = utcdate.tz_convert(tzstr)
result = utcdate.astimezone(tzstr)
assert expected == result
assert isinstance(result, Timestamp)
def test_timestamp_tz_localize_nonexistent_shift_invalid(self, offset,
tz_type):
# GH 8917, 24466
tz = tz_type + 'Europe/Warsaw'
ts = Timestamp('2015-03-29 02:20:00')
msg = "The provided timedelta will relocalize on a nonexistent time"
with pytest.raises(ValueError, match=msg):
ts.tz_localize(tz, nonexistent=timedelta(seconds=offset))
def test_replace_dst_fold(self, fold, tz):
# GH 25017
d = datetime(2019, 10, 27, 2, 30)
ts = Timestamp(d, tz=tz)
result = ts.replace(hour=1, fold=fold)
expected = Timestamp(datetime(2019, 10, 27, 1, 30)).tz_localize(
tz, ambiguous=not fold
)
assert result == expected
def test_replace_multiple(self, tz):
# GH#14621, GH#7825
# replacing datetime components with and w/o presence of a timezone
# test all
ts = Timestamp('2016-01-01 09:00:00.000000123', tz=tz)
result = ts.replace(year=2015, month=2, day=2, hour=0, minute=5,
second=5, microsecond=5, nanosecond=5)
expected = Timestamp('2015-02-02 00:05:05.000005005', tz=tz)
assert result == expected
def test_tz_localize_errors_coerce(self):
# GH 22644
# make sure errors='coerce' gets mapped correctly to nonexistent
tz = 'Europe/Warsaw'
ts = Timestamp('2015-03-29 02:00:00')
with tm.assert_produces_warning(FutureWarning):
result = ts.tz_localize(tz, errors='coerce')
expected = ts.tz_localize(tz, nonexistent='NaT')
assert result is expected
def test_round_tzaware(self):
dt = Timestamp('20130101 09:10:11', tz='US/Eastern')
result = dt.round('D')
expected = Timestamp('20130101', tz='US/Eastern')
assert result == expected
dt = Timestamp('20130101 09:10:11', tz='US/Eastern')
result = dt.round('s')
assert result == dt
def test_to_pydatetime_nonzero_nano(self):
ts = Timestamp('2011-01-01 9:00:00.123456789')
# Warn the user of data loss (nanoseconds).
with tm.assert_produces_warning(UserWarning,
check_stacklevel=False):
expected = datetime(2011, 1, 1, 9, 0, 0, 123456)
result = ts.to_pydatetime()
assert result == expected
def __init__(self, site, start, end, savepath='data'):
self.site = site
self.start = Timestamp(start)
self.end = Timestamp(end)
self.savepath = Path('.' or savepath)
self._daily_json = None
self._insta_json = None
self._daily_data = None
self._insta_data = None
def test_tz_localize_roundtrip(self, stamp, tz):
ts = Timestamp(stamp)
localized = ts.tz_localize(tz)
assert localized == Timestamp(stamp, tz=tz)
with pytest.raises(TypeError):
localized.tz_localize(tz)
reset = localized.tz_localize(None)
assert reset == ts
assert reset.tzinfo is None
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 pandas import DateOffset
>>> from dateutil.relativedelta import MO
>>> USMemorialDay = Holiday('MemorialDay', month=5, day=24,
offset=DateOffset(weekday=MO(1)))
>>> USLaborDay = Holiday('Labor Day', month=9, day=1,
offset=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 test_timestamp_tz_localize_nonexistent_shift(self, start_ts, tz,
end_ts, shift,
tz_type):
# GH 8917, 24466
tz = tz_type + tz
if isinstance(shift, str):
shift = 'shift_' + shift
ts = Timestamp(start_ts)
result = ts.tz_localize(tz, nonexistent=shift)
expected = Timestamp(end_ts).tz_localize(tz)
assert result == expected
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())
class TestDatetimeIndex:
@pytest.mark.parametrize("dt_cls", [DatetimeIndex, DatetimeArray._from_sequence])
def test_freq_validation_with_nat(self, dt_cls):
# GH#11587 make sure we get a useful error message when generate_range
# raises
msg = (
"Inferred frequency None from passed values does not conform "
"to passed frequency D"
)
with pytest.raises(ValueError, match=msg):
dt_cls([pd.NaT, pd.Timestamp("2011-01-01")], freq="D")
with pytest.raises(ValueError, match=msg):
dt_cls([pd.NaT, pd.Timestamp("2011-01-01").value], freq="D")
def test_categorical_preserves_tz(self):
# GH#18664 retain tz when going DTI-->Categorical-->DTI
# TODO: parametrize over DatetimeIndex/DatetimeArray
# once CategoricalIndex(DTA) works
dti = pd.DatetimeIndex(
[pd.NaT, "2015-01-01", "1999-04-06 15:14:13", "2015-01-01"], tz="US/Eastern"
)
ci = pd.CategoricalIndex(dti)
carr = pd.Categorical(dti)
cser = pd.Series(ci)
for obj in [ci, carr, cser]:
result = pd.DatetimeIndex(obj)
tm.assert_index_equal(result, dti)
def test_dti_with_period_data_raises(self):
# GH#23675
data = pd.PeriodIndex(["2016Q1", "2016Q2"], freq="Q")
with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
DatetimeIndex(data)
with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
to_datetime(data)
with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
DatetimeIndex(period_array(data))
with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
to_datetime(period_array(data))
def test_dti_with_timedelta64_data_raises(self):
# GH#23675 deprecated, enforrced in GH#29794
data = np.array([0], dtype="m8[ns]")
msg = r"timedelta64\[ns\] cannot be converted to datetime64"
with pytest.raises(TypeError, match=msg):
DatetimeIndex(data)
with pytest.raises(TypeError, match=msg):
to_datetime(data)
with pytest.raises(TypeError, match=msg):
DatetimeIndex(pd.TimedeltaIndex(data))
with pytest.raises(TypeError, match=msg):
to_datetime(pd.TimedeltaIndex(data))
def test_construction_caching(self):
df = pd.DataFrame(
{
"dt": pd.date_range("20130101", periods=3),
"dttz": pd.date_range("20130101", periods=3, tz="US/Eastern"),
"dt_with_null": [
pd.Timestamp("20130101"),
pd.NaT,
pd.Timestamp("20130103"),
],
"dtns": pd.date_range("20130101", periods=3, freq="ns"),
}
)
assert df.dttz.dtype.tz.zone == "US/Eastern"
@pytest.mark.parametrize(
"kwargs",
[{"tz": "dtype.tz"}, {"dtype": "dtype"}, {"dtype": "dtype", "tz": "dtype.tz"}],
)
def test_construction_with_alt(self, kwargs, tz_aware_fixture):
tz = tz_aware_fixture
i = pd.date_range("20130101", periods=5, freq="H", tz=tz)
kwargs = {key: attrgetter(val)(i) for key, val in kwargs.items()}
result = DatetimeIndex(i, **kwargs)
tm.assert_index_equal(i, result)
@pytest.mark.parametrize(
"kwargs",
[{"tz": "dtype.tz"}, {"dtype": "dtype"}, {"dtype": "dtype", "tz": "dtype.tz"}],
)
def test_construction_with_alt_tz_localize(self, kwargs, tz_aware_fixture):
tz = tz_aware_fixture
i = pd.date_range("20130101", periods=5, freq="H", tz=tz)
kwargs = {key: attrgetter(val)(i) for key, val in kwargs.items()}
if "tz" in kwargs:
result = DatetimeIndex(i.asi8, tz="UTC").tz_convert(kwargs["tz"])
expected = DatetimeIndex(i, **kwargs)
tm.assert_index_equal(result, expected)
# localize into the provided tz
i2 = DatetimeIndex(i.tz_localize(None).asi8, tz="UTC")
expected = i.tz_localize(None).tz_localize("UTC")
tm.assert_index_equal(i2, expected)
# incompat tz/dtype
msg = "cannot supply both a tz and a dtype with a tz"
with pytest.raises(ValueError, match=msg):
DatetimeIndex(i.tz_localize(None).asi8, dtype=i.dtype, tz="US/Pacific")
def test_construction_index_with_mixed_timezones(self):
# gh-11488: no tz results in DatetimeIndex
result = Index([Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx")
exp = DatetimeIndex(
[Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx"
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# same tz results in DatetimeIndex
result = Index(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="Asia/Tokyo"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-01-02 10:00")],
tz="Asia/Tokyo",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# same tz results in DatetimeIndex (DST)
result = Index(
[
Timestamp("2011-01-01 10:00", tz="US/Eastern"),
Timestamp("2011-08-01 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-08-01 10:00")],
tz="US/Eastern",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# Different tz results in Index(dtype=object)
result = Index(
[
Timestamp("2011-01-01 10:00"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
Timestamp("2011-01-01 10:00"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
result = Index(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
# length = 1
result = Index([Timestamp("2011-01-01")], name="idx")
exp = DatetimeIndex([Timestamp("2011-01-01")], name="idx")
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# length = 1 with tz
result = Index([Timestamp("2011-01-01 10:00", tz="Asia/Tokyo")], name="idx")
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00")], tz="Asia/Tokyo", name="idx"
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
def test_construction_index_with_mixed_timezones_with_NaT(self):
# see gh-11488
result = Index(
[pd.NaT, Timestamp("2011-01-01"), pd.NaT, Timestamp("2011-01-02")],
name="idx",
)
exp = DatetimeIndex(
[pd.NaT, Timestamp("2011-01-01"), pd.NaT, Timestamp("2011-01-02")],
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# Same tz results in DatetimeIndex
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="Asia/Tokyo"),
],
name="idx",
)
exp = DatetimeIndex(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00"),
],
tz="Asia/Tokyo",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# same tz results in DatetimeIndex (DST)
result = Index(
[
Timestamp("2011-01-01 10:00", tz="US/Eastern"),
pd.NaT,
Timestamp("2011-08-01 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), pd.NaT, Timestamp("2011-08-01 10:00")],
tz="US/Eastern",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# different tz results in Index(dtype=object)
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
# all NaT
result = Index([pd.NaT, pd.NaT], name="idx")
exp = DatetimeIndex([pd.NaT, pd.NaT], name="idx")
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# all NaT with tz
result = Index([pd.NaT, pd.NaT], tz="Asia/Tokyo", name="idx")
exp = DatetimeIndex([pd.NaT, pd.NaT], tz="Asia/Tokyo", name="idx")
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
def test_construction_dti_with_mixed_timezones(self):
# GH 11488 (not changed, added explicit tests)
# no tz results in DatetimeIndex
result = DatetimeIndex(
[Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx"
)
exp = DatetimeIndex(
[Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx"
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# same tz results in DatetimeIndex
result = DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="Asia/Tokyo"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-01-02 10:00")],
tz="Asia/Tokyo",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# same tz results in DatetimeIndex (DST)
result = DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="US/Eastern"),
Timestamp("2011-08-01 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-08-01 10:00")],
tz="US/Eastern",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# tz mismatch affecting to tz-aware raises TypeError/ValueError
with pytest.raises(ValueError):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
msg = "cannot be converted to datetime64"
with pytest.raises(ValueError, match=msg):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="Asia/Tokyo",
name="idx",
)
with pytest.raises(ValueError):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="US/Eastern",
name="idx",
)
with pytest.raises(ValueError, match=msg):
# passing tz should results in DatetimeIndex, then mismatch raises
# TypeError
Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="Asia/Tokyo",
name="idx",
)
def test_construction_base_constructor(self):
arr = [pd.Timestamp("2011-01-01"), pd.NaT, pd.Timestamp("2011-01-03")]
tm.assert_index_equal(pd.Index(arr), pd.DatetimeIndex(arr))
tm.assert_index_equal(pd.Index(np.array(arr)), pd.DatetimeIndex(np.array(arr)))
arr = [np.nan, pd.NaT, pd.Timestamp("2011-01-03")]
tm.assert_index_equal(pd.Index(arr), pd.DatetimeIndex(arr))
tm.assert_index_equal(pd.Index(np.array(arr)), pd.DatetimeIndex(np.array(arr)))
def test_construction_outofbounds(self):
# GH 13663
dates = [
datetime(3000, 1, 1),
datetime(4000, 1, 1),
datetime(5000, 1, 1),
datetime(6000, 1, 1),
]
exp = Index(dates, dtype=object)
# coerces to object
tm.assert_index_equal(Index(dates), exp)
with pytest.raises(OutOfBoundsDatetime):
# can't create DatetimeIndex
DatetimeIndex(dates)
def test_construction_with_ndarray(self):
# GH 5152
dates = [datetime(2013, 10, 7), datetime(2013, 10, 8), datetime(2013, 10, 9)]
data = DatetimeIndex(dates, freq=pd.offsets.BDay()).values
result = DatetimeIndex(data, freq=pd.offsets.BDay())
expected = DatetimeIndex(["2013-10-07", "2013-10-08", "2013-10-09"], freq="B")
tm.assert_index_equal(result, expected)
def test_integer_values_and_tz_interpreted_as_utc(self):
# GH-24559
val = np.datetime64("2000-01-01 00:00:00", "ns")
values = np.array([val.view("i8")])
result = DatetimeIndex(values).tz_localize("US/Central")
expected = pd.DatetimeIndex(["2000-01-01T00:00:00"], tz="US/Central")
tm.assert_index_equal(result, expected)
# but UTC is *not* deprecated.
with tm.assert_produces_warning(None):
result = DatetimeIndex(values, tz="UTC")
expected = pd.DatetimeIndex(["2000-01-01T00:00:00"], tz="US/Central")
def test_constructor_coverage(self):
rng = date_range("1/1/2000", periods=10.5)
exp = date_range("1/1/2000", periods=10)
tm.assert_index_equal(rng, exp)
msg = "periods must be a number, got foo"
with pytest.raises(TypeError, match=msg):
date_range(start="1/1/2000", periods="foo", freq="D")
with pytest.raises(TypeError):
DatetimeIndex("1/1/2000")
# generator expression
gen = (datetime(2000, 1, 1) + timedelta(i) for i in range(10))
result = DatetimeIndex(gen)
expected = DatetimeIndex(
[datetime(2000, 1, 1) + timedelta(i) for i in range(10)]
)
tm.assert_index_equal(result, expected)
# NumPy string array
strings = np.array(["2000-01-01", "2000-01-02", "2000-01-03"])
result = DatetimeIndex(strings)
expected = DatetimeIndex(strings.astype("O"))
tm.assert_index_equal(result, expected)
from_ints = DatetimeIndex(expected.asi8)
tm.assert_index_equal(from_ints, expected)
# string with NaT
strings = np.array(["2000-01-01", "2000-01-02", "NaT"])
result = DatetimeIndex(strings)
expected = DatetimeIndex(strings.astype("O"))
tm.assert_index_equal(result, expected)
from_ints = DatetimeIndex(expected.asi8)
tm.assert_index_equal(from_ints, expected)
# non-conforming
msg = (
"Inferred frequency None from passed values does not conform"
" to passed frequency D"
)
with pytest.raises(ValueError, match=msg):
DatetimeIndex(["2000-01-01", "2000-01-02", "2000-01-04"], freq="D")
msg = (
"Of the four parameters: start, end, periods, and freq, exactly"
" three must be specified"
)
with pytest.raises(ValueError, match=msg):
date_range(start="2011-01-01", freq="b")
with pytest.raises(ValueError, match=msg):
date_range(end="2011-01-01", freq="B")
with pytest.raises(ValueError, match=msg):
date_range(periods=10, freq="D")
@pytest.mark.parametrize("freq", ["AS", "W-SUN"])
def test_constructor_datetime64_tzformat(self, freq):
# see GH#6572: ISO 8601 format results in pytz.FixedOffset
idx = date_range(
"2013-01-01T00:00:00-05:00", "2016-01-01T23:59:59-05:00", freq=freq
)
expected = date_range(
"2013-01-01T00:00:00",
"2016-01-01T23:59:59",
freq=freq,
tz=pytz.FixedOffset(-300),
)
tm.assert_index_equal(idx, expected)
# Unable to use `US/Eastern` because of DST
expected_i8 = date_range(
"2013-01-01T00:00:00", "2016-01-01T23:59:59", freq=freq, tz="America/Lima"
)
tm.assert_numpy_array_equal(idx.asi8, expected_i8.asi8)
idx = date_range(
"2013-01-01T00:00:00+09:00", "2016-01-01T23:59:59+09:00", freq=freq
)
expected = date_range(
"2013-01-01T00:00:00",
"2016-01-01T23:59:59",
freq=freq,
tz=pytz.FixedOffset(540),
)
tm.assert_index_equal(idx, expected)
expected_i8 = date_range(
"2013-01-01T00:00:00", "2016-01-01T23:59:59", freq=freq, tz="Asia/Tokyo"
)
tm.assert_numpy_array_equal(idx.asi8, expected_i8.asi8)
# Non ISO 8601 format results in dateutil.tz.tzoffset
idx = date_range("2013/1/1 0:00:00-5:00", "2016/1/1 23:59:59-5:00", freq=freq)
expected = date_range(
"2013-01-01T00:00:00",
"2016-01-01T23:59:59",
freq=freq,
tz=pytz.FixedOffset(-300),
)
tm.assert_index_equal(idx, expected)
# Unable to use `US/Eastern` because of DST
expected_i8 = date_range(
"2013-01-01T00:00:00", "2016-01-01T23:59:59", freq=freq, tz="America/Lima"
)
tm.assert_numpy_array_equal(idx.asi8, expected_i8.asi8)
idx = date_range("2013/1/1 0:00:00+9:00", "2016/1/1 23:59:59+09:00", freq=freq)
expected = date_range(
"2013-01-01T00:00:00",
"2016-01-01T23:59:59",
freq=freq,
tz=pytz.FixedOffset(540),
)
tm.assert_index_equal(idx, expected)
expected_i8 = date_range(
"2013-01-01T00:00:00", "2016-01-01T23:59:59", freq=freq, tz="Asia/Tokyo"
)
tm.assert_numpy_array_equal(idx.asi8, expected_i8.asi8)
def test_constructor_dtype(self):
# passing a dtype with a tz should localize
idx = DatetimeIndex(
["2013-01-01", "2013-01-02"], dtype="datetime64[ns, US/Eastern]"
)
expected = DatetimeIndex(["2013-01-01", "2013-01-02"]).tz_localize("US/Eastern")
tm.assert_index_equal(idx, expected)
idx = DatetimeIndex(["2013-01-01", "2013-01-02"], tz="US/Eastern")
tm.assert_index_equal(idx, expected)
# if we already have a tz and its not the same, then raise
idx = DatetimeIndex(
["2013-01-01", "2013-01-02"], dtype="datetime64[ns, US/Eastern]"
)
msg = (
"cannot supply both a tz and a timezone-naive dtype"
r" \(i\.e\. datetime64\[ns\]\)"
)
with pytest.raises(ValueError, match=msg):
DatetimeIndex(idx, dtype="datetime64[ns]")
# this is effectively trying to convert tz's
msg = "data is already tz-aware US/Eastern, unable to set specified tz: CET"
with pytest.raises(TypeError, match=msg):
DatetimeIndex(idx, dtype="datetime64[ns, CET]")
msg = "cannot supply both a tz and a dtype with a tz"
with pytest.raises(ValueError, match=msg):
DatetimeIndex(idx, tz="CET", dtype="datetime64[ns, US/Eastern]")
result = DatetimeIndex(idx, dtype="datetime64[ns, US/Eastern]")
tm.assert_index_equal(idx, result)
@pytest.mark.parametrize("dtype", [object, np.int32, np.int64])
def test_constructor_invalid_dtype_raises(self, dtype):
# GH 23986
with pytest.raises(ValueError):
DatetimeIndex([1, 2], dtype=dtype)
def test_constructor_name(self):
idx = date_range(start="2000-01-01", periods=1, freq="A", name="TEST")
assert idx.name == "TEST"
def test_000constructor_resolution(self):
# 2252
t1 = Timestamp((1352934390 * 1000000000) + 1000000 + 1000 + 1)
idx = DatetimeIndex([t1])
assert idx.nanosecond[0] == t1.nanosecond
def test_disallow_setting_tz(self):
# GH 3746
dti = DatetimeIndex(["2010"], tz="UTC")
with pytest.raises(AttributeError):
dti.tz = pytz.timezone("US/Pacific")
@pytest.mark.parametrize(
"tz",
[
None,
"America/Los_Angeles",
pytz.timezone("America/Los_Angeles"),
Timestamp("2000", tz="America/Los_Angeles").tz,
],
)
def test_constructor_start_end_with_tz(self, tz):
# GH 18595
start = Timestamp("2013-01-01 06:00:00", tz="America/Los_Angeles")
end = Timestamp("2013-01-02 06:00:00", tz="America/Los_Angeles")
result = date_range(freq="D", start=start, end=end, tz=tz)
expected = DatetimeIndex(
["2013-01-01 06:00:00", "2013-01-02 06:00:00"], tz="America/Los_Angeles"
)
tm.assert_index_equal(result, expected)
# Especially assert that the timezone is consistent for pytz
assert pytz.timezone("America/Los_Angeles") is result.tz
@pytest.mark.parametrize("tz", ["US/Pacific", "US/Eastern", "Asia/Tokyo"])
def test_constructor_with_non_normalized_pytz(self, tz):
# GH 18595
non_norm_tz = Timestamp("2010", tz=tz).tz
result = DatetimeIndex(["2010"], tz=non_norm_tz)
assert pytz.timezone(tz) is result.tz
def test_constructor_timestamp_near_dst(self):
# GH 20854
ts = [
Timestamp("2016-10-30 03:00:00+0300", tz="Europe/Helsinki"),
Timestamp("2016-10-30 03:00:00+0200", tz="Europe/Helsinki"),
]
result = DatetimeIndex(ts)
expected = DatetimeIndex([ts[0].to_pydatetime(), ts[1].to_pydatetime()])
tm.assert_index_equal(result, expected)
# TODO(GH-24559): Remove the xfail for the tz-aware case.
@pytest.mark.parametrize("klass", [Index, DatetimeIndex])
@pytest.mark.parametrize("box", [np.array, partial(np.array, dtype=object), list])
@pytest.mark.parametrize(
"tz, dtype",
[("US/Pacific", "datetime64[ns, US/Pacific]"), (None, "datetime64[ns]")],
)
def test_constructor_with_int_tz(self, klass, box, tz, dtype):
# GH 20997, 20964
ts = Timestamp("2018-01-01", tz=tz)
result = klass(box([ts.value]), dtype=dtype)
expected = klass([ts])
assert result == expected
# This is the desired future behavior
# Note: this xfail is not strict because the test passes with
# None or any of the UTC variants for tz_naive_fixture
@pytest.mark.xfail(reason="Future behavior", strict=False)
@pytest.mark.filterwarnings("ignore:\\n Passing:FutureWarning")
def test_construction_int_rountrip(self, tz_naive_fixture):
# GH 12619
# TODO(GH-24559): Remove xfail
tz = tz_naive_fixture
result = 1293858000000000000
expected = DatetimeIndex([result], tz=tz).asi8[0]
assert result == expected
def test_construction_from_replaced_timestamps_with_dst(self):
# GH 18785
index = pd.date_range(
pd.Timestamp(2000, 1, 1),
pd.Timestamp(2005, 1, 1),
freq="MS",
tz="Australia/Melbourne",
)
test = pd.DataFrame({"data": range(len(index))}, index=index)
test = test.resample("Y").mean()
result = pd.DatetimeIndex([x.replace(month=6, day=1) for x in test.index])
expected = pd.DatetimeIndex(
[
"2000-06-01 00:00:00",
"2001-06-01 00:00:00",
"2002-06-01 00:00:00",
"2003-06-01 00:00:00",
"2004-06-01 00:00:00",
"2005-06-01 00:00:00",
],
tz="Australia/Melbourne",
)
tm.assert_index_equal(result, expected)
def test_construction_with_tz_and_tz_aware_dti(self):
# GH 23579
dti = date_range("2016-01-01", periods=3, tz="US/Central")
with pytest.raises(TypeError):
DatetimeIndex(dti, tz="Asia/Tokyo")
def test_construction_with_nat_and_tzlocal(self):
tz = dateutil.tz.tzlocal()
result = DatetimeIndex(["2018", "NaT"], tz=tz)
expected = DatetimeIndex([Timestamp("2018", tz=tz), pd.NaT])
tm.assert_index_equal(result, expected)
def test_constructor_no_precision_raises(self):
# GH-24753, GH-24739
msg = "with no precision is not allowed"
with pytest.raises(ValueError, match=msg):
pd.DatetimeIndex(["2000"], dtype="datetime64")
with pytest.raises(ValueError, match=msg):
pd.Index(["2000"], dtype="datetime64")
def test_constructor_wrong_precision_raises(self):
with pytest.raises(ValueError):
pd.DatetimeIndex(["2000"], dtype="datetime64[us]")
def test_index_constructor_with_numpy_object_array_and_timestamp_tz_with_nan(self):
# GH 27011
result = Index(np.array([Timestamp("2019", tz="UTC"), np.nan], dtype=object))
expected = DatetimeIndex([Timestamp("2019", tz="UTC"), pd.NaT])
tm.assert_index_equal(result, expected)
def test_construction_dti_with_mixed_timezones(self):
# GH 11488 (not changed, added explicit tests)
# no tz results in DatetimeIndex
result = DatetimeIndex(
[Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx"
)
exp = DatetimeIndex(
[Timestamp("2011-01-01"), Timestamp("2011-01-02")], name="idx"
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# same tz results in DatetimeIndex
result = DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="Asia/Tokyo"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-01-02 10:00")],
tz="Asia/Tokyo",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# same tz results in DatetimeIndex (DST)
result = DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="US/Eastern"),
Timestamp("2011-08-01 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), Timestamp("2011-08-01 10:00")],
tz="US/Eastern",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
# tz mismatch affecting to tz-aware raises TypeError/ValueError
with pytest.raises(ValueError):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
msg = "cannot be converted to datetime64"
with pytest.raises(ValueError, match=msg):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="Asia/Tokyo",
name="idx",
)
with pytest.raises(ValueError):
DatetimeIndex(
[
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="US/Eastern",
name="idx",
)
with pytest.raises(ValueError, match=msg):
# passing tz should results in DatetimeIndex, then mismatch raises
# TypeError
Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
tz="Asia/Tokyo",
name="idx",
)
def test_td_sub_timedeltalike_object_dtype_array(self):
# GH#21980
arr = np.array([Timestamp("20130101 9:01"), Timestamp("20121230 9:02")])
exp = np.array([Timestamp("20121231 9:01"), Timestamp("20121229 9:02")])
res = arr - Timedelta("1D")
tm.assert_numpy_array_equal(res, exp)
class TestDataFrameSetitemCopyViewSemantics:
def test_setitem_always_copy(self, float_frame):
assert "E" not in float_frame.columns
s = float_frame["A"].copy()
float_frame["E"] = s
float_frame["E"][5:10] = np.nan
assert notna(s[5:10]).all()
@pytest.mark.parametrize("consolidate", [True, False])
def test_setitem_partial_column_inplace(self, consolidate,
using_array_manager):
# This setting should be in-place, regardless of whether frame is
# single-block or multi-block
# GH#304 this used to be incorrectly not-inplace, in which case
# we needed to ensure _item_cache was cleared.
df = DataFrame({
"x": [1.1, 2.1, 3.1, 4.1],
"y": [5.1, 6.1, 7.1, 8.1]
},
index=[0, 1, 2, 3])
df.insert(2, "z", np.nan)
if not using_array_manager:
if consolidate:
df._consolidate_inplace()
assert len(df._mgr.blocks) == 1
else:
assert len(df._mgr.blocks) == 2
zvals = df["z"]._values
df.loc[2:, "z"] = 42
expected = Series([np.nan, np.nan, 42, 42], index=df.index, name="z")
tm.assert_series_equal(df["z"], expected)
# check setting occurred in-place
tm.assert_numpy_array_equal(zvals, expected.values)
assert np.shares_memory(zvals, df["z"]._values)
def test_setitem_duplicate_columns_not_inplace(self):
# GH#39510
cols = ["A", "B"] * 2
df = DataFrame(0.0, index=[0], columns=cols)
df_copy = df.copy()
df_view = df[:]
df["B"] = (2, 5)
expected = DataFrame([[0.0, 2, 0.0, 5]], columns=cols)
tm.assert_frame_equal(df_view, df_copy)
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize(
"value", [1, np.array([[1], [1]], dtype="int64"), [[1], [1]]])
def test_setitem_same_dtype_not_inplace(self, value, using_array_manager):
# GH#39510
cols = ["A", "B"]
df = DataFrame(0, index=[0, 1], columns=cols)
df_copy = df.copy()
df_view = df[:]
df[["B"]] = value
expected = DataFrame([[0, 1], [0, 1]], columns=cols)
tm.assert_frame_equal(df, expected)
tm.assert_frame_equal(df_view, df_copy)
@pytest.mark.parametrize(
"value", [1.0, np.array([[1.0], [1.0]]), [[1.0], [1.0]]])
def test_setitem_listlike_key_scalar_value_not_inplace(self, value):
# GH#39510
cols = ["A", "B"]
df = DataFrame(0, index=[0, 1], columns=cols)
df_copy = df.copy()
df_view = df[:]
df[["B"]] = value
expected = DataFrame([[0, 1.0], [0, 1.0]], columns=cols)
tm.assert_frame_equal(df_view, df_copy)
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize(
"indexer",
[
"a",
["a"],
pytest.param(
[True, False],
marks=pytest.mark.xfail(
reason="Boolean indexer incorrectly setting inplace",
strict=False, # passing on some builds, no obvious pattern
),
),
],
)
@pytest.mark.parametrize(
"value, set_value",
[
(1, 5),
(1.0, 5.0),
(Timestamp("2020-12-31"), Timestamp("2021-12-31")),
("a", "b"),
],
)
def test_setitem_not_operating_inplace(self, value, set_value, indexer):
# GH#43406
df = DataFrame({"a": value}, index=[0, 1])
expected = df.copy()
view = df[:]
df[indexer] = set_value
tm.assert_frame_equal(view, expected)
def time_f(): return lambda x: Timestamp(x) def fxcm_timestamp_fn(df):
def test_td_add_timedeltalike_object_dtype_array(self, op):
# GH#21980
arr = np.array([Timestamp("20130101 9:01"), Timestamp("20121230 9:02")])
exp = np.array([Timestamp("20130102 9:01"), Timestamp("20121231 9:02")])
res = op(arr, Timedelta("1D"))
tm.assert_numpy_array_equal(res, exp)
def test_index_constructor_with_numpy_object_array_and_timestamp_tz_with_nan(self):
# GH 27011
result = Index(np.array([Timestamp("2019", tz="UTC"), np.nan], dtype=object))
expected = DatetimeIndex([Timestamp("2019", tz="UTC"), pd.NaT])
tm.assert_index_equal(result, expected)
def test_bins_not_monotonic():
msg = "bins must increase monotonically"
data = [0.2, 1.4, 2.5, 6.2, 9.7, 2.1]
with pytest.raises(ValueError, match=msg):
cut(data, [0.1, 1.5, 1, 10])
@pytest.mark.parametrize(
"x, bins, expected",
[
(
date_range("2017-12-31", periods=3),
[Timestamp.min, Timestamp("2018-01-01"), Timestamp.max],
IntervalIndex.from_tuples(
[
(Timestamp.min, Timestamp("2018-01-01")),
(Timestamp("2018-01-01"), Timestamp.max),
]
),
),
(
[-1, 0, 1],
np.array(
[np.iinfo(np.int64).min, 0, np.iinfo(np.int64).max], dtype="int64"
),
IntervalIndex.from_tuples(
[(np.iinfo(np.int64).min, 0), (0, np.iinfo(np.int64).max)]
),
def test_datetimeindex_constructor_misc(self):
arr = ["1/1/2005", "1/2/2005", "Jn 3, 2005", "2005-01-04"]
msg = r"(\(')?Unknown string format(:', 'Jn 3, 2005'\))?"
with pytest.raises(ValueError, match=msg):
DatetimeIndex(arr)
arr = ["1/1/2005", "1/2/2005", "1/3/2005", "2005-01-04"]
idx1 = DatetimeIndex(arr)
arr = [datetime(2005, 1, 1), "1/2/2005", "1/3/2005", "2005-01-04"]
idx2 = DatetimeIndex(arr)
arr = [Timestamp(datetime(2005, 1, 1)), "1/2/2005", "1/3/2005", "2005-01-04"]
idx3 = DatetimeIndex(arr)
arr = np.array(["1/1/2005", "1/2/2005", "1/3/2005", "2005-01-04"], dtype="O")
idx4 = DatetimeIndex(arr)
arr = to_datetime(["1/1/2005", "1/2/2005", "1/3/2005", "2005-01-04"])
idx5 = DatetimeIndex(arr)
arr = to_datetime(["1/1/2005", "1/2/2005", "Jan 3, 2005", "2005-01-04"])
idx6 = DatetimeIndex(arr)
idx7 = DatetimeIndex(["12/05/2007", "25/01/2008"], dayfirst=True)
idx8 = DatetimeIndex(
["2007/05/12", "2008/01/25"], dayfirst=False, yearfirst=True
)
tm.assert_index_equal(idx7, idx8)
for other in [idx2, idx3, idx4, idx5, idx6]:
assert (idx1.values == other.values).all()
sdate = datetime(1999, 12, 25)
edate = datetime(2000, 1, 1)
idx = date_range(start=sdate, freq="1B", periods=20)
assert len(idx) == 20
assert idx[0] == sdate + 0 * offsets.BDay()
assert idx.freq == "B"
idx = date_range(end=edate, freq=("D", 5), periods=20)
assert len(idx) == 20
assert idx[-1] == edate
assert idx.freq == "5D"
idx1 = date_range(start=sdate, end=edate, freq="W-SUN")
idx2 = date_range(start=sdate, end=edate, freq=offsets.Week(weekday=6))
assert len(idx1) == len(idx2)
assert idx1.freq == idx2.freq
idx1 = date_range(start=sdate, end=edate, freq="QS")
idx2 = date_range(
start=sdate, end=edate, freq=offsets.QuarterBegin(startingMonth=1)
)
assert len(idx1) == len(idx2)
assert idx1.freq == idx2.freq
idx1 = date_range(start=sdate, end=edate, freq="BQ")
idx2 = date_range(
start=sdate, end=edate, freq=offsets.BQuarterEnd(startingMonth=12)
)
assert len(idx1) == len(idx2)
assert idx1.freq == idx2.freq
class TestCounting(object):
def test_cumcount(self):
df = DataFrame([['a'], ['a'], ['a'], ['b'], ['a']], columns=['A'])
g = df.groupby('A')
sg = g.A
expected = Series([0, 1, 2, 0, 3])
assert_series_equal(expected, g.cumcount())
assert_series_equal(expected, sg.cumcount())
def test_cumcount_empty(self):
ge = DataFrame().groupby(level=0)
se = Series().groupby(level=0)
# edge case, as this is usually considered float
e = Series(dtype='int64')
assert_series_equal(e, ge.cumcount())
assert_series_equal(e, se.cumcount())
def test_cumcount_dupe_index(self):
df = DataFrame([['a'], ['a'], ['a'], ['b'], ['a']],
columns=['A'],
index=[0] * 5)
g = df.groupby('A')
sg = g.A
expected = Series([0, 1, 2, 0, 3], index=[0] * 5)
assert_series_equal(expected, g.cumcount())
assert_series_equal(expected, sg.cumcount())
def test_cumcount_mi(self):
mi = MultiIndex.from_tuples([[0, 1], [1, 2], [2, 2], [2, 2], [1, 0]])
df = DataFrame([['a'], ['a'], ['a'], ['b'], ['a']],
columns=['A'],
index=mi)
g = df.groupby('A')
sg = g.A
expected = Series([0, 1, 2, 0, 3], index=mi)
assert_series_equal(expected, g.cumcount())
assert_series_equal(expected, sg.cumcount())
def test_cumcount_groupby_not_col(self):
df = DataFrame([['a'], ['a'], ['a'], ['b'], ['a']],
columns=['A'],
index=[0] * 5)
g = df.groupby([0, 0, 0, 1, 0])
sg = g.A
expected = Series([0, 1, 2, 0, 3], index=[0] * 5)
assert_series_equal(expected, g.cumcount())
assert_series_equal(expected, sg.cumcount())
def test_ngroup(self):
df = DataFrame({'A': list('aaaba')})
g = df.groupby('A')
sg = g.A
expected = Series([0, 0, 0, 1, 0])
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_distinct(self):
df = DataFrame({'A': list('abcde')})
g = df.groupby('A')
sg = g.A
expected = Series(range(5), dtype='int64')
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_one_group(self):
df = DataFrame({'A': [0] * 5})
g = df.groupby('A')
sg = g.A
expected = Series([0] * 5)
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_empty(self):
ge = DataFrame().groupby(level=0)
se = Series().groupby(level=0)
# edge case, as this is usually considered float
e = Series(dtype='int64')
assert_series_equal(e, ge.ngroup())
assert_series_equal(e, se.ngroup())
def test_ngroup_series_matches_frame(self):
df = DataFrame({'A': list('aaaba')})
s = Series(list('aaaba'))
assert_series_equal(df.groupby(s).ngroup(), s.groupby(s).ngroup())
def test_ngroup_dupe_index(self):
df = DataFrame({'A': list('aaaba')}, index=[0] * 5)
g = df.groupby('A')
sg = g.A
expected = Series([0, 0, 0, 1, 0], index=[0] * 5)
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_mi(self):
mi = MultiIndex.from_tuples([[0, 1], [1, 2], [2, 2], [2, 2], [1, 0]])
df = DataFrame({'A': list('aaaba')}, index=mi)
g = df.groupby('A')
sg = g.A
expected = Series([0, 0, 0, 1, 0], index=mi)
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_groupby_not_col(self):
df = DataFrame({'A': list('aaaba')}, index=[0] * 5)
g = df.groupby([0, 0, 0, 1, 0])
sg = g.A
expected = Series([0, 0, 0, 1, 0], index=[0] * 5)
assert_series_equal(expected, g.ngroup())
assert_series_equal(expected, sg.ngroup())
def test_ngroup_descending(self):
df = DataFrame(['a', 'a', 'b', 'a', 'b'], columns=['A'])
g = df.groupby(['A'])
ascending = Series([0, 0, 1, 0, 1])
descending = Series([1, 1, 0, 1, 0])
assert_series_equal(descending, (g.ngroups - 1) - ascending)
assert_series_equal(ascending, g.ngroup(ascending=True))
assert_series_equal(descending, g.ngroup(ascending=False))
def test_ngroup_matches_cumcount(self):
# verify one manually-worked out case works
df = DataFrame(
[['a', 'x'], ['a', 'y'], ['b', 'x'], ['a', 'x'], ['b', 'y']],
columns=['A', 'X'])
g = df.groupby(['A', 'X'])
g_ngroup = g.ngroup()
g_cumcount = g.cumcount()
expected_ngroup = Series([0, 1, 2, 0, 3])
expected_cumcount = Series([0, 0, 0, 1, 0])
assert_series_equal(g_ngroup, expected_ngroup)
assert_series_equal(g_cumcount, expected_cumcount)
def test_ngroup_cumcount_pair(self):
# brute force comparison for all small series
for p in cart_product(range(3), repeat=4):
df = DataFrame({'a': p})
g = df.groupby(['a'])
order = sorted(set(p))
ngroupd = [order.index(val) for val in p]
cumcounted = [p[:i].count(val) for i, val in enumerate(p)]
assert_series_equal(g.ngroup(), Series(ngroupd))
assert_series_equal(g.cumcount(), Series(cumcounted))
def test_ngroup_respects_groupby_order(self):
np.random.seed(0)
df = DataFrame({'a': np.random.choice(list('abcdef'), 100)})
for sort_flag in (False, True):
g = df.groupby(['a'], sort=sort_flag)
df['group_id'] = -1
df['group_index'] = -1
for i, (_, group) in enumerate(g):
df.loc[group.index, 'group_id'] = i
for j, ind in enumerate(group.index):
df.loc[ind, 'group_index'] = j
assert_series_equal(Series(df['group_id'].values), g.ngroup())
assert_series_equal(Series(df['group_index'].values), g.cumcount())
@pytest.mark.parametrize(
'datetimelike',
[[Timestamp('2016-05-%02d 20:09:25+00:00' % i) for i in range(1, 4)],
[Timestamp('2016-05-%02d 20:09:25' % i)
for i in range(1, 4)], [Timedelta(x, unit="h") for x in range(1, 4)],
[Period(freq="2W", year=2017, month=x) for x in range(1, 4)]])
def test_count_with_datetimelike(self, datetimelike):
# test for #13393, where DataframeGroupBy.count() fails
# when counting a datetimelike column.
df = DataFrame({'x': ['a', 'a', 'b'], 'y': datetimelike})
res = df.groupby('x').count()
expected = DataFrame({'y': [2, 1]}, index=['a', 'b'])
expected.index.name = "x"
assert_frame_equal(expected, res)
def test_count_with_only_nans_in_first_group(self):
# GH21956
df = DataFrame({'A': [np.nan, np.nan], 'B': ['a', 'b'], 'C': [1, 2]})
result = df.groupby(['A', 'B']).C.count()
mi = MultiIndex(levels=[[], ['a', 'b']],
codes=[[], []],
names=['A', 'B'])
expected = Series([], index=mi, dtype=np.int64, name='C')
assert_series_equal(result, expected, check_index_type=False)
def create_data():
""" create the pickle/msgpack data """
data = {
u'A': [0., 1., 2., 3., np.nan],
u'B': [0, 1, 0, 1, 0],
u'C': [u'foo1', u'foo2', u'foo3', u'foo4', u'foo5'],
u'D': date_range('1/1/2009', periods=5),
u'E': [0., 1, Timestamp('20100101'), u'foo', 2.]
}
scalars = dict(timestamp=Timestamp('20130101'), period=Period('2012', 'M'))
index = dict(int=Index(np.arange(10)),
date=date_range('20130101', periods=10),
period=period_range('2013-01-01', freq='M', periods=10),
float=Index(np.arange(10, dtype=np.float64)),
uint=Index(np.arange(10, dtype=np.uint64)),
timedelta=timedelta_range('00:00:00', freq='30T', periods=10))
if _loose_version >= LooseVersion('0.18'):
from pandas import RangeIndex
index['range'] = RangeIndex(10)
if _loose_version >= LooseVersion('0.21'):
from pandas import interval_range
index['interval'] = interval_range(0, periods=10)
mi = dict(reg2=MultiIndex.from_tuples(tuple(
zip(*[[u'bar', u'bar', u'baz', u'baz', u'foo', u'foo', u'qux', u'qux'],
[u'one', u'two', u'one', u'two', u'one', u'two', u'one', u'two']
])),
names=[u'first', u'second']))
series = dict(
float=Series(data[u'A']),
int=Series(data[u'B']),
mixed=Series(data[u'E']),
ts=Series(np.arange(10).astype(np.int64),
index=date_range('20130101', periods=10)),
mi=Series(np.arange(5).astype(np.float64),
index=MultiIndex.from_tuples(tuple(
zip(*[[1, 1, 2, 2, 2], [3, 4, 3, 4, 5]])),
names=[u'one', u'two'])),
dup=Series(np.arange(5).astype(np.float64),
index=[u'A', u'B', u'C', u'D', u'A']),
cat=Series(Categorical([u'foo', u'bar', u'baz'])),
dt=Series(date_range('20130101', periods=5)),
dt_tz=Series(date_range('20130101', periods=5, tz='US/Eastern')),
period=Series([Period('2000Q1')] * 5))
mixed_dup_df = DataFrame(data)
mixed_dup_df.columns = list(u"ABCDA")
frame = dict(
float=DataFrame({
u'A': series[u'float'],
u'B': series[u'float'] + 1
}),
int=DataFrame({
u'A': series[u'int'],
u'B': series[u'int'] + 1
}),
mixed=DataFrame({k: data[k]
for k in [u'A', u'B', u'C', u'D']}),
mi=DataFrame(
{
u'A': np.arange(5).astype(np.float64),
u'B': np.arange(5).astype(np.int64)
},
index=MultiIndex.from_tuples(tuple(
zip(*[[u'bar', u'bar', u'baz', u'baz', u'baz'],
[u'one', u'two', u'one', u'two', u'three']])),
names=[u'first', u'second'])),
dup=DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=[u'A', u'B', u'A']),
cat_onecol=DataFrame({u'A': Categorical([u'foo', u'bar'])}),
cat_and_float=DataFrame({
u'A': Categorical([u'foo', u'bar', u'baz']),
u'B': np.arange(3).astype(np.int64)
}),
mixed_dup=mixed_dup_df,
dt_mixed_tzs=DataFrame(
{
u'A': Timestamp('20130102', tz='US/Eastern'),
u'B': Timestamp('20130603', tz='CET')
},
index=range(5)),
dt_mixed2_tzs=DataFrame(
{
u'A': Timestamp('20130102', tz='US/Eastern'),
u'B': Timestamp('20130603', tz='CET'),
u'C': Timestamp('20130603', tz='UTC')
},
index=range(5)))
with catch_warnings(record=True):
mixed_dup_panel = Panel({
u'ItemA': frame[u'float'],
u'ItemB': frame[u'int']
})
mixed_dup_panel.items = [u'ItemA', u'ItemA']
panel = dict(float=Panel({
u'ItemA': frame[u'float'],
u'ItemB': frame[u'float'] + 1
}),
dup=Panel(np.arange(30).reshape(3, 5,
2).astype(np.float64),
items=[u'A', u'B', u'A']),
mixed_dup=mixed_dup_panel)
cat = dict(int8=Categorical(list('abcdefg')),
int16=Categorical(np.arange(1000)),
int32=Categorical(np.arange(10000)))
timestamp = dict(normal=Timestamp('2011-01-01'),
nat=NaT,
tz=Timestamp('2011-01-01', tz='US/Eastern'))
if _loose_version < LooseVersion('0.19.2'):
timestamp['freq'] = Timestamp('2011-01-01', offset='D')
timestamp['both'] = Timestamp('2011-01-01',
tz='Asia/Tokyo',
offset='M')
else:
timestamp['freq'] = Timestamp('2011-01-01', freq='D')
timestamp['both'] = Timestamp('2011-01-01', tz='Asia/Tokyo', freq='M')
off = {
'DateOffset': DateOffset(years=1),
'DateOffset_h_ns': DateOffset(hour=6, nanoseconds=5824),
'BusinessDay': BusinessDay(offset=timedelta(seconds=9)),
'BusinessHour': BusinessHour(normalize=True, n=6, end='15:14'),
'CustomBusinessDay': CustomBusinessDay(weekmask='Mon Fri'),
'SemiMonthBegin': SemiMonthBegin(day_of_month=9),
'SemiMonthEnd': SemiMonthEnd(day_of_month=24),
'MonthBegin': MonthBegin(1),
'MonthEnd': MonthEnd(1),
'QuarterBegin': QuarterBegin(1),
'QuarterEnd': QuarterEnd(1),
'Day': Day(1),
'YearBegin': YearBegin(1),
'YearEnd': YearEnd(1),
'Week': Week(1),
'Week_Tues': Week(2, normalize=False, weekday=1),
'WeekOfMonth': WeekOfMonth(week=3, weekday=4),
'LastWeekOfMonth': LastWeekOfMonth(n=1, weekday=3),
'FY5253': FY5253(n=2, weekday=6, startingMonth=7, variation="last"),
'Easter': Easter(),
'Hour': Hour(1),
'Minute': Minute(1)
}
return dict(series=series,
frame=frame,
panel=panel,
index=index,
scalars=scalars,
mi=mi,
sp_series=dict(float=_create_sp_series(),
ts=_create_sp_tsseries()),
sp_frame=dict(float=_create_sp_frame()),
cat=cat,
timestamp=timestamp,
offsets=off)
def test_divmod_invalid(self):
# GH#19365
td = Timedelta(days=2, hours=6)
with pytest.raises(TypeError):
divmod(td, Timestamp("2018-01-22"))
def test_construction_index_with_mixed_timezones_with_NaT(self):
# see gh-11488
result = Index(
[pd.NaT, Timestamp("2011-01-01"), pd.NaT, Timestamp("2011-01-02")],
name="idx",
)
exp = DatetimeIndex(
[pd.NaT, Timestamp("2011-01-01"), pd.NaT, Timestamp("2011-01-02")],
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# Same tz results in DatetimeIndex
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="Asia/Tokyo"),
],
name="idx",
)
exp = DatetimeIndex(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00"),
],
tz="Asia/Tokyo",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# same tz results in DatetimeIndex (DST)
result = Index(
[
Timestamp("2011-01-01 10:00", tz="US/Eastern"),
pd.NaT,
Timestamp("2011-08-01 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = DatetimeIndex(
[Timestamp("2011-01-01 10:00"), pd.NaT, Timestamp("2011-08-01 10:00")],
tz="US/Eastern",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
# different tz results in Index(dtype=object)
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
result = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
name="idx",
)
exp = Index(
[
pd.NaT,
Timestamp("2011-01-01 10:00", tz="Asia/Tokyo"),
pd.NaT,
Timestamp("2011-01-02 10:00", tz="US/Eastern"),
],
dtype="object",
name="idx",
)
tm.assert_index_equal(result, exp, exact=True)
assert not isinstance(result, DatetimeIndex)
# all NaT
result = Index([pd.NaT, pd.NaT], name="idx")
exp = DatetimeIndex([pd.NaT, pd.NaT], name="idx")
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is None
# all NaT with tz
result = Index([pd.NaT, pd.NaT], tz="Asia/Tokyo", name="idx")
exp = DatetimeIndex([pd.NaT, pd.NaT], tz="Asia/Tokyo", name="idx")
tm.assert_index_equal(result, exp, exact=True)
assert isinstance(result, DatetimeIndex)
assert result.tz is not None
assert result.tz == exp.tz
def test_convert(self):
# GH#10265
dt = datetime(2001, 1, 1, 0, 0)
td = dt - datetime(2000, 1, 1, 0, 0)
# Test coercion with mixed types
ser = Series(["a", "3.1415", dt, td])
results = ser._convert(numeric=True)
expected = Series([np.nan, 3.1415, np.nan, np.nan])
tm.assert_series_equal(results, expected)
# Test standard conversion returns original
results = ser._convert(datetime=True)
tm.assert_series_equal(results, ser)
results = ser._convert(numeric=True)
expected = Series([np.nan, 3.1415, np.nan, np.nan])
tm.assert_series_equal(results, expected)
results = ser._convert(timedelta=True)
tm.assert_series_equal(results, ser)
# test pass-through and non-conversion when other types selected
ser = Series(["1.0", "2.0", "3.0"])
results = ser._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([1.0, 2.0, 3.0])
tm.assert_series_equal(results, expected)
results = ser._convert(True, False, True)
tm.assert_series_equal(results, ser)
ser = Series(
[datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 1, 0, 0)], dtype="O"
)
results = ser._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([datetime(2001, 1, 1, 0, 0), datetime(2001, 1, 1, 0, 0)])
tm.assert_series_equal(results, expected)
results = ser._convert(datetime=False, numeric=True, timedelta=True)
tm.assert_series_equal(results, ser)
td = datetime(2001, 1, 1, 0, 0) - datetime(2000, 1, 1, 0, 0)
ser = Series([td, td], dtype="O")
results = ser._convert(datetime=True, numeric=True, timedelta=True)
expected = Series([td, td])
tm.assert_series_equal(results, expected)
results = ser._convert(True, True, False)
tm.assert_series_equal(results, ser)
ser = Series([1.0, 2, 3], index=["a", "b", "c"])
result = ser._convert(numeric=True)
tm.assert_series_equal(result, ser)
# force numeric conversion
res = ser.copy().astype("O")
res["a"] = "1"
result = res._convert(numeric=True)
tm.assert_series_equal(result, ser)
res = ser.copy().astype("O")
res["a"] = "1."
result = res._convert(numeric=True)
tm.assert_series_equal(result, ser)
res = ser.copy().astype("O")
res["a"] = "garbled"
result = res._convert(numeric=True)
expected = ser.copy()
expected["a"] = np.nan
tm.assert_series_equal(result, expected)
# GH 4119, not converting a mixed type (e.g.floats and object)
ser = Series([1, "na", 3, 4])
result = ser._convert(datetime=True, numeric=True)
expected = Series([1, np.nan, 3, 4])
tm.assert_series_equal(result, expected)
ser = Series([1, "", 3, 4])
result = ser._convert(datetime=True, numeric=True)
tm.assert_series_equal(result, expected)
# dates
ser = Series(
[
datetime(2001, 1, 1, 0, 0),
datetime(2001, 1, 2, 0, 0),
datetime(2001, 1, 3, 0, 0),
]
)
result = ser._convert(datetime=True)
expected = Series(
[Timestamp("20010101"), Timestamp("20010102"), Timestamp("20010103")],
dtype="M8[ns]",
)
tm.assert_series_equal(result, expected)
result = ser._convert(datetime=True)
tm.assert_series_equal(result, expected)
# preserver if non-object
ser = Series([1], dtype="float32")
result = ser._convert(datetime=True)
tm.assert_series_equal(result, ser)
def decode(obj):
"""
Decoder for deserializing numpy data types.
"""
typ = obj.get('typ')
if typ is None:
return obj
elif typ == 'timestamp':
return Timestamp(obj['value'], tz=obj['tz'], offset=obj['offset'])
elif typ == 'period':
return Period(ordinal=obj['ordinal'], freq=obj['freq'])
elif typ == 'index':
dtype = dtype_for(obj['dtype'])
data = unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress'))
return globals()[obj['klass']](data, dtype=dtype, name=obj['name'])
elif typ == 'multi_index':
data = unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress'))
data = [tuple(x) for x in data]
return globals()[obj['klass']].from_tuples(data, names=obj['names'])
elif typ == 'period_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'])
return globals()[obj['klass']](data, **d)
elif typ == 'datetime_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'], verify_integrity=False)
result = globals()[obj['klass']](data, **d)
tz = obj['tz']
# reverse tz conversion
if tz is not None:
result = result.tz_localize('UTC').tz_convert(tz)
return result
elif typ == 'series':
dtype = dtype_for(obj['dtype'])
index = obj['index']
return globals()[obj['klass']](unconvert(obj['data'], dtype,
obj['compress']),
index=index,
name=obj['name'])
elif typ == 'block_manager':
axes = obj['axes']
def create_block(b):
values = unconvert(b['values'], dtype_for(b['dtype']),
b['compress']).reshape(b['shape'])
return make_block(values=values,
klass=getattr(internals, b['klass']),
placement=axes[0].get_indexer(b['items']))
blocks = [create_block(b) for b in obj['blocks']]
return globals()[obj['klass']](BlockManager(blocks, axes))
elif typ == 'datetime':
return parse(obj['data'])
elif typ == 'datetime64':
return np.datetime64(parse(obj['data']))
elif typ == 'date':
return parse(obj['data']).date()
elif typ == 'timedelta':
return timedelta(*obj['data'])
elif typ == 'timedelta64':
return np.timedelta64(int(obj['data']))
#elif typ == 'sparse_series':
# dtype = dtype_for(obj['dtype'])
# return globals()[obj['klass']](
# unconvert(obj['sp_values'], dtype, obj['compress']),
# sparse_index=obj['sp_index'], index=obj['index'],
# fill_value=obj['fill_value'], kind=obj['kind'], name=obj['name'])
#elif typ == 'sparse_dataframe':
# return globals()[obj['klass']](
# obj['data'], columns=obj['columns'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind']
# )
#elif typ == 'sparse_panel':
# return globals()[obj['klass']](
# obj['data'], items=obj['items'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind'])
elif typ == 'block_index':
return globals()[obj['klass']](obj['length'], obj['blocs'],
obj['blengths'])
elif typ == 'int_index':
return globals()[obj['klass']](obj['length'], obj['indices'])
elif typ == 'ndarray':
return unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress')).reshape(obj['shape'])
elif typ == 'np_scalar':
if obj.get('sub_typ') == 'np_complex':
return c2f(obj['real'], obj['imag'], obj['dtype'])
else:
dtype = dtype_for(obj['dtype'])
try:
return dtype(obj['data'])
except:
return dtype.type(obj['data'])
elif typ == 'np_complex':
return complex(obj['real'] + '+' + obj['imag'] + 'j')
elif isinstance(obj, (dict, list, set)):
return obj
else:
return obj
class TestArithmetic(object):
@pytest.mark.parametrize("op", [operator.add, ops.radd])
@pytest.mark.parametrize("other", ["category", "Int64"])
def test_add_extension_scalar(self, other, box, op):
# GH#22378
# Check that scalars satisfying is_extension_array_dtype(obj)
# do not incorrectly try to dispatch to an ExtensionArray operation
arr = pd.Series(['a', 'b', 'c'])
expected = pd.Series([op(x, other) for x in arr])
arr = tm.box_expected(arr, box)
expected = tm.box_expected(expected, box)
result = op(arr, other)
tm.assert_equal(result, expected)
@pytest.mark.parametrize('box', [
pytest.param(pd.Index,
marks=pytest.mark.xfail(reason="Does not mask nulls",
strict=True,
raises=TypeError)), pd.Series,
pd.DataFrame
],
ids=lambda x: x.__name__)
def test_objarr_add_str(self, box):
ser = pd.Series(['x', np.nan, 'x'])
expected = pd.Series(['xa', np.nan, 'xa'])
ser = tm.box_expected(ser, box)
expected = tm.box_expected(expected, box)
result = ser + 'a'
tm.assert_equal(result, expected)
@pytest.mark.parametrize('box', [
pytest.param(pd.Index,
marks=pytest.mark.xfail(reason="Does not mask nulls",
strict=True,
raises=TypeError)), pd.Series,
pd.DataFrame
],
ids=lambda x: x.__name__)
def test_objarr_radd_str(self, box):
ser = pd.Series(['x', np.nan, 'x'])
expected = pd.Series(['ax', np.nan, 'ax'])
ser = tm.box_expected(ser, box)
expected = tm.box_expected(expected, box)
result = 'a' + ser
tm.assert_equal(result, expected)
@pytest.mark.parametrize(
'data', [[1, 2, 3], [1.1, 2.2, 3.3],
[Timestamp('2011-01-01'),
Timestamp('2011-01-02'), pd.NaT], ['x', 'y', 1]])
@pytest.mark.parametrize('dtype', [None, object])
def test_objarr_radd_str_invalid(self, dtype, data, box):
ser = Series(data, dtype=dtype)
ser = tm.box_expected(ser, box)
with pytest.raises(TypeError):
'foo_' + ser
@pytest.mark.parametrize('op',
[operator.add, ops.radd, operator.sub, ops.rsub])
def test_objarr_add_invalid(self, op, box):
# invalid ops
if box is pd.DataFrame and op is ops.radd:
pytest.xfail(reason="DataFrame op incorrectly casts the np.array"
"case to M8[ns]")
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
obj_ser = tm.box_expected(obj_ser, box)
with pytest.raises(Exception):
op(obj_ser, 1)
with pytest.raises(Exception):
op(obj_ser, np.array(1, dtype=np.int64))
# TODO: Moved from tests.series.test_operators; needs cleanup
def test_operators_na_handling(self):
ser = Series(['foo', 'bar', 'baz', np.nan])
result = 'prefix_' + ser
expected = pd.Series(
['prefix_foo', 'prefix_bar', 'prefix_baz', np.nan])
tm.assert_series_equal(result, expected)
result = ser + '_suffix'
expected = pd.Series(
['foo_suffix', 'bar_suffix', 'baz_suffix', np.nan])
tm.assert_series_equal(result, expected)
# TODO: parametrize over box
@pytest.mark.parametrize('dtype', [None, object])
def test_series_with_dtype_radd_timedelta(self, dtype):
# note this test is _not_ aimed at timedelta64-dtyped Series
ser = pd.Series([
pd.Timedelta('1 days'),
pd.Timedelta('2 days'),
pd.Timedelta('3 days')
],
dtype=dtype)
expected = pd.Series([
pd.Timedelta('4 days'),
pd.Timedelta('5 days'),
pd.Timedelta('6 days')
])
result = pd.Timedelta('3 days') + ser
tm.assert_series_equal(result, expected)
result = ser + pd.Timedelta('3 days')
tm.assert_series_equal(result, expected)
def test_construction_with_nat_and_tzlocal(self):
tz = dateutil.tz.tzlocal()
result = DatetimeIndex(["2018", "NaT"], tz=tz)
expected = DatetimeIndex([Timestamp("2018", tz=tz), pd.NaT])
tm.assert_index_equal(result, expected)
def test_td_rsub_mixed_most_timedeltalike_object_dtype_array(self):
# GH#21980
now = Timestamp.now()
arr = np.array([now, Timedelta("1D"), np.timedelta64(2, "h")])
with pytest.raises(TypeError):
Timedelta("1D") - arr
def test_maybe_cast_slice_duplicate_monotonic(self):
# https://github.com/pandas-dev/pandas/issues/16515
idx = DatetimeIndex(["2017", "2017"])
result = idx._maybe_cast_slice_bound("2017-01-01", "left", "loc")
expected = Timestamp("2017-01-01")
assert result == expected
def test_interleave(self):
# interleave with object
result = self.tzframe.assign(D='foo').values
expected = np.array(
[[
Timestamp('2013-01-01 00:00:00'),
Timestamp('2013-01-02 00:00:00'),
Timestamp('2013-01-03 00:00:00')
],
[
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern'),
pd.NaT,
Timestamp('2013-01-03 00:00:00-0500', tz='US/Eastern')
],
[
Timestamp('2013-01-01 00:00:00+0100', tz='CET'), pd.NaT,
Timestamp('2013-01-03 00:00:00+0100', tz='CET')
], ['foo', 'foo', 'foo']],
dtype=object).T
tm.assert_numpy_array_equal(result, expected)
# interleave with only datetime64[ns]
result = self.tzframe.values
expected = np.array(
[[
Timestamp('2013-01-01 00:00:00'),
Timestamp('2013-01-02 00:00:00'),
Timestamp('2013-01-03 00:00:00')
],
[
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern'),
pd.NaT,
Timestamp('2013-01-03 00:00:00-0500', tz='US/Eastern')
],
[
Timestamp('2013-01-01 00:00:00+0100', tz='CET'), pd.NaT,
Timestamp('2013-01-03 00:00:00+0100', tz='CET')
]],
dtype=object).T
tm.assert_numpy_array_equal(result, expected)
def test_generate_training_set(mocker):
mocker.patch("dagster_examples.bay_bikes.solids.read_sql_table",
side_effect=mock_read_sql)
# Execute Pipeline
test_pipeline_result = execute_pipeline(
pipeline=generate_test_training_set_pipeline,
mode="testing",
run_config=compose_training_data_env_dict(),
)
assert test_pipeline_result.success
# Check solids
EXPECTED_TRAFFIC_RECORDS = [
{
"interval_date": date(2019, 7, 31),
"peak_traffic_load": 1,
"time": Timestamp("2019-07-31 00:00:00"),
},
{
"interval_date": date(2019, 8, 31),
"peak_traffic_load": 1,
"time": Timestamp("2019-08-31 00:00:00"),
},
]
traffic_dataset = test_pipeline_result.output_for_solid(
"transform_into_traffic_dataset",
output_name="traffic_dataframe").to_dict("records")
assert all(record in EXPECTED_TRAFFIC_RECORDS
for record in traffic_dataset)
EXPECTED_WEATHER_RECORDS = [
{
"time": Timestamp("2019-08-31 00:00:00"),
"summary": "Clear throughout the day.",
"icon": "clear-day",
"sunriseTime": 1546269960,
"sunsetTime": 1546304520,
"precipIntensity": 0.0007,
"precipIntensityMax": 0.0019,
"precipProbability": 0.05,
"precipType": "rain",
"temperatureHigh": 56.71,
"temperatureHighTime": 1546294020,
"temperatureLow": 44.75,
"temperatureLowTime": 1546358040,
"dewPoint": 28.34,
"humidity": 0.43,
"pressure": 1017.7,
"windSpeed": 12.46,
"windGust": 26.85,
"windGustTime": 1546289220,
"windBearing": 0,
"cloudCover": 0.11,
"uvIndex": 2,
"uvIndexTime": 1546287180,
"visibility": 10,
"ozone": 314.4,
},
{
"time": Timestamp("2019-07-31 00:00:00"),
"summary": "Clear throughout the day.",
"icon": "clear-day",
"sunriseTime": 1546356420,
"sunsetTime": 1546390920,
"precipIntensity": 0.0005,
"precipIntensityMax": 0.0016,
"precipProbability": 0.02,
"precipType": "sunny",
"temperatureHigh": 55.91,
"temperatureHighTime": 1546382040,
"temperatureLow": 41.18,
"temperatureLowTime": 1546437660,
"dewPoint": 20.95,
"humidity": 0.33,
"pressure": 1023.3,
"windSpeed": 6.77,
"windGust": 22.08,
"windGustTime": 1546343340,
"windBearing": 22,
"cloudCover": 0.1,
"uvIndex": 2,
"uvIndexTime": 1546373580,
"visibility": 10,
"ozone": 305.3,
},
]
weather_dataset = test_pipeline_result.output_for_solid(
"produce_weather_dataset",
output_name="weather_dataframe").to_dict("records")
assert all(record in EXPECTED_WEATHER_RECORDS
for record in weather_dataset)
# Ensure we are generating the expected training set
training_set, labels = test_pipeline_result.output_for_solid(
"produce_training_set")
assert len(labels) == 1 and labels[0] == 1
assert array_equal(
training_set,
[[
[
1546356420.0,
1546390920.0,
0.0005,
0.0016,
0.02,
55.91,
1546382040.0,
41.18,
1546437660.0,
20.95,
0.33,
1023.3,
6.77,
22.08,
1546343340.0,
22.0,
0.1,
2.0,
1546373580.0,
10.0,
305.3,
],
[
1546269960.0,
1546304520.0,
0.0007,
0.0019,
0.05,
56.71,
1546294020.0,
44.75,
1546358040.0,
28.34,
0.43,
1017.7,
12.46,
26.85,
1546289220.0,
0.0,
0.11,
2.0,
1546287180.0,
10.0,
314.4,
],
]],
)
materialization_events = [
event for event in test_pipeline_result.step_event_list
if event.solid_name == "upload_training_set_to_gcs"
and event.event_type_value == "STEP_MATERIALIZATION"
]
assert len(materialization_events) == 1
materialization = materialization_events[
0].event_specific_data.materialization
assert materialization.asset_key.path[0:5] == [
"gs",
"dagster",
"scratch",
"ccdfe1e",
"training_data",
]
materialization_event_metadata = materialization.metadata_entries
assert len(materialization_event_metadata) == 1
assert materialization_event_metadata[
0].label == "google cloud storage URI"
assert materialization_event_metadata[0].entry_data.text.startswith(
"gs://dagster-scratch-ccdfe1e/training_data")
# Clean up
shutil.rmtree(os.path.join(tempfile.gettempdir(), "testing-storage"),
ignore_errors=True)
MockDailyBarReader,
)
from zipline.testing.fixtures import (
WithAdjustmentReader,
ZiplineTestCase,
)
# Test calendar ranges over the month of June 2015
# June 2015
# Mo Tu We Th Fr Sa Su
# 1 2 3 4 5 6 7
# 8 9 10 11 12 13 14
# 15 16 17 18 19 20 21
# 22 23 24 25 26 27 28
# 29 30
TEST_CALENDAR_START = Timestamp('2015-06-01', tz='UTC')
TEST_CALENDAR_STOP = Timestamp('2015-06-30', tz='UTC')
TEST_QUERY_START = Timestamp('2015-06-10', tz='UTC')
TEST_QUERY_STOP = Timestamp('2015-06-19', tz='UTC')
# One asset for each of the cases enumerated in load_raw_arrays_from_bcolz.
EQUITY_INFO = DataFrame(
[
# 1) The equity's trades start and end before query.
{
'start_date': '2015-06-01',
'end_date': '2015-06-05'
},
# 2) The equity's trades start and end after query.
{
class TestDataFrameSetItem:
def test_setitem_str_subclass(self):
# GH#37366
class mystring(str):
pass
data = ["2020-10-22 01:21:00+00:00"]
index = DatetimeIndex(data)
df = DataFrame({"a": [1]}, index=index)
df["b"] = 2
df[mystring("c")] = 3
expected = DataFrame({
"a": [1],
"b": [2],
mystring("c"): [3]
},
index=index)
tm.assert_equal(df, expected)
@pytest.mark.parametrize(
"dtype", ["int32", "int64", "uint32", "uint64", "float32", "float64"])
def test_setitem_dtype(self, dtype, float_frame):
arr = np.random.randn(len(float_frame))
float_frame[dtype] = np.array(arr, dtype=dtype)
assert float_frame[dtype].dtype.name == dtype
def test_setitem_list_not_dataframe(self, float_frame):
data = np.random.randn(len(float_frame), 2)
float_frame[["A", "B"]] = data
tm.assert_almost_equal(float_frame[["A", "B"]].values, data)
def test_setitem_error_msmgs(self):
# GH 7432
df = DataFrame(
{
"bar": [1, 2, 3],
"baz": ["d", "e", "f"]
},
index=Index(["a", "b", "c"], name="foo"),
)
ser = Series(
["g", "h", "i", "j"],
index=Index(["a", "b", "c", "a"], name="foo"),
name="fiz",
)
msg = "cannot reindex on an axis with duplicate labels"
with pytest.raises(ValueError, match=msg):
with tm.assert_produces_warning(FutureWarning, match="non-unique"):
df["newcol"] = ser
# GH 4107, more descriptive error message
df = DataFrame(np.random.randint(0, 2, (4, 4)),
columns=["a", "b", "c", "d"])
msg = "incompatible index of inserted column with frame index"
with pytest.raises(TypeError, match=msg):
df["gr"] = df.groupby(["b", "c"]).count()
def test_setitem_benchmark(self):
# from the vb_suite/frame_methods/frame_insert_columns
N = 10
K = 5
df = DataFrame(index=range(N))
new_col = np.random.randn(N)
for i in range(K):
df[i] = new_col
expected = DataFrame(np.repeat(new_col, K).reshape(N, K),
index=range(N))
tm.assert_frame_equal(df, expected)
def test_setitem_different_dtype(self):
df = DataFrame(np.random.randn(5, 3),
index=np.arange(5),
columns=["c", "b", "a"])
df.insert(0, "foo", df["a"])
df.insert(2, "bar", df["c"])
# diff dtype
# new item
df["x"] = df["a"].astype("float32")
result = df.dtypes
expected = Series(
[np.dtype("float64")] * 5 + [np.dtype("float32")],
index=["foo", "c", "bar", "b", "a", "x"],
)
tm.assert_series_equal(result, expected)
# replacing current (in different block)
df["a"] = df["a"].astype("float32")
result = df.dtypes
expected = Series(
[np.dtype("float64")] * 4 + [np.dtype("float32")] * 2,
index=["foo", "c", "bar", "b", "a", "x"],
)
tm.assert_series_equal(result, expected)
df["y"] = df["a"].astype("int32")
result = df.dtypes
expected = Series(
[np.dtype("float64")] * 4 + [np.dtype("float32")] * 2 +
[np.dtype("int32")],
index=["foo", "c", "bar", "b", "a", "x", "y"],
)
tm.assert_series_equal(result, expected)
def test_setitem_empty_columns(self):
# GH 13522
df = DataFrame(index=["A", "B", "C"])
df["X"] = df.index
df["X"] = ["x", "y", "z"]
exp = DataFrame(data={"X": ["x", "y", "z"]}, index=["A", "B", "C"])
tm.assert_frame_equal(df, exp)
def test_setitem_dt64_index_empty_columns(self):
rng = date_range("1/1/2000 00:00:00", "1/1/2000 1:59:50", freq="10s")
df = DataFrame(index=np.arange(len(rng)))
df["A"] = rng
assert df["A"].dtype == np.dtype("M8[ns]")
def test_setitem_timestamp_empty_columns(self):
# GH#19843
df = DataFrame(index=range(3))
df["now"] = Timestamp("20130101", tz="UTC")
expected = DataFrame([[Timestamp("20130101", tz="UTC")]] * 3,
index=[0, 1, 2],
columns=["now"])
tm.assert_frame_equal(df, expected)
def test_setitem_wrong_length_categorical_dtype_raises(self):
# GH#29523
cat = Categorical.from_codes([0, 1, 1, 0, 1, 2], ["a", "b", "c"])
df = DataFrame(range(10), columns=["bar"])
msg = (rf"Length of values \({len(cat)}\) "
rf"does not match length of index \({len(df)}\)")
with pytest.raises(ValueError, match=msg):
df["foo"] = cat
def test_setitem_with_sparse_value(self):
# GH#8131
df = DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
sp_array = SparseArray([0, 0, 1])
df["new_column"] = sp_array
expected = Series(sp_array, name="new_column")
tm.assert_series_equal(df["new_column"], expected)
def test_setitem_with_unaligned_sparse_value(self):
df = DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
sp_series = Series(SparseArray([0, 0, 1]), index=[2, 1, 0])
df["new_column"] = sp_series
expected = Series(SparseArray([1, 0, 0]), name="new_column")
tm.assert_series_equal(df["new_column"], expected)
def test_setitem_period_preserves_dtype(self):
# GH: 26861
data = [Period("2003-12", "D")]
result = DataFrame([])
result["a"] = data
expected = DataFrame({"a": data})
tm.assert_frame_equal(result, expected)
def test_setitem_dict_preserves_dtypes(self):
# https://github.com/pandas-dev/pandas/issues/34573
expected = DataFrame({
"a": Series([0, 1, 2], dtype="int64"),
"b": Series([1, 2, 3], dtype=float),
"c": Series([1, 2, 3], dtype=float),
"d": Series([1, 2, 3], dtype="uint32"),
})
df = DataFrame({
"a": Series([], dtype="int64"),
"b": Series([], dtype=float),
"c": Series([], dtype=float),
"d": Series([], dtype="uint32"),
})
for idx, b in enumerate([1, 2, 3]):
df.loc[df.shape[0]] = {
"a": int(idx),
"b": float(b),
"c": float(b),
"d": np.uint32(b),
}
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize(
"obj,dtype",
[
(Period("2020-01"), PeriodDtype("M")),
(
Interval(left=0, right=5, inclusive="right"),
IntervalDtype("int64", "right"),
),
(
Timestamp("2011-01-01", tz="US/Eastern"),
DatetimeTZDtype(tz="US/Eastern"),
),
],
)
def test_setitem_extension_types(self, obj, dtype):
# GH: 34832
expected = DataFrame({
"idx": [1, 2, 3],
"obj": Series([obj] * 3, dtype=dtype)
})
df = DataFrame({"idx": [1, 2, 3]})
df["obj"] = obj
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize(
"ea_name",
[
dtype.name for dtype in ea_registry.dtypes
# property would require instantiation
if not isinstance(dtype.name, property)
]
# mypy doesn't allow adding lists of different types
# https://github.com/python/mypy/issues/5492
+ ["datetime64[ns, UTC]", "period[D]"], # type: ignore[list-item]
)
def test_setitem_with_ea_name(self, ea_name):
# GH 38386
result = DataFrame([0])
result[ea_name] = [1]
expected = DataFrame({0: [0], ea_name: [1]})
tm.assert_frame_equal(result, expected)
def test_setitem_dt64_ndarray_with_NaT_and_diff_time_units(self):
# GH#7492
data_ns = np.array([1, "nat"], dtype="datetime64[ns]")
result = Series(data_ns).to_frame()
result["new"] = data_ns
expected = DataFrame({
0: [1, None],
"new": [1, None]
},
dtype="datetime64[ns]")
tm.assert_frame_equal(result, expected)
# OutOfBoundsDatetime error shouldn't occur
data_s = np.array([1, "nat"], dtype="datetime64[s]")
result["new"] = data_s
expected = DataFrame({
0: [1, None],
"new": [1e9, None]
},
dtype="datetime64[ns]")
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize("unit", ["h", "m", "s", "ms", "D", "M", "Y"])
def test_frame_setitem_datetime64_col_other_units(self, unit):
# Check that non-nano dt64 values get cast to dt64 on setitem
# into a not-yet-existing column
n = 100
dtype = np.dtype(f"M8[{unit}]")
vals = np.arange(n, dtype=np.int64).view(dtype)
ex_vals = vals.astype("datetime64[ns]")
df = DataFrame({"ints": np.arange(n)}, index=np.arange(n))
df[unit] = vals
assert df[unit].dtype == np.dtype("M8[ns]")
assert (df[unit].values == ex_vals).all()
@pytest.mark.parametrize("unit", ["h", "m", "s", "ms", "D", "M", "Y"])
def test_frame_setitem_existing_datetime64_col_other_units(self, unit):
# Check that non-nano dt64 values get cast to dt64 on setitem
# into an already-existing dt64 column
n = 100
dtype = np.dtype(f"M8[{unit}]")
vals = np.arange(n, dtype=np.int64).view(dtype)
ex_vals = vals.astype("datetime64[ns]")
df = DataFrame({"ints": np.arange(n)}, index=np.arange(n))
df["dates"] = np.arange(n, dtype=np.int64).view("M8[ns]")
# We overwrite existing dt64 column with new, non-nano dt64 vals
df["dates"] = vals
assert (df["dates"].values == ex_vals).all()
def test_setitem_dt64tz(self, timezone_frame):
df = timezone_frame
idx = df["B"].rename("foo")
# setitem
df["C"] = idx
tm.assert_series_equal(df["C"], Series(idx, name="C"))
df["D"] = "foo"
df["D"] = idx
tm.assert_series_equal(df["D"], Series(idx, name="D"))
del df["D"]
# assert that A & C are not sharing the same base (e.g. they
# are copies)
v1 = df._mgr.arrays[1]
v2 = df._mgr.arrays[2]
tm.assert_extension_array_equal(v1, v2)
v1base = v1._data.base
v2base = v2._data.base
assert v1base is None or (id(v1base) != id(v2base))
# with nan
df2 = df.copy()
df2.iloc[1, 1] = NaT
df2.iloc[1, 2] = NaT
result = df2["B"]
tm.assert_series_equal(notna(result),
Series([True, False, True], name="B"))
tm.assert_series_equal(df2.dtypes, df.dtypes)
def test_setitem_periodindex(self):
rng = period_range("1/1/2000", periods=5, name="index")
df = DataFrame(np.random.randn(5, 3), index=rng)
df["Index"] = rng
rs = Index(df["Index"])
tm.assert_index_equal(rs, rng, check_names=False)
assert rs.name == "Index"
assert rng.name == "index"
rs = df.reset_index().set_index("index")
assert isinstance(rs.index, PeriodIndex)
tm.assert_index_equal(rs.index, rng)
def test_setitem_complete_column_with_array(self):
# GH#37954
df = DataFrame({"a": ["one", "two", "three"], "b": [1, 2, 3]})
arr = np.array([[1, 1], [3, 1], [5, 1]])
df[["c", "d"]] = arr
expected = DataFrame({
"a": ["one", "two", "three"],
"b": [1, 2, 3],
"c": [1, 3, 5],
"d": [1, 1, 1],
})
expected["c"] = expected["c"].astype(arr.dtype)
expected["d"] = expected["d"].astype(arr.dtype)
assert expected["c"].dtype == arr.dtype
assert expected["d"].dtype == arr.dtype
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize("dtype", ["f8", "i8", "u8"])
def test_setitem_bool_with_numeric_index(self, dtype):
# GH#36319
cols = Index([1, 2, 3], dtype=dtype)
df = DataFrame(np.random.randn(3, 3), columns=cols)
df[False] = ["a", "b", "c"]
expected_cols = Index([1, 2, 3, False], dtype=object)
if dtype == "f8":
expected_cols = Index([1.0, 2.0, 3.0, False], dtype=object)
tm.assert_index_equal(df.columns, expected_cols)
@pytest.mark.parametrize("indexer", ["B", ["B"]])
def test_setitem_frame_length_0_str_key(self, indexer):
# GH#38831
df = DataFrame(columns=["A", "B"])
other = DataFrame({"B": [1, 2]})
df[indexer] = other
expected = DataFrame({"A": [np.nan] * 2, "B": [1, 2]})
expected["A"] = expected["A"].astype("object")
tm.assert_frame_equal(df, expected)
def test_setitem_frame_duplicate_columns(self, using_array_manager):
# GH#15695
warn = FutureWarning if using_array_manager else None
msg = "will attempt to set the values inplace"
cols = ["A", "B", "C"] * 2
df = DataFrame(index=range(3), columns=cols)
df.loc[0, "A"] = (0, 3)
with tm.assert_produces_warning(warn, match=msg):
df.loc[:, "B"] = (1, 4)
df["C"] = (2, 5)
expected = DataFrame(
[
[0, 1, 2, 3, 4, 5],
[np.nan, 1, 2, np.nan, 4, 5],
[np.nan, 1, 2, np.nan, 4, 5],
],
dtype="object",
)
if using_array_manager:
# setitem replaces column so changes dtype
expected.columns = cols
expected["C"] = expected["C"].astype("int64")
# TODO(ArrayManager) .loc still overwrites
expected["B"] = expected["B"].astype("int64")
else:
# set these with unique columns to be extra-unambiguous
expected[2] = expected[2].astype(np.int64)
expected[5] = expected[5].astype(np.int64)
expected.columns = cols
tm.assert_frame_equal(df, expected)
def test_setitem_frame_duplicate_columns_size_mismatch(self):
# GH#39510
cols = ["A", "B", "C"] * 2
df = DataFrame(index=range(3), columns=cols)
with pytest.raises(ValueError,
match="Columns must be same length as key"):
df[["A"]] = (0, 3, 5)
df2 = df.iloc[:, :3] # unique columns
with pytest.raises(ValueError,
match="Columns must be same length as key"):
df2[["A"]] = (0, 3, 5)
@pytest.mark.parametrize("cols", [["a", "b", "c"], ["a", "a", "a"]])
def test_setitem_df_wrong_column_number(self, cols):
# GH#38604
df = DataFrame([[1, 2, 3]], columns=cols)
rhs = DataFrame([[10, 11]], columns=["d", "e"])
msg = "Columns must be same length as key"
with pytest.raises(ValueError, match=msg):
df["a"] = rhs
def test_setitem_listlike_indexer_duplicate_columns(self):
# GH#38604
df = DataFrame([[1, 2, 3]], columns=["a", "b", "b"])
rhs = DataFrame([[10, 11, 12]], columns=["a", "b", "b"])
df[["a", "b"]] = rhs
expected = DataFrame([[10, 11, 12]], columns=["a", "b", "b"])
tm.assert_frame_equal(df, expected)
df[["c", "b"]] = rhs
expected = DataFrame([[10, 11, 12, 10]], columns=["a", "b", "b", "c"])
tm.assert_frame_equal(df, expected)
def test_setitem_listlike_indexer_duplicate_columns_not_equal_length(self):
# GH#39403
df = DataFrame([[1, 2, 3]], columns=["a", "b", "b"])
rhs = DataFrame([[10, 11]], columns=["a", "b"])
msg = "Columns must be same length as key"
with pytest.raises(ValueError, match=msg):
df[["a", "b"]] = rhs
def test_setitem_intervals(self):
df = DataFrame({"A": range(10)})
ser = cut(df["A"], 5)
assert isinstance(ser.cat.categories, IntervalIndex)
# B & D end up as Categoricals
# the remainder are converted to in-line objects
# containing an IntervalIndex.values
df["B"] = ser
df["C"] = np.array(ser)
df["D"] = ser.values
df["E"] = np.array(ser.values)
df["F"] = ser.astype(object)
assert is_categorical_dtype(df["B"].dtype)
assert is_interval_dtype(df["B"].cat.categories)
assert is_categorical_dtype(df["D"].dtype)
assert is_interval_dtype(df["D"].cat.categories)
# These go through the Series constructor and so get inferred back
# to IntervalDtype
assert is_interval_dtype(df["C"])
assert is_interval_dtype(df["E"])
# But the Series constructor doesn't do inference on Series objects,
# so setting df["F"] doesn't get cast back to IntervalDtype
assert is_object_dtype(df["F"])
# they compare equal as Index
# when converted to numpy objects
c = lambda x: Index(np.array(x))
tm.assert_index_equal(c(df.B), c(df.B))
tm.assert_index_equal(c(df.B), c(df.C), check_names=False)
tm.assert_index_equal(c(df.B), c(df.D), check_names=False)
tm.assert_index_equal(c(df.C), c(df.D), check_names=False)
# B & D are the same Series
tm.assert_series_equal(df["B"], df["B"])
tm.assert_series_equal(df["B"], df["D"], check_names=False)
# C & E are the same Series
tm.assert_series_equal(df["C"], df["C"])
tm.assert_series_equal(df["C"], df["E"], check_names=False)
def test_setitem_categorical(self):
# GH#35369
df = DataFrame({"h": Series(list("mn")).astype("category")})
df.h = df.h.cat.reorder_categories(["n", "m"])
expected = DataFrame(
{"h": Categorical(["m", "n"]).reorder_categories(["n", "m"])})
tm.assert_frame_equal(df, expected)
def test_setitem_with_empty_listlike(self):
# GH#17101
index = Index([], name="idx")
result = DataFrame(columns=["A"], index=index)
result["A"] = []
expected = DataFrame(columns=["A"], index=index)
tm.assert_index_equal(result.index, expected.index)
@pytest.mark.parametrize(
"cols, values, expected",
[
(["C", "D", "D", "a"], [1, 2, 3, 4], 4), # with duplicates
(["D", "C", "D", "a"], [1, 2, 3, 4], 4), # mixed order
(["C", "B", "B", "a"], [1, 2, 3, 4], 4), # other duplicate cols
(["C", "B", "a"], [1, 2, 3], 3), # no duplicates
(["B", "C", "a"], [3, 2, 1], 1), # alphabetical order
(["C", "a", "B"], [3, 2, 1], 2), # in the middle
],
)
def test_setitem_same_column(self, cols, values, expected):
# GH#23239
df = DataFrame([values], columns=cols)
df["a"] = df["a"]
result = df["a"].values[0]
assert result == expected
def test_setitem_multi_index(self):
# GH#7655, test that assigning to a sub-frame of a frame
# with multi-index columns aligns both rows and columns
it = ["jim", "joe", "jolie"], ["first",
"last"], ["left", "center", "right"]
cols = MultiIndex.from_product(it)
index = date_range("20141006", periods=20)
vals = np.random.randint(1, 1000, (len(index), len(cols)))
df = DataFrame(vals, columns=cols, index=index)
i, j = df.index.values.copy(), it[-1][:]
np.random.shuffle(i)
df["jim"] = df["jolie"].loc[i, ::-1]
tm.assert_frame_equal(df["jim"], df["jolie"])
np.random.shuffle(j)
df[("joe", "first")] = df[("jolie", "last")].loc[i, j]
tm.assert_frame_equal(df[("joe", "first")], df[("jolie", "last")])
np.random.shuffle(j)
df[("joe", "last")] = df[("jolie", "first")].loc[i, j]
tm.assert_frame_equal(df[("joe", "last")], df[("jolie", "first")])
@pytest.mark.parametrize(
"columns,box,expected",
[
(
["A", "B", "C", "D"],
7,
DataFrame(
[[7, 7, 7, 7], [7, 7, 7, 7], [7, 7, 7, 7]],
columns=["A", "B", "C", "D"],
),
),
(
["C", "D"],
[7, 8],
DataFrame(
[[1, 2, 7, 8], [3, 4, 7, 8], [5, 6, 7, 8]],
columns=["A", "B", "C", "D"],
),
),
(
["A", "B", "C"],
np.array([7, 8, 9], dtype=np.int64),
DataFrame([[7, 8, 9], [7, 8, 9], [7, 8, 9]],
columns=["A", "B", "C"]),
),
(
["B", "C", "D"],
[[7, 8, 9], [10, 11, 12], [13, 14, 15]],
DataFrame(
[[1, 7, 8, 9], [3, 10, 11, 12], [5, 13, 14, 15]],
columns=["A", "B", "C", "D"],
),
),
(
["C", "A", "D"],
np.array([[7, 8, 9], [10, 11, 12], [13, 14, 15]],
dtype=np.int64),
DataFrame(
[[8, 2, 7, 9], [11, 4, 10, 12], [14, 6, 13, 15]],
columns=["A", "B", "C", "D"],
),
),
(
["A", "C"],
DataFrame([[7, 8], [9, 10], [11, 12]], columns=["A", "C"]),
DataFrame([[7, 2, 8], [9, 4, 10], [11, 6, 12]],
columns=["A", "B", "C"]),
),
],
)
def test_setitem_list_missing_columns(self, columns, box, expected):
# GH#29334
df = DataFrame([[1, 2], [3, 4], [5, 6]], columns=["A", "B"])
df[columns] = box
tm.assert_frame_equal(df, expected)
def test_setitem_list_of_tuples(self, float_frame):
tuples = list(zip(float_frame["A"], float_frame["B"]))
float_frame["tuples"] = tuples
result = float_frame["tuples"]
expected = Series(tuples, index=float_frame.index, name="tuples")
tm.assert_series_equal(result, expected)
def test_setitem_iloc_generator(self):
# GH#39614
df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
indexer = (x for x in [1, 2])
df.iloc[indexer] = 1
expected = DataFrame({"a": [1, 1, 1], "b": [4, 1, 1]})
tm.assert_frame_equal(df, expected)
def test_setitem_iloc_two_dimensional_generator(self):
df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
indexer = (x for x in [1, 2])
df.iloc[indexer, 1] = 1
expected = DataFrame({"a": [1, 2, 3], "b": [4, 1, 1]})
tm.assert_frame_equal(df, expected)
def test_setitem_dtypes_bytes_type_to_object(self):
# GH 20734
index = Series(name="id", dtype="S24")
df = DataFrame(index=index)
df["a"] = Series(name="a", index=index, dtype=np.uint32)
df["b"] = Series(name="b", index=index, dtype="S64")
df["c"] = Series(name="c", index=index, dtype="S64")
df["d"] = Series(name="d", index=index, dtype=np.uint8)
result = df.dtypes
expected = Series([np.uint32, object, object, np.uint8],
index=list("abcd"))
tm.assert_series_equal(result, expected)
def test_boolean_mask_nullable_int64(self):
# GH 28928
result = DataFrame({
"a": [3, 4],
"b": [5, 6]
}).astype({
"a": "int64",
"b": "Int64"
})
mask = Series(False, index=result.index)
result.loc[mask, "a"] = result["a"]
result.loc[mask, "b"] = result["b"]
expected = DataFrame({
"a": [3, 4],
"b": [5, 6]
}).astype({
"a": "int64",
"b": "Int64"
})
tm.assert_frame_equal(result, expected)
def test_setitem_ea_dtype_rhs_series(self):
# GH#47425
df = DataFrame({"a": [1, 2]})
df["a"] = Series([1, 2], dtype="Int64")
expected = DataFrame({"a": [1, 2]}, dtype="Int64")
tm.assert_frame_equal(df, expected)
# TODO(ArrayManager) set column with 2d column array, see #44788
@td.skip_array_manager_not_yet_implemented
def test_setitem_npmatrix_2d(self):
# GH#42376
# for use-case df["x"] = sparse.random(10, 10).mean(axis=1)
expected = DataFrame(
{
"np-array": np.ones(10),
"np-matrix": np.ones(10)
},
index=np.arange(10))
a = np.ones((10, 1))
df = DataFrame(index=np.arange(10))
df["np-array"] = a
# Instantiation of `np.matrix` gives PendingDeprecationWarning
with tm.assert_produces_warning(PendingDeprecationWarning):
df["np-matrix"] = np.matrix(a)
tm.assert_frame_equal(df, expected)
@pytest.mark.parametrize("vals", [{}, {"d": "a"}])
def test_setitem_aligning_dict_with_index(self, vals):
# GH#47216
df = DataFrame({"a": [1, 2], "b": [3, 4], **vals})
df.loc[:, "a"] = {1: 100, 0: 200}
df.loc[:, "c"] = {0: 5, 1: 6}
df.loc[:, "e"] = {1: 5}
expected = DataFrame({
"a": [200, 100],
"b": [3, 4],
**vals, "c": [5, 6],
"e": [np.nan, 5]
})
tm.assert_frame_equal(df, expected)
def test_setitem_rhs_dataframe(self):
# GH#47578
df = DataFrame({"a": [1, 2]})
df["a"] = DataFrame({"a": [10, 11]}, index=[1, 2])
expected = DataFrame({"a": [np.nan, 10]})
tm.assert_frame_equal(df, expected)
df = DataFrame({"a": [1, 2]})
df.isetitem(0, DataFrame({"a": [10, 11]}, index=[1, 2]))
tm.assert_frame_equal(df, expected)
def test_000constructor_resolution(self):
# 2252
t1 = Timestamp((1352934390 * 1000000000) + 1000000 + 1000 + 1)
idx = DatetimeIndex([t1])
assert idx.nanosecond[0] == t1.nanosecond
def test_constructor_with_int_tz(self, klass, box, tz, dtype):
# GH 20997, 20964
ts = Timestamp("2018-01-01", tz=tz)
result = klass(box([ts.value]), dtype=dtype)
expected = klass([ts])
assert result == expected
tm.assert_frame_equal(result, expected)
# prod
result = df.groupby(pd.cut(df["a"], grps), observed=observed)._cython_agg_general(
"prod"
)
expected = pd.DataFrame(
{"a": [1, 1, 1716, 1]},
index=pd.CategoricalIndex(intervals, name="a", ordered=True),
)
if observed:
expected = expected[expected.a != 1]
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize("op", ["first", "last", "max", "min"])
@pytest.mark.parametrize(
"data", [Timestamp("2016-10-14 21:00:44.557"), Timedelta("17088 days 21:00:44.557")]
)
def test_cython_with_timestamp_and_nat(op, data):
# https://github.com/pandas-dev/pandas/issues/19526
df = DataFrame({"a": [0, 1], "b": [data, NaT]})
index = Index([0, 1], name="a")
# We will group by a and test the cython aggregations
expected = DataFrame({"b": [data, NaT]}, index=index)
result = df.groupby("a").aggregate(op)
tm.assert_frame_equal(expected, result)
def test_compare_hour13(self):
r = Timestamp("2000-08-12T13:00:00").to_julian_date()
assert r == 2_451_769.0416666666666666
def test_constructor_with_non_normalized_pytz(self, tz):
# GH 18595
non_norm_tz = Timestamp("2010", tz=tz).tz
result = DatetimeIndex(["2010"], tz=non_norm_tz)
assert pytz.timezone(tz) is result.tz
class TestTimedeltaMultiplicationDivision:
"""
Tests for Timedelta methods:
__mul__, __rmul__,
__div__, __rdiv__,
__truediv__, __rtruediv__,
__floordiv__, __rfloordiv__,
__mod__, __rmod__,
__divmod__, __rdivmod__
"""
# ---------------------------------------------------------------
# Timedelta.__mul__, __rmul__
@pytest.mark.parametrize(
"td_nat", [NaT, np.timedelta64("NaT", "ns"), np.timedelta64("NaT")]
)
@pytest.mark.parametrize("op", [operator.mul, ops.rmul])
def test_td_mul_nat(self, op, td_nat):
# GH#19819
td = Timedelta(10, unit="d")
with pytest.raises(TypeError):
op(td, td_nat)
@pytest.mark.parametrize("nan", [np.nan, np.float64("NaN"), float("nan")])
@pytest.mark.parametrize("op", [operator.mul, ops.rmul])
def test_td_mul_nan(self, op, nan):
# np.float64('NaN') has a 'dtype' attr, avoid treating as array
td = Timedelta(10, unit="d")
result = op(td, nan)
assert result is NaT
@pytest.mark.parametrize("op", [operator.mul, ops.rmul])
def test_td_mul_scalar(self, op):
# GH#19738
td = Timedelta(minutes=3)
result = op(td, 2)
assert result == Timedelta(minutes=6)
result = op(td, 1.5)
assert result == Timedelta(minutes=4, seconds=30)
assert op(td, np.nan) is NaT
assert op(-1, td).value == -1 * td.value
assert op(-1.0, td).value == -1.0 * td.value
with pytest.raises(TypeError):
# timedelta * datetime is gibberish
op(td, Timestamp(2016, 1, 2))
with pytest.raises(TypeError):
# invalid multiply with another timedelta
op(td, td)
# ---------------------------------------------------------------
# Timedelta.__div__, __truediv__
def test_td_div_timedeltalike_scalar(self):
# GH#19738
td = Timedelta(10, unit="d")
result = td / offsets.Hour(1)
assert result == 240
assert td / td == 1
assert td / np.timedelta64(60, "h") == 4
assert np.isnan(td / NaT)
def test_td_div_numeric_scalar(self):
# GH#19738
td = Timedelta(10, unit="d")
result = td / 2
assert isinstance(result, Timedelta)
assert result == Timedelta(days=5)
result = td / 5.0
assert isinstance(result, Timedelta)
assert result == Timedelta(days=2)
@pytest.mark.parametrize("nan", [np.nan, np.float64("NaN"), float("nan")])
def test_td_div_nan(self, nan):
# np.float64('NaN') has a 'dtype' attr, avoid treating as array
td = Timedelta(10, unit="d")
result = td / nan
assert result is NaT
result = td // nan
assert result is NaT
# ---------------------------------------------------------------
# Timedelta.__rdiv__
def test_td_rdiv_timedeltalike_scalar(self):
# GH#19738
td = Timedelta(10, unit="d")
result = offsets.Hour(1) / td
assert result == 1 / 240.0
assert np.timedelta64(60, "h") / td == 0.25
# ---------------------------------------------------------------
# Timedelta.__floordiv__
def test_td_floordiv_timedeltalike_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
scalar = Timedelta(hours=3, minutes=3)
assert td // scalar == 1
assert -td // scalar.to_pytimedelta() == -2
assert (2 * td) // scalar.to_timedelta64() == 2
def test_td_floordiv_null_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
assert td // np.nan is NaT
assert np.isnan(td // NaT)
assert np.isnan(td // np.timedelta64("NaT"))
def test_td_floordiv_offsets(self):
# GH#19738
td = Timedelta(hours=3, minutes=4)
assert td // offsets.Hour(1) == 3
assert td // offsets.Minute(2) == 92
def test_td_floordiv_invalid_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
with pytest.raises(TypeError):
td // np.datetime64("2016-01-01", dtype="datetime64[us]")
def test_td_floordiv_numeric_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
expected = Timedelta(hours=1, minutes=32)
assert td // 2 == expected
assert td // 2.0 == expected
assert td // np.float64(2.0) == expected
assert td // np.int32(2.0) == expected
assert td // np.uint8(2.0) == expected
def test_td_floordiv_timedeltalike_array(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
scalar = Timedelta(hours=3, minutes=3)
# Array-like others
assert td // np.array(scalar.to_timedelta64()) == 1
res = (3 * td) // np.array([scalar.to_timedelta64()])
expected = np.array([3], dtype=np.int64)
tm.assert_numpy_array_equal(res, expected)
res = (10 * td) // np.array([scalar.to_timedelta64(), np.timedelta64("NaT")])
expected = np.array([10, np.nan])
tm.assert_numpy_array_equal(res, expected)
def test_td_floordiv_numeric_series(self):
# GH#18846
td = Timedelta(hours=3, minutes=4)
ser = pd.Series([1], dtype=np.int64)
res = td // ser
assert res.dtype.kind == "m"
# ---------------------------------------------------------------
# Timedelta.__rfloordiv__
def test_td_rfloordiv_timedeltalike_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
scalar = Timedelta(hours=3, minutes=4)
# scalar others
# x // Timedelta is defined only for timedelta-like x. int-like,
# float-like, and date-like, in particular, should all either
# a) raise TypeError directly or
# b) return NotImplemented, following which the reversed
# operation will raise TypeError.
assert td.__rfloordiv__(scalar) == 1
assert (-td).__rfloordiv__(scalar.to_pytimedelta()) == -2
assert (2 * td).__rfloordiv__(scalar.to_timedelta64()) == 0
def test_td_rfloordiv_null_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
assert np.isnan(td.__rfloordiv__(NaT))
assert np.isnan(td.__rfloordiv__(np.timedelta64("NaT")))
def test_td_rfloordiv_offsets(self):
# GH#19738
assert offsets.Hour(1) // Timedelta(minutes=25) == 2
def test_td_rfloordiv_invalid_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
dt64 = np.datetime64("2016-01-01", dtype="datetime64[us]")
with pytest.raises(TypeError):
td.__rfloordiv__(dt64)
def test_td_rfloordiv_numeric_scalar(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
assert td.__rfloordiv__(np.nan) is NotImplemented
assert td.__rfloordiv__(3.5) is NotImplemented
assert td.__rfloordiv__(2) is NotImplemented
with pytest.raises(TypeError):
td.__rfloordiv__(np.float64(2.0))
with pytest.raises(TypeError):
td.__rfloordiv__(np.uint8(9))
with pytest.raises(TypeError, match="Invalid dtype"):
# deprecated GH#19761, enforced GH#29797
td.__rfloordiv__(np.int32(2.0))
def test_td_rfloordiv_timedeltalike_array(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
scalar = Timedelta(hours=3, minutes=4)
# Array-like others
assert td.__rfloordiv__(np.array(scalar.to_timedelta64())) == 1
res = td.__rfloordiv__(np.array([(3 * scalar).to_timedelta64()]))
expected = np.array([3], dtype=np.int64)
tm.assert_numpy_array_equal(res, expected)
arr = np.array([(10 * scalar).to_timedelta64(), np.timedelta64("NaT")])
res = td.__rfloordiv__(arr)
expected = np.array([10, np.nan])
tm.assert_numpy_array_equal(res, expected)
def test_td_rfloordiv_numeric_series(self):
# GH#18846
td = Timedelta(hours=3, minutes=3)
ser = pd.Series([1], dtype=np.int64)
res = td.__rfloordiv__(ser)
assert res is NotImplemented
with pytest.raises(TypeError, match="Invalid dtype"):
# Deprecated GH#19761, enforced GH#29797
# TODO: GH-19761. Change to TypeError.
ser // td
# ----------------------------------------------------------------
# Timedelta.__mod__, __rmod__
def test_mod_timedeltalike(self):
# GH#19365
td = Timedelta(hours=37)
# Timedelta-like others
result = td % Timedelta(hours=6)
assert isinstance(result, Timedelta)
assert result == Timedelta(hours=1)
result = td % timedelta(minutes=60)
assert isinstance(result, Timedelta)
assert result == Timedelta(0)
result = td % NaT
assert result is NaT
def test_mod_timedelta64_nat(self):
# GH#19365
td = Timedelta(hours=37)
result = td % np.timedelta64("NaT", "ns")
assert result is NaT
def test_mod_timedelta64(self):
# GH#19365
td = Timedelta(hours=37)
result = td % np.timedelta64(2, "h")
assert isinstance(result, Timedelta)
assert result == Timedelta(hours=1)
def test_mod_offset(self):
# GH#19365
td = Timedelta(hours=37)
result = td % offsets.Hour(5)
assert isinstance(result, Timedelta)
assert result == Timedelta(hours=2)
def test_mod_numeric(self):
# GH#19365
td = Timedelta(hours=37)
# Numeric Others
result = td % 2
assert isinstance(result, Timedelta)
assert result == Timedelta(0)
result = td % 1e12
assert isinstance(result, Timedelta)
assert result == Timedelta(minutes=3, seconds=20)
result = td % int(1e12)
assert isinstance(result, Timedelta)
assert result == Timedelta(minutes=3, seconds=20)
def test_mod_invalid(self):
# GH#19365
td = Timedelta(hours=37)
with pytest.raises(TypeError):
td % Timestamp("2018-01-22")
with pytest.raises(TypeError):
td % []
def test_rmod_pytimedelta(self):
# GH#19365
td = Timedelta(minutes=3)
result = timedelta(minutes=4) % td
assert isinstance(result, Timedelta)
assert result == Timedelta(minutes=1)
def test_rmod_timedelta64(self):
# GH#19365
td = Timedelta(minutes=3)
result = np.timedelta64(5, "m") % td
assert isinstance(result, Timedelta)
assert result == Timedelta(minutes=2)
def test_rmod_invalid(self):
# GH#19365
td = Timedelta(minutes=3)
with pytest.raises(TypeError):
Timestamp("2018-01-22") % td
with pytest.raises(TypeError):
15 % td
with pytest.raises(TypeError):
16.0 % td
with pytest.raises(TypeError):
np.array([22, 24]) % td
# ----------------------------------------------------------------
# Timedelta.__divmod__, __rdivmod__
def test_divmod_numeric(self):
# GH#19365
td = Timedelta(days=2, hours=6)
result = divmod(td, 53 * 3600 * 1e9)
assert result[0] == Timedelta(1, unit="ns")
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(hours=1)
assert result
result = divmod(td, np.nan)
assert result[0] is NaT
assert result[1] is NaT
def test_divmod(self):
# GH#19365
td = Timedelta(days=2, hours=6)
result = divmod(td, timedelta(days=1))
assert result[0] == 2
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(hours=6)
result = divmod(td, 54)
assert result[0] == Timedelta(hours=1)
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(0)
result = divmod(td, NaT)
assert np.isnan(result[0])
assert result[1] is NaT
def test_divmod_offset(self):
# GH#19365
td = Timedelta(days=2, hours=6)
result = divmod(td, offsets.Hour(-4))
assert result[0] == -14
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(hours=-2)
def test_divmod_invalid(self):
# GH#19365
td = Timedelta(days=2, hours=6)
with pytest.raises(TypeError):
divmod(td, Timestamp("2018-01-22"))
def test_rdivmod_pytimedelta(self):
# GH#19365
result = divmod(timedelta(days=2, hours=6), Timedelta(days=1))
assert result[0] == 2
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(hours=6)
def test_rdivmod_offset(self):
result = divmod(offsets.Hour(54), Timedelta(hours=-4))
assert result[0] == -14
assert isinstance(result[1], Timedelta)
assert result[1] == Timedelta(hours=-2)
def test_rdivmod_invalid(self):
# GH#19365
td = Timedelta(minutes=3)
with pytest.raises(TypeError):
divmod(Timestamp("2018-01-22"), td)
with pytest.raises(TypeError):
divmod(15, td)
with pytest.raises(TypeError):
divmod(16.0, td)
with pytest.raises(TypeError):
divmod(np.array([22, 24]), td)
# ----------------------------------------------------------------
@pytest.mark.parametrize(
"op", [operator.mul, ops.rmul, operator.truediv, ops.rdiv, ops.rsub]
)
@pytest.mark.parametrize(
"arr",
[
np.array([Timestamp("20130101 9:01"), Timestamp("20121230 9:02")]),
np.array([Timestamp.now(), Timedelta("1D")]),
],
)
def test_td_op_timedelta_timedeltalike_array(self, op, arr):
with pytest.raises(TypeError):
op(arr, Timedelta("1D"))
class TestContains:
def test_contains(self):
ci = CategoricalIndex(list("aabbca"),
categories=list("cabdef"),
ordered=False)
assert "a" in ci
assert "z" not in ci
assert "e" not in ci
assert np.nan not in ci
# assert codes NOT in index
assert 0 not in ci
assert 1 not in ci
def test_contains_nan(self):
ci = CategoricalIndex(list("aabbca") + [np.nan],
categories=list("cabdef"))
assert np.nan in ci
@pytest.mark.parametrize("unwrap", [True, False])
def test_contains_na_dtype(self, unwrap):
dti = pd.date_range("2016-01-01", periods=100).insert(0, pd.NaT)
pi = dti.to_period("D")
tdi = dti - dti[-1]
ci = CategoricalIndex(dti)
obj = ci
if unwrap:
obj = ci._data
assert np.nan in obj
assert None in obj
assert pd.NaT in obj
assert np.datetime64("NaT") in obj
assert np.timedelta64("NaT") not in obj
obj2 = CategoricalIndex(tdi)
if unwrap:
obj2 = obj2._data
assert np.nan in obj2
assert None in obj2
assert pd.NaT in obj2
assert np.datetime64("NaT") not in obj2
assert np.timedelta64("NaT") in obj2
obj3 = CategoricalIndex(pi)
if unwrap:
obj3 = obj3._data
assert np.nan in obj3
assert None in obj3
assert pd.NaT in obj3
assert np.datetime64("NaT") not in obj3
assert np.timedelta64("NaT") not in obj3
@pytest.mark.parametrize(
"item, expected",
[
(pd.Interval(0, 1), True),
(1.5, True),
(pd.Interval(0.5, 1.5), False),
("a", False),
(Timestamp(1), False),
(pd.Timedelta(1), False),
],
ids=str,
)
def test_contains_interval(self, item, expected):
# GH 23705
ci = CategoricalIndex(IntervalIndex.from_breaks(range(3)))
result = item in ci
assert result is expected
def test_contains_list(self):
# GH#21729
idx = CategoricalIndex([1, 2, 3])
assert "a" not in idx
with pytest.raises(TypeError, match="unhashable type"):
["a"] in idx
with pytest.raises(TypeError, match="unhashable type"):
["a", "b"] in idx
