def test_get_year_end(self):
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.SAT).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 8, 31))
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.SUN).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 9, 1))
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.FRI).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 8, 30))
offset_n = FY5253(weekday=WeekDay.TUE,
startingMonth=12,
variation="nearest")
assert (offset_n.get_year_end(datetime(2012, 1,
1)) == datetime(2013, 1, 1))
assert (offset_n.get_year_end(datetime(2012, 1,
10)) == datetime(2013, 1, 1))
assert (offset_n.get_year_end(datetime(2013, 1,
1)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
2)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
3)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
10)) == datetime(2013, 12, 31))
JNJ = FY5253(n=1, startingMonth=12, weekday=6, variation="nearest")
assert (JNJ.get_year_end(datetime(2006, 1,
1)) == datetime(2006, 12, 31))
def test_fy5253_nearest_onoffset():
# GH#18877 dates on the year-end but not normalized to midnight
offset = FY5253(n=3, startingMonth=7, variation="nearest", weekday=2)
ts = Timestamp('2032-07-28 00:12:59.035729419+0000', tz='Africa/Dakar')
fast = offset.onOffset(ts)
slow = (ts + offset) - offset == ts
assert fast == slow
def test_fy5253_last_onoffset():
# GH#18877 dates on the year-end but not normalized to midnight
offset = FY5253(n=-5, startingMonth=5, variation="last", weekday=0)
ts = Timestamp("1984-05-28 06:29:43.955911354+0200", tz="Europe/San_Marino")
fast = offset.is_on_offset(ts)
slow = (ts + offset) - offset == ts
assert fast == slow
def test_apply(self):
date_seq_nem_8_sat = [datetime(2006, 9, 2), datetime(2007, 9, 1),
datetime(2008, 8, 30), datetime(2009, 8, 29),
datetime(2010, 8, 28), datetime(2011, 9, 3)]
JNJ = [datetime(2005, 1, 2), datetime(2006, 1, 1),
datetime(2006, 12, 31), datetime(2007, 12, 30),
datetime(2008, 12, 28), datetime(2010, 1, 3),
datetime(2011, 1, 2), datetime(2012, 1, 1),
datetime(2012, 12, 30)]
DEC_SAT = FY5253(n=-1, startingMonth=12, weekday=5,
variation="nearest")
tests = [
(makeFY5253NearestEndMonth(startingMonth=8,
weekday=WeekDay.SAT),
date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(n=1, startingMonth=8,
weekday=WeekDay.SAT),
date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(startingMonth=8, weekday=WeekDay.SAT),
[datetime(2006, 9, 1)] + date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(n=1, startingMonth=8,
weekday=WeekDay.SAT),
[datetime(2006, 9, 3)] + date_seq_nem_8_sat[1:]),
(makeFY5253NearestEndMonth(n=-1, startingMonth=8,
weekday=WeekDay.SAT),
list(reversed(date_seq_nem_8_sat))),
(makeFY5253NearestEndMonth(n=1, startingMonth=12,
weekday=WeekDay.SUN), JNJ),
(makeFY5253NearestEndMonth(n=-1, startingMonth=12,
weekday=WeekDay.SUN),
list(reversed(JNJ))),
(makeFY5253NearestEndMonth(n=1, startingMonth=12,
weekday=WeekDay.SUN),
[datetime(2005, 1, 2), datetime(2006, 1, 1)]),
(makeFY5253NearestEndMonth(n=1, startingMonth=12,
weekday=WeekDay.SUN),
[datetime(2006, 1, 2), datetime(2006, 12, 31)]),
(DEC_SAT, [datetime(2013, 1, 15), datetime(2012, 12, 29)])
]
for test in tests:
offset, data = test
current = data[0]
for datum in data[1:]:
current = current + offset
assert current == datum
def test_bunched_yearends():
# GH#14774 cases with two fiscal year-ends in the same calendar-year
fy = FY5253(n=1, weekday=5, startingMonth=12, variation='nearest')
dt = Timestamp('2004-01-01')
assert fy.rollback(dt) == Timestamp('2002-12-28')
assert (-fy).apply(dt) == Timestamp('2002-12-28')
assert dt - fy == Timestamp('2002-12-28')
assert fy.rollforward(dt) == Timestamp('2004-01-03')
assert fy.apply(dt) == Timestamp('2004-01-03')
assert fy + dt == Timestamp('2004-01-03')
assert dt + fy == Timestamp('2004-01-03')
# Same thing, but starting from a Timestamp in the previous year.
dt = Timestamp('2003-12-31')
assert fy.rollback(dt) == Timestamp('2002-12-28')
assert (-fy).apply(dt) == Timestamp('2002-12-28')
assert dt - fy == Timestamp('2002-12-28')
def create_data():
""" create the pickle/msgpack data """
data = {
'A': [0., 1., 2., 3., np.nan],
'B': [0, 1, 0, 1, 0],
'C': ['foo1', 'foo2', 'foo3', 'foo4', 'foo5'],
'D': date_range('1/1/2009', periods=5),
'E': [0., 1, Timestamp('20100101'), '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(*[['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']])),
names=['first', 'second']))
series = dict(float=Series(data['A']),
int=Series(data['B']),
mixed=Series(data['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=['one',
'two'])),
dup=Series(np.arange(5).astype(np.float64),
index=['A', 'B', 'C', 'D', 'A']),
cat=Series(Categorical(['foo', 'bar', '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("ABCDA")
frame = dict(float=DataFrame({
'A': series['float'],
'B': series['float'] + 1
}),
int=DataFrame({
'A': series['int'],
'B': series['int'] + 1
}),
mixed=DataFrame({k: data[k]
for k in ['A', 'B', 'C', 'D']}),
mi=DataFrame(
{
'A': np.arange(5).astype(np.float64),
'B': np.arange(5).astype(np.int64)
},
index=MultiIndex.from_tuples(tuple(
zip(*[['bar', 'bar', 'baz', 'baz', 'baz'],
['one', 'two', 'one', 'two', 'three']])),
names=['first', 'second'])),
dup=DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=['A', 'B', 'A']),
cat_onecol=DataFrame({'A': Categorical(['foo', 'bar'])}),
cat_and_float=DataFrame({
'A':
Categorical(['foo', 'bar', 'baz']),
'B':
np.arange(3).astype(np.int64)
}),
mixed_dup=mixed_dup_df,
dt_mixed_tzs=DataFrame(
{
'A': Timestamp('20130102', tz='US/Eastern'),
'B': Timestamp('20130603', tz='CET')
},
index=range(5)),
dt_mixed2_tzs=DataFrame(
{
'A': Timestamp('20130102', tz='US/Eastern'),
'B': Timestamp('20130603', tz='CET'),
'C': Timestamp('20130603', tz='UTC')
},
index=range(5)))
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,
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)
class TestFY5253NearestEndMonthQuarter(Base):
offset_nem_sat_aug_4 = makeFY5253NearestEndMonthQuarter(
1, startingMonth=8, weekday=WeekDay.SAT, qtr_with_extra_week=4)
offset_nem_thu_aug_4 = makeFY5253NearestEndMonthQuarter(
1, startingMonth=8, weekday=WeekDay.THU, qtr_with_extra_week=4)
offset_n = FY5253(weekday=WeekDay.TUE,
startingMonth=12,
variation="nearest")
on_offset_cases = [
# From Wikipedia
(offset_nem_sat_aug_4, datetime(2006, 9, 2), True),
(offset_nem_sat_aug_4, datetime(2007, 9, 1), True),
(offset_nem_sat_aug_4, datetime(2008, 8, 30), True),
(offset_nem_sat_aug_4, datetime(2009, 8, 29), True),
(offset_nem_sat_aug_4, datetime(2010, 8, 28), True),
(offset_nem_sat_aug_4, datetime(2011, 9, 3), True),
(offset_nem_sat_aug_4, datetime(2016, 9, 3), True),
(offset_nem_sat_aug_4, datetime(2017, 9, 2), True),
(offset_nem_sat_aug_4, datetime(2018, 9, 1), True),
(offset_nem_sat_aug_4, datetime(2019, 8, 31), True),
(offset_nem_sat_aug_4, datetime(2006, 8, 27), False),
(offset_nem_sat_aug_4, datetime(2007, 8, 28), False),
(offset_nem_sat_aug_4, datetime(2008, 8, 31), False),
(offset_nem_sat_aug_4, datetime(2009, 8, 30), False),
(offset_nem_sat_aug_4, datetime(2010, 8, 29), False),
(offset_nem_sat_aug_4, datetime(2011, 8, 28), False),
(offset_nem_sat_aug_4, datetime(2006, 8, 25), False),
(offset_nem_sat_aug_4, datetime(2007, 8, 24), False),
(offset_nem_sat_aug_4, datetime(2008, 8, 29), False),
(offset_nem_sat_aug_4, datetime(2009, 8, 28), False),
(offset_nem_sat_aug_4, datetime(2010, 8, 27), False),
(offset_nem_sat_aug_4, datetime(2011, 8, 26), False),
(offset_nem_sat_aug_4, datetime(2019, 8, 30), False),
# From Micron, see:
# http://google.brand.edgar-online.com/?sym=MU&formtypeID=7
(offset_nem_thu_aug_4, datetime(2012, 8, 30), True),
(offset_nem_thu_aug_4, datetime(2011, 9, 1), True),
# See: http://google.brand.edgar-online.com/?sym=MU&formtypeID=13
(offset_nem_thu_aug_4, datetime(2013, 5, 30), True),
(offset_nem_thu_aug_4, datetime(2013, 2, 28), True),
(offset_nem_thu_aug_4, datetime(2012, 11, 29), True),
(offset_nem_thu_aug_4, datetime(2012, 5, 31), True),
(offset_nem_thu_aug_4, datetime(2007, 3, 1), True),
(offset_nem_thu_aug_4, datetime(1994, 3, 3), True),
(offset_n, datetime(2012, 12, 31), False),
(offset_n, datetime(2013, 1, 1), True),
(offset_n, datetime(2013, 1, 2), False)
]
@pytest.mark.parametrize('case', on_offset_cases)
def test_onOffset(self, case):
offset, dt, expected = case
assert_onOffset(offset, dt, expected)
def test_offset(self):
offset = makeFY5253NearestEndMonthQuarter(1,
startingMonth=8,
weekday=WeekDay.THU,
qtr_with_extra_week=4)
MU = [
datetime(2012, 5, 31),
datetime(2012, 8, 30),
datetime(2012, 11, 29),
datetime(2013, 2, 28),
datetime(2013, 5, 30)
]
date = MU[0] + relativedelta(days=-1)
for expected in MU:
assert_offset_equal(offset, date, expected)
date = date + offset
assert_offset_equal(offset, datetime(2012, 5, 31),
datetime(2012, 8, 30))
assert_offset_equal(offset, datetime(2012, 5, 30),
datetime(2012, 5, 31))
offset2 = FY5253Quarter(weekday=5,
startingMonth=12,
variation="last",
qtr_with_extra_week=4)
assert_offset_equal(offset2, datetime(2013, 1, 15),
datetime(2013, 3, 30))
def makeFY5253LastOfMonth(*args, **kwds):
return FY5253(*args, variation="last", **kwds)
def makeFY5253NearestEndMonth(*args, **kwds):
return FY5253(*args, variation="nearest", **kwds)
class TestFY5253NearestEndMonth(Base):
def test_get_year_end(self):
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.SAT).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 8, 31))
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.SUN).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 9, 1))
assert (makeFY5253NearestEndMonth(
startingMonth=8, weekday=WeekDay.FRI).get_year_end(
datetime(2013, 1, 1)) == datetime(2013, 8, 30))
offset_n = FY5253(weekday=WeekDay.TUE,
startingMonth=12,
variation="nearest")
assert (offset_n.get_year_end(datetime(2012, 1,
1)) == datetime(2013, 1, 1))
assert (offset_n.get_year_end(datetime(2012, 1,
10)) == datetime(2013, 1, 1))
assert (offset_n.get_year_end(datetime(2013, 1,
1)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
2)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
3)) == datetime(2013, 12, 31))
assert (offset_n.get_year_end(datetime(2013, 1,
10)) == datetime(2013, 12, 31))
JNJ = FY5253(n=1, startingMonth=12, weekday=6, variation="nearest")
assert (JNJ.get_year_end(datetime(2006, 1,
1)) == datetime(2006, 12, 31))
offset_lom_aug_sat = makeFY5253NearestEndMonth(1,
startingMonth=8,
weekday=WeekDay.SAT)
offset_lom_aug_thu = makeFY5253NearestEndMonth(1,
startingMonth=8,
weekday=WeekDay.THU)
offset_n = FY5253(weekday=WeekDay.TUE,
startingMonth=12,
variation="nearest")
on_offset_cases = [
# From Wikipedia (see:
# http://en.wikipedia.org/wiki/4%E2%80%934%E2%80%935_calendar
# #Saturday_nearest_the_end_of_month)
# 2006-09-02 2006 September 2
# 2007-09-01 2007 September 1
# 2008-08-30 2008 August 30 (leap year)
# 2009-08-29 2009 August 29
# 2010-08-28 2010 August 28
# 2011-09-03 2011 September 3
# 2012-09-01 2012 September 1 (leap year)
# 2013-08-31 2013 August 31
# 2014-08-30 2014 August 30
# 2015-08-29 2015 August 29
# 2016-09-03 2016 September 3 (leap year)
# 2017-09-02 2017 September 2
# 2018-09-01 2018 September 1
# 2019-08-31 2019 August 31
(offset_lom_aug_sat, datetime(2006, 9, 2), True),
(offset_lom_aug_sat, datetime(2007, 9, 1), True),
(offset_lom_aug_sat, datetime(2008, 8, 30), True),
(offset_lom_aug_sat, datetime(2009, 8, 29), True),
(offset_lom_aug_sat, datetime(2010, 8, 28), True),
(offset_lom_aug_sat, datetime(2011, 9, 3), True),
(offset_lom_aug_sat, datetime(2016, 9, 3), True),
(offset_lom_aug_sat, datetime(2017, 9, 2), True),
(offset_lom_aug_sat, datetime(2018, 9, 1), True),
(offset_lom_aug_sat, datetime(2019, 8, 31), True),
(offset_lom_aug_sat, datetime(2006, 8, 27), False),
(offset_lom_aug_sat, datetime(2007, 8, 28), False),
(offset_lom_aug_sat, datetime(2008, 8, 31), False),
(offset_lom_aug_sat, datetime(2009, 8, 30), False),
(offset_lom_aug_sat, datetime(2010, 8, 29), False),
(offset_lom_aug_sat, datetime(2011, 8, 28), False),
(offset_lom_aug_sat, datetime(2006, 8, 25), False),
(offset_lom_aug_sat, datetime(2007, 8, 24), False),
(offset_lom_aug_sat, datetime(2008, 8, 29), False),
(offset_lom_aug_sat, datetime(2009, 8, 28), False),
(offset_lom_aug_sat, datetime(2010, 8, 27), False),
(offset_lom_aug_sat, datetime(2011, 8, 26), False),
(offset_lom_aug_sat, datetime(2019, 8, 30), False),
# From Micron, see:
# http://google.brand.edgar-online.com/?sym=MU&formtypeID=7
(offset_lom_aug_thu, datetime(2012, 8, 30), True),
(offset_lom_aug_thu, datetime(2011, 9, 1), True),
(offset_n, datetime(2012, 12, 31), False),
(offset_n, datetime(2013, 1, 1), True),
(offset_n, datetime(2013, 1, 2), False)
]
@pytest.mark.parametrize('case', on_offset_cases)
def test_onOffset(self, case):
offset, dt, expected = case
assert_onOffset(offset, dt, expected)
def test_apply(self):
date_seq_nem_8_sat = [
datetime(2006, 9, 2),
datetime(2007, 9, 1),
datetime(2008, 8, 30),
datetime(2009, 8, 29),
datetime(2010, 8, 28),
datetime(2011, 9, 3)
]
JNJ = [
datetime(2005, 1, 2),
datetime(2006, 1, 1),
datetime(2006, 12, 31),
datetime(2007, 12, 30),
datetime(2008, 12, 28),
datetime(2010, 1, 3),
datetime(2011, 1, 2),
datetime(2012, 1, 1),
datetime(2012, 12, 30)
]
DEC_SAT = FY5253(n=-1,
startingMonth=12,
weekday=5,
variation="nearest")
tests = [(makeFY5253NearestEndMonth(startingMonth=8,
weekday=WeekDay.SAT),
date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(n=1,
startingMonth=8,
weekday=WeekDay.SAT),
date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(startingMonth=8,
weekday=WeekDay.SAT),
[datetime(2006, 9, 1)] + date_seq_nem_8_sat),
(makeFY5253NearestEndMonth(n=1,
startingMonth=8,
weekday=WeekDay.SAT),
[datetime(2006, 9, 3)] + date_seq_nem_8_sat[1:]),
(makeFY5253NearestEndMonth(n=-1,
startingMonth=8,
weekday=WeekDay.SAT),
list(reversed(date_seq_nem_8_sat))),
(makeFY5253NearestEndMonth(n=1,
startingMonth=12,
weekday=WeekDay.SUN), JNJ),
(makeFY5253NearestEndMonth(n=-1,
startingMonth=12,
weekday=WeekDay.SUN),
list(reversed(JNJ))),
(makeFY5253NearestEndMonth(n=1,
startingMonth=12,
weekday=WeekDay.SUN),
[datetime(2005, 1, 2),
datetime(2006, 1, 1)]),
(makeFY5253NearestEndMonth(n=1,
startingMonth=12,
weekday=WeekDay.SUN),
[datetime(2006, 1, 2),
datetime(2006, 12, 31)]),
(DEC_SAT, [datetime(2013, 1, 15),
datetime(2012, 12, 29)])]
for test in tests:
offset, data = test
current = data[0]
for datum in data[1:]:
current = current + offset
assert current == datum
def create_data():
""" create the pickle/msgpack data """
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
}
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),
)
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(*[
["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
["one", "two", "one", "two", "one", "two", "one", "two"],
])),
names=["first", "second"],
))
series = dict(
float=Series(data["A"]),
int=Series(data["B"]),
mixed=Series(data["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=["one", "two"]),
),
dup=Series(np.arange(5).astype(np.float64),
index=["A", "B", "C", "D", "A"]),
cat=Series(Categorical(["foo", "bar", "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("ABCDA")
frame = dict(
float=DataFrame({
"A": series["float"],
"B": series["float"] + 1
}),
int=DataFrame({
"A": series["int"],
"B": series["int"] + 1
}),
mixed=DataFrame({k: data[k]
for k in ["A", "B", "C", "D"]}),
mi=DataFrame(
{
"A": np.arange(5).astype(np.float64),
"B": np.arange(5).astype(np.int64)
},
index=MultiIndex.from_tuples(
tuple(
zip(*[
["bar", "bar", "baz", "baz", "baz"],
["one", "two", "one", "two", "three"],
])),
names=["first", "second"],
),
),
dup=DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=["A", "B", "A"]),
cat_onecol=DataFrame({"A": Categorical(["foo", "bar"])}),
cat_and_float=DataFrame({
"A": Categorical(["foo", "bar", "baz"]),
"B": np.arange(3).astype(np.int64),
}),
mixed_dup=mixed_dup_df,
dt_mixed_tzs=DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
},
index=range(5),
),
dt_mixed2_tzs=DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
"C": Timestamp("20130603", tz="UTC"),
},
index=range(5),
),
)
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"),
)
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,
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 create_data():
"""create the pickle data"""
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
}
scalars = {
"timestamp": Timestamp("20130101"),
"period": Period("2012", "M")
}
index = {
"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),
}
index["range"] = RangeIndex(10)
index["interval"] = interval_range(0, periods=10)
mi = {
"reg2":
MultiIndex.from_tuples(
tuple(
zip(*[
["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
["one", "two", "one", "two", "one", "two", "one", "two"],
])),
names=["first", "second"],
)
}
series = {
"float":
Series(data["A"]),
"int":
Series(data["B"]),
"mixed":
Series(data["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=["one", "two"]),
),
"dup":
Series(np.arange(5).astype(np.float64),
index=["A", "B", "C", "D", "A"]),
"cat":
Series(Categorical(["foo", "bar", "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("ABCDA")
frame = {
"float":
DataFrame({
"A": series["float"],
"B": series["float"] + 1
}),
"int":
DataFrame({
"A": series["int"],
"B": series["int"] + 1
}),
"mixed":
DataFrame({k: data[k]
for k in ["A", "B", "C", "D"]}),
"mi":
DataFrame(
{
"A": np.arange(5).astype(np.float64),
"B": np.arange(5).astype(np.int64)
},
index=MultiIndex.from_tuples(
tuple(
zip(*[
["bar", "bar", "baz", "baz", "baz"],
["one", "two", "one", "two", "three"],
])),
names=["first", "second"],
),
),
"dup":
DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=["A", "B", "A"]),
"cat_onecol":
DataFrame({"A": Categorical(["foo", "bar"])}),
"cat_and_float":
DataFrame({
"A": Categorical(["foo", "bar", "baz"]),
"B": np.arange(3).astype(np.int64),
}),
"mixed_dup":
mixed_dup_df,
"dt_mixed_tzs":
DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
},
index=range(5),
),
"dt_mixed2_tzs":
DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
"C": Timestamp("20130603", tz="UTC"),
},
index=range(5),
),
}
cat = {
"int8": Categorical(list("abcdefg")),
"int16": Categorical(np.arange(1000)),
"int32": Categorical(np.arange(10000)),
}
timestamp = {
"normal": Timestamp("2011-01-01"),
"nat": NaT,
"tz": Timestamp("2011-01-01", tz="US/Eastern"),
}
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 {
"series": series,
"frame": frame,
"index": index,
"scalars": scalars,
"mi": mi,
"sp_series": {
"float": _create_sp_series(),
"ts": _create_sp_tsseries()
},
"sp_frame": {
"float": _create_sp_frame()
},
"cat": cat,
"timestamp": timestamp,
"offsets": off,
}
