def test_difference_sort(self, sort):
index = pd.TimedeltaIndex(["5 days", "3 days", "2 days", "4 days",
"1 days", "0 days"])
other = timedelta_range("1 days", "4 days", freq="D")
idx_diff = index.difference(other, sort)
expected = TimedeltaIndex(["5 days", "0 days"], freq=None)
if sort is None:
expected = expected.sort_values()
tm.assert_index_equal(idx_diff, expected)
tm.assert_attr_equal('freq', idx_diff, expected)
other = timedelta_range("2 days", "5 days", freq="D")
idx_diff = index.difference(other, sort)
expected = TimedeltaIndex(["1 days", "0 days"], freq=None)
if sort is None:
expected = expected.sort_values()
tm.assert_index_equal(idx_diff, expected)
tm.assert_attr_equal('freq', idx_diff, expected)
def test_get_loc_nat(self):
tidx = TimedeltaIndex(['1 days 01:00:00', 'NaT', '2 days 01:00:00'])
self.assertEqual(tidx.get_loc(pd.NaT), 1)
self.assertEqual(tidx.get_loc(None), 1)
self.assertEqual(tidx.get_loc(float('nan')), 1)
self.assertEqual(tidx.get_loc(np.nan), 1)
def test_get_duplicates(self):
idx = TimedeltaIndex(['1 day', '2 day', '2 day', '3 day', '3day',
'4day'])
result = idx.get_duplicates()
ex = TimedeltaIndex(['2 day', '3day'])
self.assert_index_equal(result, ex)
def test_value_counts_unique(self):
# GH 7735
idx = timedelta_range('1 days 09:00:00', freq='H', periods=10)
# create repeated values, 'n'th element is repeated by n+1 times
idx = TimedeltaIndex(np.repeat(idx.values, range(1, len(idx) + 1)))
exp_idx = timedelta_range('1 days 18:00:00', freq='-1H', periods=10)
expected = Series(range(10, 0, -1), index=exp_idx, dtype='int64')
for obj in [idx, Series(idx)]:
tm.assert_series_equal(obj.value_counts(), expected)
expected = timedelta_range('1 days 09:00:00', freq='H', periods=10)
tm.assert_index_equal(idx.unique(), expected)
idx = TimedeltaIndex(['1 days 09:00:00', '1 days 09:00:00',
'1 days 09:00:00', '1 days 08:00:00',
'1 days 08:00:00', pd.NaT])
exp_idx = TimedeltaIndex(['1 days 09:00:00', '1 days 08:00:00'])
expected = Series([3, 2], index=exp_idx)
for obj in [idx, Series(idx)]:
tm.assert_series_equal(obj.value_counts(), expected)
exp_idx = TimedeltaIndex(['1 days 09:00:00', '1 days 08:00:00',
pd.NaT])
expected = Series([3, 2, 1], index=exp_idx)
for obj in [idx, Series(idx)]:
tm.assert_series_equal(obj.value_counts(dropna=False), expected)
tm.assert_index_equal(idx.unique(), exp_idx)
def test_take_fill_value(self):
# GH 12631
idx = TimedeltaIndex(['1 days', '2 days', '3 days'],
name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = TimedeltaIndex(['2 days', '1 days', '3 days'],
name='xxx')
tm.assert_index_equal(result, expected)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = TimedeltaIndex(['2 days', '1 days', 'NaT'],
name='xxx')
tm.assert_index_equal(result, expected)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False,
fill_value=True)
expected = TimedeltaIndex(['2 days', '1 days', '3 days'],
name='xxx')
tm.assert_index_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assert_raises_regex(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assert_raises_regex(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
idx.take(np.array([1, -5]))
class TimedeltaIndexing(object):
def setup(self):
self.index = TimedeltaIndex(start='1985', periods=1000, freq='D')
self.index2 = TimedeltaIndex(start='1986', periods=1000, freq='D')
self.series = Series(range(1000), index=self.index)
self.timedelta = self.index[500]
def time_get_loc(self):
self.index.get_loc(self.timedelta)
def time_shape(self):
self.index.shape
def time_shallow_copy(self):
self.index._shallow_copy()
def time_series_loc(self):
self.series.loc[self.timedelta]
def time_align(self):
DataFrame({'a': self.series, 'b': self.series[:500]})
def time_intersection(self):
self.index.intersection(self.index2)
def time_union(self):
self.index.union(self.index2)
def time_unique(self):
self.index.unique()
def test_get_loc_nat(self):
tidx = TimedeltaIndex(['1 days 01:00:00', 'NaT', '2 days 01:00:00'])
assert tidx.get_loc(pd.NaT) == 1
assert tidx.get_loc(None) == 1
assert tidx.get_loc(float('nan')) == 1
assert tidx.get_loc(np.nan) == 1
def test_union_bug_1745(self):
left = TimedeltaIndex(["1 day 15:19:49.695000"])
right = TimedeltaIndex(["2 day 13:04:21.322000", "1 day 15:27:24.873000", "1 day 15:31:05.350000"])
result = left.union(right)
exp = TimedeltaIndex(sorted(set(list(left)) | set(list(right))))
self.assertTrue(result.equals(exp))
def test_astype_object_with_nat(self):
idx = TimedeltaIndex([timedelta(days=1), timedelta(days=2), NaT,
timedelta(days=4)], name='idx')
expected_list = [Timedelta('1 days'), Timedelta('2 days'), NaT,
Timedelta('4 days')]
result = idx.astype(object)
expected = Index(expected_list, dtype=object, name='idx')
tm.assert_index_equal(result, expected)
assert idx.tolist() == expected_list
def test_union_coverage(self):
idx = TimedeltaIndex(["3d", "1d", "2d"])
ordered = TimedeltaIndex(idx.order(), freq="infer")
result = ordered.union(idx)
self.assertTrue(result.equals(ordered))
result = ordered[:0].union(ordered)
self.assertTrue(result.equals(ordered))
self.assertEqual(result.freq, ordered.freq)
def test_get_duplicates(self):
idx = TimedeltaIndex(['1 day', '2 day', '2 day', '3 day', '3day',
'4day'])
with warnings.catch_warnings(record=True):
# Deprecated - see GH20239
result = idx.get_duplicates()
ex = TimedeltaIndex(['2 day', '3day'])
tm.assert_index_equal(result, ex)
def test_union_coverage(self):
idx = TimedeltaIndex(['3d','1d','2d'])
ordered = TimedeltaIndex(idx.order(), freq='infer')
result = ordered.union(idx)
self.assertTrue(result.equals(ordered))
result = ordered[:0].union(ordered)
self.assertTrue(result.equals(ordered))
self.assertEqual(result.freq, ordered.freq)
def test_union_bug_1745(self):
left = TimedeltaIndex(['1 day 15:19:49.695000'])
right = TimedeltaIndex(['2 day 13:04:21.322000',
'1 day 15:27:24.873000',
'1 day 15:31:05.350000'])
result = left.union(right)
exp = TimedeltaIndex(sorted(set(list(left)) | set(list(right))))
tm.assert_index_equal(result, exp)
def test_get_duplicates(self):
idx = TimedeltaIndex(['1 day', '2 day', '2 day', '3 day', '3day',
'4day'])
with tm.assert_produces_warning(FutureWarning):
# Deprecated - see GH20239
result = idx.get_duplicates()
ex = TimedeltaIndex(['2 day', '3day'])
tm.assert_index_equal(result, ex)
def test_union_coverage(self):
idx = TimedeltaIndex(['3d', '1d', '2d'])
ordered = TimedeltaIndex(idx.sort_values(), freq='infer')
result = ordered.union(idx)
tm.assert_index_equal(result, ordered)
result = ordered[:0].union(ordered)
tm.assert_index_equal(result, ordered)
assert result.freq == ordered.freq
def test_misc_coverage(self):
rng = timedelta_range("1 day", periods=5)
result = rng.groupby(rng.days)
tm.assert_isinstance(list(result.values())[0][0], Timedelta)
idx = TimedeltaIndex(["3d", "1d", "2d"])
self.assertTrue(idx.equals(list(idx)))
non_td = Index(list("abc"))
self.assertFalse(idx.equals(list(non_td)))
def test_misc_coverage(self):
rng = timedelta_range('1 day', periods=5)
result = rng.groupby(rng.days)
tm.assertIsInstance(list(result.values())[0][0], Timedelta)
idx = TimedeltaIndex(['3d', '1d', '2d'])
self.assertFalse(idx.equals(list(idx)))
non_td = Index(list('abc'))
self.assertFalse(idx.equals(list(non_td)))
def test_tdi_floordiv_timedelta_scalar(self, scalar_td):
# GH#19125
tdi = TimedeltaIndex(['00:05:03', '00:05:03', pd.NaT], freq=None)
expected = pd.Index([2.0, 2.0, np.nan])
res = tdi.__rfloordiv__(scalar_td)
tm.assert_index_equal(res, expected)
expected = pd.Index([0.0, 0.0, np.nan])
res = tdi // (scalar_td)
tm.assert_index_equal(res, expected)
def test_union(self):
i1 = timedelta_range('1day', periods=5)
i2 = timedelta_range('3day', periods=5)
result = i1.union(i2)
expected = timedelta_range('1day', periods=7)
tm.assert_index_equal(result, expected)
i1 = Int64Index(np.arange(0, 20, 2))
i2 = TimedeltaIndex(start='1 day', periods=10, freq='D')
i1.union(i2) # Works
i2.union(i1) # Fails with "AttributeError: can't set attribute"
def test_freq_setter(self, values, freq):
# GH 20678
idx = TimedeltaIndex(values)
# can set to an offset, converting from string if necessary
idx.freq = freq
assert idx.freq == freq
assert isinstance(idx.freq, ABCDateOffset)
# can reset to None
idx.freq = None
assert idx.freq is None
def test_union(self):
i1 = timedelta_range("1day", periods=5)
i2 = timedelta_range("3day", periods=5)
result = i1.union(i2)
expected = timedelta_range("1day", periods=7)
self.assert_numpy_array_equal(result, expected)
i1 = Int64Index(np.arange(0, 20, 2))
i2 = TimedeltaIndex(start="1 day", periods=10, freq="D")
i1.union(i2) # Works
i2.union(i1) # Fails with "AttributeError: can't set attribute"
def test_is_timedelta():
assert (com.is_timedelta64_dtype('timedelta64'))
assert (com.is_timedelta64_dtype('timedelta64[ns]'))
assert (not com.is_timedelta64_ns_dtype('timedelta64'))
assert (com.is_timedelta64_ns_dtype('timedelta64[ns]'))
tdi = TimedeltaIndex([1e14, 2e14], dtype='timedelta64')
assert (com.is_timedelta64_dtype(tdi))
assert (com.is_timedelta64_ns_dtype(tdi))
assert (com.is_timedelta64_ns_dtype(tdi.astype('timedelta64[ns]')))
# Conversion to Int64Index:
assert (not com.is_timedelta64_ns_dtype(tdi.astype('timedelta64')))
assert (not com.is_timedelta64_ns_dtype(tdi.astype('timedelta64[h]')))
def test_take2(self):
tds = ['1day 02:00:00', '1 day 04:00:00', '1 day 10:00:00']
idx = TimedeltaIndex(start='1d', end='2d', freq='H', name='idx')
expected = TimedeltaIndex(tds, freq=None, name='idx')
taken1 = idx.take([2, 4, 10])
taken2 = idx[[2, 4, 10]]
for taken in [taken1, taken2]:
tm.assert_index_equal(taken, expected)
assert isinstance(taken, TimedeltaIndex)
assert taken.freq is None
assert taken.name == expected.name
def test_insert(self):
idx = TimedeltaIndex(['4day', '1day', '2day'], name='idx')
result = idx.insert(2, timedelta(days=5))
exp = TimedeltaIndex(['4day', '1day', '5day', '2day'], name='idx')
tm.assert_index_equal(result, exp)
# insertion of non-datetime should coerce to object index
result = idx.insert(1, 'inserted')
expected = Index([Timedelta('4day'), 'inserted', Timedelta('1day'),
Timedelta('2day')], name='idx')
assert not isinstance(result, TimedeltaIndex)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
idx = timedelta_range('1day 00:00:01', periods=3, freq='s', name='idx')
# preserve freq
expected_0 = TimedeltaIndex(['1day', '1day 00:00:01', '1day 00:00:02',
'1day 00:00:03'],
name='idx', freq='s')
expected_3 = TimedeltaIndex(['1day 00:00:01', '1day 00:00:02',
'1day 00:00:03', '1day 00:00:04'],
name='idx', freq='s')
# reset freq to None
expected_1_nofreq = TimedeltaIndex(['1day 00:00:01', '1day 00:00:01',
'1day 00:00:02', '1day 00:00:03'],
name='idx', freq=None)
expected_3_nofreq = TimedeltaIndex(['1day 00:00:01', '1day 00:00:02',
'1day 00:00:03', '1day 00:00:05'],
name='idx', freq=None)
cases = [(0, Timedelta('1day'), expected_0),
(-3, Timedelta('1day'), expected_0),
(3, Timedelta('1day 00:00:04'), expected_3),
(1, Timedelta('1day 00:00:01'), expected_1_nofreq),
(3, Timedelta('1day 00:00:05'), expected_3_nofreq)]
for n, d, expected in cases:
result = idx.insert(n, d)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
assert result.freq == expected.freq
# GH 18295 (test missing)
expected = TimedeltaIndex(['1day', pd.NaT, '2day', '3day'])
for na in (np.nan, pd.NaT, None):
result = timedelta_range('1day', '3day').insert(1, na)
tm.assert_index_equal(result, expected)
def test_is_timedelta(self):
self.assertTrue(is_timedelta64_dtype('timedelta64'))
self.assertTrue(is_timedelta64_dtype('timedelta64[ns]'))
self.assertFalse(is_timedelta64_ns_dtype('timedelta64'))
self.assertTrue(is_timedelta64_ns_dtype('timedelta64[ns]'))
tdi = TimedeltaIndex([1e14, 2e14], dtype='timedelta64')
self.assertTrue(is_timedelta64_dtype(tdi))
self.assertTrue(is_timedelta64_ns_dtype(tdi))
self.assertTrue(is_timedelta64_ns_dtype(tdi.astype('timedelta64[ns]')))
# Conversion to Int64Index:
self.assertFalse(is_timedelta64_ns_dtype(tdi.astype('timedelta64')))
self.assertFalse(is_timedelta64_ns_dtype(tdi.astype('timedelta64[h]')))
def test_take(self):
tds = ['1day 02:00:00','1 day 04:00:00','1 day 10:00:00']
idx = TimedeltaIndex(start='1d',end='2d',freq='H',name='idx')
expected = TimedeltaIndex(tds, freq=None, name='idx')
taken1 = idx.take([2, 4, 10])
taken2 = idx[[2,4,10]]
for taken in [taken1, taken2]:
self.assertTrue(taken.equals(expected))
tm.assert_isinstance(taken, TimedeltaIndex)
self.assertIsNone(taken.freq)
self.assertEqual(taken.name, expected.name)
def test_is_timedelta(self):
assert is_timedelta64_dtype('timedelta64')
assert is_timedelta64_dtype('timedelta64[ns]')
assert not is_timedelta64_ns_dtype('timedelta64')
assert is_timedelta64_ns_dtype('timedelta64[ns]')
tdi = TimedeltaIndex([1e14, 2e14], dtype='timedelta64')
assert is_timedelta64_dtype(tdi)
assert is_timedelta64_ns_dtype(tdi)
assert is_timedelta64_ns_dtype(tdi.astype('timedelta64[ns]'))
# Conversion to Int64Index:
assert not is_timedelta64_ns_dtype(tdi.astype('timedelta64'))
assert not is_timedelta64_ns_dtype(tdi.astype('timedelta64[h]'))
def test_take(self):
tds = ["1day 02:00:00", "1 day 04:00:00", "1 day 10:00:00"]
idx = TimedeltaIndex(start="1d", end="2d", freq="H", name="idx")
expected = TimedeltaIndex(tds, freq=None, name="idx")
taken1 = idx.take([2, 4, 10])
taken2 = idx[[2, 4, 10]]
for taken in [taken1, taken2]:
self.assertTrue(taken.equals(expected))
tm.assert_isinstance(taken, TimedeltaIndex)
self.assertIsNone(taken.freq)
self.assertEqual(taken.name, expected.name)
def test_repeat(self):
index = pd.timedelta_range('1 days', periods=2, freq='D')
exp = pd.TimedeltaIndex(['1 days', '1 days', '2 days', '2 days'])
for res in [index.repeat(2), np.repeat(index, 2)]:
tm.assert_index_equal(res, exp)
self.assertIsNone(res.freq)
index = TimedeltaIndex(['1 days', 'NaT', '3 days'])
exp = TimedeltaIndex(['1 days', '1 days', '1 days',
'NaT', 'NaT', 'NaT',
'3 days', '3 days', '3 days'])
for res in [index.repeat(3), np.repeat(index, 3)]:
tm.assert_index_equal(res, exp)
self.assertIsNone(res.freq)
def test_astype_timedelta64(self):
# GH 13149, GH 13209
idx = TimedeltaIndex([1e14, 'NaT', pd.NaT, np.NaN])
result = idx.astype('timedelta64')
expected = Float64Index([1e+14] + [np.NaN] * 3, dtype='float64')
tm.assert_index_equal(result, expected)
result = idx.astype('timedelta64[ns]')
tm.assert_index_equal(result, idx)
self.assertFalse(result is idx)
result = idx.astype('timedelta64[ns]', copy=False)
tm.assert_index_equal(result, idx)
self.assertTrue(result is idx)
def test_astype_raises(self, dtype):
# GH 13149, GH 13209
idx = TimedeltaIndex([1e14, 'NaT', NaT, np.NaN])
msg = 'Cannot cast TimedeltaArray to dtype'
with pytest.raises(TypeError, match=msg):
idx.astype(dtype)
def test_take_fill_value(self):
# GH 12631
idx = TimedeltaIndex(['1 days', '2 days', '3 days'], name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = TimedeltaIndex(['2 days', '1 days', '3 days'], name='xxx')
tm.assert_index_equal(result, expected)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = TimedeltaIndex(['2 days', '1 days', 'NaT'], name='xxx')
tm.assert_index_equal(result, expected)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = TimedeltaIndex(['2 days', '1 days', '3 days'], name='xxx')
tm.assert_index_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assert_raises_regex(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assert_raises_regex(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
idx.take(np.array([1, -5]))
def test_insert(self):
idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
result = idx.insert(2, timedelta(days=5))
exp = TimedeltaIndex(["4day", "1day", "5day", "2day"], name="idx")
tm.assert_index_equal(result, exp)
# insertion of non-datetime should coerce to object index
result = idx.insert(1, "inserted")
expected = Index(
[
Timedelta("4day"), "inserted",
Timedelta("1day"),
Timedelta("2day")
],
name="idx",
)
assert not isinstance(result, TimedeltaIndex)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
idx = timedelta_range("1day 00:00:01", periods=3, freq="s", name="idx")
# preserve freq
expected_0 = TimedeltaIndex(
["1day", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"],
name="idx",
freq="s",
)
expected_3 = TimedeltaIndex(
[
"1day 00:00:01", "1day 00:00:02", "1day 00:00:03",
"1day 00:00:04"
],
name="idx",
freq="s",
)
# reset freq to None
expected_1_nofreq = TimedeltaIndex(
[
"1day 00:00:01", "1day 00:00:01", "1day 00:00:02",
"1day 00:00:03"
],
name="idx",
freq=None,
)
expected_3_nofreq = TimedeltaIndex(
[
"1day 00:00:01", "1day 00:00:02", "1day 00:00:03",
"1day 00:00:05"
],
name="idx",
freq=None,
)
cases = [
(0, Timedelta("1day"), expected_0),
(-3, Timedelta("1day"), expected_0),
(3, Timedelta("1day 00:00:04"), expected_3),
(1, Timedelta("1day 00:00:01"), expected_1_nofreq),
(3, Timedelta("1day 00:00:05"), expected_3_nofreq),
]
for n, d, expected in cases:
result = idx.insert(n, d)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
assert result.freq == expected.freq
def test_insert_invalid_na(self):
idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
with pytest.raises(TypeError, match="incompatible label"):
idx.insert(0, np.datetime64("NaT"))
def test_take_fill_value(self):
# GH 12631
idx = TimedeltaIndex(["1 days", "2 days", "3 days"], name="xxx")
result = idx.take(np.array([1, 0, -1]))
expected = TimedeltaIndex(["2 days", "1 days", "3 days"], name="xxx")
tm.assert_index_equal(result, expected)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = TimedeltaIndex(["2 days", "1 days", "NaT"], name="xxx")
tm.assert_index_equal(result, expected)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True)
expected = TimedeltaIndex(["2 days", "1 days", "3 days"], name="xxx")
tm.assert_index_equal(result, expected)
msg = (
"When allow_fill=True and fill_value is not None, "
"all indices must be >= -1"
)
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
msg = "index -5 is out of bounds for (axis 0 with )?size 3"
with pytest.raises(IndexError, match=msg):
idx.take(np.array([1, -5]))
@pytest.mark.parametrize(
"op_name",
[
"left_plus_right", "right_plus_left", "left_minus_right",
"right_minus_left"
],
)
@pytest.mark.parametrize(
"value",
[
DatetimeIndex(["2011-01-01", "2011-01-02"], name="x"),
DatetimeIndex(["2011-01-01", "2011-01-02"], tz="US/Eastern", name="x"),
DatetimeArray._from_sequence(["2011-01-01", "2011-01-02"]),
DatetimeArray._from_sequence(["2011-01-01", "2011-01-02"],
dtype=DatetimeTZDtype(tz="US/Pacific")),
TimedeltaIndex(["1 day", "2 day"], name="x"),
],
)
def test_nat_arithmetic_index(op_name, value):
# see gh-11718
exp_name = "x"
exp_data = [NaT] * 2
if is_datetime64_any_dtype(value.dtype) and "plus" in op_name:
expected = DatetimeIndex(exp_data, tz=value.tz, name=exp_name)
else:
expected = TimedeltaIndex(exp_data, name=exp_name)
if not isinstance(value, Index):
expected = expected.array
def test_shift(self, datetime_series):
shifted = datetime_series.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, datetime_series.index)
tm.assert_index_equal(unshifted.index, datetime_series.index)
tm.assert_numpy_array_equal(
unshifted.dropna().values, datetime_series.values[:-1]
)
offset = BDay()
shifted = datetime_series.shift(1, freq=offset)
unshifted = shifted.shift(-1, freq=offset)
tm.assert_series_equal(unshifted, datetime_series)
unshifted = datetime_series.shift(0, freq=offset)
tm.assert_series_equal(unshifted, datetime_series)
shifted = datetime_series.shift(1, freq="B")
unshifted = shifted.shift(-1, freq="B")
tm.assert_series_equal(unshifted, datetime_series)
# corner case
unshifted = datetime_series.shift(0)
tm.assert_series_equal(unshifted, datetime_series)
# Shifting with PeriodIndex
ps = tm.makePeriodSeries()
shifted = ps.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, ps.index)
tm.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.dropna().values, ps.values[:-1])
shifted2 = ps.shift(1, "B")
shifted3 = ps.shift(1, BDay())
tm.assert_series_equal(shifted2, shifted3)
tm.assert_series_equal(ps, shifted2.shift(-1, "B"))
msg = "Given freq D does not match PeriodIndex freq B"
with pytest.raises(ValueError, match=msg):
ps.shift(freq="D")
# legacy support
shifted4 = ps.shift(1, freq="B")
tm.assert_series_equal(shifted2, shifted4)
shifted5 = ps.shift(1, freq=BDay())
tm.assert_series_equal(shifted5, shifted4)
# 32-bit taking
# GH#8129
index = date_range("2000-01-01", periods=5)
for dtype in ["int32", "int64"]:
s1 = Series(np.arange(5, dtype=dtype), index=index)
p = s1.iloc[1]
result = s1.shift(periods=p)
expected = Series([np.nan, 0, 1, 2, 3], index=index)
tm.assert_series_equal(result, expected)
# GH#8260
# with tz
s = Series(
date_range("2000-01-01 09:00:00", periods=5, tz="US/Eastern"), name="foo"
)
result = s - s.shift()
exp = Series(TimedeltaIndex(["NaT"] + ["1 days"] * 4), name="foo")
tm.assert_series_equal(result, exp)
# incompat tz
s2 = Series(date_range("2000-01-01 09:00:00", periods=5, tz="CET"), name="foo")
msg = "DatetimeArray subtraction must have the same timezones or no timezones"
with pytest.raises(TypeError, match=msg):
s - s2
def diff(arr, n, axis=0):
""" difference of n between self,
analagoust to s-s.shift(n) """
n = int(n)
na = np.nan
dtype = arr.dtype
is_timedelta = False
if needs_i8_conversion(arr):
dtype = np.float64
arr = arr.view('i8')
na = iNaT
is_timedelta = True
elif issubclass(dtype.type, np.integer):
dtype = np.float64
elif issubclass(dtype.type, np.bool_):
dtype = np.object_
dtype = np.dtype(dtype)
out_arr = np.empty(arr.shape, dtype=dtype)
na_indexer = [slice(None)] * arr.ndim
na_indexer[axis] = slice(None, n) if n >= 0 else slice(n, None)
out_arr[tuple(na_indexer)] = na
if arr.ndim == 2 and arr.dtype.name in _diff_special:
f = _diff_special[arr.dtype.name]
f(arr, out_arr, n, axis)
else:
res_indexer = [slice(None)] * arr.ndim
res_indexer[axis] = slice(n, None) if n >= 0 else slice(None, n)
res_indexer = tuple(res_indexer)
lag_indexer = [slice(None)] * arr.ndim
lag_indexer[axis] = slice(None, -n) if n > 0 else slice(-n, None)
lag_indexer = tuple(lag_indexer)
# need to make sure that we account for na for datelike/timedelta
# we don't actually want to subtract these i8 numbers
if is_timedelta:
res = arr[res_indexer]
lag = arr[lag_indexer]
mask = (arr[res_indexer] == na) | (arr[lag_indexer] == na)
if mask.any():
res = res.copy()
res[mask] = 0
lag = lag.copy()
lag[mask] = 0
result = res - lag
result[mask] = na
out_arr[res_indexer] = result
else:
out_arr[res_indexer] = arr[res_indexer] - arr[lag_indexer]
if is_timedelta:
from pandas import TimedeltaIndex
out_arr = TimedeltaIndex(out_arr.ravel().astype('int64')).asi8.reshape(
out_arr.shape).astype('timedelta64[ns]')
return out_arr
def test_shift_no_freq(self):
# GH#19147
tdi = TimedeltaIndex(["1 days 01:00:00", "2 days 01:00:00"], freq=None)
with pytest.raises(NullFrequencyError, match="Cannot shift with no freq"):
tdi.shift(2)
def test_tdi_shift_empty(self):
# GH#9903
idx = TimedeltaIndex([], name="xxx")
tm.assert_index_equal(idx.shift(0, freq="H"), idx)
tm.assert_index_equal(idx.shift(3, freq="H"), idx)
def test_subtraction_ops_with_tz(self):
# check that dt/dti subtraction ops with tz are validated
dti = date_range('20130101', periods=3)
ts = Timestamp('20130101')
dt = ts.to_pydatetime()
dti_tz = date_range('20130101', periods=3).tz_localize('US/Eastern')
ts_tz = Timestamp('20130101').tz_localize('US/Eastern')
ts_tz2 = Timestamp('20130101').tz_localize('CET')
dt_tz = ts_tz.to_pydatetime()
td = Timedelta('1 days')
def _check(result, expected):
assert result == expected
assert isinstance(result, Timedelta)
# scalars
result = ts - ts
expected = Timedelta('0 days')
_check(result, expected)
result = dt_tz - ts_tz
expected = Timedelta('0 days')
_check(result, expected)
result = ts_tz - dt_tz
expected = Timedelta('0 days')
_check(result, expected)
# tz mismatches
pytest.raises(TypeError, lambda: dt_tz - ts)
pytest.raises(TypeError, lambda: dt_tz - dt)
pytest.raises(TypeError, lambda: dt_tz - ts_tz2)
pytest.raises(TypeError, lambda: dt - dt_tz)
pytest.raises(TypeError, lambda: ts - dt_tz)
pytest.raises(TypeError, lambda: ts_tz2 - ts)
pytest.raises(TypeError, lambda: ts_tz2 - dt)
pytest.raises(TypeError, lambda: ts_tz - ts_tz2)
# with dti
pytest.raises(TypeError, lambda: dti - ts_tz)
pytest.raises(TypeError, lambda: dti_tz - ts)
pytest.raises(TypeError, lambda: dti_tz - ts_tz2)
result = dti_tz - dt_tz
expected = TimedeltaIndex(['0 days', '1 days', '2 days'])
tm.assert_index_equal(result, expected)
result = dt_tz - dti_tz
expected = TimedeltaIndex(['0 days', '-1 days', '-2 days'])
tm.assert_index_equal(result, expected)
result = dti_tz - ts_tz
expected = TimedeltaIndex(['0 days', '1 days', '2 days'])
tm.assert_index_equal(result, expected)
result = ts_tz - dti_tz
expected = TimedeltaIndex(['0 days', '-1 days', '-2 days'])
tm.assert_index_equal(result, expected)
result = td - td
expected = Timedelta('0 days')
_check(result, expected)
result = dti_tz - td
expected = DatetimeIndex(
['20121231', '20130101', '20130102'], tz='US/Eastern')
tm.assert_index_equal(result, expected)
def test_argmin_argmax(self):
idx = TimedeltaIndex(
["1 day 00:00:05", "1 day 00:00:01", "1 day 00:00:02"])
assert idx.argmin() == 1
assert idx.argmax() == 0
def test_tdi_div_tdlike_scalar_with_nat(self, delta):
rng = TimedeltaIndex(['1 days', pd.NaT, '2 days'], name='foo')
expected = Float64Index([12, np.nan, 24], name='foo')
result = rng / delta
tm.assert_index_equal(result, expected)
def test_tdi_radd_timestamp(self):
idx = TimedeltaIndex(['1 day', '2 day'])
result = Timestamp('2011-01-01') + idx
expected = DatetimeIndex(['2011-01-02', '2011-01-03'])
tm.assert_index_equal(result, expected)
def test_order(self):
# GH 10295
idx1 = TimedeltaIndex(["1 day", "2 day", "3 day"],
freq="D",
name="idx")
idx2 = TimedeltaIndex(["1 hour", "2 hour", "3 hour"],
freq="H",
name="idx")
for idx in [idx1, idx2]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, idx)
assert ordered.freq == idx.freq
ordered = idx.sort_values(ascending=False)
expected = idx[::-1]
tm.assert_index_equal(ordered, expected)
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, idx)
tm.assert_numpy_array_equal(indexer,
np.array([0, 1, 2]),
check_dtype=False)
assert ordered.freq == idx.freq
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
tm.assert_index_equal(ordered, idx[::-1])
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
idx1 = TimedeltaIndex(
["1 hour", "3 hour", "5 hour", "2 hour ", "1 hour"], name="idx1")
exp1 = TimedeltaIndex(
["1 hour", "1 hour", "2 hour", "3 hour", "5 hour"], name="idx1")
idx2 = TimedeltaIndex(["1 day", "3 day", "5 day", "2 day", "1 day"],
name="idx2")
for idx, expected in [(idx1, exp1), (idx1, exp1), (idx1, exp1)]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, expected)
assert ordered.freq is None
ordered = idx.sort_values(ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, expected)
exp = np.array([0, 4, 3, 1, 2])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
exp = np.array([2, 1, 3, 4, 0])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
import pandas.core.dtypes.concat as _concat
from pandas import DatetimeIndex, Period, PeriodIndex, Series, TimedeltaIndex
@pytest.mark.parametrize(
"to_concat, expected",
[
# int/float/str
([["a"], [1, 2]], ["i", "object"]),
([[3, 4], [1, 2]], ["i"]),
([[3, 4], [1, 2.1]], ["i", "f"]),
# datetimelike
([DatetimeIndex(["2011-01-01"]),
DatetimeIndex(["2011-01-02"])], ["datetime"]),
([TimedeltaIndex(["1 days"]),
TimedeltaIndex(["2 days"])], ["timedelta"]),
# datetimelike object
(
[
DatetimeIndex(["2011-01-01"]),
DatetimeIndex(["2011-01-02"], tz="US/Eastern"),
],
["datetime", "datetime64[ns, US/Eastern]"],
),
(
[
DatetimeIndex(["2011-01-01"], tz="Asia/Tokyo"),
DatetimeIndex(["2011-01-02"], tz="US/Eastern"),
],
["datetime64[ns, Asia/Tokyo]", "datetime64[ns, US/Eastern]"],
def test_value_counts_datetime64(self):
klasses = [Index, Series]
for klass in klasses:
# GH 3002, datetime64[ns]
# don't test names though
txt = "\n".join([
'xxyyzz20100101PIE', 'xxyyzz20100101GUM', 'xxyyzz20100101EGG',
'xxyyww20090101EGG', 'foofoo20080909PIE', 'foofoo20080909GUM'
])
f = StringIO(txt)
df = pd.read_fwf(f,
widths=[6, 8, 3],
names=["person_id", "dt", "food"],
parse_dates=["dt"])
s = klass(df['dt'].copy())
s.name = None
idx = pd.to_datetime([
'2010-01-01 00:00:00Z', '2008-09-09 00:00:00Z',
'2009-01-01 00:00:00X'
])
expected_s = Series([3, 2, 1], index=idx)
tm.assert_series_equal(s.value_counts(), expected_s)
expected = np_array_datetime64_compat([
'2010-01-01 00:00:00Z', '2009-01-01 00:00:00Z',
'2008-09-09 00:00:00Z'
],
dtype='datetime64[ns]')
if isinstance(s, Index):
tm.assert_index_equal(s.unique(), DatetimeIndex(expected))
else:
tm.assert_numpy_array_equal(s.unique(), expected)
self.assertEqual(s.nunique(), 3)
# with NaT
s = df['dt'].copy()
s = klass([v for v in s.values] + [pd.NaT])
result = s.value_counts()
self.assertEqual(result.index.dtype, 'datetime64[ns]')
tm.assert_series_equal(result, expected_s)
result = s.value_counts(dropna=False)
expected_s[pd.NaT] = 1
tm.assert_series_equal(result, expected_s)
unique = s.unique()
self.assertEqual(unique.dtype, 'datetime64[ns]')
# numpy_array_equal cannot compare pd.NaT
if isinstance(s, Index):
exp_idx = DatetimeIndex(expected.tolist() + [pd.NaT])
tm.assert_index_equal(unique, exp_idx)
else:
tm.assert_numpy_array_equal(unique[:3], expected)
self.assertTrue(pd.isnull(unique[3]))
self.assertEqual(s.nunique(), 3)
self.assertEqual(s.nunique(dropna=False), 4)
# timedelta64[ns]
td = df.dt - df.dt + timedelta(1)
td = klass(td, name='dt')
result = td.value_counts()
expected_s = Series([6], index=[Timedelta('1day')], name='dt')
tm.assert_series_equal(result, expected_s)
expected = TimedeltaIndex(['1 days'], name='dt')
if isinstance(td, Index):
tm.assert_index_equal(td.unique(), expected)
else:
tm.assert_numpy_array_equal(td.unique(), expected.values)
td2 = timedelta(1) + (df.dt - df.dt)
td2 = klass(td2, name='dt')
result2 = td2.value_counts()
tm.assert_series_equal(result2, expected_s)
def test_unit_m_y_raises(self, unit):
msg = "Units 'M' and 'Y' are no longer supported"
with pytest.raises(ValueError, match=msg):
TimedeltaIndex([1, 3, 7], unit)
def test_value_counts_inferred(self):
klasses = [Index, Series]
for klass in klasses:
s_values = ['a', 'b', 'b', 'b', 'b', 'c', 'd', 'd', 'a', 'a']
s = klass(s_values)
expected = Series([4, 3, 2, 1], index=['b', 'a', 'd', 'c'])
tm.assert_series_equal(s.value_counts(), expected)
self.assert_numpy_array_equal(s.unique(), np.unique(s_values))
self.assertEqual(s.nunique(), 4)
# don't sort, have to sort after the fact as not sorting is platform-dep
hist = s.value_counts(sort=False)
hist.sort()
expected = Series([3, 1, 4, 2], index=list('acbd'))
expected.sort()
tm.assert_series_equal(hist, expected)
# sort ascending
hist = s.value_counts(ascending=True)
expected = Series([1, 2, 3, 4], index=list('cdab'))
tm.assert_series_equal(hist, expected)
# relative histogram.
hist = s.value_counts(normalize=True)
expected = Series([.4, .3, .2, .1], index=['b', 'a', 'd', 'c'])
tm.assert_series_equal(hist, expected)
# bins
self.assertRaises(TypeError,
lambda bins: s.value_counts(bins=bins), 1)
s1 = Series([1, 1, 2, 3])
res1 = s1.value_counts(bins=1)
exp1 = Series({0.998: 4})
tm.assert_series_equal(res1, exp1)
res1n = s1.value_counts(bins=1, normalize=True)
exp1n = Series({0.998: 1.0})
tm.assert_series_equal(res1n, exp1n)
self.assert_numpy_array_equal(s1.unique(), np.array([1, 2, 3]))
self.assertEqual(s1.nunique(), 3)
res4 = s1.value_counts(bins=4)
exp4 = Series({
0.998: 2,
1.5: 1,
2.0: 0,
2.5: 1
},
index=[0.998, 2.5, 1.5, 2.0])
tm.assert_series_equal(res4, exp4)
res4n = s1.value_counts(bins=4, normalize=True)
exp4n = Series({
0.998: 0.5,
1.5: 0.25,
2.0: 0.0,
2.5: 0.25
},
index=[0.998, 2.5, 1.5, 2.0])
tm.assert_series_equal(res4n, exp4n)
# handle NA's properly
s_values = [
'a', 'b', 'b', 'b', np.nan, np.nan, 'd', 'd', 'a', 'a', 'b'
]
s = klass(s_values)
expected = Series([4, 3, 2], index=['b', 'a', 'd'])
tm.assert_series_equal(s.value_counts(), expected)
self.assert_numpy_array_equal(
s.unique(), np.array(['a', 'b', np.nan, 'd'], dtype='O'))
self.assertEqual(s.nunique(), 3)
s = klass({})
expected = Series([], dtype=np.int64)
tm.assert_series_equal(s.value_counts(), expected)
self.assert_numpy_array_equal(s.unique(), np.array([]))
self.assertEqual(s.nunique(), 0)
# GH 3002, datetime64[ns]
txt = "\n".join([
'xxyyzz20100101PIE', 'xxyyzz20100101GUM', 'xxyyzz20100101EGG',
'xxyyww20090101EGG', 'foofoo20080909PIE', 'foofoo20080909GUM'
])
f = StringIO(txt)
df = pd.read_fwf(f,
widths=[6, 8, 3],
names=["person_id", "dt", "food"],
parse_dates=["dt"])
s = klass(df['dt'].copy())
idx = pd.to_datetime([
'2010-01-01 00:00:00Z', '2008-09-09 00:00:00Z',
'2009-01-01 00:00:00X'
])
expected_s = Series([3, 2, 1], index=idx)
tm.assert_series_equal(s.value_counts(), expected_s)
expected = np.array([
'2010-01-01 00:00:00Z', '2009-01-01 00:00:00Z',
'2008-09-09 00:00:00Z'
],
dtype='datetime64[ns]')
if isinstance(s, DatetimeIndex):
expected = DatetimeIndex(expected)
self.assertTrue(s.unique().equals(expected))
else:
self.assert_numpy_array_equal(s.unique(), expected)
self.assertEqual(s.nunique(), 3)
# with NaT
s = df['dt'].copy()
s = klass([v for v in s.values] + [pd.NaT])
result = s.value_counts()
self.assertEqual(result.index.dtype, 'datetime64[ns]')
tm.assert_series_equal(result, expected_s)
result = s.value_counts(dropna=False)
expected_s[pd.NaT] = 1
tm.assert_series_equal(result, expected_s)
unique = s.unique()
self.assertEqual(unique.dtype, 'datetime64[ns]')
# numpy_array_equal cannot compare pd.NaT
self.assert_numpy_array_equal(unique[:3], expected)
self.assertTrue(unique[3] is pd.NaT
or unique[3].astype('int64') == pd.tslib.iNaT)
self.assertEqual(s.nunique(), 3)
self.assertEqual(s.nunique(dropna=False), 4)
# timedelta64[ns]
td = df.dt - df.dt + timedelta(1)
td = klass(td)
result = td.value_counts()
expected_s = Series([6], index=[Timedelta('1day')])
tm.assert_series_equal(result, expected_s)
expected = TimedeltaIndex(['1 days'])
if isinstance(td, TimedeltaIndex):
self.assertTrue(td.unique().equals(expected))
else:
self.assert_numpy_array_equal(td.unique(), expected.values)
td2 = timedelta(1) + (df.dt - df.dt)
td2 = klass(td2)
result2 = td2.value_counts()
tm.assert_series_equal(result2, expected_s)
def test_order(self):
# GH 10295
idx1 = TimedeltaIndex(['1 day', '2 day', '3 day'],
freq='D',
name='idx')
idx2 = TimedeltaIndex(['1 hour', '2 hour', '3 hour'],
freq='H',
name='idx')
for idx in [idx1, idx2]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, idx)
assert ordered.freq == idx.freq
ordered = idx.sort_values(ascending=False)
expected = idx[::-1]
tm.assert_index_equal(ordered, expected)
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, idx)
tm.assert_numpy_array_equal(indexer,
np.array([0, 1, 2]),
check_dtype=False)
assert ordered.freq == idx.freq
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
tm.assert_index_equal(ordered, idx[::-1])
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
idx1 = TimedeltaIndex(
['1 hour', '3 hour', '5 hour', '2 hour ', '1 hour'], name='idx1')
exp1 = TimedeltaIndex(
['1 hour', '1 hour', '2 hour', '3 hour', '5 hour'], name='idx1')
idx2 = TimedeltaIndex(['1 day', '3 day', '5 day', '2 day', '1 day'],
name='idx2')
# TODO(wesm): unused?
# exp2 = TimedeltaIndex(['1 day', '1 day', '2 day',
# '3 day', '5 day'], name='idx2')
# idx3 = TimedeltaIndex([pd.NaT, '3 minute', '5 minute',
# '2 minute', pd.NaT], name='idx3')
# exp3 = TimedeltaIndex([pd.NaT, pd.NaT, '2 minute', '3 minute',
# '5 minute'], name='idx3')
for idx, expected in [(idx1, exp1), (idx1, exp1), (idx1, exp1)]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, expected)
assert ordered.freq is None
ordered = idx.sort_values(ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, expected)
exp = np.array([0, 4, 3, 1, 2])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
exp = np.array([2, 1, 3, 4, 0])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
def test_infer_freq(self, freq_sample):
# GH#11018
idx = pd.timedelta_range("1", freq=freq_sample, periods=10)
result = TimedeltaIndex(idx.asi8, freq="infer")
tm.assert_index_equal(idx, result)
assert result.freq == freq_sample
def test_dt_namespace_accessor(self):
# GH 7207, 11128
# test .dt namespace accessor
ok_for_period = PeriodIndex._datetimelike_ops
ok_for_period_methods = ['strftime', 'to_timestamp', 'asfreq']
ok_for_dt = DatetimeIndex._datetimelike_ops
ok_for_dt_methods = [
'to_period', 'to_pydatetime', 'tz_localize', 'tz_convert',
'normalize', 'strftime', 'round', 'floor', 'ceil', 'weekday_name'
]
ok_for_td = TimedeltaIndex._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):
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)):
self.assertEqual(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
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(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
self.assertEqual(str(tz_result), 'US/Eastern')
freq_result = s.dt.freq
self.assertEqual(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)
# 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 = s.dt.round('D')
expected = Series(pd.to_datetime(
['2012-01-02', '2012-01-02', '2012-01-01']),
name='xxx')
tm.assert_series_equal(result, expected)
# round with tz
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)
# floor
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.floor('D')
expected = Series(pd.to_datetime(
['2012-01-01', '2012-01-01', '2012-01-01']),
name='xxx')
tm.assert_series_equal(result, expected)
# ceil
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.ceil('D')
expected = Series(pd.to_datetime(
['2012-01-02', '2012-01-02', '2012-01-02']),
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
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(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
self.assertEqual(str(tz_result), 'CET')
freq_result = s.dt.freq
self.assertEqual(freq_result,
DatetimeIndex(s.values, freq='infer').freq)
# timedeltaindex
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
self.assertIsInstance(result, DataFrame)
tm.assert_index_equal(result.index, s.index)
result = s.dt.to_pytimedelta()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.total_seconds()
self.assertIsInstance(result, pd.Series)
self.assertTrue(result.dtype == 'float64')
freq_result = s.dt.freq
self.assertEqual(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 = pd.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
self.assertEqual(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 list(sorted(set(results)))
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
s = Series(
period_range('20130101', periods=5, freq='D', name='xxx').asobject)
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_period + ok_for_period_methods))))
# 11295
# ambiguous time error on the conversions
s = Series(pd.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, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
exp_values = pd.date_range('2015-01-01',
'2016-01-01',
freq='T',
tz='UTC').tz_convert('America/Chicago')
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 tm.assertRaisesRegexp(ValueError, "modifications"):
s.dt.hour = 5
# trying to set a copy
with pd.option_context('chained_assignment', 'raise'):
def f():
s.dt.hour[0] = 5
self.assertRaises(com.SettingWithCopyError, f)
def test_insert_nat(self, null):
# GH 18295 (test missing)
idx = timedelta_range("1day", "3day")
result = idx.insert(1, null)
expected = TimedeltaIndex(["1day", pd.NaT, "2day", "3day"])
tm.assert_index_equal(result, expected)
def test_value_counts_datetime64(self, index_or_series):
klass = index_or_series
# GH 3002, datetime64[ns]
# don't test names though
txt = "\n".join([
"xxyyzz20100101PIE",
"xxyyzz20100101GUM",
"xxyyzz20100101EGG",
"xxyyww20090101EGG",
"foofoo20080909PIE",
"foofoo20080909GUM",
])
f = StringIO(txt)
df = pd.read_fwf(f,
widths=[6, 8, 3],
names=["person_id", "dt", "food"],
parse_dates=["dt"])
s = klass(df["dt"].copy())
s.name = None
idx = pd.to_datetime([
"2010-01-01 00:00:00", "2008-09-09 00:00:00", "2009-01-01 00:00:00"
])
expected_s = Series([3, 2, 1], index=idx)
tm.assert_series_equal(s.value_counts(), expected_s)
expected = np_array_datetime64_compat(
[
"2010-01-01 00:00:00", "2009-01-01 00:00:00",
"2008-09-09 00:00:00"
],
dtype="datetime64[ns]",
)
if isinstance(s, Index):
tm.assert_index_equal(s.unique(), DatetimeIndex(expected))
else:
tm.assert_numpy_array_equal(s.unique(), expected)
assert s.nunique() == 3
# with NaT
s = df["dt"].copy()
s = klass(list(s.values) + [pd.NaT])
result = s.value_counts()
assert result.index.dtype == "datetime64[ns]"
tm.assert_series_equal(result, expected_s)
result = s.value_counts(dropna=False)
expected_s[pd.NaT] = 1
tm.assert_series_equal(result, expected_s)
unique = s.unique()
assert unique.dtype == "datetime64[ns]"
# numpy_array_equal cannot compare pd.NaT
if isinstance(s, Index):
exp_idx = DatetimeIndex(expected.tolist() + [pd.NaT])
tm.assert_index_equal(unique, exp_idx)
else:
tm.assert_numpy_array_equal(unique[:3], expected)
assert pd.isna(unique[3])
assert s.nunique() == 3
assert s.nunique(dropna=False) == 4
# timedelta64[ns]
td = df.dt - df.dt + timedelta(1)
td = klass(td, name="dt")
result = td.value_counts()
expected_s = Series([6], index=[Timedelta("1day")], name="dt")
tm.assert_series_equal(result, expected_s)
expected = TimedeltaIndex(["1 days"], name="dt")
if isinstance(td, Index):
tm.assert_index_equal(td.unique(), expected)
else:
tm.assert_numpy_array_equal(td.unique(), expected.values)
td2 = timedelta(1) + (df.dt - df.dt)
td2 = klass(td2, name="dt")
result2 = td2.value_counts()
tm.assert_series_equal(result2, expected_s)
tm.assert_numpy_array_equal(result, expected)
def test_strftime_nat(self):
# GH 29578
arr = PeriodArray(PeriodIndex(["2019-01-01", NaT], dtype="period[D]"))
result = arr.strftime("%Y-%m-%d")
expected = np.array(["2019-01-01", np.nan], dtype=object)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"arr,casting_nats",
[
(
TimedeltaIndex(["1 Day", "3 Hours", "NaT"])._data,
(NaT, np.timedelta64("NaT", "ns")),
),
(
pd.date_range("2000-01-01", periods=3, freq="D")._data,
(NaT, np.datetime64("NaT", "ns")),
),
(pd.period_range("2000-01-01", periods=3, freq="D")._data, (NaT, )),
],
ids=lambda x: type(x).__name__,
)
def test_casting_nat_setitem_array(arr, casting_nats):
expected = type(arr)._from_sequence([NaT, arr[1], arr[2]])
for nat in casting_nats:
arr = arr.copy()
def test_round(self):
t1 = Timedelta('1 days 02:34:56.789123456')
t2 = Timedelta('-1 days 02:34:56.789123456')
for (freq, s1, s2) in [
('N', t1, t2),
('U', Timedelta('1 days 02:34:56.789123000'),
Timedelta('-1 days 02:34:56.789123000')),
('L', Timedelta('1 days 02:34:56.789000000'),
Timedelta('-1 days 02:34:56.789000000')),
('S', Timedelta('1 days 02:34:57'), Timedelta('-1 days 02:34:57')),
('2S', Timedelta('1 days 02:34:56'),
Timedelta('-1 days 02:34:56')),
('5S', Timedelta('1 days 02:34:55'),
Timedelta('-1 days 02:34:55')),
('T', Timedelta('1 days 02:35:00'), Timedelta('-1 days 02:35:00')),
('12T', Timedelta('1 days 02:36:00'),
Timedelta('-1 days 02:36:00')),
('H', Timedelta('1 days 03:00:00'), Timedelta('-1 days 03:00:00')),
('d', Timedelta('1 days'), Timedelta('-1 days'))
]:
r1 = t1.round(freq)
assert r1 == s1
r2 = t2.round(freq)
assert r2 == s2
# invalid
for freq in ['Y', 'M', 'foobar']:
pytest.raises(ValueError, lambda: t1.round(freq))
t1 = timedelta_range('1 days', periods=3, freq='1 min 2 s 3 us')
t2 = -1 * t1
t1a = timedelta_range('1 days', periods=3, freq='1 min 2 s')
t1c = pd.TimedeltaIndex([1, 1, 1], unit='D')
# note that negative times round DOWN! so don't give whole numbers
for (freq, s1, s2) in [
('N', t1, t2), ('U', t1, t2),
('L', t1a,
TimedeltaIndex([
'-1 days +00:00:00', '-2 days +23:58:58', '-2 days +23:57:56'
],
dtype='timedelta64[ns]',
freq=None)),
('S', t1a,
TimedeltaIndex([
'-1 days +00:00:00', '-2 days +23:58:58', '-2 days +23:57:56'
],
dtype='timedelta64[ns]',
freq=None)),
('12T', t1c,
TimedeltaIndex(['-1 days', '-1 days', '-1 days'],
dtype='timedelta64[ns]',
freq=None)),
('H', t1c,
TimedeltaIndex(['-1 days', '-1 days', '-1 days'],
dtype='timedelta64[ns]',
freq=None)),
('d', t1c, pd.TimedeltaIndex([-1, -1, -1], unit='D'))
]:
r1 = t1.round(freq)
tm.assert_index_equal(r1, s1)
r2 = t2.round(freq)
tm.assert_index_equal(r2, s2)
# invalid
for freq in ['Y', 'M', 'foobar']:
pytest.raises(ValueError, lambda: t1.round(freq))
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 = DatetimeIndex._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
def to_perioddelta(self, freq) -> TimedeltaIndex:
from pandas.core.indexes.api import TimedeltaIndex
arr = self._data.to_perioddelta(freq)
return TimedeltaIndex._simple_new(arr, name=self.name)
def test_to_timedelta(self):
def conv(v):
return v.astype('m8[ns]')
d1 = np.timedelta64(1, 'D')
assert (to_timedelta(
'1 days 06:05:01.00003',
box=False) == conv(d1 +
np.timedelta64(6 * 3600 + 5 * 60 + 1, 's') +
np.timedelta64(30, 'us')))
assert (to_timedelta('15.5us',
box=False) == conv(np.timedelta64(15500, 'ns')))
# empty string
result = to_timedelta('', box=False)
assert result.astype('int64') == iNaT
result = to_timedelta(['', ''])
assert isna(result).all()
# pass thru
result = to_timedelta(np.array([np.timedelta64(1, 's')]))
expected = pd.Index(np.array([np.timedelta64(1, 's')]))
tm.assert_index_equal(result, expected)
# ints
result = np.timedelta64(0, 'ns')
expected = to_timedelta(0, box=False)
assert result == expected
# Series
expected = Series([timedelta(days=1), timedelta(days=1, seconds=1)])
result = to_timedelta(Series(['1d', '1days 00:00:01']))
tm.assert_series_equal(result, expected)
# with units
result = TimedeltaIndex([
np.timedelta64(0, 'ns'),
np.timedelta64(10, 's').astype('m8[ns]')
])
expected = to_timedelta([0, 10], unit='s')
tm.assert_index_equal(result, expected)
# single element conversion
v = timedelta(seconds=1)
result = to_timedelta(v, box=False)
expected = np.timedelta64(timedelta(seconds=1))
assert result == expected
v = np.timedelta64(timedelta(seconds=1))
result = to_timedelta(v, box=False)
expected = np.timedelta64(timedelta(seconds=1))
assert result == expected
# arrays of various dtypes
arr = np.array([1] * 5, dtype='int64')
result = to_timedelta(arr, unit='s')
expected = TimedeltaIndex([np.timedelta64(1, 's')] * 5)
tm.assert_index_equal(result, expected)
arr = np.array([1] * 5, dtype='int64')
result = to_timedelta(arr, unit='m')
expected = TimedeltaIndex([np.timedelta64(1, 'm')] * 5)
tm.assert_index_equal(result, expected)
arr = np.array([1] * 5, dtype='int64')
result = to_timedelta(arr, unit='h')
expected = TimedeltaIndex([np.timedelta64(1, 'h')] * 5)
tm.assert_index_equal(result, expected)
arr = np.array([1] * 5, dtype='timedelta64[s]')
result = to_timedelta(arr)
expected = TimedeltaIndex([np.timedelta64(1, 's')] * 5)
tm.assert_index_equal(result, expected)
arr = np.array([1] * 5, dtype='timedelta64[D]')
result = to_timedelta(arr)
expected = TimedeltaIndex([np.timedelta64(1, 'D')] * 5)
tm.assert_index_equal(result, expected)
# Test with lists as input when box=false
expected = np.array(np.arange(3) * 1000000000, dtype='timedelta64[ns]')
result = to_timedelta(range(3), unit='s', box=False)
tm.assert_numpy_array_equal(expected, result)
result = to_timedelta(np.arange(3), unit='s', box=False)
tm.assert_numpy_array_equal(expected, result)
result = to_timedelta([0, 1, 2], unit='s', box=False)
tm.assert_numpy_array_equal(expected, result)
# Tests with fractional seconds as input:
expected = np.array([0, 500000000, 800000000, 1200000000],
dtype='timedelta64[ns]')
result = to_timedelta([0., 0.5, 0.8, 1.2], unit='s', box=False)
tm.assert_numpy_array_equal(expected, result)
def test_tdi_sub_timestamp_raises(self):
idx = TimedeltaIndex(['1 day', '2 day'])
msg = "cannot subtract a datelike from a TimedeltaIndex"
with tm.assert_raises_regex(TypeError, msg):
idx - Timestamp('2011-01-01')