class TestTimestampProperties:
def test_properties_business(self):
ts = Timestamp("2017-10-01", freq="B")
control = Timestamp("2017-10-01")
assert ts.dayofweek == 6
assert ts.day_of_week == 6
assert not ts.is_month_start # not a weekday
assert not ts.is_quarter_start # not a weekday
# Control case: non-business is month/qtr start
assert control.is_month_start
assert control.is_quarter_start
ts = Timestamp("2017-09-30", freq="B")
control = Timestamp("2017-09-30")
assert ts.dayofweek == 5
assert ts.day_of_week == 5
assert not ts.is_month_end # not a weekday
assert not ts.is_quarter_end # not a weekday
# Control case: non-business is month/qtr start
assert control.is_month_end
assert control.is_quarter_end
def test_fields(self):
def check(value, equal):
# that we are int like
assert isinstance(value, int)
assert value == equal
# GH 10050
ts = Timestamp("2015-05-10 09:06:03.000100001")
check(ts.year, 2015)
check(ts.month, 5)
check(ts.day, 10)
check(ts.hour, 9)
check(ts.minute, 6)
check(ts.second, 3)
msg = "'Timestamp' object has no attribute 'millisecond'"
with pytest.raises(AttributeError, match=msg):
ts.millisecond
check(ts.microsecond, 100)
check(ts.nanosecond, 1)
check(ts.dayofweek, 6)
check(ts.day_of_week, 6)
check(ts.quarter, 2)
check(ts.dayofyear, 130)
check(ts.day_of_year, 130)
check(ts.week, 19)
check(ts.daysinmonth, 31)
check(ts.daysinmonth, 31)
# GH 13303
ts = Timestamp("2014-12-31 23:59:00-05:00", tz="US/Eastern")
check(ts.year, 2014)
check(ts.month, 12)
check(ts.day, 31)
check(ts.hour, 23)
check(ts.minute, 59)
check(ts.second, 0)
msg = "'Timestamp' object has no attribute 'millisecond'"
with pytest.raises(AttributeError, match=msg):
ts.millisecond
check(ts.microsecond, 0)
check(ts.nanosecond, 0)
check(ts.dayofweek, 2)
check(ts.day_of_week, 2)
check(ts.quarter, 4)
check(ts.dayofyear, 365)
check(ts.day_of_year, 365)
check(ts.week, 1)
check(ts.daysinmonth, 31)
ts = Timestamp("2014-01-01 00:00:00+01:00")
starts = ["is_month_start", "is_quarter_start", "is_year_start"]
for start in starts:
assert getattr(ts, start)
ts = Timestamp("2014-12-31 23:59:59+01:00")
ends = ["is_month_end", "is_year_end", "is_quarter_end"]
for end in ends:
assert getattr(ts, end)
# GH 12806
@pytest.mark.parametrize(
"area_data",
[
Timestamp("2017-08-28 23:00:00"),
Timestamp("2017-08-28 23:00:00", tz="EST")
],
)
@pytest.mark.parametrize("time_locale",
[None] if tm.get_locales() is None else [None] +
tm.get_locales())
def test_names(self, data, time_locale):
# GH 17354
# Test .day_name(), .month_name
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
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_is_leap_year(self, tz_naive_fixture):
tz = tz_naive_fixture
# GH 13727
dt = Timestamp("2000-01-01 00:00:00", tz=tz)
assert dt.is_leap_year
assert isinstance(dt.is_leap_year, bool)
dt = Timestamp("1999-01-01 00:00:00", tz=tz)
assert not dt.is_leap_year
dt = Timestamp("2004-01-01 00:00:00", tz=tz)
assert dt.is_leap_year
dt = Timestamp("2100-01-01 00:00:00", tz=tz)
assert not dt.is_leap_year
def test_woy_boundary(self):
# make sure weeks at year boundaries are correct
d = datetime(2013, 12, 31)
result = Timestamp(d).week
expected = 1 # ISO standard
assert result == expected
d = datetime(2008, 12, 28)
result = Timestamp(d).week
expected = 52 # ISO standard
assert result == expected
d = datetime(2009, 12, 31)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
d = datetime(2010, 1, 1)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
d = datetime(2010, 1, 3)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
result = np.array([
Timestamp(datetime(*args)).week
for args in [(2000, 1, 1), (2000, 1, 2), (2005, 1, 1), (2005, 1,
2)]
])
assert (result == [52, 52, 53, 53]).all()
def test_resolution(self):
# GH#21336, GH#21365
dt = Timestamp("2100-01-01 00:00:00")
assert dt.resolution == Timedelta(nanoseconds=1)
# Check that the attribute is available on the class, mirroring
# the stdlib datetime behavior
assert Timestamp.resolution == Timedelta(nanoseconds=1)
class TestDatetime64:
def test_datetimeindex_accessors(self):
dti_naive = date_range(freq="D", start=datetime(1998, 1, 1), periods=365)
# GH#13303
dti_tz = date_range(
freq="D", start=datetime(1998, 1, 1), periods=365, tz="US/Eastern"
)
for dti in [dti_naive, dti_tz]:
assert dti.year[0] == 1998
assert dti.month[0] == 1
assert dti.day[0] == 1
assert dti.hour[0] == 0
assert dti.minute[0] == 0
assert dti.second[0] == 0
assert dti.microsecond[0] == 0
assert dti.dayofweek[0] == 3
assert dti.dayofyear[0] == 1
assert dti.dayofyear[120] == 121
assert dti.isocalendar().week[0] == 1
assert dti.isocalendar().week[120] == 18
assert dti.quarter[0] == 1
assert dti.quarter[120] == 2
assert dti.days_in_month[0] == 31
assert dti.days_in_month[90] == 30
assert dti.is_month_start[0]
assert not dti.is_month_start[1]
assert dti.is_month_start[31]
assert dti.is_quarter_start[0]
assert dti.is_quarter_start[90]
assert dti.is_year_start[0]
assert not dti.is_year_start[364]
assert not dti.is_month_end[0]
assert dti.is_month_end[30]
assert not dti.is_month_end[31]
assert dti.is_month_end[364]
assert not dti.is_quarter_end[0]
assert not dti.is_quarter_end[30]
assert dti.is_quarter_end[89]
assert dti.is_quarter_end[364]
assert not dti.is_year_end[0]
assert dti.is_year_end[364]
assert len(dti.year) == 365
assert len(dti.month) == 365
assert len(dti.day) == 365
assert len(dti.hour) == 365
assert len(dti.minute) == 365
assert len(dti.second) == 365
assert len(dti.microsecond) == 365
assert len(dti.dayofweek) == 365
assert len(dti.dayofyear) == 365
assert len(dti.isocalendar()) == 365
assert len(dti.quarter) == 365
assert len(dti.is_month_start) == 365
assert len(dti.is_month_end) == 365
assert len(dti.is_quarter_start) == 365
assert len(dti.is_quarter_end) == 365
assert len(dti.is_year_start) == 365
assert len(dti.is_year_end) == 365
dti.name = "name"
# non boolean accessors -> return Index
for accessor in DatetimeIndex._field_ops:
if accessor in ["week", "weekofyear"]:
# GH#33595 Deprecate week and weekofyear
continue
res = getattr(dti, accessor)
assert len(res) == 365
assert isinstance(res, Index)
assert res.name == "name"
# boolean accessors -> return array
for accessor in DatetimeIndex._bool_ops:
res = getattr(dti, accessor)
assert len(res) == 365
assert isinstance(res, np.ndarray)
# test boolean indexing
res = dti[dti.is_quarter_start]
exp = dti[[0, 90, 181, 273]]
tm.assert_index_equal(res, exp)
res = dti[dti.is_leap_year]
exp = DatetimeIndex([], freq="D", tz=dti.tz, name="name")
tm.assert_index_equal(res, exp)
def test_datetimeindex_accessors2(self):
dti = date_range(freq="BQ-FEB", start=datetime(1998, 1, 1), periods=4)
assert sum(dti.is_quarter_start) == 0
assert sum(dti.is_quarter_end) == 4
assert sum(dti.is_year_start) == 0
assert sum(dti.is_year_end) == 1
def test_datetimeindex_accessors3(self):
# Ensure is_start/end accessors throw ValueError for CustomBusinessDay,
bday_egypt = offsets.CustomBusinessDay(weekmask="Sun Mon Tue Wed Thu")
dti = date_range(datetime(2013, 4, 30), periods=5, freq=bday_egypt)
msg = "Custom business days is not supported by is_month_start"
with pytest.raises(ValueError, match=msg):
dti.is_month_start
def test_datetimeindex_accessors4(self):
dti = DatetimeIndex(["2000-01-01", "2000-01-02", "2000-01-03"])
assert dti.is_month_start[0] == 1
def test_datetimeindex_accessors5(self):
tests = [
(Timestamp("2013-06-01", freq="M").is_month_start, 1),
(Timestamp("2013-06-01", freq="BM").is_month_start, 0),
(Timestamp("2013-06-03", freq="M").is_month_start, 0),
(Timestamp("2013-06-03", freq="BM").is_month_start, 1),
(Timestamp("2013-02-28", freq="Q-FEB").is_month_end, 1),
(Timestamp("2013-02-28", freq="Q-FEB").is_quarter_end, 1),
(Timestamp("2013-02-28", freq="Q-FEB").is_year_end, 1),
(Timestamp("2013-03-01", freq="Q-FEB").is_month_start, 1),
(Timestamp("2013-03-01", freq="Q-FEB").is_quarter_start, 1),
(Timestamp("2013-03-01", freq="Q-FEB").is_year_start, 1),
(Timestamp("2013-03-31", freq="QS-FEB").is_month_end, 1),
(Timestamp("2013-03-31", freq="QS-FEB").is_quarter_end, 0),
(Timestamp("2013-03-31", freq="QS-FEB").is_year_end, 0),
(Timestamp("2013-02-01", freq="QS-FEB").is_month_start, 1),
(Timestamp("2013-02-01", freq="QS-FEB").is_quarter_start, 1),
(Timestamp("2013-02-01", freq="QS-FEB").is_year_start, 1),
(Timestamp("2013-06-30", freq="BQ").is_month_end, 0),
(Timestamp("2013-06-30", freq="BQ").is_quarter_end, 0),
(Timestamp("2013-06-30", freq="BQ").is_year_end, 0),
(Timestamp("2013-06-28", freq="BQ").is_month_end, 1),
(Timestamp("2013-06-28", freq="BQ").is_quarter_end, 1),
(Timestamp("2013-06-28", freq="BQ").is_year_end, 0),
(Timestamp("2013-06-30", freq="BQS-APR").is_month_end, 0),
(Timestamp("2013-06-30", freq="BQS-APR").is_quarter_end, 0),
(Timestamp("2013-06-30", freq="BQS-APR").is_year_end, 0),
(Timestamp("2013-06-28", freq="BQS-APR").is_month_end, 1),
(Timestamp("2013-06-28", freq="BQS-APR").is_quarter_end, 1),
(Timestamp("2013-03-29", freq="BQS-APR").is_year_end, 1),
(Timestamp("2013-11-01", freq="AS-NOV").is_year_start, 1),
(Timestamp("2013-10-31", freq="AS-NOV").is_year_end, 1),
(Timestamp("2012-02-01").days_in_month, 29),
(Timestamp("2013-02-01").days_in_month, 28),
]
for ts, value in tests:
assert ts == value
def test_datetimeindex_accessors6(self):
# GH 6538: Check that DatetimeIndex and its TimeStamp elements
# return the same weekofyear accessor close to new year w/ tz
dates = ["2013/12/29", "2013/12/30", "2013/12/31"]
dates = DatetimeIndex(dates, tz="Europe/Brussels")
expected = [52, 1, 1]
assert dates.isocalendar().week.tolist() == expected
assert [d.weekofyear for d in dates] == expected
# GH 12806
@pytest.mark.parametrize(
"time_locale", [None] if tm.get_locales() is None else [None] + tm.get_locales()
)
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 = 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.day_name(locale=time_locale)[day] == name
assert dti.day_name(locale=None)[day] == eng_name
ts = Timestamp(datetime(2016, 4, day))
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 = 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
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()
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])
def test_nanosecond_field(self):
dti = DatetimeIndex(np.arange(10))
tm.assert_index_equal(dti.nanosecond, Index(np.arange(10, dtype=np.int64)))
class TestSeriesDatetimeValues:
def test_dt_namespace_accessor(self):
# GH 7207, 11128
# test .dt namespace accessor
ok_for_period = PeriodArray._datetimelike_ops
ok_for_period_methods = ["strftime", "to_timestamp", "asfreq"]
ok_for_dt = DatetimeArray._datetimelike_ops
ok_for_dt_methods = [
"to_period",
"to_pydatetime",
"tz_localize",
"tz_convert",
"normalize",
"strftime",
"round",
"floor",
"ceil",
"day_name",
"month_name",
"isocalendar",
]
ok_for_td = TimedeltaArray._datetimelike_ops
ok_for_td_methods = [
"components",
"to_pytimedelta",
"total_seconds",
"round",
"floor",
"ceil",
]
def get_expected(s, name):
result = getattr(Index(s._values), prop)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype("int64")
elif not is_list_like(result) or isinstance(result, DataFrame):
return result
return Series(result, index=s.index, name=s.name)
def compare(s, name):
a = getattr(s.dt, prop)
b = get_expected(s, prop)
if not (is_list_like(a) and is_list_like(b)):
assert a == b
elif isinstance(a, DataFrame):
tm.assert_frame_equal(a, b)
else:
tm.assert_series_equal(a, b)
# datetimeindex
cases = [
Series(date_range("20130101", periods=5), name="xxx"),
Series(date_range("20130101", periods=5, freq="s"), name="xxx"),
Series(date_range("20130101 00:00:00", periods=5, freq="ms"), name="xxx"),
]
for s in cases:
for prop in ok_for_dt:
# we test freq below
# we ignore week and weekofyear because they are deprecated
if prop not in ["freq", "week", "weekofyear"]:
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
assert isinstance(result, np.ndarray)
assert result.dtype == object
result = s.dt.tz_localize("US/Eastern")
exp_values = DatetimeIndex(s.values).tz_localize("US/Eastern")
expected = Series(exp_values, index=s.index, name="xxx")
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
assert str(tz_result) == "US/Eastern"
freq_result = s.dt.freq
assert freq_result == DatetimeIndex(s.values, freq="infer").freq
# let's localize, then convert
result = s.dt.tz_localize("UTC").dt.tz_convert("US/Eastern")
exp_values = (
DatetimeIndex(s.values).tz_localize("UTC").tz_convert("US/Eastern")
)
expected = Series(exp_values, index=s.index, name="xxx")
tm.assert_series_equal(result, expected)
# datetimeindex with tz
s = Series(date_range("20130101", periods=5, tz="US/Eastern"), name="xxx")
for prop in ok_for_dt:
# we test freq below
# we ignore week and weekofyear because they are deprecated
if prop not in ["freq", "week", "weekofyear"]:
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
assert isinstance(result, np.ndarray)
assert result.dtype == object
result = s.dt.tz_convert("CET")
expected = Series(s._values.tz_convert("CET"), index=s.index, name="xxx")
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
assert str(tz_result) == "CET"
freq_result = s.dt.freq
assert freq_result == DatetimeIndex(s.values, freq="infer").freq
# timedelta index
cases = [
Series(
timedelta_range("1 day", periods=5), index=list("abcde"), name="xxx"
),
Series(timedelta_range("1 day 01:23:45", periods=5, freq="s"), name="xxx"),
Series(
timedelta_range("2 days 01:23:45.012345", periods=5, freq="ms"),
name="xxx",
),
]
for s in cases:
for prop in ok_for_td:
# we test freq below
if prop != "freq":
compare(s, prop)
for prop in ok_for_td_methods:
getattr(s.dt, prop)
result = s.dt.components
assert isinstance(result, DataFrame)
tm.assert_index_equal(result.index, s.index)
result = s.dt.to_pytimedelta()
assert isinstance(result, np.ndarray)
assert result.dtype == object
result = s.dt.total_seconds()
assert isinstance(result, Series)
assert result.dtype == "float64"
freq_result = s.dt.freq
assert freq_result == TimedeltaIndex(s.values, freq="infer").freq
# both
index = date_range("20130101", periods=3, freq="D")
s = Series(date_range("20140204", periods=3, freq="s"), index=index, name="xxx")
exp = Series(
np.array([2014, 2014, 2014], dtype="int64"), index=index, name="xxx"
)
tm.assert_series_equal(s.dt.year, exp)
exp = Series(np.array([2, 2, 2], dtype="int64"), index=index, name="xxx")
tm.assert_series_equal(s.dt.month, exp)
exp = Series(np.array([0, 1, 2], dtype="int64"), index=index, name="xxx")
tm.assert_series_equal(s.dt.second, exp)
exp = Series([s[0]] * 3, index=index, name="xxx")
tm.assert_series_equal(s.dt.normalize(), exp)
# periodindex
cases = [Series(period_range("20130101", periods=5, freq="D"), name="xxx")]
for s in cases:
for prop in ok_for_period:
# we test freq below
if prop != "freq":
compare(s, prop)
for prop in ok_for_period_methods:
getattr(s.dt, prop)
freq_result = s.dt.freq
assert freq_result == PeriodIndex(s.values).freq
# test limited display api
def get_dir(s):
results = [r for r in s.dt.__dir__() if not r.startswith("_")]
return sorted(set(results))
s = Series(date_range("20130101", periods=5, freq="D"), name="xxx")
results = get_dir(s)
tm.assert_almost_equal(results, sorted(set(ok_for_dt + ok_for_dt_methods)))
s = Series(
period_range("20130101", periods=5, freq="D", name="xxx").astype(object)
)
results = get_dir(s)
tm.assert_almost_equal(
results, sorted(set(ok_for_period + ok_for_period_methods))
)
# 11295
# ambiguous time error on the conversions
s = Series(date_range("2015-01-01", "2016-01-01", freq="T"), name="xxx")
s = s.dt.tz_localize("UTC").dt.tz_convert("America/Chicago")
results = get_dir(s)
tm.assert_almost_equal(results, sorted(set(ok_for_dt + ok_for_dt_methods)))
exp_values = date_range(
"2015-01-01", "2016-01-01", freq="T", tz="UTC"
).tz_convert("America/Chicago")
# freq not preserved by tz_localize above
exp_values = exp_values._with_freq(None)
expected = Series(exp_values, name="xxx")
tm.assert_series_equal(s, expected)
# no setting allowed
s = Series(date_range("20130101", periods=5, freq="D"), name="xxx")
with pytest.raises(ValueError, match="modifications"):
s.dt.hour = 5
# trying to set a copy
msg = "modifications to a property of a datetimelike.+not supported"
with pd.option_context("chained_assignment", "raise"):
with pytest.raises(com.SettingWithCopyError, match=msg):
s.dt.hour[0] = 5
@pytest.mark.parametrize(
"method, dates",
[
["round", ["2012-01-02", "2012-01-02", "2012-01-01"]],
["floor", ["2012-01-01", "2012-01-01", "2012-01-01"]],
["ceil", ["2012-01-02", "2012-01-02", "2012-01-02"]],
],
)
def test_dt_round(self, method, dates):
# round
s = Series(
pd.to_datetime(
["2012-01-01 13:00:00", "2012-01-01 12:01:00", "2012-01-01 08:00:00"]
),
name="xxx",
)
result = getattr(s.dt, method)("D")
expected = Series(pd.to_datetime(dates), name="xxx")
tm.assert_series_equal(result, expected)
def test_dt_round_tz(self):
s = Series(
pd.to_datetime(
["2012-01-01 13:00:00", "2012-01-01 12:01:00", "2012-01-01 08:00:00"]
),
name="xxx",
)
result = s.dt.tz_localize("UTC").dt.tz_convert("US/Eastern").dt.round("D")
exp_values = pd.to_datetime(
["2012-01-01", "2012-01-01", "2012-01-01"]
).tz_localize("US/Eastern")
expected = Series(exp_values, name="xxx")
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("method", ["ceil", "round", "floor"])
def test_dt_round_tz_ambiguous(self, method):
# GH 18946 round near "fall back" DST
df1 = DataFrame(
[
pd.to_datetime("2017-10-29 02:00:00+02:00", utc=True),
pd.to_datetime("2017-10-29 02:00:00+01:00", utc=True),
pd.to_datetime("2017-10-29 03:00:00+01:00", utc=True),
],
columns=["date"],
)
df1["date"] = df1["date"].dt.tz_convert("Europe/Madrid")
# infer
result = getattr(df1.date.dt, method)("H", ambiguous="infer")
expected = df1["date"]
tm.assert_series_equal(result, expected)
# bool-array
result = getattr(df1.date.dt, method)("H", ambiguous=[True, False, False])
tm.assert_series_equal(result, expected)
# NaT
result = getattr(df1.date.dt, method)("H", ambiguous="NaT")
expected = df1["date"].copy()
expected.iloc[0:2] = pd.NaT
tm.assert_series_equal(result, expected)
# raise
with tm.external_error_raised(pytz.AmbiguousTimeError):
getattr(df1.date.dt, method)("H", ambiguous="raise")
@pytest.mark.parametrize(
"method, ts_str, freq",
[
["ceil", "2018-03-11 01:59:00-0600", "5min"],
["round", "2018-03-11 01:59:00-0600", "5min"],
["floor", "2018-03-11 03:01:00-0500", "2H"],
],
)
def test_dt_round_tz_nonexistent(self, method, ts_str, freq):
# GH 23324 round near "spring forward" DST
s = Series([pd.Timestamp(ts_str, tz="America/Chicago")])
result = getattr(s.dt, method)(freq, nonexistent="shift_forward")
expected = Series([pd.Timestamp("2018-03-11 03:00:00", tz="America/Chicago")])
tm.assert_series_equal(result, expected)
result = getattr(s.dt, method)(freq, nonexistent="NaT")
expected = Series([pd.NaT]).dt.tz_localize(result.dt.tz)
tm.assert_series_equal(result, expected)
with pytest.raises(pytz.NonExistentTimeError, match="2018-03-11 02:00:00"):
getattr(s.dt, method)(freq, nonexistent="raise")
def test_dt_namespace_accessor_categorical(self):
# GH 19468
dti = DatetimeIndex(["20171111", "20181212"]).repeat(2)
s = Series(pd.Categorical(dti), name="foo")
result = s.dt.year
expected = Series([2017, 2017, 2018, 2018], name="foo")
tm.assert_series_equal(result, expected)
def test_dt_tz_localize_categorical(self, tz_aware_fixture):
# GH 27952
tz = tz_aware_fixture
datetimes = Series(
["2019-01-01", "2019-01-01", "2019-01-02"], dtype="datetime64[ns]"
)
categorical = datetimes.astype("category")
result = categorical.dt.tz_localize(tz)
expected = datetimes.dt.tz_localize(tz)
tm.assert_series_equal(result, expected)
def test_dt_tz_convert_categorical(self, tz_aware_fixture):
# GH 27952
tz = tz_aware_fixture
datetimes = Series(
["2019-01-01", "2019-01-01", "2019-01-02"], dtype="datetime64[ns, MET]"
)
categorical = datetimes.astype("category")
result = categorical.dt.tz_convert(tz)
expected = datetimes.dt.tz_convert(tz)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("accessor", ["year", "month", "day"])
def test_dt_other_accessors_categorical(self, accessor):
# GH 27952
datetimes = Series(
["2018-01-01", "2018-01-01", "2019-01-02"], dtype="datetime64[ns]"
)
categorical = datetimes.astype("category")
result = getattr(categorical.dt, accessor)
expected = getattr(datetimes.dt, accessor)
tm.assert_series_equal(result, expected)
def test_dt_accessor_no_new_attributes(self):
# https://github.com/pandas-dev/pandas/issues/10673
s = Series(date_range("20130101", periods=5, freq="D"))
with pytest.raises(AttributeError, match="You cannot add any new attribute"):
s.dt.xlabel = "a"
@pytest.mark.parametrize(
"time_locale", [None] if tm.get_locales() is None else [None] + tm.get_locales()
)
def test_dt_accessor_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:]
s = Series(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 s.dt.day_name(locale=time_locale)[day] == name
assert s.dt.day_name(locale=None)[day] == eng_name
s = s.append(Series([pd.NaT]))
assert np.isnan(s.dt.day_name(locale=time_locale).iloc[-1])
s = Series(date_range(freq="M", start="2012", end="2013"))
result = s.dt.month_name(locale=time_locale)
expected = Series([month.capitalize() for month in expected_months])
# work around https://github.com/pandas-dev/pandas/issues/22342
result = result.str.normalize("NFD")
expected = expected.str.normalize("NFD")
tm.assert_series_equal(result, expected)
for s_date, expected in zip(s, expected_months):
result = s_date.month_name(locale=time_locale)
expected = expected.capitalize()
result = unicodedata.normalize("NFD", result)
expected = unicodedata.normalize("NFD", expected)
assert result == expected
s = s.append(Series([pd.NaT]))
assert np.isnan(s.dt.month_name(locale=time_locale).iloc[-1])
def test_strftime(self):
# GH 10086
s = Series(date_range("20130101", periods=5))
result = s.dt.strftime("%Y/%m/%d")
expected = Series(
["2013/01/01", "2013/01/02", "2013/01/03", "2013/01/04", "2013/01/05"]
)
tm.assert_series_equal(result, expected)
s = Series(date_range("2015-02-03 11:22:33.4567", periods=5))
result = s.dt.strftime("%Y/%m/%d %H-%M-%S")
expected = Series(
[
"2015/02/03 11-22-33",
"2015/02/04 11-22-33",
"2015/02/05 11-22-33",
"2015/02/06 11-22-33",
"2015/02/07 11-22-33",
]
)
tm.assert_series_equal(result, expected)
s = Series(period_range("20130101", periods=5))
result = s.dt.strftime("%Y/%m/%d")
expected = Series(
["2013/01/01", "2013/01/02", "2013/01/03", "2013/01/04", "2013/01/05"]
)
tm.assert_series_equal(result, expected)
s = Series(period_range("2015-02-03 11:22:33.4567", periods=5, freq="s"))
result = s.dt.strftime("%Y/%m/%d %H-%M-%S")
expected = Series(
[
"2015/02/03 11-22-33",
"2015/02/03 11-22-34",
"2015/02/03 11-22-35",
"2015/02/03 11-22-36",
"2015/02/03 11-22-37",
]
)
tm.assert_series_equal(result, expected)
s = Series(date_range("20130101", periods=5))
s.iloc[0] = pd.NaT
result = s.dt.strftime("%Y/%m/%d")
expected = Series(
[np.nan, "2013/01/02", "2013/01/03", "2013/01/04", "2013/01/05"]
)
tm.assert_series_equal(result, expected)
datetime_index = date_range("20150301", periods=5)
result = datetime_index.strftime("%Y/%m/%d")
expected = Index(
["2015/03/01", "2015/03/02", "2015/03/03", "2015/03/04", "2015/03/05"],
dtype=np.object_,
)
# dtype may be S10 or U10 depending on python version
tm.assert_index_equal(result, expected)
period_index = period_range("20150301", periods=5)
result = period_index.strftime("%Y/%m/%d")
expected = Index(
["2015/03/01", "2015/03/02", "2015/03/03", "2015/03/04", "2015/03/05"],
dtype="=U10",
)
tm.assert_index_equal(result, expected)
s = Series([datetime(2013, 1, 1, 2, 32, 59), datetime(2013, 1, 2, 14, 32, 1)])
result = s.dt.strftime("%Y-%m-%d %H:%M:%S")
expected = Series(["2013-01-01 02:32:59", "2013-01-02 14:32:01"])
tm.assert_series_equal(result, expected)
s = Series(period_range("20130101", periods=4, freq="H"))
result = s.dt.strftime("%Y/%m/%d %H:%M:%S")
expected = Series(
[
"2013/01/01 00:00:00",
"2013/01/01 01:00:00",
"2013/01/01 02:00:00",
"2013/01/01 03:00:00",
]
)
s = Series(period_range("20130101", periods=4, freq="L"))
result = s.dt.strftime("%Y/%m/%d %H:%M:%S.%l")
expected = Series(
[
"2013/01/01 00:00:00.000",
"2013/01/01 00:00:00.001",
"2013/01/01 00:00:00.002",
"2013/01/01 00:00:00.003",
]
)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"data",
[
DatetimeIndex(["2019-01-01", pd.NaT]),
PeriodIndex(["2019-01-01", pd.NaT], dtype="period[D]"),
],
)
def test_strftime_nat(self, data):
# GH 29578
s = Series(data)
result = s.dt.strftime("%Y-%m-%d")
expected = Series(["2019-01-01", np.nan])
tm.assert_series_equal(result, expected)
def test_valid_dt_with_missing_values(self):
from datetime import (
date,
time,
)
# GH 8689
s = Series(date_range("20130101", periods=5, freq="D"))
s.iloc[2] = pd.NaT
for attr in ["microsecond", "nanosecond", "second", "minute", "hour", "day"]:
expected = getattr(s.dt, attr).copy()
expected.iloc[2] = np.nan
result = getattr(s.dt, attr)
tm.assert_series_equal(result, expected)
result = s.dt.date
expected = Series(
[
date(2013, 1, 1),
date(2013, 1, 2),
np.nan,
date(2013, 1, 4),
date(2013, 1, 5),
],
dtype="object",
)
tm.assert_series_equal(result, expected)
result = s.dt.time
expected = Series([time(0), time(0), np.nan, time(0), time(0)], dtype="object")
tm.assert_series_equal(result, expected)
def test_dt_accessor_api(self):
# GH 9322
from pandas.core.indexes.accessors import (
CombinedDatetimelikeProperties,
DatetimeProperties,
)
assert Series.dt is CombinedDatetimelikeProperties
s = Series(date_range("2000-01-01", periods=3))
assert isinstance(s.dt, DatetimeProperties)
@pytest.mark.parametrize(
"ser", [Series(np.arange(5)), Series(list("abcde")), Series(np.random.randn(5))]
)
def test_dt_accessor_invalid(self, ser):
# GH#9322 check that series with incorrect dtypes don't have attr
with pytest.raises(AttributeError, match="only use .dt accessor"):
ser.dt
assert not hasattr(ser, "dt")
def test_dt_accessor_updates_on_inplace(self):
s = Series(date_range("2018-01-01", periods=10))
s[2] = None
return_value = s.fillna(pd.Timestamp("2018-01-01"), inplace=True)
assert return_value is None
result = s.dt.date
assert result[0] == result[2]
def test_date_tz(self):
# GH11757
rng = DatetimeIndex(
["2014-04-04 23:56", "2014-07-18 21:24", "2015-11-22 22:14"],
tz="US/Eastern",
)
s = Series(rng)
expected = Series([date(2014, 4, 4), date(2014, 7, 18), date(2015, 11, 22)])
tm.assert_series_equal(s.dt.date, expected)
tm.assert_series_equal(s.apply(lambda x: x.date()), expected)
def test_dt_timetz_accessor(self, tz_naive_fixture):
# GH21358
tz = maybe_get_tz(tz_naive_fixture)
dtindex = DatetimeIndex(
["2014-04-04 23:56", "2014-07-18 21:24", "2015-11-22 22:14"], tz=tz
)
s = Series(dtindex)
expected = Series(
[time(23, 56, tzinfo=tz), time(21, 24, tzinfo=tz), time(22, 14, tzinfo=tz)]
)
result = s.dt.timetz
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"input_series, expected_output",
[
[["2020-01-01"], [[2020, 1, 3]]],
[[pd.NaT], [[np.NaN, np.NaN, np.NaN]]],
[["2019-12-31", "2019-12-29"], [[2020, 1, 2], [2019, 52, 7]]],
[["2010-01-01", pd.NaT], [[2009, 53, 5], [np.NaN, np.NaN, np.NaN]]],
# see GH#36032
[["2016-01-08", "2016-01-04"], [[2016, 1, 5], [2016, 1, 1]]],
[["2016-01-07", "2016-01-01"], [[2016, 1, 4], [2015, 53, 5]]],
],
)
@pytest.mark.filterwarnings("ignore:Inferring datetime64:FutureWarning")
def test_isocalendar(self, input_series, expected_output):
result = pd.to_datetime(Series(input_series)).dt.isocalendar()
expected_frame = DataFrame(
expected_output, columns=["year", "week", "day"], dtype="UInt32"
)
tm.assert_frame_equal(result, expected_frame)
class TestTimestampProperties:
def test_freq_deprecation(self):
# GH#41586
msg = "The 'freq' argument in Timestamp is deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
# warning issued at construction
ts = Timestamp("2021-06-01", freq="D")
ts2 = Timestamp("2021-06-01", freq="B")
msg = "Timestamp.freq is deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
# warning issued at attribute lookup
ts.freq
for per in ["month", "quarter", "year"]:
for side in ["start", "end"]:
attr = f"is_{per}_{side}"
with tm.assert_produces_warning(FutureWarning, match=msg):
getattr(ts2, attr)
# is_(month|quarter|year)_(start|end) does _not_ issue a warning
# with freq="D" bc the result will be unaffected by the deprecation
with tm.assert_produces_warning(None):
getattr(ts, attr)
@pytest.mark.filterwarnings("ignore:The 'freq' argument:FutureWarning")
@pytest.mark.filterwarnings(
"ignore:Timestamp.freq is deprecated:FutureWarning")
def test_properties_business(self):
ts = Timestamp("2017-10-01", freq="B")
control = Timestamp("2017-10-01")
assert ts.dayofweek == 6
assert ts.day_of_week == 6
assert not ts.is_month_start # not a weekday
assert not ts.freq.is_month_start(ts)
assert ts.freq.is_month_start(ts + Timedelta(days=1))
assert not ts.is_quarter_start # not a weekday
assert not ts.freq.is_quarter_start(ts)
assert ts.freq.is_quarter_start(ts + Timedelta(days=1))
# Control case: non-business is month/qtr start
assert control.is_month_start
assert control.is_quarter_start
ts = Timestamp("2017-09-30", freq="B")
control = Timestamp("2017-09-30")
assert ts.dayofweek == 5
assert ts.day_of_week == 5
assert not ts.is_month_end # not a weekday
assert not ts.freq.is_month_end(ts)
assert ts.freq.is_month_end(ts - Timedelta(days=1))
assert not ts.is_quarter_end # not a weekday
assert not ts.freq.is_quarter_end(ts)
assert ts.freq.is_quarter_end(ts - Timedelta(days=1))
# Control case: non-business is month/qtr start
assert control.is_month_end
assert control.is_quarter_end
@pytest.mark.parametrize(
"attr, expected",
[
["year", 2014],
["month", 12],
["day", 31],
["hour", 23],
["minute", 59],
["second", 0],
["microsecond", 0],
["nanosecond", 0],
["dayofweek", 2],
["day_of_week", 2],
["quarter", 4],
["dayofyear", 365],
["day_of_year", 365],
["week", 1],
["daysinmonth", 31],
],
)
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_fields(self, attr, expected, tz):
# GH 10050
# GH 13303
ts = Timestamp("2014-12-31 23:59:00", tz=tz)
result = getattr(ts, attr)
# that we are int like
assert isinstance(result, int)
assert result == expected
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_millisecond_raises(self, tz):
ts = Timestamp("2014-12-31 23:59:00", tz=tz)
msg = "'Timestamp' object has no attribute 'millisecond'"
with pytest.raises(AttributeError, match=msg):
ts.millisecond
@pytest.mark.parametrize(
"start", ["is_month_start", "is_quarter_start", "is_year_start"])
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_is_start(self, start, tz):
ts = Timestamp("2014-01-01 00:00:00", tz=tz)
assert getattr(ts, start)
@pytest.mark.parametrize("end",
["is_month_end", "is_year_end", "is_quarter_end"])
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_is_end(self, end, tz):
ts = Timestamp("2014-12-31 23:59:59", tz=tz)
assert getattr(ts, end)
# GH 12806
@pytest.mark.parametrize(
"data",
[
Timestamp("2017-08-28 23:00:00"),
Timestamp("2017-08-28 23:00:00", tz="EST")
],
)
# error: Unsupported operand types for + ("List[None]" and "List[str]")
@pytest.mark.parametrize(
"time_locale",
[None] + (tm.get_locales() or []) # type: ignore[operator]
)
def test_names(self, data, time_locale):
# GH 17354
# Test .day_name(), .month_name
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
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_is_leap_year(self, tz_naive_fixture):
tz = tz_naive_fixture
# GH 13727
dt = Timestamp("2000-01-01 00:00:00", tz=tz)
assert dt.is_leap_year
assert isinstance(dt.is_leap_year, bool)
dt = Timestamp("1999-01-01 00:00:00", tz=tz)
assert not dt.is_leap_year
dt = Timestamp("2004-01-01 00:00:00", tz=tz)
assert dt.is_leap_year
dt = Timestamp("2100-01-01 00:00:00", tz=tz)
assert not dt.is_leap_year
def test_woy_boundary(self):
# make sure weeks at year boundaries are correct
d = datetime(2013, 12, 31)
result = Timestamp(d).week
expected = 1 # ISO standard
assert result == expected
d = datetime(2008, 12, 28)
result = Timestamp(d).week
expected = 52 # ISO standard
assert result == expected
d = datetime(2009, 12, 31)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
d = datetime(2010, 1, 1)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
d = datetime(2010, 1, 3)
result = Timestamp(d).week
expected = 53 # ISO standard
assert result == expected
result = np.array([
Timestamp(datetime(*args)).week
for args in [(2000, 1, 1), (2000, 1, 2), (2005, 1, 1), (2005, 1,
2)]
])
assert (result == [52, 52, 53, 53]).all()
def test_resolution(self):
# GH#21336, GH#21365
dt = Timestamp("2100-01-01 00:00:00")
assert dt.resolution == Timedelta(nanoseconds=1)
# Check that the attribute is available on the class, mirroring
# the stdlib datetime behavior
assert Timestamp.resolution == Timedelta(nanoseconds=1)
