def test_tdi_iadd_timedeltalike(self, delta):
# only test adding/sub offsets as + is now numeric
rng = timedelta_range('1 days', '10 days')
expected = timedelta_range('1 days 02:00:00', '10 days 02:00:00',
freq='D')
rng += delta
tm.assert_index_equal(rng, expected)
def test_constructor_coverage(self):
rng = timedelta_range('1 days', periods=10.5)
exp = timedelta_range('1 days', periods=10)
tm.assert_index_equal(rng, exp)
msg = 'periods must be a number, got foo'
with pytest.raises(TypeError, match=msg):
TimedeltaIndex(start='1 days', periods='foo', freq='D')
pytest.raises(ValueError, TimedeltaIndex, start='1 days',
end='10 days')
with pytest.raises(TypeError):
TimedeltaIndex('1 days')
# generator expression
gen = (timedelta(i) for i in range(10))
result = TimedeltaIndex(gen)
expected = TimedeltaIndex([timedelta(i) for i in range(10)])
tm.assert_index_equal(result, expected)
# NumPy string array
strings = np.array(['1 days', '2 days', '3 days'])
result = TimedeltaIndex(strings)
expected = to_timedelta([1, 2, 3], unit='d')
tm.assert_index_equal(result, expected)
from_ints = TimedeltaIndex(expected.asi8)
tm.assert_index_equal(from_ints, expected)
# non-conforming freq
pytest.raises(ValueError, TimedeltaIndex,
['1 days', '2 days', '4 days'], freq='D')
pytest.raises(ValueError, TimedeltaIndex, periods=10, freq='D')
def test_delete(self):
idx = timedelta_range(start='1 Days', periods=5, freq='D', name='idx')
# prserve freq
expected_0 = timedelta_range(start='2 Days', periods=4, freq='D',
name='idx')
expected_4 = timedelta_range(start='1 Days', periods=4, freq='D',
name='idx')
# reset freq to None
expected_1 = TimedeltaIndex(
['1 day', '3 day', '4 day', '5 day'], freq=None, name='idx')
cases = {0: expected_0,
-5: expected_0,
-1: expected_4,
4: expected_4,
1: expected_1}
for n, expected in compat.iteritems(cases):
result = idx.delete(n)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
assert result.freq == expected.freq
with pytest.raises((IndexError, ValueError)):
# either depeidnig on numpy version
result = idx.delete(5)
def test_delete_slice(self):
idx = timedelta_range(start='1 days', periods=10, freq='D', name='idx')
# prserve freq
expected_0_2 = timedelta_range(start='4 days', periods=7, freq='D',
name='idx')
expected_7_9 = timedelta_range(start='1 days', periods=7, freq='D',
name='idx')
# reset freq to None
expected_3_5 = TimedeltaIndex(['1 d', '2 d', '3 d',
'7 d', '8 d', '9 d', '10d'],
freq=None, name='idx')
cases = {(0, 1, 2): expected_0_2,
(7, 8, 9): expected_7_9,
(3, 4, 5): expected_3_5}
for n, expected in compat.iteritems(cases):
result = idx.delete(n)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
assert result.freq == expected.freq
result = idx.delete(slice(n[0], n[-1] + 1))
tm.assert_index_equal(result, expected)
assert result.name == expected.name
assert result.freq == expected.freq
def test_categorical_repr_timedelta_ordered(self):
idx = timedelta_range('1 days', periods=5)
c = Categorical(idx, ordered=True)
exp = """[1 days, 2 days, 3 days, 4 days, 5 days]
Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]""" # noqa
assert repr(c) == exp
c = Categorical(idx.append(idx), categories=idx, ordered=True)
exp = """[1 days, 2 days, 3 days, 4 days, 5 days, 1 days, 2 days, 3 days, 4 days, 5 days]
Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]""" # noqa
assert repr(c) == exp
idx = timedelta_range('1 hours', periods=20)
c = Categorical(idx, ordered=True)
exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
Length: 20
Categories (20, timedelta64[ns]): [0 days 01:00:00 < 1 days 01:00:00 < 2 days 01:00:00 <
3 days 01:00:00 ... 16 days 01:00:00 < 17 days 01:00:00 <
18 days 01:00:00 < 19 days 01:00:00]""" # noqa
assert repr(c) == exp
c = Categorical(idx.append(idx), categories=idx, ordered=True)
exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
Length: 40
Categories (20, timedelta64[ns]): [0 days 01:00:00 < 1 days 01:00:00 < 2 days 01:00:00 <
3 days 01:00:00 ... 16 days 01:00:00 < 17 days 01:00:00 <
18 days 01:00:00 < 19 days 01:00:00]""" # noqa
assert repr(c) == exp
def test_categorical_series_repr_timedelta(self):
idx = timedelta_range('1 days', periods=5)
s = Series(Categorical(idx))
exp = """0 1 days
1 2 days
2 3 days
3 4 days
4 5 days
dtype: category
Categories (5, timedelta64[ns]): [1 days, 2 days, 3 days, 4 days, 5 days]"""
assert repr(s) == exp
idx = timedelta_range('1 hours', periods=10)
s = Series(Categorical(idx))
exp = """0 0 days 01:00:00
1 1 days 01:00:00
2 2 days 01:00:00
3 3 days 01:00:00
4 4 days 01:00:00
5 5 days 01:00:00
6 6 days 01:00:00
7 7 days 01:00:00
8 8 days 01:00:00
9 9 days 01:00:00
dtype: category
Categories (10, timedelta64[ns]): [0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00,
3 days 01:00:00, ..., 6 days 01:00:00, 7 days 01:00:00,
8 days 01:00:00, 9 days 01:00:00]""" # noqa
assert repr(s) == exp
def test_getitem(self):
idx1 = timedelta_range('1 day', '31 day', freq='D', name='idx')
for idx in [idx1]:
result = idx[0]
assert result == Timedelta('1 day')
result = idx[0:5]
expected = timedelta_range('1 day', '5 day', freq='D',
name='idx')
tm.assert_index_equal(result, expected)
assert result.freq == expected.freq
result = idx[0:10:2]
expected = timedelta_range('1 day', '9 day', freq='2D',
name='idx')
tm.assert_index_equal(result, expected)
assert result.freq == expected.freq
result = idx[-20:-5:3]
expected = timedelta_range('12 day', '24 day', freq='3D',
name='idx')
tm.assert_index_equal(result, expected)
assert result.freq == expected.freq
result = idx[4::-1]
expected = TimedeltaIndex(['5 day', '4 day', '3 day',
'2 day', '1 day'],
freq='-1D', name='idx')
tm.assert_index_equal(result, expected)
assert result.freq == expected.freq
def test_tdi_sub_int(self, one):
rng = timedelta_range('1 days 09:00:00', freq='H', periods=10)
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
# GH#22535
result = rng - one
expected = timedelta_range('1 days 08:00:00', freq='H', periods=10)
tm.assert_index_equal(result, expected)
def test_categorical_series_repr_timedelta_ordered(self):
idx = timedelta_range('1 days', periods=5)
s = Series(Categorical(idx, ordered=True))
exp = """0 1 days
1 2 days
2 3 days
3 4 days
4 5 days
dtype: category
Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]""" # noqa
assert repr(s) == exp
idx = timedelta_range('1 hours', periods=10)
s = Series(Categorical(idx, ordered=True))
exp = """0 0 days 01:00:00
1 1 days 01:00:00
2 2 days 01:00:00
3 3 days 01:00:00
4 4 days 01:00:00
5 5 days 01:00:00
6 6 days 01:00:00
7 7 days 01:00:00
8 8 days 01:00:00
9 9 days 01:00:00
dtype: category
Categories (10, timedelta64[ns]): [0 days 01:00:00 < 1 days 01:00:00 < 2 days 01:00:00 <
3 days 01:00:00 ... 6 days 01:00:00 < 7 days 01:00:00 <
8 days 01:00:00 < 9 days 01:00:00]""" # noqa
assert repr(s) == exp
def test_constructor_coverage(self):
rng = timedelta_range('1 days', periods=10.5)
exp = timedelta_range('1 days', periods=10)
self.assertTrue(rng.equals(exp))
self.assertRaises(ValueError, TimedeltaIndex, start='1 days',
periods='foo', freq='D')
self.assertRaises(ValueError, TimedeltaIndex, start='1 days',
end='10 days')
self.assertRaises(ValueError, TimedeltaIndex, '1 days')
# generator expression
gen = (timedelta(i) for i in range(10))
result = TimedeltaIndex(gen)
expected = TimedeltaIndex([timedelta(i) for i in range(10)])
self.assertTrue(result.equals(expected))
# NumPy string array
strings = np.array(['1 days', '2 days', '3 days'])
result = TimedeltaIndex(strings)
expected = to_timedelta([1,2,3],unit='d')
self.assertTrue(result.equals(expected))
from_ints = TimedeltaIndex(expected.asi8)
self.assertTrue(from_ints.equals(expected))
# non-conforming freq
self.assertRaises(ValueError, TimedeltaIndex,
['1 days', '2 days', '4 days'],
freq='D')
self.assertRaises(ValueError, TimedeltaIndex, periods=10, freq='D')
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")
tm.assert_series_equal(idx.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)
tm.assert_series_equal(idx.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)
tm.assert_series_equal(idx.value_counts(dropna=False), expected)
tm.assert_index_equal(idx.unique(), exp_idx)
def test_intersection_zero_length(self, period_1, period_2, sort):
# GH 24471 test for non overlap the intersection should be zero length
index_1 = timedelta_range('1 day', periods=period_1, freq='h')
index_2 = timedelta_range('1 day', periods=period_2, freq='h')
expected = timedelta_range('1 day', periods=0, freq='h')
result = index_1.intersection(index_2, sort=sort)
tm.assert_index_equal(result, expected)
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_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_sub_isub(self):
# only test adding/sub offsets as - is now numeric
# offset
offsets = [pd.offsets.Hour(2), timedelta(hours=2),
np.timedelta64(2, 'h'), Timedelta(hours=2)]
for delta in offsets:
rng = timedelta_range('1 days', '10 days')
result = rng - delta
expected = timedelta_range('0 days 22:00:00', '9 days 22:00:00')
tm.assert_index_equal(result, expected)
rng -= delta
tm.assert_index_equal(rng, expected)
# int
rng = timedelta_range('1 days 09:00:00', freq='H', periods=10)
result = rng - 1
expected = timedelta_range('1 days 08:00:00', freq='H', periods=10)
tm.assert_index_equal(result, expected)
rng -= 1
tm.assert_index_equal(rng, expected)
idx = TimedeltaIndex(['1 day', '2 day'])
msg = "cannot subtract a datelike from a TimedeltaIndex"
with tm.assertRaisesRegexp(TypeError, msg):
idx - Timestamp('2011-01-01')
result = Timestamp('2011-01-01') + idx
expected = DatetimeIndex(['2011-01-02', '2011-01-03'])
tm.assert_index_equal(result, expected)
def test_constructor_coverage(self):
rng = timedelta_range("1 days", periods=10.5)
exp = timedelta_range("1 days", periods=10)
self.assertTrue(rng.equals(exp))
self.assertRaises(ValueError, TimedeltaIndex, start="1 days", periods="foo", freq="D")
self.assertRaises(ValueError, TimedeltaIndex, start="1 days", end="10 days")
self.assertRaises(ValueError, TimedeltaIndex, "1 days")
# generator expression
gen = (timedelta(i) for i in range(10))
result = TimedeltaIndex(gen)
expected = TimedeltaIndex([timedelta(i) for i in range(10)])
self.assertTrue(result.equals(expected))
# NumPy string array
strings = np.array(["1 days", "2 days", "3 days"])
result = TimedeltaIndex(strings)
expected = to_timedelta([1, 2, 3], unit="d")
self.assertTrue(result.equals(expected))
from_ints = TimedeltaIndex(expected.asi8)
self.assertTrue(from_ints.equals(expected))
# non-conforming freq
self.assertRaises(ValueError, TimedeltaIndex, ["1 days", "2 days", "4 days"], freq="D")
self.assertRaises(ValueError, TimedeltaIndex, periods=10, freq="D")
def test_tdi_iadd_int(self, one):
rng = timedelta_range('1 days 09:00:00', freq='H', periods=10)
expected = timedelta_range('1 days 10:00:00', freq='H', periods=10)
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
# GH#22535
rng += one
tm.assert_index_equal(rng, expected)
def test_zero_length_input_index(self, sort):
# GH 24966 test for 0-len intersections are copied
index_1 = timedelta_range('1 day', periods=0, freq='h')
index_2 = timedelta_range('1 day', periods=3, freq='h')
result = index_1.intersection(index_2, sort=sort)
assert index_1 is not result
assert index_2 is not result
tm.assert_copy(result, index_1)
def test_resample_single_period_timedelta():
s = Series(list(range(5)), index=pd.timedelta_range(
'1 day', freq='s', periods=5))
result = s.resample('2s').sum()
expected = Series([1, 5, 4], index=pd.timedelta_range(
'1 day', freq='2s', periods=3))
assert_series_equal(result, expected)
def test_union_bug_1730(self):
rng_a = timedelta_range('1 day', periods=4, freq='3H')
rng_b = timedelta_range('1 day', periods=4, freq='4H')
result = rng_a.union(rng_b)
exp = TimedeltaIndex(sorted(set(list(rng_a)) | set(list(rng_b))))
tm.assert_index_equal(result, exp)
def test_union_bug_1730(self):
rng_a = timedelta_range("1 day", periods=4, freq="3H")
rng_b = timedelta_range("1 day", periods=4, freq="4H")
result = rng_a.union(rng_b)
exp = TimedeltaIndex(sorted(set(list(rng_a)) | set(list(rng_b))))
self.assertTrue(result.equals(exp))
def test_tdi_add_int(self, one):
# Variants of `one` for #19012
rng = timedelta_range('1 days 09:00:00', freq='H', periods=10)
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
# GH#22535
result = rng + one
expected = timedelta_range('1 days 10:00:00', freq='H', periods=10)
tm.assert_index_equal(result, 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)
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_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_from_arrays_index_series_timedelta():
idx1 = pd.timedelta_range('1 days', freq='D', periods=3)
idx2 = pd.timedelta_range('2 hours', freq='H', periods=3)
result = pd.MultiIndex.from_arrays([idx1, idx2])
tm.assert_index_equal(result.get_level_values(0), idx1)
tm.assert_index_equal(result.get_level_values(1), idx2)
result2 = pd.MultiIndex.from_arrays([pd.Series(idx1), pd.Series(idx2)])
tm.assert_index_equal(result2.get_level_values(0), idx1)
tm.assert_index_equal(result2.get_level_values(1), idx2)
tm.assert_index_equal(result, result2)
def test_intersection_bug_1708(self):
index_1 = timedelta_range("1 day", periods=4, freq="h")
index_2 = index_1 + pd.offsets.Hour(5)
result = index_1 & index_2
self.assertEqual(len(result), 0)
index_1 = timedelta_range("1 day", periods=4, freq="h")
index_2 = index_1 + pd.offsets.Hour(1)
result = index_1 & index_2
expected = timedelta_range("1 day 01:00:00", periods=3, freq="h")
tm.assert_index_equal(result, expected)
def test_intersection_equal(self, sort):
# GH 24471 Test intersection outcome given the sort keyword
# for equal indicies intersection should return the original index
first = timedelta_range('1 day', periods=4, freq='h')
second = timedelta_range('1 day', periods=4, freq='h')
intersect = first.intersection(second, sort=sort)
if sort is None:
tm.assert_index_equal(intersect, second.sort_values())
assert tm.equalContents(intersect, second)
# Corner cases
inter = first.intersection(first, sort=sort)
assert inter is first
def test_intersection_bug_1708(self):
index_1 = timedelta_range('1 day', periods=4, freq='h')
index_2 = index_1 + pd.offsets.Hour(5)
result = index_1 & index_2
assert len(result) == 0
index_1 = timedelta_range('1 day', periods=4, freq='h')
index_2 = index_1 + pd.offsets.Hour(1)
result = index_1 & index_2
expected = timedelta_range('1 day 01:00:00', periods=3, freq='h')
tm.assert_index_equal(result, expected)
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_categorical_index_repr_timedelta_ordered(self):
idx = timedelta_range('1 days', periods=5)
i = CategoricalIndex(Categorical(idx, ordered=True))
exp = """CategoricalIndex(['1 days', '2 days', '3 days', '4 days', '5 days'], categories=[1 days 00:00:00, 2 days 00:00:00, 3 days 00:00:00, 4 days 00:00:00, 5 days 00:00:00], ordered=True, dtype='category')""" # noqa
assert repr(i) == exp
idx = timedelta_range('1 hours', periods=10)
i = CategoricalIndex(Categorical(idx, ordered=True))
exp = """CategoricalIndex(['0 days 01:00:00', '1 days 01:00:00', '2 days 01:00:00',
'3 days 01:00:00', '4 days 01:00:00', '5 days 01:00:00',
'6 days 01:00:00', '7 days 01:00:00', '8 days 01:00:00',
'9 days 01:00:00'],
categories=[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, 5 days 01:00:00, 6 days 01:00:00, 7 days 01:00:00, ...], ordered=True, dtype='category')""" # noqa
assert repr(i) == exp
class TestIntervalIndex:
index = IntervalIndex.from_arrays([0, 1], [1, 2])
def create_index(self, closed="right"):
return IntervalIndex.from_breaks(range(11), closed=closed)
def create_index_with_nan(self, closed="right"):
mask = [True, False] + [True] * 8
return IntervalIndex.from_arrays(
np.where(mask, np.arange(10), np.nan),
np.where(mask, np.arange(1, 11), np.nan),
closed=closed,
)
def test_properties(self, closed):
index = self.create_index(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
tm.assert_index_equal(index.left, Index(np.arange(10)))
tm.assert_index_equal(index.right, Index(np.arange(1, 11)))
tm.assert_index_equal(index.mid, Index(np.arange(0.5, 10.5)))
assert index.closed == closed
ivs = [Interval(l, r, closed) for l, r in zip(range(10), range(1, 11))]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
# with nans
index = self.create_index_with_nan(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
expected_left = Index([0, np.nan, 2, 3, 4, 5, 6, 7, 8, 9])
expected_right = expected_left + 1
expected_mid = expected_left + 0.5
tm.assert_index_equal(index.left, expected_left)
tm.assert_index_equal(index.right, expected_right)
tm.assert_index_equal(index.mid, expected_mid)
assert index.closed == closed
ivs = [
Interval(l, r, closed) if notna(l) else np.nan
for l, r in zip(expected_left, expected_right)
]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
@pytest.mark.parametrize(
"breaks",
[
[1, 1, 2, 5, 15, 53, 217, 1014, 5335, 31240, 201608],
[-np.inf, -100, -10, 0.5, 1, 1.5, 3.8, 101, 202, np.inf],
pd.to_datetime(["20170101", "20170202", "20170303", "20170404"]),
pd.to_timedelta(["1ns", "2ms", "3s", "4M", "5H", "6D"]),
],
)
def test_length(self, closed, breaks):
# GH 18789
index = IntervalIndex.from_breaks(breaks, closed=closed)
result = index.length
expected = Index(iv.length for iv in index)
tm.assert_index_equal(result, expected)
# with NA
index = index.insert(1, np.nan)
result = index.length
expected = Index(iv.length if notna(iv) else iv for iv in index)
tm.assert_index_equal(result, expected)
def test_with_nans(self, closed):
index = self.create_index(closed=closed)
assert index.hasnans is False
result = index.isna()
expected = np.zeros(len(index), dtype=bool)
tm.assert_numpy_array_equal(result, expected)
result = index.notna()
expected = np.ones(len(index), dtype=bool)
tm.assert_numpy_array_equal(result, expected)
index = self.create_index_with_nan(closed=closed)
assert index.hasnans is True
result = index.isna()
expected = np.array([False, True] + [False] * (len(index) - 2))
tm.assert_numpy_array_equal(result, expected)
result = index.notna()
expected = np.array([True, False] + [True] * (len(index) - 2))
tm.assert_numpy_array_equal(result, expected)
def test_copy(self, closed):
expected = self.create_index(closed=closed)
result = expected.copy()
assert result.equals(expected)
result = expected.copy(deep=True)
assert result.equals(expected)
assert result.left is not expected.left
def test_ensure_copied_data(self, closed):
# exercise the copy flag in the constructor
# not copying
index = self.create_index(closed=closed)
result = IntervalIndex(index, copy=False)
tm.assert_numpy_array_equal(index.left.values,
result.left.values,
check_same="same")
tm.assert_numpy_array_equal(index.right.values,
result.right.values,
check_same="same")
# by-definition make a copy
result = IntervalIndex(np.array(index), copy=False)
tm.assert_numpy_array_equal(index.left.values,
result.left.values,
check_same="copy")
tm.assert_numpy_array_equal(index.right.values,
result.right.values,
check_same="copy")
def test_delete(self, closed):
expected = IntervalIndex.from_breaks(np.arange(1, 11), closed=closed)
result = self.create_index(closed=closed).delete(0)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"data",
[
interval_range(0, periods=10, closed="neither"),
interval_range(1.7, periods=8, freq=2.5, closed="both"),
interval_range(Timestamp("20170101"), periods=12, closed="left"),
interval_range(Timedelta("1 day"), periods=6, closed="right"),
],
)
def test_insert(self, data):
item = data[0]
idx_item = IntervalIndex([item])
# start
expected = idx_item.append(data)
result = data.insert(0, item)
tm.assert_index_equal(result, expected)
# end
expected = data.append(idx_item)
result = data.insert(len(data), item)
tm.assert_index_equal(result, expected)
# mid
expected = data[:3].append(idx_item).append(data[3:])
result = data.insert(3, item)
tm.assert_index_equal(result, expected)
# invalid type
msg = "can only insert Interval objects and NA into an IntervalIndex"
with pytest.raises(ValueError, match=msg):
data.insert(1, "foo")
# invalid closed
msg = "inserted item must be closed on the same side as the index"
for closed in {"left", "right", "both", "neither"} - {item.closed}:
with pytest.raises(ValueError, match=msg):
bad_item = Interval(item.left, item.right, closed=closed)
data.insert(1, bad_item)
# GH 18295 (test missing)
na_idx = IntervalIndex([np.nan], closed=data.closed)
for na in (np.nan, pd.NaT, None):
expected = data[:1].append(na_idx).append(data[1:])
result = data.insert(1, na)
tm.assert_index_equal(result, expected)
def test_is_unique_interval(self, closed):
"""
Interval specific tests for is_unique in addition to base class tests
"""
# unique overlapping - distinct endpoints
idx = IntervalIndex.from_tuples([(0, 1), (0.5, 1.5)], closed=closed)
assert idx.is_unique is True
# unique overlapping - shared endpoints
idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)],
closed=closed)
assert idx.is_unique is True
# unique nested
idx = IntervalIndex.from_tuples([(-1, 1), (-2, 2)], closed=closed)
assert idx.is_unique is True
def test_monotonic(self, closed):
# increasing non-overlapping
idx = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)],
closed=closed)
assert idx.is_monotonic is True
assert idx._is_strictly_monotonic_increasing is True
assert idx.is_monotonic_decreasing is False
assert idx._is_strictly_monotonic_decreasing is False
# decreasing non-overlapping
idx = IntervalIndex.from_tuples([(4, 5), (2, 3), (1, 2)],
closed=closed)
assert idx.is_monotonic is False
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is True
assert idx._is_strictly_monotonic_decreasing is True
# unordered non-overlapping
idx = IntervalIndex.from_tuples([(0, 1), (4, 5), (2, 3)],
closed=closed)
assert idx.is_monotonic is False
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is False
assert idx._is_strictly_monotonic_decreasing is False
# increasing overlapping
idx = IntervalIndex.from_tuples([(0, 2), (0.5, 2.5), (1, 3)],
closed=closed)
assert idx.is_monotonic is True
assert idx._is_strictly_monotonic_increasing is True
assert idx.is_monotonic_decreasing is False
assert idx._is_strictly_monotonic_decreasing is False
# decreasing overlapping
idx = IntervalIndex.from_tuples([(1, 3), (0.5, 2.5), (0, 2)],
closed=closed)
assert idx.is_monotonic is False
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is True
assert idx._is_strictly_monotonic_decreasing is True
# unordered overlapping
idx = IntervalIndex.from_tuples([(0.5, 2.5), (0, 2), (1, 3)],
closed=closed)
assert idx.is_monotonic is False
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is False
assert idx._is_strictly_monotonic_decreasing is False
# increasing overlapping shared endpoints
idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)],
closed=closed)
assert idx.is_monotonic is True
assert idx._is_strictly_monotonic_increasing is True
assert idx.is_monotonic_decreasing is False
assert idx._is_strictly_monotonic_decreasing is False
# decreasing overlapping shared endpoints
idx = pd.IntervalIndex.from_tuples([(2, 3), (1, 3), (1, 2)],
closed=closed)
assert idx.is_monotonic is False
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is True
assert idx._is_strictly_monotonic_decreasing is True
# stationary
idx = IntervalIndex.from_tuples([(0, 1), (0, 1)], closed=closed)
assert idx.is_monotonic is True
assert idx._is_strictly_monotonic_increasing is False
assert idx.is_monotonic_decreasing is True
assert idx._is_strictly_monotonic_decreasing is False
# empty
idx = IntervalIndex([], closed=closed)
assert idx.is_monotonic is True
assert idx._is_strictly_monotonic_increasing is True
assert idx.is_monotonic_decreasing is True
assert idx._is_strictly_monotonic_decreasing is True
def test_get_item(self, closed):
i = IntervalIndex.from_arrays((0, 1, np.nan), (1, 2, np.nan),
closed=closed)
assert i[0] == Interval(0.0, 1.0, closed=closed)
assert i[1] == Interval(1.0, 2.0, closed=closed)
assert isna(i[2])
result = i[0:1]
expected = IntervalIndex.from_arrays((0.0, ), (1.0, ), closed=closed)
tm.assert_index_equal(result, expected)
result = i[0:2]
expected = IntervalIndex.from_arrays((0.0, 1), (1.0, 2.0),
closed=closed)
tm.assert_index_equal(result, expected)
result = i[1:3]
expected = IntervalIndex.from_arrays((1.0, np.nan), (2.0, np.nan),
closed=closed)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"breaks",
[
date_range("20180101", periods=4),
date_range("20180101", periods=4, tz="US/Eastern"),
timedelta_range("0 days", periods=4),
],
ids=lambda x: str(x.dtype),
)
def test_maybe_convert_i8(self, breaks):
# GH 20636
index = IntervalIndex.from_breaks(breaks)
# intervalindex
result = index._maybe_convert_i8(index)
expected = IntervalIndex.from_breaks(breaks.asi8)
tm.assert_index_equal(result, expected)
# interval
interval = Interval(breaks[0], breaks[1])
result = index._maybe_convert_i8(interval)
expected = Interval(breaks[0].value, breaks[1].value)
assert result == expected
# datetimelike index
result = index._maybe_convert_i8(breaks)
expected = Index(breaks.asi8)
tm.assert_index_equal(result, expected)
# datetimelike scalar
result = index._maybe_convert_i8(breaks[0])
expected = breaks[0].value
assert result == expected
# list-like of datetimelike scalars
result = index._maybe_convert_i8(list(breaks))
expected = Index(breaks.asi8)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"breaks",
[
date_range("2018-01-01", periods=5),
timedelta_range("0 days", periods=5)
],
)
def test_maybe_convert_i8_nat(self, breaks):
# GH 20636
index = IntervalIndex.from_breaks(breaks)
to_convert = breaks._constructor([pd.NaT] * 3)
expected = pd.Float64Index([np.nan] * 3)
result = index._maybe_convert_i8(to_convert)
tm.assert_index_equal(result, expected)
to_convert = to_convert.insert(0, breaks[0])
expected = expected.insert(0, float(breaks[0].value))
result = index._maybe_convert_i8(to_convert)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"breaks",
[np.arange(5, dtype="int64"),
np.arange(5, dtype="float64")],
ids=lambda x: str(x.dtype),
)
@pytest.mark.parametrize(
"make_key",
[
IntervalIndex.from_breaks,
lambda breaks: Interval(breaks[0], breaks[1]),
lambda breaks: breaks,
lambda breaks: breaks[0],
list,
],
ids=["IntervalIndex", "Interval", "Index", "scalar", "list"],
)
def test_maybe_convert_i8_numeric(self, breaks, make_key):
# GH 20636
index = IntervalIndex.from_breaks(breaks)
key = make_key(breaks)
# no conversion occurs for numeric
result = index._maybe_convert_i8(key)
assert result is key
@pytest.mark.parametrize(
"breaks1, breaks2",
permutations(
[
date_range("20180101", periods=4),
date_range("20180101", periods=4, tz="US/Eastern"),
timedelta_range("0 days", periods=4),
],
2,
),
ids=lambda x: str(x.dtype),
)
@pytest.mark.parametrize(
"make_key",
[
IntervalIndex.from_breaks,
lambda breaks: Interval(breaks[0], breaks[1]),
lambda breaks: breaks,
lambda breaks: breaks[0],
list,
],
ids=["IntervalIndex", "Interval", "Index", "scalar", "list"],
)
def test_maybe_convert_i8_errors(self, breaks1, breaks2, make_key):
# GH 20636
index = IntervalIndex.from_breaks(breaks1)
key = make_key(breaks2)
msg = (
f"Cannot index an IntervalIndex of subtype {breaks1.dtype} with "
f"values of dtype {breaks2.dtype}")
msg = re.escape(msg)
with pytest.raises(ValueError, match=msg):
index._maybe_convert_i8(key)
def test_contains_method(self):
# can select values that are IN the range of a value
i = IntervalIndex.from_arrays([0, 1], [1, 2])
expected = np.array([False, False], dtype="bool")
actual = i.contains(0)
tm.assert_numpy_array_equal(actual, expected)
actual = i.contains(3)
tm.assert_numpy_array_equal(actual, expected)
expected = np.array([True, False], dtype="bool")
actual = i.contains(0.5)
tm.assert_numpy_array_equal(actual, expected)
actual = i.contains(1)
tm.assert_numpy_array_equal(actual, expected)
# __contains__ not implemented for "interval in interval", follow
# that for the contains method for now
with pytest.raises(NotImplementedError,
match="contains not implemented for two"):
i.contains(Interval(0, 1))
def test_contains_dunder(self):
index = IntervalIndex.from_arrays([0, 1], [1, 2], closed="right")
# __contains__ requires perfect matches to intervals.
assert 0 not in index
assert 1 not in index
assert 2 not in index
assert Interval(0, 1, closed="right") in index
assert Interval(0, 2, closed="right") not in index
assert Interval(0, 0.5, closed="right") not in index
assert Interval(3, 5, closed="right") not in index
assert Interval(-1, 0, closed="left") not in index
assert Interval(0, 1, closed="left") not in index
assert Interval(0, 1, closed="both") not in index
def test_dropna(self, closed):
expected = IntervalIndex.from_tuples([(0.0, 1.0), (1.0, 2.0)],
closed=closed)
ii = IntervalIndex.from_tuples([(0, 1), (1, 2), np.nan], closed=closed)
result = ii.dropna()
tm.assert_index_equal(result, expected)
ii = IntervalIndex.from_arrays([0, 1, np.nan], [1, 2, np.nan],
closed=closed)
result = ii.dropna()
tm.assert_index_equal(result, expected)
def test_non_contiguous(self, closed):
index = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
target = [0.5, 1.5, 2.5]
actual = index.get_indexer(target)
expected = np.array([0, -1, 1], dtype="intp")
tm.assert_numpy_array_equal(actual, expected)
assert 1.5 not in index
def test_isin(self, closed):
index = self.create_index(closed=closed)
expected = np.array([True] + [False] * (len(index) - 1))
result = index.isin(index[:1])
tm.assert_numpy_array_equal(result, expected)
result = index.isin([index[0]])
tm.assert_numpy_array_equal(result, expected)
other = IntervalIndex.from_breaks(np.arange(-2, 10), closed=closed)
expected = np.array([True] * (len(index) - 1) + [False])
result = index.isin(other)
tm.assert_numpy_array_equal(result, expected)
result = index.isin(other.tolist())
tm.assert_numpy_array_equal(result, expected)
for other_closed in {"right", "left", "both", "neither"}:
other = self.create_index(closed=other_closed)
expected = np.repeat(closed == other_closed, len(index))
result = index.isin(other)
tm.assert_numpy_array_equal(result, expected)
result = index.isin(other.tolist())
tm.assert_numpy_array_equal(result, expected)
def test_comparison(self):
actual = Interval(0, 1) < self.index
expected = np.array([False, True])
tm.assert_numpy_array_equal(actual, expected)
actual = Interval(0.5, 1.5) < self.index
expected = np.array([False, True])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index > Interval(0.5, 1.5)
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == self.index
expected = np.array([True, True])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index <= self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index >= self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index < self.index
expected = np.array([False, False])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index > self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == IntervalIndex.from_breaks([0, 1, 2], "left")
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == self.index.values
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index.values == self.index
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index <= self.index.values
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index != self.index.values
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index > self.index.values
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index.values > self.index
tm.assert_numpy_array_equal(actual, np.array([False, False]))
# invalid comparisons
actual = self.index == 0
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index == self.index.left
tm.assert_numpy_array_equal(actual, np.array([False, False]))
msg = ("not supported between instances of 'int' and "
"'pandas._libs.interval.Interval'")
with pytest.raises(TypeError, match=msg):
self.index > 0
with pytest.raises(TypeError, match=msg):
self.index <= 0
with pytest.raises(TypeError, match=msg):
self.index > np.arange(2)
msg = "Lengths must match to compare"
with pytest.raises(ValueError, match=msg):
self.index > np.arange(3)
def test_missing_values(self, closed):
idx = Index([
np.nan,
Interval(0, 1, closed=closed),
Interval(1, 2, closed=closed)
])
idx2 = IntervalIndex.from_arrays([np.nan, 0, 1], [np.nan, 1, 2],
closed=closed)
assert idx.equals(idx2)
msg = ("missing values must be missing in the same location both left "
"and right sides")
with pytest.raises(ValueError, match=msg):
IntervalIndex.from_arrays([np.nan, 0, 1],
np.array([0, 1, 2]),
closed=closed)
tm.assert_numpy_array_equal(isna(idx), np.array([True, False, False]))
def test_sort_values(self, closed):
index = self.create_index(closed=closed)
result = index.sort_values()
tm.assert_index_equal(result, index)
result = index.sort_values(ascending=False)
tm.assert_index_equal(result, index[::-1])
# with nan
index = IntervalIndex([Interval(1, 2), np.nan, Interval(0, 1)])
result = index.sort_values()
expected = IntervalIndex([Interval(0, 1), Interval(1, 2), np.nan])
tm.assert_index_equal(result, expected)
result = index.sort_values(ascending=False)
expected = IntervalIndex([np.nan, Interval(1, 2), Interval(0, 1)])
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("tz", [None, "US/Eastern"])
def test_datetime(self, tz):
start = Timestamp("2000-01-01", tz=tz)
dates = date_range(start=start, periods=10)
index = IntervalIndex.from_breaks(dates)
# test mid
start = Timestamp("2000-01-01T12:00", tz=tz)
expected = date_range(start=start, periods=9)
tm.assert_index_equal(index.mid, expected)
# __contains__ doesn't check individual points
assert Timestamp("2000-01-01", tz=tz) not in index
assert Timestamp("2000-01-01T12", tz=tz) not in index
assert Timestamp("2000-01-02", tz=tz) not in index
iv_true = Interval(Timestamp("2000-01-02", tz=tz),
Timestamp("2000-01-03", tz=tz))
iv_false = Interval(Timestamp("1999-12-31", tz=tz),
Timestamp("2000-01-01", tz=tz))
assert iv_true in index
assert iv_false not in index
# .contains does check individual points
assert not index.contains(Timestamp("2000-01-01", tz=tz)).any()
assert index.contains(Timestamp("2000-01-01T12", tz=tz)).any()
assert index.contains(Timestamp("2000-01-02", tz=tz)).any()
# test get_indexer
start = Timestamp("1999-12-31T12:00", tz=tz)
target = date_range(start=start, periods=7, freq="12H")
actual = index.get_indexer(target)
expected = np.array([-1, -1, 0, 0, 1, 1, 2], dtype="intp")
tm.assert_numpy_array_equal(actual, expected)
start = Timestamp("2000-01-08T18:00", tz=tz)
target = date_range(start=start, periods=7, freq="6H")
actual = index.get_indexer(target)
expected = np.array([7, 7, 8, 8, 8, 8, -1], dtype="intp")
tm.assert_numpy_array_equal(actual, expected)
def test_append(self, closed):
index1 = IntervalIndex.from_arrays([0, 1], [1, 2], closed=closed)
index2 = IntervalIndex.from_arrays([1, 2], [2, 3], closed=closed)
result = index1.append(index2)
expected = IntervalIndex.from_arrays([0, 1, 1, 2], [1, 2, 2, 3],
closed=closed)
tm.assert_index_equal(result, expected)
result = index1.append([index1, index2])
expected = IntervalIndex.from_arrays([0, 1, 0, 1, 1, 2],
[1, 2, 1, 2, 2, 3],
closed=closed)
tm.assert_index_equal(result, expected)
msg = "Intervals must all be closed on the same side"
for other_closed in {"left", "right", "both", "neither"} - {closed}:
index_other_closed = IntervalIndex.from_arrays([0, 1], [1, 2],
closed=other_closed)
with pytest.raises(ValueError, match=msg):
index1.append(index_other_closed)
def test_is_non_overlapping_monotonic(self, closed):
# Should be True in all cases
tpls = [(0, 1), (2, 3), (4, 5), (6, 7)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is True
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is True
# Should be False in all cases (overlapping)
tpls = [(0, 2), (1, 3), (4, 5), (6, 7)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is False
# Should be False in all cases (non-monotonic)
tpls = [(0, 1), (2, 3), (6, 7), (4, 5)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is False
# Should be False for closed='both', otherwise True (GH16560)
if closed == "both":
idx = IntervalIndex.from_breaks(range(4), closed=closed)
assert idx.is_non_overlapping_monotonic is False
else:
idx = IntervalIndex.from_breaks(range(4), closed=closed)
assert idx.is_non_overlapping_monotonic is True
@pytest.mark.parametrize(
"start, shift, na_value",
[
(0, 1, np.nan),
(Timestamp("2018-01-01"), Timedelta("1 day"), pd.NaT),
(Timedelta("0 days"), Timedelta("1 day"), pd.NaT),
],
)
def test_is_overlapping(self, start, shift, na_value, closed):
# GH 23309
# see test_interval_tree.py for extensive tests; interface tests here
# non-overlapping
tuples = [(start + n * shift, start + (n + 1) * shift)
for n in (0, 2, 4)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
assert index.is_overlapping is False
# non-overlapping with NA
tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
assert index.is_overlapping is False
# overlapping
tuples = [(start + n * shift, start + (n + 2) * shift)
for n in range(3)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
assert index.is_overlapping is True
# overlapping with NA
tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
assert index.is_overlapping is True
# common endpoints
tuples = [(start + n * shift, start + (n + 1) * shift)
for n in range(3)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
result = index.is_overlapping
expected = closed == "both"
assert result is expected
# common endpoints with NA
tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
index = IntervalIndex.from_tuples(tuples, closed=closed)
result = index.is_overlapping
assert result is expected
@pytest.mark.parametrize(
"tuples",
[
list(zip(range(10), range(1, 11))),
list(
zip(
date_range("20170101", periods=10),
date_range("20170101", periods=10),
)),
list(
zip(
timedelta_range("0 days", periods=10),
timedelta_range("1 day", periods=10),
)),
],
)
def test_to_tuples(self, tuples):
# GH 18756
idx = IntervalIndex.from_tuples(tuples)
result = idx.to_tuples()
expected = Index(com.asarray_tuplesafe(tuples))
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"tuples",
[
list(zip(range(10), range(1, 11))) + [np.nan],
list(
zip(
date_range("20170101", periods=10),
date_range("20170101", periods=10),
)) + [np.nan],
list(
zip(
timedelta_range("0 days", periods=10),
timedelta_range("1 day", periods=10),
)) + [np.nan],
],
)
@pytest.mark.parametrize("na_tuple", [True, False])
def test_to_tuples_na(self, tuples, na_tuple):
# GH 18756
idx = IntervalIndex.from_tuples(tuples)
result = idx.to_tuples(na_tuple=na_tuple)
# check the non-NA portion
expected_notna = Index(com.asarray_tuplesafe(tuples[:-1]))
result_notna = result[:-1]
tm.assert_index_equal(result_notna, expected_notna)
# check the NA portion
result_na = result[-1]
if na_tuple:
assert isinstance(result_na, tuple)
assert len(result_na) == 2
assert all(isna(x) for x in result_na)
else:
assert isna(result_na)
def test_nbytes(self):
# GH 19209
left = np.arange(0, 4, dtype="i8")
right = np.arange(1, 5, dtype="i8")
result = IntervalIndex.from_arrays(left, right).nbytes
expected = 64 # 4 * 8 * 2
assert result == expected
@pytest.mark.parametrize("new_closed",
["left", "right", "both", "neither"])
def test_set_closed(self, name, closed, new_closed):
# GH 21670
index = interval_range(0, 5, closed=closed, name=name)
result = index.set_closed(new_closed)
expected = interval_range(0, 5, closed=new_closed, name=name)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("bad_closed", ["foo", 10, "LEFT", True, False])
def test_set_closed_errors(self, bad_closed):
# GH 21670
index = interval_range(0, 5)
msg = f"invalid option for 'closed': {bad_closed}"
with pytest.raises(ValueError, match=msg):
index.set_closed(bad_closed)
def test_is_all_dates(self):
# GH 23576
year_2017 = pd.Interval(pd.Timestamp("2017-01-01 00:00:00"),
pd.Timestamp("2018-01-01 00:00:00"))
year_2017_index = pd.IntervalIndex([year_2017])
assert not year_2017_index.is_all_dates
@pytest.mark.parametrize("key", [[5], (2, 3)])
def test_get_value_non_scalar_errors(self, key):
# GH 31117
idx = IntervalIndex.from_tuples([(1, 3), (2, 4), (3, 5), (7, 10),
(3, 10)])
s = pd.Series(range(len(idx)), index=idx)
msg = str(key)
with pytest.raises(InvalidIndexError, match=msg):
with tm.assert_produces_warning(FutureWarning):
idx.get_value(s, key)
def test_unknown_attribute(self):
# see gh-9680
tdi = pd.timedelta_range(start=0, periods=10, freq='1s')
ts = pd.Series(np.random.normal(size=10), index=tdi)
assert 'foo' not in ts.__dict__.keys()
pytest.raises(AttributeError, lambda: ts.foo)
class TestCategoricalConstructors:
def test_validate_ordered(self):
# see gh-14058
exp_msg = "'ordered' must either be 'True' or 'False'"
exp_err = TypeError
# This should be a boolean.
ordered = np.array([0, 1, 2])
with pytest.raises(exp_err, match=exp_msg):
Categorical([1, 2, 3], ordered=ordered)
with pytest.raises(exp_err, match=exp_msg):
Categorical.from_codes([0, 0, 1],
categories=["a", "b", "c"],
ordered=ordered)
def test_constructor_empty(self):
# GH 17248
c = Categorical([])
expected = Index([])
tm.assert_index_equal(c.categories, expected)
c = Categorical([], categories=[1, 2, 3])
expected = pd.Int64Index([1, 2, 3])
tm.assert_index_equal(c.categories, expected)
def test_constructor_empty_boolean(self):
# see gh-22702
cat = Categorical([], categories=[True, False])
categories = sorted(cat.categories.tolist())
assert categories == [False, True]
def test_constructor_tuples(self):
values = np.array([(1, ), (1, 2), (1, ), (1, 2)], dtype=object)
result = Categorical(values)
expected = Index([(1, ), (1, 2)], tupleize_cols=False)
tm.assert_index_equal(result.categories, expected)
assert result.ordered is False
def test_constructor_tuples_datetimes(self):
# numpy will auto reshape when all of the tuples are the
# same len, so add an extra one with 2 items and slice it off
values = np.array(
[
(Timestamp("2010-01-01"), ),
(Timestamp("2010-01-02"), ),
(Timestamp("2010-01-01"), ),
(Timestamp("2010-01-02"), ),
("a", "b"),
],
dtype=object,
)[:-1]
result = Categorical(values)
expected = Index(
[(Timestamp("2010-01-01"), ), (Timestamp("2010-01-02"), )],
tupleize_cols=False,
)
tm.assert_index_equal(result.categories, expected)
def test_constructor_unsortable(self):
# it works!
arr = np.array([1, 2, 3, datetime.now()], dtype="O")
factor = Categorical(arr, ordered=False)
assert not factor.ordered
# this however will raise as cannot be sorted
msg = ("'values' is not ordered, please explicitly specify the "
"categories order by passing in a categories argument.")
with pytest.raises(TypeError, match=msg):
Categorical(arr, ordered=True)
def test_constructor_interval(self):
result = Categorical(
[Interval(1, 2), Interval(2, 3),
Interval(3, 6)], ordered=True)
ii = IntervalIndex([Interval(1, 2), Interval(2, 3), Interval(3, 6)])
exp = Categorical(ii, ordered=True)
tm.assert_categorical_equal(result, exp)
tm.assert_index_equal(result.categories, ii)
def test_constructor(self):
exp_arr = np.array(["a", "b", "c", "a", "b", "c"], dtype=np.object_)
c1 = Categorical(exp_arr)
tm.assert_numpy_array_equal(c1.__array__(), exp_arr)
c2 = Categorical(exp_arr, categories=["a", "b", "c"])
tm.assert_numpy_array_equal(c2.__array__(), exp_arr)
c2 = Categorical(exp_arr, categories=["c", "b", "a"])
tm.assert_numpy_array_equal(c2.__array__(), exp_arr)
# categories must be unique
msg = "Categorical categories must be unique"
with pytest.raises(ValueError, match=msg):
Categorical([1, 2], [1, 2, 2])
with pytest.raises(ValueError, match=msg):
Categorical(["a", "b"], ["a", "b", "b"])
# The default should be unordered
c1 = Categorical(["a", "b", "c", "a"])
assert not c1.ordered
# Categorical as input
c1 = Categorical(["a", "b", "c", "a"])
c2 = Categorical(c1)
tm.assert_categorical_equal(c1, c2)
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
c2 = Categorical(c1)
tm.assert_categorical_equal(c1, c2)
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
c2 = Categorical(c1)
tm.assert_categorical_equal(c1, c2)
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
c2 = Categorical(c1, categories=["a", "b", "c"])
tm.assert_numpy_array_equal(c1.__array__(), c2.__array__())
tm.assert_index_equal(c2.categories, Index(["a", "b", "c"]))
# Series of dtype category
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
c2 = Categorical(Series(c1))
tm.assert_categorical_equal(c1, c2)
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
c2 = Categorical(Series(c1))
tm.assert_categorical_equal(c1, c2)
# Series
c1 = Categorical(["a", "b", "c", "a"])
c2 = Categorical(Series(["a", "b", "c", "a"]))
tm.assert_categorical_equal(c1, c2)
c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
c2 = Categorical(Series(["a", "b", "c", "a"]),
categories=["a", "b", "c", "d"])
tm.assert_categorical_equal(c1, c2)
# This should result in integer categories, not float!
cat = Categorical([1, 2, 3, np.nan], categories=[1, 2, 3])
assert is_integer_dtype(cat.categories)
# https://github.com/pandas-dev/pandas/issues/3678
cat = Categorical([np.nan, 1, 2, 3])
assert is_integer_dtype(cat.categories)
# this should result in floats
cat = Categorical([np.nan, 1, 2.0, 3])
assert is_float_dtype(cat.categories)
cat = Categorical([np.nan, 1.0, 2.0, 3.0])
assert is_float_dtype(cat.categories)
# This doesn't work -> this would probably need some kind of "remember
# the original type" feature to try to cast the array interface result
# to...
# vals = np.asarray(cat[cat.notna()])
# assert is_integer_dtype(vals)
# corner cases
cat = Categorical([1])
assert len(cat.categories) == 1
assert cat.categories[0] == 1
assert len(cat.codes) == 1
assert cat.codes[0] == 0
cat = Categorical(["a"])
assert len(cat.categories) == 1
assert cat.categories[0] == "a"
assert len(cat.codes) == 1
assert cat.codes[0] == 0
# Scalars should be converted to lists
cat = Categorical(1)
assert len(cat.categories) == 1
assert cat.categories[0] == 1
assert len(cat.codes) == 1
assert cat.codes[0] == 0
# two arrays
# - when the first is an integer dtype and the second is not
# - when the resulting codes are all -1/NaN
with tm.assert_produces_warning(None):
c_old = Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])
with tm.assert_produces_warning(None):
c_old = Categorical([0, 1, 2, 0, 1, 2], categories=[3, 4,
5]) # noqa
# the next one are from the old docs
with tm.assert_produces_warning(None):
c_old2 = Categorical([0, 1, 2, 0, 1, 2], [1, 2, 3]) # noqa
cat = Categorical([1, 2], categories=[1, 2, 3])
# this is a legitimate constructor
with tm.assert_produces_warning(None):
c = Categorical( # noqa
np.array([], dtype="int64"),
categories=[3, 2, 1],
ordered=True)
def test_constructor_with_existing_categories(self):
# GH25318: constructing with pd.Series used to bogusly skip recoding
# categories
c0 = Categorical(["a", "b", "c", "a"])
c1 = Categorical(["a", "b", "c", "a"], categories=["b", "c"])
c2 = Categorical(c0, categories=c1.categories)
tm.assert_categorical_equal(c1, c2)
c3 = Categorical(Series(c0), categories=c1.categories)
tm.assert_categorical_equal(c1, c3)
def test_constructor_not_sequence(self):
# https://github.com/pandas-dev/pandas/issues/16022
msg = r"^Parameter 'categories' must be list-like, was"
with pytest.raises(TypeError, match=msg):
Categorical(["a", "b"], categories="a")
def test_constructor_with_null(self):
# Cannot have NaN in categories
msg = "Categorical categories cannot be null"
with pytest.raises(ValueError, match=msg):
Categorical([np.nan, "a", "b", "c"],
categories=[np.nan, "a", "b", "c"])
with pytest.raises(ValueError, match=msg):
Categorical([None, "a", "b", "c"],
categories=[None, "a", "b", "c"])
with pytest.raises(ValueError, match=msg):
Categorical(
DatetimeIndex(["nat", "20160101"]),
categories=[NaT, Timestamp("20160101")],
)
def test_constructor_with_index(self):
ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
tm.assert_categorical_equal(ci.values, Categorical(ci))
ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
tm.assert_categorical_equal(
ci.values, Categorical(ci.astype(object),
categories=ci.categories))
def test_constructor_with_generator(self):
# This was raising an Error in isna(single_val).any() because isna
# returned a scalar for a generator
exp = Categorical([0, 1, 2])
cat = Categorical(x for x in [0, 1, 2])
tm.assert_categorical_equal(cat, exp)
cat = Categorical(range(3))
tm.assert_categorical_equal(cat, exp)
MultiIndex.from_product([range(5), ["a", "b", "c"]])
# check that categories accept generators and sequences
cat = Categorical([0, 1, 2], categories=(x for x in [0, 1, 2]))
tm.assert_categorical_equal(cat, exp)
cat = Categorical([0, 1, 2], categories=range(3))
tm.assert_categorical_equal(cat, exp)
@pytest.mark.parametrize(
"dtl",
[
date_range("1995-01-01 00:00:00", periods=5, freq="s"),
date_range(
"1995-01-01 00:00:00", periods=5, freq="s", tz="US/Eastern"),
timedelta_range("1 day", periods=5, freq="s"),
],
)
def test_constructor_with_datetimelike(self, dtl):
# see gh-12077
# constructor with a datetimelike and NaT
s = Series(dtl)
c = Categorical(s)
expected = type(dtl)(s)
expected._data.freq = None
tm.assert_index_equal(c.categories, expected)
tm.assert_numpy_array_equal(c.codes, np.arange(5, dtype="int8"))
# with NaT
s2 = s.copy()
s2.iloc[-1] = NaT
c = Categorical(s2)
expected = type(dtl)(s2.dropna())
expected._data.freq = None
tm.assert_index_equal(c.categories, expected)
exp = np.array([0, 1, 2, 3, -1], dtype=np.int8)
tm.assert_numpy_array_equal(c.codes, exp)
result = repr(c)
assert "NaT" in result
def test_constructor_from_index_series_datetimetz(self):
idx = date_range("2015-01-01 10:00",
freq="D",
periods=3,
tz="US/Eastern")
idx = idx._with_freq(None) # freq not preserved in result.categories
result = Categorical(idx)
tm.assert_index_equal(result.categories, idx)
result = Categorical(Series(idx))
tm.assert_index_equal(result.categories, idx)
def test_constructor_from_index_series_timedelta(self):
idx = timedelta_range("1 days", freq="D", periods=3)
idx = idx._with_freq(None) # freq not preserved in result.categories
result = Categorical(idx)
tm.assert_index_equal(result.categories, idx)
result = Categorical(Series(idx))
tm.assert_index_equal(result.categories, idx)
def test_constructor_from_index_series_period(self):
idx = period_range("2015-01-01", freq="D", periods=3)
result = Categorical(idx)
tm.assert_index_equal(result.categories, idx)
result = Categorical(Series(idx))
tm.assert_index_equal(result.categories, idx)
@pytest.mark.parametrize(
"values",
[
np.array([1.0, 1.2, 1.8, np.nan]),
np.array([1, 2, 3], dtype="int64"),
["a", "b", "c", np.nan],
[pd.Period("2014-01"),
pd.Period("2014-02"), NaT],
[Timestamp("2014-01-01"),
Timestamp("2014-01-02"), NaT],
[
Timestamp("2014-01-01", tz="US/Eastern"),
Timestamp("2014-01-02", tz="US/Eastern"),
NaT,
],
],
)
def test_constructor_invariant(self, values):
# GH 14190
c = Categorical(values)
c2 = Categorical(c)
tm.assert_categorical_equal(c, c2)
@pytest.mark.parametrize("ordered", [True, False])
def test_constructor_with_dtype(self, ordered):
categories = ["b", "a", "c"]
dtype = CategoricalDtype(categories, ordered=ordered)
result = Categorical(["a", "b", "a", "c"], dtype=dtype)
expected = Categorical(["a", "b", "a", "c"],
categories=categories,
ordered=ordered)
tm.assert_categorical_equal(result, expected)
assert result.ordered is ordered
def test_constructor_dtype_and_others_raises(self):
dtype = CategoricalDtype(["a", "b"], ordered=True)
msg = "Cannot specify `categories` or `ordered` together with `dtype`."
with pytest.raises(ValueError, match=msg):
Categorical(["a", "b"], categories=["a", "b"], dtype=dtype)
with pytest.raises(ValueError, match=msg):
Categorical(["a", "b"], ordered=True, dtype=dtype)
with pytest.raises(ValueError, match=msg):
Categorical(["a", "b"], ordered=False, dtype=dtype)
@pytest.mark.parametrize("categories", [None, ["a", "b"], ["a", "c"]])
@pytest.mark.parametrize("ordered", [True, False])
def test_constructor_str_category(self, categories, ordered):
result = Categorical(["a", "b"],
categories=categories,
ordered=ordered,
dtype="category")
expected = Categorical(["a", "b"],
categories=categories,
ordered=ordered)
tm.assert_categorical_equal(result, expected)
def test_constructor_str_unknown(self):
with pytest.raises(ValueError, match="Unknown dtype"):
Categorical([1, 2], dtype="foo")
def test_constructor_np_strs(self):
# GH#31499 Hastable.map_locations needs to work on np.str_ objects
cat = Categorical(["1", "0", "1"], [np.str_("0"), np.str_("1")])
assert all(isinstance(x, np.str_) for x in cat.categories)
def test_constructor_from_categorical_with_dtype(self):
dtype = CategoricalDtype(["a", "b", "c"], ordered=True)
values = Categorical(["a", "b", "d"])
result = Categorical(values, dtype=dtype)
# We use dtype.categories, not values.categories
expected = Categorical(["a", "b", "d"],
categories=["a", "b", "c"],
ordered=True)
tm.assert_categorical_equal(result, expected)
def test_constructor_from_categorical_with_unknown_dtype(self):
dtype = CategoricalDtype(None, ordered=True)
values = Categorical(["a", "b", "d"])
result = Categorical(values, dtype=dtype)
# We use values.categories, not dtype.categories
expected = Categorical(["a", "b", "d"],
categories=["a", "b", "d"],
ordered=True)
tm.assert_categorical_equal(result, expected)
def test_constructor_from_categorical_string(self):
values = Categorical(["a", "b", "d"])
# use categories, ordered
result = Categorical(values,
categories=["a", "b", "c"],
ordered=True,
dtype="category")
expected = Categorical(["a", "b", "d"],
categories=["a", "b", "c"],
ordered=True)
tm.assert_categorical_equal(result, expected)
# No string
result = Categorical(values, categories=["a", "b", "c"], ordered=True)
tm.assert_categorical_equal(result, expected)
def test_constructor_with_categorical_categories(self):
# GH17884
expected = Categorical(["a", "b"], categories=["a", "b", "c"])
result = Categorical(["a", "b"],
categories=Categorical(["a", "b", "c"]))
tm.assert_categorical_equal(result, expected)
result = Categorical(["a", "b"],
categories=CategoricalIndex(["a", "b", "c"]))
tm.assert_categorical_equal(result, expected)
@pytest.mark.parametrize("klass",
[lambda x: np.array(x, dtype=object), list])
def test_construction_with_null(self, klass, nulls_fixture):
# https://github.com/pandas-dev/pandas/issues/31927
values = klass(["a", nulls_fixture, "b"])
result = Categorical(values)
dtype = CategoricalDtype(["a", "b"])
codes = [0, -1, 1]
expected = Categorical.from_codes(codes=codes, dtype=dtype)
tm.assert_categorical_equal(result, expected)
def test_from_codes_empty(self):
cat = ["a", "b", "c"]
result = Categorical.from_codes([], categories=cat)
expected = Categorical([], categories=cat)
tm.assert_categorical_equal(result, expected)
def test_from_codes_too_few_categories(self):
dtype = CategoricalDtype(categories=[1, 2])
msg = "codes need to be between "
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([1, 2], categories=dtype.categories)
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([1, 2], dtype=dtype)
def test_from_codes_non_int_codes(self):
dtype = CategoricalDtype(categories=[1, 2])
msg = "codes need to be array-like integers"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes(["a"], categories=dtype.categories)
with pytest.raises(ValueError, match=msg):
Categorical.from_codes(["a"], dtype=dtype)
def test_from_codes_non_unique_categories(self):
with pytest.raises(ValueError,
match="Categorical categories must be unique"):
Categorical.from_codes([0, 1, 2], categories=["a", "a", "b"])
def test_from_codes_nan_cat_included(self):
with pytest.raises(ValueError,
match="Categorical categories cannot be null"):
Categorical.from_codes([0, 1, 2], categories=["a", "b", np.nan])
def test_from_codes_too_negative(self):
dtype = CategoricalDtype(categories=["a", "b", "c"])
msg = r"codes need to be between -1 and len\(categories\)-1"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([-2, 1, 2], categories=dtype.categories)
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([-2, 1, 2], dtype=dtype)
def test_from_codes(self):
dtype = CategoricalDtype(categories=["a", "b", "c"])
exp = Categorical(["a", "b", "c"], ordered=False)
res = Categorical.from_codes([0, 1, 2], categories=dtype.categories)
tm.assert_categorical_equal(exp, res)
res = Categorical.from_codes([0, 1, 2], dtype=dtype)
tm.assert_categorical_equal(exp, res)
@pytest.mark.parametrize("klass", [Categorical, CategoricalIndex])
def test_from_codes_with_categorical_categories(self, klass):
# GH17884
expected = Categorical(["a", "b"], categories=["a", "b", "c"])
result = Categorical.from_codes([0, 1],
categories=klass(["a", "b", "c"]))
tm.assert_categorical_equal(result, expected)
@pytest.mark.parametrize("klass", [Categorical, CategoricalIndex])
def test_from_codes_with_non_unique_categorical_categories(self, klass):
with pytest.raises(ValueError,
match="Categorical categories must be unique"):
Categorical.from_codes([0, 1], klass(["a", "b", "a"]))
def test_from_codes_with_nan_code(self):
# GH21767
codes = [1, 2, np.nan]
dtype = CategoricalDtype(categories=["a", "b", "c"])
with pytest.raises(ValueError,
match="codes need to be array-like integers"):
Categorical.from_codes(codes, categories=dtype.categories)
with pytest.raises(ValueError,
match="codes need to be array-like integers"):
Categorical.from_codes(codes, dtype=dtype)
@pytest.mark.parametrize("codes", [[1.0, 2.0, 0], [1.1, 2.0, 0]])
def test_from_codes_with_float(self, codes):
# GH21767
# float codes should raise even if values are equal to integers
dtype = CategoricalDtype(categories=["a", "b", "c"])
msg = "codes need to be array-like integers"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes(codes, dtype.categories)
with pytest.raises(ValueError, match=msg):
Categorical.from_codes(codes, dtype=dtype)
def test_from_codes_with_dtype_raises(self):
msg = "Cannot specify"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([0, 1],
categories=["a", "b"],
dtype=CategoricalDtype(["a", "b"]))
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([0, 1],
ordered=True,
dtype=CategoricalDtype(["a", "b"]))
def test_from_codes_neither(self):
msg = "Both were None"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes([0, 1])
def test_from_codes_with_nullable_int(self):
codes = pd.array([0, 1], dtype="Int64")
categories = ["a", "b"]
result = Categorical.from_codes(codes, categories=categories)
expected = Categorical.from_codes(codes.to_numpy(int),
categories=categories)
tm.assert_categorical_equal(result, expected)
def test_from_codes_with_nullable_int_na_raises(self):
codes = pd.array([0, None], dtype="Int64")
categories = ["a", "b"]
msg = "codes cannot contain NA values"
with pytest.raises(ValueError, match=msg):
Categorical.from_codes(codes, categories=categories)
@pytest.mark.parametrize("dtype", [None, "category"])
def test_from_inferred_categories(self, dtype):
cats = ["a", "b"]
codes = np.array([0, 0, 1, 1], dtype="i8")
result = Categorical._from_inferred_categories(cats, codes, dtype)
expected = Categorical.from_codes(codes, cats)
tm.assert_categorical_equal(result, expected)
@pytest.mark.parametrize("dtype", [None, "category"])
def test_from_inferred_categories_sorts(self, dtype):
cats = ["b", "a"]
codes = np.array([0, 1, 1, 1], dtype="i8")
result = Categorical._from_inferred_categories(cats, codes, dtype)
expected = Categorical.from_codes([1, 0, 0, 0], ["a", "b"])
tm.assert_categorical_equal(result, expected)
def test_from_inferred_categories_dtype(self):
cats = ["a", "b", "d"]
codes = np.array([0, 1, 0, 2], dtype="i8")
dtype = CategoricalDtype(["c", "b", "a"], ordered=True)
result = Categorical._from_inferred_categories(cats, codes, dtype)
expected = Categorical(["a", "b", "a", "d"],
categories=["c", "b", "a"],
ordered=True)
tm.assert_categorical_equal(result, expected)
def test_from_inferred_categories_coerces(self):
cats = ["1", "2", "bad"]
codes = np.array([0, 0, 1, 2], dtype="i8")
dtype = CategoricalDtype([1, 2])
result = Categorical._from_inferred_categories(cats, codes, dtype)
expected = Categorical([1, 1, 2, np.nan])
tm.assert_categorical_equal(result, expected)
@pytest.mark.parametrize("ordered", [None, True, False])
def test_construction_with_ordered(self, ordered):
# GH 9347, 9190
cat = Categorical([0, 1, 2], ordered=ordered)
assert cat.ordered == bool(ordered)
@pytest.mark.xfail(reason="Imaginary values not supported in Categorical")
def test_constructor_imaginary(self):
values = [1, 2, 3 + 1j]
c1 = Categorical(values)
tm.assert_index_equal(c1.categories, Index(values))
tm.assert_numpy_array_equal(np.array(c1), np.array(values))
def test_constructor_string_and_tuples(self):
# GH 21416
c = Categorical(
np.array(["c", ("a", "b"), ("b", "a"), "c"], dtype=object))
expected_index = Index([("a", "b"), ("b", "a"), "c"])
assert c.categories.equals(expected_index)
def test_interval(self):
idx = pd.interval_range(0, 10, periods=10)
cat = Categorical(idx, categories=idx)
expected_codes = np.arange(10, dtype="int8")
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
# infer categories
cat = Categorical(idx)
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
# list values
cat = Categorical(list(idx))
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
# list values, categories
cat = Categorical(list(idx), categories=list(idx))
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
# shuffled
values = idx.take([1, 2, 0])
cat = Categorical(values, categories=idx)
tm.assert_numpy_array_equal(cat.codes, np.array([1, 2, 0],
dtype="int8"))
tm.assert_index_equal(cat.categories, idx)
# extra
values = pd.interval_range(8, 11, periods=3)
cat = Categorical(values, categories=idx)
expected_codes = np.array([8, 9, -1], dtype="int8")
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
# overlapping
idx = pd.IntervalIndex([pd.Interval(0, 2), pd.Interval(0, 1)])
cat = Categorical(idx, categories=idx)
expected_codes = np.array([0, 1], dtype="int8")
tm.assert_numpy_array_equal(cat.codes, expected_codes)
tm.assert_index_equal(cat.categories, idx)
class TestGetLoc:
@pytest.mark.parametrize("side", ["right", "left", "both", "neither"])
def test_get_loc_interval(self, closed, side):
idx = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
for bound in [[0, 1], [1, 2], [2, 3], [3, 4], [0, 2], [2.5, 3],
[-1, 4]]:
# if get_loc is supplied an interval, it should only search
# for exact matches, not overlaps or covers, else KeyError.
msg = re.escape(
f"Interval({bound[0]}, {bound[1]}, closed='{side}')")
if closed == side:
if bound == [0, 1]:
assert idx.get_loc(Interval(0, 1, closed=side)) == 0
elif bound == [2, 3]:
assert idx.get_loc(Interval(2, 3, closed=side)) == 1
else:
with pytest.raises(KeyError, match=msg):
idx.get_loc(Interval(*bound, closed=side))
else:
with pytest.raises(KeyError, match=msg):
idx.get_loc(Interval(*bound, closed=side))
@pytest.mark.parametrize("scalar", [-0.5, 0, 0.5, 1, 1.5, 2, 2.5, 3, 3.5])
def test_get_loc_scalar(self, closed, scalar):
# correct = {side: {query: answer}}.
# If query is not in the dict, that query should raise a KeyError
correct = {
"right": {
0.5: 0,
1: 0,
2.5: 1,
3: 1
},
"left": {
0: 0,
0.5: 0,
2: 1,
2.5: 1
},
"both": {
0: 0,
0.5: 0,
1: 0,
2: 1,
2.5: 1,
3: 1
},
"neither": {
0.5: 0,
2.5: 1
},
}
idx = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
# if get_loc is supplied a scalar, it should return the index of
# the interval which contains the scalar, or KeyError.
if scalar in correct[closed].keys():
assert idx.get_loc(scalar) == correct[closed][scalar]
else:
with pytest.raises(KeyError, match=str(scalar)):
idx.get_loc(scalar)
@pytest.mark.parametrize("scalar", [-1, 0, 0.5, 3, 4.5, 5, 6])
def test_get_loc_length_one_scalar(self, scalar, closed):
# GH 20921
index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
if scalar in index[0]:
result = index.get_loc(scalar)
assert result == 0
else:
with pytest.raises(KeyError, match=str(scalar)):
index.get_loc(scalar)
@pytest.mark.parametrize("other_closed",
["left", "right", "both", "neither"])
@pytest.mark.parametrize("left, right", [(0, 5), (-1, 4), (-1, 6), (6, 7)])
def test_get_loc_length_one_interval(self, left, right, closed,
other_closed):
# GH 20921
index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
interval = Interval(left, right, closed=other_closed)
if interval == index[0]:
result = index.get_loc(interval)
assert result == 0
else:
with pytest.raises(
KeyError,
match=re.escape(
f"Interval({left}, {right}, closed='{other_closed}')"),
):
index.get_loc(interval)
# Make consistent with test_interval_new.py (see #16316, #16386)
@pytest.mark.parametrize(
"breaks",
[
date_range("20180101", periods=4),
date_range("20180101", periods=4, tz="US/Eastern"),
timedelta_range("0 days", periods=4),
],
ids=lambda x: str(x.dtype),
)
def test_get_loc_datetimelike_nonoverlapping(self, breaks):
# GH 20636
# nonoverlapping = IntervalIndex method and no i8 conversion
index = IntervalIndex.from_breaks(breaks)
value = index[0].mid
result = index.get_loc(value)
expected = 0
assert result == expected
interval = Interval(index[0].left, index[0].right)
result = index.get_loc(interval)
expected = 0
assert result == expected
@pytest.mark.parametrize(
"arrays",
[
(date_range("20180101",
periods=4), date_range("20180103", periods=4)),
(
date_range("20180101", periods=4, tz="US/Eastern"),
date_range("20180103", periods=4, tz="US/Eastern"),
),
(
timedelta_range("0 days", periods=4),
timedelta_range("2 days", periods=4),
),
],
ids=lambda x: str(x[0].dtype),
)
def test_get_loc_datetimelike_overlapping(self, arrays):
# GH 20636
index = IntervalIndex.from_arrays(*arrays)
value = index[0].mid + Timedelta("12 hours")
result = index.get_loc(value)
expected = slice(0, 2, None)
assert result == expected
interval = Interval(index[0].left, index[0].right)
result = index.get_loc(interval)
expected = 0
assert result == expected
@pytest.mark.parametrize(
"values",
[
date_range("2018-01-04", periods=4, freq="-1D"),
date_range("2018-01-04", periods=4, freq="-1D", tz="US/Eastern"),
timedelta_range("3 days", periods=4, freq="-1D"),
np.arange(3.0, -1.0, -1.0),
np.arange(3, -1, -1),
],
ids=lambda x: str(x.dtype),
)
def test_get_loc_decreasing(self, values):
# GH 25860
index = IntervalIndex.from_arrays(values[1:], values[:-1])
result = index.get_loc(index[0])
expected = 0
assert result == expected
@pytest.mark.parametrize("key", [[5], (2, 3)])
def test_get_loc_non_scalar_errors(self, key):
# GH 31117
idx = IntervalIndex.from_tuples([(1, 3), (2, 4), (3, 5), (7, 10),
(3, 10)])
msg = str(key)
with pytest.raises(InvalidIndexError, match=msg):
idx.get_loc(key)
def test_get_indexer_with_nans(self):
# GH#41831
index = IntervalIndex([np.nan, Interval(1, 2), np.nan])
expected = np.array([True, False, True])
for key in [None, np.nan, NA]:
assert key in index
result = index.get_loc(key)
tm.assert_numpy_array_equal(result, expected)
for key in [
NaT,
np.timedelta64("NaT", "ns"),
np.datetime64("NaT", "ns")
]:
with pytest.raises(KeyError, match=str(key)):
index.get_loc(key)
return 'Samsung'
return x
df.insert(0, 'inc', range(1, len(df) + 1))
df['lastTimeSeen'] = pd.to_datetime(df['lastTimeSeen'],
format='%Y-%m-%d %H:%M:%S')
df['firstTimeSeen'] = pd.to_datetime(df['firstTimeSeen'],
format='%Y-%m-%d %H:%M:%S')
df['stationMacVendor'] = df['stationMacVendor'].map(clean_manufacturer)
df['date'] = df['firstTimeSeen'].map(
lambda x: datetime.strftime(x, '%d-%m-%Y'))
df['time'] = df['firstTimeSeen'].map(
lambda x: datetime.strftime(x, '%H:%M:%S'))
tbins = pd.timedelta_range(0, periods=25, freq='H')
tslots = pd.cut(pd.to_timedelta(df['time']), bins=tbins)
dfheatmap = df.replace(0,
np.nan).groupby([tslots,
pd.cut(df['packets'],
1)]).packets.mean().unstack()
df['power'] = df['power'].map(lambda x: '{0:,.0f}'.format(x))
df['packets'] = df['packets'].map(lambda x: '{0:,.0f}'.format(x))
df['packetsAvg'] = df['packetsAvg'].map(lambda x: '{0:,.1f}'.format(x))
df['powerAvg'] = df['powerAvg'].apply(lambda x: '{0:,.1f}'.format(x))
df['packetsTotal'] = df['packetsTotal'].map(lambda x: '{0:,.0f}'.format(x))
df['timeSeen'] = df['timeSeen'].map(lambda x: '{0:,.0f}'.format(x))
#df['timeSeenTotal'] = df['timeSeenTotal'].map(lambda x: '{0:,}'.format(x))
df.set_index('lastTimeSeen', inplace=True)
Timedelta,
Timestamp,
date_range,
period_range,
timedelta_range,
)
import pandas._testing as tm
from pandas.core.arrays import IntervalArray
@pytest.fixture(
params=[
(Index([0, 2, 4, 4]), Index([1, 3, 5, 8])),
(Index([0.0, 1.0, 2.0, np.nan]), Index([1.0, 2.0, 3.0, np.nan])),
(
timedelta_range("0 days", periods=3).insert(4, pd.NaT),
timedelta_range("1 day", periods=3).insert(4, pd.NaT),
),
(
date_range("20170101", periods=3).insert(4, pd.NaT),
date_range("20170102", periods=3).insert(4, pd.NaT),
),
(
date_range("20170101", periods=3,
tz="US/Eastern").insert(4, pd.NaT),
date_range("20170102", periods=3,
tz="US/Eastern").insert(4, pd.NaT),
),
],
ids=lambda x: str(x[0].dtype),
)
def test_arg_passthru():
# make sure that we are passing thru kwargs
# to our agg functions
# GH3668
# GH5724
df = DataFrame(
{
"group": [1, 1, 2],
"int": [1, 2, 3],
"float": [4.0, 5.0, 6.0],
"string": list("abc"),
"category_string": Series(list("abc")).astype("category"),
"category_int": [7, 8, 9],
"datetime": pd.date_range("20130101", periods=3),
"datetimetz": pd.date_range("20130101", periods=3,
tz="US/Eastern"),
"timedelta": pd.timedelta_range("1 s", periods=3, freq="s"),
},
columns=[
"group",
"int",
"float",
"string",
"category_string",
"category_int",
"datetime",
"datetimetz",
"timedelta",
],
)
expected_columns_numeric = Index(["int", "float", "category_int"])
# mean / median
expected = DataFrame(
{
"category_int": [7.5, 9],
"float": [4.5, 6.0],
"timedelta": [pd.Timedelta("1.5s"),
pd.Timedelta("3s")],
"int": [1.5, 3],
"datetime": [
Timestamp("2013-01-01 12:00:00"),
Timestamp("2013-01-03 00:00:00"),
],
"datetimetz": [
Timestamp("2013-01-01 12:00:00", tz="US/Eastern"),
Timestamp("2013-01-03 00:00:00", tz="US/Eastern"),
],
},
index=Index([1, 2], name="group"),
columns=[
"int", "float", "category_int", "datetime", "datetimetz",
"timedelta"
],
)
for attr in ["mean", "median"]:
result = getattr(df.groupby("group"), attr)()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = getattr(df.groupby("group"), attr)(numeric_only=False)
tm.assert_frame_equal(result.reindex_like(expected), expected)
# TODO: min, max *should* handle
# categorical (ordered) dtype
expected_columns = Index([
"int",
"float",
"string",
"category_int",
"datetime",
"datetimetz",
"timedelta",
])
for attr in ["min", "max"]:
result = getattr(df.groupby("group"), attr)()
tm.assert_index_equal(result.columns, expected_columns)
result = getattr(df.groupby("group"), attr)(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index([
"int",
"float",
"string",
"category_string",
"category_int",
"datetime",
"datetimetz",
"timedelta",
])
for attr in ["first", "last"]:
result = getattr(df.groupby("group"), attr)()
tm.assert_index_equal(result.columns, expected_columns)
result = getattr(df.groupby("group"), attr)(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(
["int", "float", "string", "category_int", "timedelta"])
result = df.groupby("group").sum()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = df.groupby("group").sum(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(["int", "float", "category_int"])
for attr in ["prod", "cumprod"]:
result = getattr(df.groupby("group"), attr)()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = getattr(df.groupby("group"), attr)(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
# like min, max, but don't include strings
expected_columns = Index([
"int", "float", "category_int", "datetime", "datetimetz", "timedelta"
])
for attr in ["cummin", "cummax"]:
result = getattr(df.groupby("group"), attr)()
# GH 15561: numeric_only=False set by default like min/max
tm.assert_index_equal(result.columns, expected_columns)
result = getattr(df.groupby("group"), attr)(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(["int", "float", "category_int", "timedelta"])
result = getattr(df.groupby("group"), "cumsum")()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = getattr(df.groupby("group"), "cumsum")(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
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))
class SharedTests:
index_cls: type[DatetimeIndex | PeriodIndex | TimedeltaIndex]
@pytest.fixture
def arr1d(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
return arr
def test_compare_len1_raises(self, arr1d):
# make sure we raise when comparing with different lengths, specific
# to the case where one has length-1, which numpy would broadcast
arr = arr1d
idx = self.index_cls(arr)
with pytest.raises(ValueError, match="Lengths must match"):
arr == arr[:1]
# test the index classes while we're at it, GH#23078
with pytest.raises(ValueError, match="Lengths must match"):
idx <= idx[[0]]
@pytest.mark.parametrize(
"result",
[
pd.date_range("2020", periods=3),
pd.date_range("2020", periods=3, tz="UTC"),
pd.timedelta_range("0 days", periods=3),
pd.period_range("2020Q1", periods=3, freq="Q"),
],
)
def test_compare_with_Categorical(self, result):
expected = pd.Categorical(result)
assert all(result == expected)
assert not any(result != expected)
@pytest.mark.parametrize("reverse", [True, False])
@pytest.mark.parametrize("as_index", [True, False])
def test_compare_categorical_dtype(self, arr1d, as_index, reverse,
ordered):
other = pd.Categorical(arr1d, ordered=ordered)
if as_index:
other = pd.CategoricalIndex(other)
left, right = arr1d, other
if reverse:
left, right = right, left
ones = np.ones(arr1d.shape, dtype=bool)
zeros = ~ones
result = left == right
tm.assert_numpy_array_equal(result, ones)
result = left != right
tm.assert_numpy_array_equal(result, zeros)
if not reverse and not as_index:
# Otherwise Categorical raises TypeError bc it is not ordered
# TODO: we should probably get the same behavior regardless?
result = left < right
tm.assert_numpy_array_equal(result, zeros)
result = left <= right
tm.assert_numpy_array_equal(result, ones)
result = left > right
tm.assert_numpy_array_equal(result, zeros)
result = left >= right
tm.assert_numpy_array_equal(result, ones)
def test_take(self):
data = np.arange(100, dtype="i8") * 24 * 3600 * 10**9
np.random.shuffle(data)
freq = None if self.array_cls is not PeriodArray else "D"
arr = self.array_cls(data, freq=freq)
idx = self.index_cls._simple_new(arr)
takers = [1, 4, 94]
result = arr.take(takers)
expected = idx.take(takers)
tm.assert_index_equal(self.index_cls(result), expected)
takers = np.array([1, 4, 94])
result = arr.take(takers)
expected = idx.take(takers)
tm.assert_index_equal(self.index_cls(result), expected)
@pytest.mark.parametrize("fill_value",
[2, 2.0, Timestamp(2021, 1, 1, 12).time])
def test_take_fill_raises(self, fill_value):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
msg = f"value should be a '{arr._scalar_type.__name__}' or 'NaT'. Got"
with pytest.raises(TypeError, match=msg):
arr.take([0, 1], allow_fill=True, fill_value=fill_value)
def test_take_fill(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
result = arr.take([-1, 1], allow_fill=True, fill_value=None)
assert result[0] is NaT
result = arr.take([-1, 1], allow_fill=True, fill_value=np.nan)
assert result[0] is NaT
result = arr.take([-1, 1], allow_fill=True, fill_value=NaT)
assert result[0] is NaT
def test_take_fill_str(self, arr1d):
# Cast str fill_value matching other fill_value-taking methods
result = arr1d.take([-1, 1],
allow_fill=True,
fill_value=str(arr1d[-1]))
expected = arr1d[[-1, 1]]
tm.assert_equal(result, expected)
msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
with pytest.raises(TypeError, match=msg):
arr1d.take([-1, 1], allow_fill=True, fill_value="foo")
def test_concat_same_type(self, arr1d):
arr = arr1d
idx = self.index_cls(arr)
idx = idx.insert(0, NaT)
arr = self.array_cls(idx)
result = arr._concat_same_type([arr[:-1], arr[1:], arr])
arr2 = arr.astype(object)
expected = self.index_cls(np.concatenate([arr2[:-1], arr2[1:], arr2]),
None)
tm.assert_index_equal(self.index_cls(result), expected)
def test_unbox_scalar(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
result = arr._unbox_scalar(arr[0])
expected = arr._data.dtype.type
assert isinstance(result, expected)
result = arr._unbox_scalar(NaT)
assert isinstance(result, expected)
msg = f"'value' should be a {self.scalar_type.__name__}."
with pytest.raises(ValueError, match=msg):
arr._unbox_scalar("foo")
def test_check_compatible_with(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
arr._check_compatible_with(arr[0])
arr._check_compatible_with(arr[:1])
arr._check_compatible_with(NaT)
def test_scalar_from_string(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
result = arr._scalar_from_string(str(arr[0]))
assert result == arr[0]
def test_reduce_invalid(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
msg = f"'{type(arr).__name__}' does not implement reduction 'not a method'"
with pytest.raises(TypeError, match=msg):
arr._reduce("not a method")
@pytest.mark.parametrize("method", ["pad", "backfill"])
def test_fillna_method_doesnt_change_orig(self, method):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
arr[4] = NaT
fill_value = arr[3] if method == "pad" else arr[5]
result = arr.fillna(method=method)
assert result[4] == fill_value
# check that the original was not changed
assert arr[4] is NaT
def test_searchsorted(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
# scalar
result = arr.searchsorted(arr[1])
assert result == 1
result = arr.searchsorted(arr[2], side="right")
assert result == 3
# own-type
result = arr.searchsorted(arr[1:3])
expected = np.array([1, 2], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
result = arr.searchsorted(arr[1:3], side="right")
expected = np.array([2, 3], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
# GH#29884 match numpy convention on whether NaT goes
# at the end or the beginning
result = arr.searchsorted(NaT)
assert result == 10
@pytest.mark.parametrize("box", [None, "index", "series"])
def test_searchsorted_castable_strings(self, arr1d, box, request,
string_storage):
if isinstance(arr1d, DatetimeArray):
tz = arr1d.tz
ts1, ts2 = arr1d[1:3]
if tz is not None and ts1.tz.tzname(ts1) != ts2.tz.tzname(ts2):
# If we have e.g. tzutc(), when we cast to string and parse
# back we get pytz.UTC, and then consider them different timezones
# so incorrectly raise.
mark = pytest.mark.xfail(
raises=TypeError,
reason="timezone comparisons inconsistent")
request.node.add_marker(mark)
arr = arr1d
if box is None:
pass
elif box == "index":
# Test the equivalent Index.searchsorted method while we're here
arr = self.index_cls(arr)
else:
# Test the equivalent Series.searchsorted method while we're here
arr = pd.Series(arr)
# scalar
result = arr.searchsorted(str(arr[1]))
assert result == 1
result = arr.searchsorted(str(arr[2]), side="right")
assert result == 3
result = arr.searchsorted([str(x) for x in arr[1:3]])
expected = np.array([1, 2], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
with pytest.raises(
TypeError,
match=re.escape(
f"value should be a '{arr1d._scalar_type.__name__}', 'NaT', "
"or array of those. Got 'str' instead."),
):
arr.searchsorted("foo")
arr_type = "StringArray" if string_storage == "python" else "ArrowStringArray"
with pd.option_context("string_storage", string_storage):
with pytest.raises(
TypeError,
match=re.escape(
f"value should be a '{arr1d._scalar_type.__name__}', 'NaT', "
f"or array of those. Got '{arr_type}' instead."),
):
arr.searchsorted([str(arr[1]), "baz"])
def test_getitem_near_implementation_bounds(self):
# We only check tz-naive for DTA bc the bounds are slightly different
# for other tzs
i8vals = np.asarray([NaT.value + n for n in range(1, 5)], dtype="i8")
arr = self.array_cls(i8vals, freq="ns")
arr[0] # should not raise OutOfBoundsDatetime
index = pd.Index(arr)
index[0] # should not raise OutOfBoundsDatetime
ser = pd.Series(arr)
ser[0] # should not raise OutOfBoundsDatetime
def test_getitem_2d(self, arr1d):
# 2d slicing on a 1D array
expected = type(arr1d)(arr1d._data[:, np.newaxis], dtype=arr1d.dtype)
result = arr1d[:, np.newaxis]
tm.assert_equal(result, expected)
# Lookup on a 2D array
arr2d = expected
expected = type(arr2d)(arr2d._data[:3, 0], dtype=arr2d.dtype)
result = arr2d[:3, 0]
tm.assert_equal(result, expected)
# Scalar lookup
result = arr2d[-1, 0]
expected = arr1d[-1]
assert result == expected
def test_iter_2d(self, arr1d):
data2d = arr1d._data[:3, np.newaxis]
arr2d = type(arr1d)._simple_new(data2d, dtype=arr1d.dtype)
result = list(arr2d)
assert len(result) == 3
for x in result:
assert isinstance(x, type(arr1d))
assert x.ndim == 1
assert x.dtype == arr1d.dtype
def test_repr_2d(self, arr1d):
data2d = arr1d._data[:3, np.newaxis]
arr2d = type(arr1d)._simple_new(data2d, dtype=arr1d.dtype)
result = repr(arr2d)
if isinstance(arr2d, TimedeltaArray):
expected = (f"<{type(arr2d).__name__}>\n"
"[\n"
f"['{arr1d[0]._repr_base()}'],\n"
f"['{arr1d[1]._repr_base()}'],\n"
f"['{arr1d[2]._repr_base()}']\n"
"]\n"
f"Shape: (3, 1), dtype: {arr1d.dtype}")
else:
expected = (f"<{type(arr2d).__name__}>\n"
"[\n"
f"['{arr1d[0]}'],\n"
f"['{arr1d[1]}'],\n"
f"['{arr1d[2]}']\n"
"]\n"
f"Shape: (3, 1), dtype: {arr1d.dtype}")
assert result == expected
def test_setitem(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
arr[0] = arr[1]
expected = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
expected[0] = expected[1]
tm.assert_numpy_array_equal(arr.asi8, expected)
arr[:2] = arr[-2:]
expected[:2] = expected[-2:]
tm.assert_numpy_array_equal(arr.asi8, expected)
@pytest.mark.parametrize(
"box",
[
pd.Index,
pd.Series,
np.array,
list,
PandasArray,
],
)
def test_setitem_object_dtype(self, box, arr1d):
expected = arr1d.copy()[::-1]
if expected.dtype.kind in ["m", "M"]:
expected = expected._with_freq(None)
vals = expected
if box is list:
vals = list(vals)
elif box is np.array:
# if we do np.array(x).astype(object) then dt64 and td64 cast to ints
vals = np.array(vals.astype(object))
elif box is PandasArray:
vals = box(np.asarray(vals, dtype=object))
else:
vals = box(vals).astype(object)
arr1d[:] = vals
tm.assert_equal(arr1d, expected)
def test_setitem_strs(self, arr1d, request):
# Check that we parse strs in both scalar and listlike
if isinstance(arr1d, DatetimeArray):
tz = arr1d.tz
ts1, ts2 = arr1d[-2:]
if tz is not None and ts1.tz.tzname(ts1) != ts2.tz.tzname(ts2):
# If we have e.g. tzutc(), when we cast to string and parse
# back we get pytz.UTC, and then consider them different timezones
# so incorrectly raise.
mark = pytest.mark.xfail(
raises=TypeError,
reason="timezone comparisons inconsistent")
request.node.add_marker(mark)
# Setting list-like of strs
expected = arr1d.copy()
expected[[0, 1]] = arr1d[-2:]
result = arr1d.copy()
result[:2] = [str(x) for x in arr1d[-2:]]
tm.assert_equal(result, expected)
# Same thing but now for just a scalar str
expected = arr1d.copy()
expected[0] = arr1d[-1]
result = arr1d.copy()
result[0] = str(arr1d[-1])
tm.assert_equal(result, expected)
@pytest.mark.parametrize("as_index", [True, False])
def test_setitem_categorical(self, arr1d, as_index):
expected = arr1d.copy()[::-1]
if not isinstance(expected, PeriodArray):
expected = expected._with_freq(None)
cat = pd.Categorical(arr1d)
if as_index:
cat = pd.CategoricalIndex(cat)
arr1d[:] = cat[::-1]
tm.assert_equal(arr1d, expected)
def test_setitem_raises(self):
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
val = arr[0]
with pytest.raises(IndexError, match="index 12 is out of bounds"):
arr[12] = val
with pytest.raises(TypeError, match="value should be a.* 'object'"):
arr[0] = object()
msg = "cannot set using a list-like indexer with a different length"
with pytest.raises(ValueError, match=msg):
# GH#36339
arr[[]] = [arr[1]]
msg = "cannot set using a slice indexer with a different length than"
with pytest.raises(ValueError, match=msg):
# GH#36339
arr[1:1] = arr[:3]
@pytest.mark.parametrize("box", [list, np.array, pd.Index, pd.Series])
def test_setitem_numeric_raises(self, arr1d, box):
# We dont case e.g. int64 to our own dtype for setitem
msg = (f"value should be a '{arr1d._scalar_type.__name__}', "
"'NaT', or array of those. Got")
with pytest.raises(TypeError, match=msg):
arr1d[:2] = box([0, 1])
with pytest.raises(TypeError, match=msg):
arr1d[:2] = box([0.0, 1.0])
def test_inplace_arithmetic(self):
# GH#24115 check that iadd and isub are actually in-place
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
expected = arr + pd.Timedelta(days=1)
arr += pd.Timedelta(days=1)
tm.assert_equal(arr, expected)
expected = arr - pd.Timedelta(days=1)
arr -= pd.Timedelta(days=1)
tm.assert_equal(arr, expected)
def test_shift_fill_int_deprecated(self):
# GH#31971
data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
arr = self.array_cls(data, freq="D")
msg = "Passing <class 'int'> to shift"
with tm.assert_produces_warning(FutureWarning, match=msg):
result = arr.shift(1, fill_value=1)
expected = arr.copy()
if self.array_cls is PeriodArray:
fill_val = PeriodArray._scalar_type._from_ordinal(1, freq=arr.freq)
else:
fill_val = arr._scalar_type(1)
expected[0] = fill_val
expected[1:] = arr[:-1]
tm.assert_equal(result, expected)
def test_median(self, arr1d):
arr = arr1d
if len(arr) % 2 == 0:
# make it easier to define `expected`
arr = arr[:-1]
expected = arr[len(arr) // 2]
result = arr.median()
assert type(result) is type(expected)
assert result == expected
arr[len(arr) // 2] = NaT
if not isinstance(expected, Period):
expected = arr[len(arr) // 2 - 1:len(arr) // 2 + 2].mean()
assert arr.median(skipna=False) is NaT
result = arr.median()
assert type(result) is type(expected)
assert result == expected
assert arr[:0].median() is NaT
assert arr[:0].median(skipna=False) is NaT
# 2d Case
arr2 = arr.reshape(-1, 1)
result = arr2.median(axis=None)
assert type(result) is type(expected)
assert result == expected
assert arr2.median(axis=None, skipna=False) is NaT
result = arr2.median(axis=0)
expected2 = type(arr)._from_sequence([expected], dtype=arr.dtype)
tm.assert_equal(result, expected2)
result = arr2.median(axis=0, skipna=False)
expected2 = type(arr)._from_sequence([NaT], dtype=arr.dtype)
tm.assert_equal(result, expected2)
result = arr2.median(axis=1)
tm.assert_equal(result, arr)
result = arr2.median(axis=1, skipna=False)
tm.assert_equal(result, arr)
def test_from_integer_array(self):
arr = np.array([1, 2, 3], dtype=np.int64)
expected = self.array_cls(arr, dtype=self.example_dtype)
data = pd.array(arr, dtype="Int64")
result = self.array_cls(data, dtype=self.example_dtype)
tm.assert_extension_array_equal(result, expected)
"""
def test_slice_with_zero_step_raises(index, frame_or_series, indexer_sli):
ts = frame_or_series(np.arange(len(index)), index=index)
with pytest.raises(ValueError, match="slice step cannot be zero"):
indexer_sli(ts)[::0]
@pytest.mark.parametrize(
"index",
[
date_range("2014-01-01", periods=20, freq="MS"),
period_range("2014-01", periods=20, freq="M"),
timedelta_range("0", periods=20, freq="H"),
],
)
def test_slice_with_negative_step(index):
keystr1 = str(index[9])
keystr2 = str(index[13])
ser = Series(np.arange(20), index)
SLC = IndexSlice
for key in [keystr1, index[9]]:
tm.assert_indexing_slices_equivalent(ser, SLC[key::-1], SLC[9::-1])
tm.assert_indexing_slices_equivalent(ser, SLC[:key:-1], SLC[:8:-1])
for key2 in [keystr2, index[13]]:
tm.assert_indexing_slices_equivalent(ser, SLC[key2:key:-1],
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_timedelta_property(attr):
s = pd.Series(pd.timedelta_range("2000", periods=4))
s.attrs = {"a": 1}
result = getattr(s.dt, attr)
assert result.attrs == {"a": 1}
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
Interval,
IntervalIndex,
Timedelta,
Timestamp,
date_range,
timedelta_range,
)
import pandas._testing as tm
from pandas.core.arrays import IntervalArray
@pytest.fixture(
params=[
(Index([0, 2, 4]), Index([1, 3, 5])),
(Index([0.0, 1.0, 2.0]), Index([1.0, 2.0, 3.0])),
(timedelta_range("0 days", periods=3), timedelta_range("1 day", periods=3)),
(date_range("20170101", periods=3), date_range("20170102", periods=3)),
(
date_range("20170101", periods=3, tz="US/Eastern"),
date_range("20170102", periods=3, tz="US/Eastern"),
),
],
ids=lambda x: str(x[0].dtype),
)
def left_right_dtypes(request):
"""
Fixture for building an IntervalArray from various dtypes
"""
return request.param
def _nonempty_index(idx):
typ = type(idx)
if typ is pd.RangeIndex:
return pd.RangeIndex(2, name=idx.name)
elif typ in _numeric_index_types:
return typ([1, 2], name=idx.name)
elif typ is pd.Index:
return pd.Index(["a", "b"], name=idx.name)
elif typ is pd.DatetimeIndex:
start = "1970-01-01"
# Need a non-monotonic decreasing index to avoid issues with
# partial string indexing see https://github.com/dask/dask/issues/2389
# and https://github.com/pandas-dev/pandas/issues/16515
# This doesn't mean `_meta_nonempty` should ever rely on
# `self.monotonic_increasing` or `self.monotonic_decreasing`
try:
return pd.date_range(start=start,
periods=2,
freq=idx.freq,
tz=idx.tz,
name=idx.name)
except ValueError: # older pandas versions
data = [start, "1970-01-02"] if idx.freq is None else None
return pd.DatetimeIndex(data,
start=start,
periods=2,
freq=idx.freq,
tz=idx.tz,
name=idx.name)
elif typ is pd.PeriodIndex:
return pd.period_range(start="1970-01-01",
periods=2,
freq=idx.freq,
name=idx.name)
elif typ is pd.TimedeltaIndex:
start = np.timedelta64(1, "D")
try:
return pd.timedelta_range(start=start,
periods=2,
freq=idx.freq,
name=idx.name)
except ValueError: # older pandas versions
start = np.timedelta64(1, "D")
data = [start, start + 1] if idx.freq is None else None
return pd.TimedeltaIndex(data,
start=start,
periods=2,
freq=idx.freq,
name=idx.name)
elif typ is pd.CategoricalIndex:
if len(idx.categories) == 0:
data = pd.Categorical(_nonempty_index(idx.categories),
ordered=idx.ordered)
else:
data = pd.Categorical.from_codes([-1, 0],
categories=idx.categories,
ordered=idx.ordered)
return pd.CategoricalIndex(data, name=idx.name)
elif typ is pd.MultiIndex:
levels = [_nonempty_index(l) for l in idx.levels]
codes = [[0, 0] for i in idx.levels]
try:
return pd.MultiIndex(levels=levels, codes=codes, names=idx.names)
except TypeError: # older pandas versions
return pd.MultiIndex(levels=levels, labels=codes, names=idx.names)
raise TypeError("Don't know how to handle index of "
"type {0}".format(typename(type(idx))))
def test_arg_passthru():
# make sure that we are passing thru kwargs
# to our agg functions
# GH3668
# GH5724
df = pd.DataFrame(
{'group': [1, 1, 2],
'int': [1, 2, 3],
'float': [4., 5., 6.],
'string': list('abc'),
'category_string': pd.Series(list('abc')).astype('category'),
'category_int': [7, 8, 9],
'datetime': pd.date_range('20130101', periods=3),
'datetimetz': pd.date_range('20130101',
periods=3,
tz='US/Eastern'),
'timedelta': pd.timedelta_range('1 s', periods=3, freq='s')},
columns=['group', 'int', 'float', 'string',
'category_string', 'category_int',
'datetime', 'datetimetz',
'timedelta'])
expected_columns_numeric = Index(['int', 'float', 'category_int'])
# mean / median
expected = pd.DataFrame(
{'category_int': [7.5, 9],
'float': [4.5, 6.],
'timedelta': [pd.Timedelta('1.5s'),
pd.Timedelta('3s')],
'int': [1.5, 3],
'datetime': [pd.Timestamp('2013-01-01 12:00:00'),
pd.Timestamp('2013-01-03 00:00:00')],
'datetimetz': [
pd.Timestamp('2013-01-01 12:00:00', tz='US/Eastern'),
pd.Timestamp('2013-01-03 00:00:00', tz='US/Eastern')]},
index=Index([1, 2], name='group'),
columns=['int', 'float', 'category_int',
'datetime', 'datetimetz', 'timedelta'])
for attr in ['mean', 'median']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = f(numeric_only=False)
tm.assert_frame_equal(result.reindex_like(expected), expected)
# TODO: min, max *should* handle
# categorical (ordered) dtype
expected_columns = Index(['int', 'float', 'string',
'category_int',
'datetime', 'datetimetz',
'timedelta'])
for attr in ['min', 'max']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(['int', 'float', 'string',
'category_string', 'category_int',
'datetime', 'datetimetz',
'timedelta'])
for attr in ['first', 'last']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(['int', 'float', 'string',
'category_int', 'timedelta'])
for attr in ['sum']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(['int', 'float', 'category_int'])
for attr in ['prod', 'cumprod']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
# like min, max, but don't include strings
expected_columns = Index(['int', 'float',
'category_int',
'datetime', 'datetimetz',
'timedelta'])
for attr in ['cummin', 'cummax']:
f = getattr(df.groupby('group'), attr)
result = f()
# GH 15561: numeric_only=False set by default like min/max
tm.assert_index_equal(result.columns, expected_columns)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
expected_columns = Index(['int', 'float', 'category_int',
'timedelta'])
for attr in ['cumsum']:
f = getattr(df.groupby('group'), attr)
result = f()
tm.assert_index_equal(result.columns, expected_columns_numeric)
result = f(numeric_only=False)
tm.assert_index_equal(result.columns, expected_columns)
class TestComparison:
@pytest.fixture(params=[operator.eq, operator.ne])
def op(self, request):
return request.param
@pytest.fixture(
params=[
IntervalArray.from_arrays,
IntervalIndex.from_arrays,
create_categorical_intervals,
create_series_intervals,
create_series_categorical_intervals,
],
ids=[
"IntervalArray",
"IntervalIndex",
"Categorical[Interval]",
"Series[Interval]",
"Series[Categorical[Interval]]",
],
)
def interval_constructor(self, request):
"""
Fixture for all pandas native interval constructors.
To be used as the LHS of IntervalArray comparisons.
"""
return request.param
def elementwise_comparison(self, op, array, other):
"""
Helper that performs elementwise comparisons between `array` and `other`
"""
other = other if is_list_like(other) else [other] * len(array)
expected = np.array([op(x, y) for x, y in zip(array, other)])
if isinstance(other, Series):
return Series(expected, index=other.index)
return expected
def test_compare_scalar_interval(self, op, array):
# matches first interval
other = array[0]
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
# matches on a single endpoint but not both
other = Interval(array.left[0], array.right[1])
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
def test_compare_scalar_interval_mixed_closed(self, op, closed,
other_closed):
array = IntervalArray.from_arrays(range(2), range(1, 3), closed=closed)
other = Interval(0, 1, closed=other_closed)
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
def test_compare_scalar_na(self, op, array, nulls_fixture, request):
result = op(array, nulls_fixture)
expected = self.elementwise_comparison(op, array, nulls_fixture)
if nulls_fixture is pd.NA and array.dtype.subtype != "int64":
mark = pytest.mark.xfail(
reason="broken for non-integer IntervalArray; see GH 31882")
request.node.add_marker(mark)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"other",
[
0,
1.0,
True,
"foo",
Timestamp("2017-01-01"),
Timestamp("2017-01-01", tz="US/Eastern"),
Timedelta("0 days"),
Period("2017-01-01", "D"),
],
)
def test_compare_scalar_other(self, op, array, other):
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
def test_compare_list_like_interval(self, op, array, interval_constructor):
# same endpoints
other = interval_constructor(array.left, array.right)
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_equal(result, expected)
# different endpoints
other = interval_constructor(array.left[::-1], array.right[::-1])
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_equal(result, expected)
# all nan endpoints
other = interval_constructor([np.nan] * 4, [np.nan] * 4)
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_equal(result, expected)
def test_compare_list_like_interval_mixed_closed(self, op,
interval_constructor,
closed, other_closed):
array = IntervalArray.from_arrays(range(2), range(1, 3), closed=closed)
other = interval_constructor(range(2),
range(1, 3),
closed=other_closed)
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_equal(result, expected)
@pytest.mark.parametrize(
"other",
[
(
Interval(0, 1),
Interval(Timedelta("1 day"), Timedelta("2 days")),
Interval(4, 5, "both"),
Interval(10, 20, "neither"),
),
(0, 1.5, Timestamp("20170103"), np.nan),
(
Timestamp("20170102", tz="US/Eastern"),
Timedelta("2 days"),
"baz",
pd.NaT,
),
],
)
def test_compare_list_like_object(self, op, array, other):
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
def test_compare_list_like_nan(self, op, array, nulls_fixture, request):
other = [nulls_fixture] * 4
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
if nulls_fixture is pd.NA and array.dtype.subtype != "i8":
reason = "broken for non-integer IntervalArray; see GH 31882"
mark = pytest.mark.xfail(reason=reason)
request.node.add_marker(mark)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize(
"other",
[
np.arange(4, dtype="int64"),
np.arange(4, dtype="float64"),
date_range("2017-01-01", periods=4),
date_range("2017-01-01", periods=4, tz="US/Eastern"),
timedelta_range("0 days", periods=4),
period_range("2017-01-01", periods=4, freq="D"),
Categorical(list("abab")),
Categorical(date_range("2017-01-01", periods=4)),
pd.array(list("abcd")),
pd.array(["foo", 3.14, None, object()]),
],
ids=lambda x: str(x.dtype),
)
def test_compare_list_like_other(self, op, array, other):
result = op(array, other)
expected = self.elementwise_comparison(op, array, other)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("length", [1, 3, 5])
@pytest.mark.parametrize("other_constructor", [IntervalArray, list])
def test_compare_length_mismatch_errors(self, op, other_constructor,
length):
array = IntervalArray.from_arrays(range(4), range(1, 5))
other = other_constructor([Interval(0, 1)] * length)
with pytest.raises(ValueError, match="Lengths must match to compare"):
op(array, other)
@pytest.mark.parametrize(
"constructor, expected_type, assert_func",
[
(IntervalIndex, np.array, tm.assert_numpy_array_equal),
(Series, Series, tm.assert_series_equal),
],
)
def test_index_series_compat(self, op, constructor, expected_type,
assert_func):
# IntervalIndex/Series that rely on IntervalArray for comparisons
breaks = range(4)
index = constructor(IntervalIndex.from_breaks(breaks))
# scalar comparisons
other = index[0]
result = op(index, other)
expected = expected_type(self.elementwise_comparison(op, index, other))
assert_func(result, expected)
other = breaks[0]
result = op(index, other)
expected = expected_type(self.elementwise_comparison(op, index, other))
assert_func(result, expected)
# list-like comparisons
other = IntervalArray.from_breaks(breaks)
result = op(index, other)
expected = expected_type(self.elementwise_comparison(op, index, other))
assert_func(result, expected)
other = [index[0], breaks[0], "foo"]
result = op(index, other)
expected = expected_type(self.elementwise_comparison(op, index, other))
assert_func(result, expected)
@pytest.mark.parametrize("scalars", ["a", False, 1, 1.0, None])
def test_comparison_operations(self, scalars):
# GH #28981
expected = Series([False, False])
s = Series([Interval(0, 1), Interval(1, 2)], dtype="interval")
result = s == scalars
tm.assert_series_equal(result, expected)
def test_basic(self, fp, df_full):
df = df_full
df["datetime_tz"] = pd.date_range("20130101", periods=3, tz="US/Eastern")
df["timedelta"] = pd.timedelta_range("1 day", periods=3)
check_round_trip(df, fp)
class TestPartialSetting:
def test_partial_setting(self):
# GH2578, allow ix and friends to partially set
# series
s_orig = Series([1, 2, 3])
s = s_orig.copy()
s[5] = 5
expected = Series([1, 2, 3, 5], index=[0, 1, 2, 5])
tm.assert_series_equal(s, expected)
s = s_orig.copy()
s.loc[5] = 5
expected = Series([1, 2, 3, 5], index=[0, 1, 2, 5])
tm.assert_series_equal(s, expected)
s = s_orig.copy()
s[5] = 5.0
expected = Series([1, 2, 3, 5.0], index=[0, 1, 2, 5])
tm.assert_series_equal(s, expected)
s = s_orig.copy()
s.loc[5] = 5.0
expected = Series([1, 2, 3, 5.0], index=[0, 1, 2, 5])
tm.assert_series_equal(s, expected)
# iloc/iat raise
s = s_orig.copy()
msg = "iloc cannot enlarge its target object"
with pytest.raises(IndexError, match=msg):
s.iloc[3] = 5.0
msg = "index 3 is out of bounds for axis 0 with size 3"
with pytest.raises(IndexError, match=msg):
s.iat[3] = 5.0
# ## frame ##
df_orig = DataFrame(np.arange(6).reshape(3, 2),
columns=["A", "B"],
dtype="int64")
# iloc/iat raise
df = df_orig.copy()
msg = "iloc cannot enlarge its target object"
with pytest.raises(IndexError, match=msg):
df.iloc[4, 2] = 5.0
msg = "index 2 is out of bounds for axis 0 with size 2"
with pytest.raises(IndexError, match=msg):
df.iat[4, 2] = 5.0
# row setting where it exists
expected = DataFrame(dict({"A": [0, 4, 4], "B": [1, 5, 5]}))
df = df_orig.copy()
df.iloc[1] = df.iloc[2]
tm.assert_frame_equal(df, expected)
expected = DataFrame(dict({"A": [0, 4, 4], "B": [1, 5, 5]}))
df = df_orig.copy()
df.loc[1] = df.loc[2]
tm.assert_frame_equal(df, expected)
# like 2578, partial setting with dtype preservation
expected = DataFrame(dict({"A": [0, 2, 4, 4], "B": [1, 3, 5, 5]}))
df = df_orig.copy()
df.loc[3] = df.loc[2]
tm.assert_frame_equal(df, expected)
# single dtype frame, overwrite
expected = DataFrame(dict({"A": [0, 2, 4], "B": [0, 2, 4]}))
df = df_orig.copy()
df.loc[:, "B"] = df.loc[:, "A"]
tm.assert_frame_equal(df, expected)
# mixed dtype frame, overwrite
expected = DataFrame(dict({"A": [0, 2, 4], "B": Series([0, 2, 4])}))
df = df_orig.copy()
df["B"] = df["B"].astype(np.float64)
df.loc[:, "B"] = df.loc[:, "A"]
tm.assert_frame_equal(df, expected)
# single dtype frame, partial setting
expected = df_orig.copy()
expected["C"] = df["A"]
df = df_orig.copy()
df.loc[:, "C"] = df.loc[:, "A"]
tm.assert_frame_equal(df, expected)
# mixed frame, partial setting
expected = df_orig.copy()
expected["C"] = df["A"]
df = df_orig.copy()
df.loc[:, "C"] = df.loc[:, "A"]
tm.assert_frame_equal(df, expected)
def test_partial_setting2(self):
# GH 8473
dates = date_range("1/1/2000", periods=8)
df_orig = DataFrame(np.random.randn(8, 4),
index=dates,
columns=["A", "B", "C", "D"])
expected = pd.concat(
[df_orig,
DataFrame({"A": 7}, index=dates[-1:] + dates.freq)],
sort=True)
df = df_orig.copy()
df.loc[dates[-1] + dates.freq, "A"] = 7
tm.assert_frame_equal(df, expected)
df = df_orig.copy()
df.at[dates[-1] + dates.freq, "A"] = 7
tm.assert_frame_equal(df, expected)
exp_other = DataFrame({0: 7}, index=dates[-1:] + dates.freq)
expected = pd.concat([df_orig, exp_other], axis=1)
df = df_orig.copy()
df.loc[dates[-1] + dates.freq, 0] = 7
tm.assert_frame_equal(df, expected)
df = df_orig.copy()
df.at[dates[-1] + dates.freq, 0] = 7
tm.assert_frame_equal(df, expected)
# TODO(ArrayManager)
# df.loc[0] = Series(1, index=range(4)) case creates float columns
# instead of object dtype
@td.skip_array_manager_not_yet_implemented
def test_partial_setting_mixed_dtype(self):
# in a mixed dtype environment, try to preserve dtypes
# by appending
df = DataFrame([[True, 1], [False, 2]], columns=["female", "fitness"])
s = df.loc[1].copy()
s.name = 2
expected = df.append(s)
df.loc[2] = df.loc[1]
tm.assert_frame_equal(df, expected)
# columns will align
df = DataFrame(columns=["A", "B"])
df.loc[0] = Series(1, index=range(4))
expected = DataFrame(columns=["A", "B"], index=[0], dtype=np.float64)
tm.assert_frame_equal(df, expected)
# columns will align
# TODO: it isn't great that this behavior depends on consolidation
df = DataFrame(columns=["A", "B"])._consolidate()
df.loc[0] = Series(1, index=["B"])
exp = DataFrame([[np.nan, 1]],
columns=["A", "B"],
index=[0],
dtype="float64")
tm.assert_frame_equal(df, exp)
# list-like must conform
df = DataFrame(columns=["A", "B"])
msg = "cannot set a row with mismatched columns"
with pytest.raises(ValueError, match=msg):
df.loc[0] = [1, 2, 3]
df = DataFrame(columns=["A", "B"])
df.loc[3] = [6, 7]
exp = DataFrame([[6, 7]],
index=[3],
columns=["A", "B"],
dtype=np.int64)
tm.assert_frame_equal(df, exp)
def test_series_partial_set(self):
# partial set with new index
# Regression from GH4825
ser = Series([0.1, 0.2], index=[1, 2])
# loc equiv to .reindex
expected = Series([np.nan, 0.2, np.nan], index=[3, 2, 3])
with pytest.raises(KeyError, match=r"not in index"):
ser.loc[[3, 2, 3]]
result = ser.reindex([3, 2, 3])
tm.assert_series_equal(result, expected, check_index_type=True)
expected = Series([np.nan, 0.2, np.nan, np.nan], index=[3, 2, 3, "x"])
with pytest.raises(KeyError, match="not in index"):
ser.loc[[3, 2, 3, "x"]]
result = ser.reindex([3, 2, 3, "x"])
tm.assert_series_equal(result, expected, check_index_type=True)
expected = Series([0.2, 0.2, 0.1], index=[2, 2, 1])
result = ser.loc[[2, 2, 1]]
tm.assert_series_equal(result, expected, check_index_type=True)
expected = Series([0.2, 0.2, np.nan, 0.1], index=[2, 2, "x", 1])
with pytest.raises(KeyError, match="not in index"):
ser.loc[[2, 2, "x", 1]]
result = ser.reindex([2, 2, "x", 1])
tm.assert_series_equal(result, expected, check_index_type=True)
# raises as nothing is in the index
msg = (r"\"None of \[Int64Index\(\[3, 3, 3\], dtype='int64'\)\] are "
r"in the \[index\]\"")
with pytest.raises(KeyError, match=msg):
ser.loc[[3, 3, 3]]
expected = Series([0.2, 0.2, np.nan], index=[2, 2, 3])
with pytest.raises(KeyError, match="not in index"):
ser.loc[[2, 2, 3]]
result = ser.reindex([2, 2, 3])
tm.assert_series_equal(result, expected, check_index_type=True)
s = Series([0.1, 0.2, 0.3], index=[1, 2, 3])
expected = Series([0.3, np.nan, np.nan], index=[3, 4, 4])
with pytest.raises(KeyError, match="not in index"):
s.loc[[3, 4, 4]]
result = s.reindex([3, 4, 4])
tm.assert_series_equal(result, expected, check_index_type=True)
s = Series([0.1, 0.2, 0.3, 0.4], index=[1, 2, 3, 4])
expected = Series([np.nan, 0.3, 0.3], index=[5, 3, 3])
with pytest.raises(KeyError, match="not in index"):
s.loc[[5, 3, 3]]
result = s.reindex([5, 3, 3])
tm.assert_series_equal(result, expected, check_index_type=True)
s = Series([0.1, 0.2, 0.3, 0.4], index=[1, 2, 3, 4])
expected = Series([np.nan, 0.4, 0.4], index=[5, 4, 4])
with pytest.raises(KeyError, match="not in index"):
s.loc[[5, 4, 4]]
result = s.reindex([5, 4, 4])
tm.assert_series_equal(result, expected, check_index_type=True)
s = Series([0.1, 0.2, 0.3, 0.4], index=[4, 5, 6, 7])
expected = Series([0.4, np.nan, np.nan], index=[7, 2, 2])
with pytest.raises(KeyError, match="not in index"):
s.loc[[7, 2, 2]]
result = s.reindex([7, 2, 2])
tm.assert_series_equal(result, expected, check_index_type=True)
s = Series([0.1, 0.2, 0.3, 0.4], index=[1, 2, 3, 4])
expected = Series([0.4, np.nan, np.nan], index=[4, 5, 5])
with pytest.raises(KeyError, match="not in index"):
s.loc[[4, 5, 5]]
result = s.reindex([4, 5, 5])
tm.assert_series_equal(result, expected, check_index_type=True)
# iloc
expected = Series([0.2, 0.2, 0.1, 0.1], index=[2, 2, 1, 1])
result = ser.iloc[[1, 1, 0, 0]]
tm.assert_series_equal(result, expected, check_index_type=True)
def test_series_partial_set_with_name(self):
# GH 11497
idx = Index([1, 2], dtype="int64", name="idx")
ser = Series([0.1, 0.2], index=idx, name="s")
# loc
with pytest.raises(KeyError, match=r"\[3\] not in index"):
ser.loc[[3, 2, 3]]
with pytest.raises(KeyError, match=r"not in index"):
ser.loc[[3, 2, 3, "x"]]
exp_idx = Index([2, 2, 1], dtype="int64", name="idx")
expected = Series([0.2, 0.2, 0.1], index=exp_idx, name="s")
result = ser.loc[[2, 2, 1]]
tm.assert_series_equal(result, expected, check_index_type=True)
with pytest.raises(KeyError, match=r"\['x'\] not in index"):
ser.loc[[2, 2, "x", 1]]
# raises as nothing is in the index
msg = (r"\"None of \[Int64Index\(\[3, 3, 3\], dtype='int64', "
r"name='idx'\)\] are in the \[index\]\"")
with pytest.raises(KeyError, match=msg):
ser.loc[[3, 3, 3]]
with pytest.raises(KeyError, match="not in index"):
ser.loc[[2, 2, 3]]
idx = Index([1, 2, 3], dtype="int64", name="idx")
with pytest.raises(KeyError, match="not in index"):
Series([0.1, 0.2, 0.3], index=idx, name="s").loc[[3, 4, 4]]
idx = Index([1, 2, 3, 4], dtype="int64", name="idx")
with pytest.raises(KeyError, match="not in index"):
Series([0.1, 0.2, 0.3, 0.4], index=idx, name="s").loc[[5, 3, 3]]
idx = Index([1, 2, 3, 4], dtype="int64", name="idx")
with pytest.raises(KeyError, match="not in index"):
Series([0.1, 0.2, 0.3, 0.4], index=idx, name="s").loc[[5, 4, 4]]
idx = Index([4, 5, 6, 7], dtype="int64", name="idx")
with pytest.raises(KeyError, match="not in index"):
Series([0.1, 0.2, 0.3, 0.4], index=idx, name="s").loc[[7, 2, 2]]
idx = Index([1, 2, 3, 4], dtype="int64", name="idx")
with pytest.raises(KeyError, match="not in index"):
Series([0.1, 0.2, 0.3, 0.4], index=idx, name="s").loc[[4, 5, 5]]
# iloc
exp_idx = Index([2, 2, 1, 1], dtype="int64", name="idx")
expected = Series([0.2, 0.2, 0.1, 0.1], index=exp_idx, name="s")
result = ser.iloc[[1, 1, 0, 0]]
tm.assert_series_equal(result, expected, check_index_type=True)
@pytest.mark.parametrize("key", [100, 100.0])
def test_setitem_with_expansion_numeric_into_datetimeindex(self, key):
# GH#4940 inserting non-strings
orig = tm.makeTimeDataFrame()
df = orig.copy()
df.loc[key, :] = df.iloc[0]
ex_index = Index(list(orig.index) + [key],
dtype=object,
name=orig.index.name)
ex_data = np.concatenate([orig.values, df.iloc[[0]].values], axis=0)
expected = DataFrame(ex_data, index=ex_index, columns=orig.columns)
tm.assert_frame_equal(df, expected)
def test_partial_set_invalid(self):
# GH 4940
# allow only setting of 'valid' values
orig = tm.makeTimeDataFrame()
# allow object conversion here
df = orig.copy()
df.loc["a", :] = df.iloc[0]
exp = orig.append(Series(df.iloc[0], name="a"))
tm.assert_frame_equal(df, exp)
tm.assert_index_equal(df.index, Index(orig.index.tolist() + ["a"]))
assert df.index.dtype == "object"
def test_partial_set_empty_frame(self):
# partially set with an empty object
# frame
df = DataFrame()
msg = "cannot set a frame with no defined columns"
with pytest.raises(ValueError, match=msg):
df.loc[1] = 1
with pytest.raises(ValueError, match=msg):
df.loc[1] = Series([1], index=["foo"])
msg = "cannot set a frame with no defined index and a scalar"
with pytest.raises(ValueError, match=msg):
df.loc[:, 1] = 1
def test_partial_set_empty_frame2(self):
# these work as they don't really change
# anything but the index
# GH5632
expected = DataFrame(columns=["foo"], index=Index([], dtype="object"))
df = DataFrame(index=Index([], dtype="object"))
df["foo"] = Series([], dtype="object")
tm.assert_frame_equal(df, expected)
df = DataFrame()
df["foo"] = Series(df.index)
tm.assert_frame_equal(df, expected)
df = DataFrame()
df["foo"] = df.index
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame3(self):
expected = DataFrame(columns=["foo"], index=Index([], dtype="int64"))
expected["foo"] = expected["foo"].astype("float64")
df = DataFrame(index=Index([], dtype="int64"))
df["foo"] = []
tm.assert_frame_equal(df, expected)
df = DataFrame(index=Index([], dtype="int64"))
df["foo"] = Series(np.arange(len(df)), dtype="float64")
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame4(self):
df = DataFrame(index=Index([], dtype="int64"))
df["foo"] = range(len(df))
expected = DataFrame(columns=["foo"], index=Index([], dtype="int64"))
# range is int-dtype-like, so we get int64 dtype
expected["foo"] = expected["foo"].astype("int64")
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame5(self):
df = DataFrame()
tm.assert_index_equal(df.columns, Index([], dtype=object))
df2 = DataFrame()
df2[1] = Series([1], index=["foo"])
df.loc[:, 1] = Series([1], index=["foo"])
tm.assert_frame_equal(df, DataFrame([[1]], index=["foo"], columns=[1]))
tm.assert_frame_equal(df, df2)
def test_partial_set_empty_frame_no_index(self):
# no index to start
expected = DataFrame({0: Series(1, index=range(4))},
columns=["A", "B", 0])
df = DataFrame(columns=["A", "B"])
df[0] = Series(1, index=range(4))
df.dtypes
str(df)
tm.assert_frame_equal(df, expected)
df = DataFrame(columns=["A", "B"])
df.loc[:, 0] = Series(1, index=range(4))
df.dtypes
str(df)
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame_row(self):
# GH5720, GH5744
# don't create rows when empty
expected = DataFrame(columns=["A", "B", "New"],
index=Index([], dtype="int64"))
expected["A"] = expected["A"].astype("int64")
expected["B"] = expected["B"].astype("float64")
expected["New"] = expected["New"].astype("float64")
df = DataFrame({"A": [1, 2, 3], "B": [1.2, 4.2, 5.2]})
y = df[df.A > 5]
y["New"] = np.nan
tm.assert_frame_equal(y, expected)
# tm.assert_frame_equal(y,expected)
expected = DataFrame(columns=["a", "b", "c c", "d"])
expected["d"] = expected["d"].astype("int64")
df = DataFrame(columns=["a", "b", "c c"])
df["d"] = 3
tm.assert_frame_equal(df, expected)
tm.assert_series_equal(df["c c"], Series(name="c c", dtype=object))
# reindex columns is ok
df = DataFrame({"A": [1, 2, 3], "B": [1.2, 4.2, 5.2]})
y = df[df.A > 5]
result = y.reindex(columns=["A", "B", "C"])
expected = DataFrame(columns=["A", "B", "C"],
index=Index([], dtype="int64"))
expected["A"] = expected["A"].astype("int64")
expected["B"] = expected["B"].astype("float64")
expected["C"] = expected["C"].astype("float64")
tm.assert_frame_equal(result, expected)
def test_partial_set_empty_frame_set_series(self):
# GH 5756
# setting with empty Series
df = DataFrame(Series(dtype=object))
expected = DataFrame({0: Series(dtype=object)})
tm.assert_frame_equal(df, expected)
df = DataFrame(Series(name="foo", dtype=object))
expected = DataFrame({"foo": Series(dtype=object)})
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame_empty_copy_assignment(self):
# GH 5932
# copy on empty with assignment fails
df = DataFrame(index=[0])
df = df.copy()
df["a"] = 0
expected = DataFrame(0, index=[0], columns=["a"])
tm.assert_frame_equal(df, expected)
def test_partial_set_empty_frame_empty_consistencies(self):
# GH 6171
# consistency on empty frames
df = DataFrame(columns=["x", "y"])
df["x"] = [1, 2]
expected = DataFrame({"x": [1, 2], "y": [np.nan, np.nan]})
tm.assert_frame_equal(df, expected, check_dtype=False)
df = DataFrame(columns=["x", "y"])
df["x"] = ["1", "2"]
expected = DataFrame({
"x": ["1", "2"],
"y": [np.nan, np.nan]
},
dtype=object)
tm.assert_frame_equal(df, expected)
df = DataFrame(columns=["x", "y"])
df.loc[0, "x"] = 1
expected = DataFrame({"x": [1], "y": [np.nan]})
tm.assert_frame_equal(df, expected, check_dtype=False)
@pytest.mark.parametrize(
"idx,labels,expected_idx",
[
(
period_range(start="2000", periods=20, freq="D"),
["2000-01-04", "2000-01-08", "2000-01-12"],
[
Period("2000-01-04", freq="D"),
Period("2000-01-08", freq="D"),
Period("2000-01-12", freq="D"),
],
),
(
date_range(start="2000", periods=20, freq="D"),
["2000-01-04", "2000-01-08", "2000-01-12"],
[
Timestamp("2000-01-04"),
Timestamp("2000-01-08"),
Timestamp("2000-01-12"),
],
),
(
pd.timedelta_range(start="1 day", periods=20),
["4D", "8D", "12D"],
[
pd.Timedelta("4 day"),
pd.Timedelta("8 day"),
pd.Timedelta("12 day")
],
),
],
)
def test_loc_with_list_of_strings_representing_datetimes(
self, idx, labels, expected_idx, frame_or_series):
# GH 11278
obj = frame_or_series(range(20), index=idx)
expected_value = [3, 7, 11]
expected = frame_or_series(expected_value, expected_idx)
tm.assert_equal(expected, obj.loc[labels])
if frame_or_series is Series:
tm.assert_series_equal(expected, obj[labels])
@pytest.mark.parametrize(
"idx,labels",
[
(
period_range(start="2000", periods=20, freq="D"),
["2000-01-04", "2000-01-30"],
),
(
date_range(start="2000", periods=20, freq="D"),
["2000-01-04", "2000-01-30"],
),
(pd.timedelta_range(start="1 day",
periods=20), ["3 day", "30 day"]),
],
)
def test_loc_with_list_of_strings_representing_datetimes_missing_value(
self, idx, labels):
# GH 11278
s = Series(range(20), index=idx)
df = DataFrame(range(20), index=idx)
msg = r"not in index"
with pytest.raises(KeyError, match=msg):
s.loc[labels]
with pytest.raises(KeyError, match=msg):
s[labels]
with pytest.raises(KeyError, match=msg):
df.loc[labels]
@pytest.mark.parametrize(
"idx,labels,msg",
[
(
period_range(start="2000", periods=20, freq="D"),
["4D", "8D"],
(r"None of \[Index\(\['4D', '8D'\], dtype='object'\)\] "
r"are in the \[index\]"),
),
(
date_range(start="2000", periods=20, freq="D"),
["4D", "8D"],
(r"None of \[Index\(\['4D', '8D'\], dtype='object'\)\] "
r"are in the \[index\]"),
),
(
pd.timedelta_range(start="1 day", periods=20),
["2000-01-04", "2000-01-08"],
(r"None of \[Index\(\['2000-01-04', '2000-01-08'\], "
r"dtype='object'\)\] are in the \[index\]"),
),
],
)
def test_loc_with_list_of_strings_representing_datetimes_not_matched_type(
self, idx, labels, msg):
# GH 11278
s = Series(range(20), index=idx)
df = DataFrame(range(20), index=idx)
with pytest.raises(KeyError, match=msg):
s.loc[labels]
with pytest.raises(KeyError, match=msg):
s[labels]
with pytest.raises(KeyError, match=msg):
df.loc[labels]
def test_index_name_empty(self):
# GH 31368
df = DataFrame({}, index=pd.RangeIndex(0, name="df_index"))
series = Series(1.23, index=pd.RangeIndex(4, name="series_index"))
df["series"] = series
expected = DataFrame({"series": [1.23] * 4},
index=pd.RangeIndex(4, name="df_index"))
tm.assert_frame_equal(df, expected)
# GH 36527
df = DataFrame()
series = Series(1.23, index=pd.RangeIndex(4, name="series_index"))
df["series"] = series
expected = DataFrame({"series": [1.23] * 4},
index=pd.RangeIndex(4, name="series_index"))
tm.assert_frame_equal(df, expected)
def test_slice_irregular_datetime_index_with_nan(self):
# GH36953
index = pd.to_datetime(
["2012-01-01", "2012-01-02", "2012-01-03", None])
df = DataFrame(range(len(index)), index=index)
expected = DataFrame(range(len(index[:3])), index=index[:3])
result = df["2012-01-01":"2012-01-04"]
tm.assert_frame_equal(result, expected)
def test_count_nonnumeric_types():
# GH12541
cols = [
"int",
"float",
"string",
"datetime",
"timedelta",
"periods",
"fl_inf",
"fl_nan",
"str_nan",
"dt_nat",
"periods_nat",
]
dt_nat_col = [
Timestamp("20170101"),
Timestamp("20170203"),
Timestamp(None)
]
df = DataFrame(
{
"int": [1, 2, 3],
"float": [4.0, 5.0, 6.0],
"string": list("abc"),
"datetime": date_range("20170101", periods=3),
"timedelta": timedelta_range("1 s", periods=3, freq="s"),
"periods": [
Period("2012-01"),
Period("2012-02"),
Period("2012-03"),
],
"fl_inf": [1.0, 2.0, np.Inf],
"fl_nan": [1.0, 2.0, np.NaN],
"str_nan": ["aa", "bb", np.NaN],
"dt_nat": dt_nat_col,
"periods_nat": [
Period("2012-01"),
Period("2012-02"),
Period(None),
],
},
columns=cols,
)
expected = DataFrame(
{
"int": [1.0, 2.0, 2.0],
"float": [1.0, 2.0, 2.0],
"string": [1.0, 2.0, 2.0],
"datetime": [1.0, 2.0, 2.0],
"timedelta": [1.0, 2.0, 2.0],
"periods": [1.0, 2.0, 2.0],
"fl_inf": [1.0, 2.0, 2.0],
"fl_nan": [1.0, 2.0, 1.0],
"str_nan": [1.0, 2.0, 1.0],
"dt_nat": [1.0, 2.0, 1.0],
"periods_nat": [1.0, 2.0, 1.0],
},
columns=cols,
)
result = df.rolling(window=2, min_periods=0).count()
tm.assert_frame_equal(result, expected)
result = df.rolling(1, min_periods=0).count()
expected = df.notna().astype(float)
tm.assert_frame_equal(result, expected)
class Base:
"""
Common tests for all variations of IntervalIndex construction. Input data
to be supplied in breaks format, then converted by the subclass method
get_kwargs_from_breaks to the expected format.
"""
@pytest.mark.parametrize(
"breaks",
[
[3, 14, 15, 92, 653],
np.arange(10, dtype="int64"),
Int64Index(range(-10, 11)),
Float64Index(np.arange(20, 30, 0.5)),
date_range("20180101", periods=10),
date_range("20180101", periods=10, tz="US/Eastern"),
timedelta_range("1 day", periods=10),
],
)
def test_constructor(self, constructor, breaks, closed, name):
result_kwargs = self.get_kwargs_from_breaks(breaks, closed)
result = constructor(closed=closed, name=name, **result_kwargs)
assert result.closed == closed
assert result.name == name
assert result.dtype.subtype == getattr(breaks, "dtype", "int64")
tm.assert_index_equal(result.left, Index(breaks[:-1]))
tm.assert_index_equal(result.right, Index(breaks[1:]))
@pytest.mark.parametrize(
"breaks, subtype",
[
(Int64Index([0, 1, 2, 3, 4]), "float64"),
(Int64Index([0, 1, 2, 3, 4]), "datetime64[ns]"),
(Int64Index([0, 1, 2, 3, 4]), "timedelta64[ns]"),
(Float64Index([0, 1, 2, 3, 4]), "int64"),
(date_range("2017-01-01", periods=5), "int64"),
(timedelta_range("1 day", periods=5), "int64"),
],
)
def test_constructor_dtype(self, constructor, breaks, subtype):
# GH 19262: conversion via dtype parameter
expected_kwargs = self.get_kwargs_from_breaks(breaks.astype(subtype))
expected = constructor(**expected_kwargs)
result_kwargs = self.get_kwargs_from_breaks(breaks)
iv_dtype = IntervalDtype(subtype)
for dtype in (iv_dtype, str(iv_dtype)):
result = constructor(dtype=dtype, **result_kwargs)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("breaks",
[[np.nan] * 2, [np.nan] * 4, [np.nan] * 50])
def test_constructor_nan(self, constructor, breaks, closed):
# GH 18421
result_kwargs = self.get_kwargs_from_breaks(breaks)
result = constructor(closed=closed, **result_kwargs)
expected_subtype = np.float64
expected_values = np.array(breaks[:-1], dtype=object)
assert result.closed == closed
assert result.dtype.subtype == expected_subtype
tm.assert_numpy_array_equal(result._ndarray_values, expected_values)
@pytest.mark.parametrize(
"breaks",
[
[],
np.array([], dtype="int64"),
np.array([], dtype="float64"),
np.array([], dtype="datetime64[ns]"),
np.array([], dtype="timedelta64[ns]"),
],
)
def test_constructor_empty(self, constructor, breaks, closed):
# GH 18421
result_kwargs = self.get_kwargs_from_breaks(breaks)
result = constructor(closed=closed, **result_kwargs)
expected_values = np.array([], dtype=object)
expected_subtype = getattr(breaks, "dtype", np.int64)
assert result.empty
assert result.closed == closed
assert result.dtype.subtype == expected_subtype
tm.assert_numpy_array_equal(result._ndarray_values, expected_values)
@pytest.mark.parametrize(
"breaks",
[
tuple("0123456789"),
list("abcdefghij"),
np.array(list("abcdefghij"), dtype=object),
np.array(list("abcdefghij"), dtype="<U1"),
],
)
def test_constructor_string(self, constructor, breaks):
# GH 19016
msg = ("category, object, and string subtypes are not supported "
"for IntervalIndex")
with pytest.raises(TypeError, match=msg):
constructor(**self.get_kwargs_from_breaks(breaks))
@pytest.mark.parametrize("cat_constructor",
[Categorical, CategoricalIndex])
def test_constructor_categorical_valid(self, constructor, cat_constructor):
# GH 21243/21253
if isinstance(constructor, partial) and constructor.func is Index:
# Index is defined to create CategoricalIndex from categorical data
pytest.skip()
breaks = np.arange(10, dtype="int64")
expected = IntervalIndex.from_breaks(breaks)
cat_breaks = cat_constructor(breaks)
result_kwargs = self.get_kwargs_from_breaks(cat_breaks)
result = constructor(**result_kwargs)
tm.assert_index_equal(result, expected)
def test_generic_errors(self, constructor):
# filler input data to be used when supplying invalid kwargs
filler = self.get_kwargs_from_breaks(range(10))
# invalid closed
msg = "invalid option for 'closed': invalid"
with pytest.raises(ValueError, match=msg):
constructor(closed="invalid", **filler)
# unsupported dtype
msg = "dtype must be an IntervalDtype, got int64"
with pytest.raises(TypeError, match=msg):
constructor(dtype="int64", **filler)
# invalid dtype
msg = "data type [\"']invalid[\"'] not understood"
with pytest.raises(TypeError, match=msg):
constructor(dtype="invalid", **filler)
# no point in nesting periods in an IntervalIndex
periods = period_range("2000-01-01", periods=10)
periods_kwargs = self.get_kwargs_from_breaks(periods)
msg = "Period dtypes are not supported, use a PeriodIndex instead"
with pytest.raises(ValueError, match=msg):
constructor(**periods_kwargs)
# decreasing values
decreasing_kwargs = self.get_kwargs_from_breaks(range(10, -1, -1))
msg = "left side of interval must be <= right side"
with pytest.raises(ValueError, match=msg):
constructor(**decreasing_kwargs)
def test_dt_accessor_api_for_categorical(self):
# https://github.com/pandas-dev/pandas/issues/10661
s_dr = Series(date_range("1/1/2015", periods=5, tz="MET"))
c_dr = s_dr.astype("category")
s_pr = Series(period_range("1/1/2015", freq="D", periods=5))
c_pr = s_pr.astype("category")
s_tdr = Series(timedelta_range("1 days", "10 days"))
c_tdr = s_tdr.astype("category")
# only testing field (like .day)
# and bool (is_month_start)
get_ops = lambda x: x._datetimelike_ops
test_data = [
("Datetime", get_ops(DatetimeIndex), s_dr, c_dr),
("Period", get_ops(PeriodArray), s_pr, c_pr),
("Timedelta", get_ops(TimedeltaIndex), s_tdr, c_tdr),
]
assert isinstance(c_dr.dt, Properties)
special_func_defs = [
("strftime", ("%Y-%m-%d",), {}),
("tz_convert", ("EST",), {}),
("round", ("D",), {}),
("floor", ("D",), {}),
("ceil", ("D",), {}),
("asfreq", ("D",), {}),
# FIXME: don't leave commented-out
# ('tz_localize', ("UTC",), {}),
]
_special_func_names = [f[0] for f in special_func_defs]
# the series is already localized
_ignore_names = ["tz_localize", "components"]
for name, attr_names, s, c in test_data:
func_names = [
f
for f in dir(s.dt)
if not (
f.startswith("_")
or f in attr_names
or f in _special_func_names
or f in _ignore_names
)
]
func_defs = [(f, (), {}) for f in func_names]
for f_def in special_func_defs:
if f_def[0] in dir(s.dt):
func_defs.append(f_def)
for func, args, kwargs in func_defs:
with warnings.catch_warnings():
if func == "to_period":
# dropping TZ
warnings.simplefilter("ignore", UserWarning)
res = getattr(c.dt, func)(*args, **kwargs)
exp = getattr(s.dt, func)(*args, **kwargs)
tm.assert_equal(res, exp)
for attr in attr_names:
if attr in ["week", "weekofyear"]:
# GH#33595 Deprecate week and weekofyear
continue
res = getattr(c.dt, attr)
exp = getattr(s.dt, attr)
if isinstance(res, DataFrame):
tm.assert_frame_equal(res, exp)
elif isinstance(res, Series):
tm.assert_series_equal(res, exp)
else:
tm.assert_almost_equal(res, exp)
invalid = Series([1, 2, 3]).astype("category")
msg = "Can only use .dt accessor with datetimelike"
with pytest.raises(AttributeError, match=msg):
invalid.dt
assert not hasattr(invalid, "str")
)
def test_invalid_nat_setitem_array(arr, non_casting_nats):
msg = (
"value should be a '(Timestamp|Timedelta|Period)', 'NaT', or array of those. "
"Got '(timedelta64|datetime64|int)' instead.")
for nat in non_casting_nats:
with pytest.raises(TypeError, match=msg):
arr[0] = nat
@pytest.mark.parametrize(
"arr",
[
pd.date_range("2000", periods=4).array,
pd.timedelta_range("2000", periods=4).array,
],
)
def test_to_numpy_extra(arr):
arr[0] = NaT
original = arr.copy()
result = arr.to_numpy()
assert np.isnan(result[0])
result = arr.to_numpy(dtype="int64")
assert result[0] == -9223372036854775808
result = arr.to_numpy(dtype="int64", na_value=0)
assert result[0] == 0
class TestSeriesConstructors(TestData):
def test_invalid_dtype(self):
# GH15520
msg = 'not understood'
invalid_list = [pd.Timestamp, 'pd.Timestamp', list]
for dtype in invalid_list:
with tm.assert_raises_regex(TypeError, msg):
Series([], name='time', dtype=dtype)
def test_scalar_conversion(self):
# Pass in scalar is disabled
scalar = Series(0.5)
assert not isinstance(scalar, float)
# Coercion
assert float(Series([1.])) == 1.0
assert int(Series([1.])) == 1
assert long(Series([1.])) == 1
def test_constructor(self):
assert self.ts.index.is_all_dates
# Pass in Series
derived = Series(self.ts)
assert derived.index.is_all_dates
assert tm.equalContents(derived.index, self.ts.index)
# Ensure new index is not created
assert id(self.ts.index) == id(derived.index)
# Mixed type Series
mixed = Series(['hello', np.NaN], index=[0, 1])
assert mixed.dtype == np.object_
assert mixed[1] is np.NaN
assert not self.empty.index.is_all_dates
assert not Series({}).index.is_all_dates
pytest.raises(Exception,
Series,
np.random.randn(3, 3),
index=np.arange(3))
mixed.name = 'Series'
rs = Series(mixed).name
xp = 'Series'
assert rs == xp
# raise on MultiIndex GH4187
m = MultiIndex.from_arrays([[1, 2], [3, 4]])
pytest.raises(NotImplementedError, Series, m)
@pytest.mark.parametrize('input_class', [list, dict, OrderedDict])
def test_constructor_empty(self, input_class):
empty = Series()
empty2 = Series(input_class())
# these are Index() and RangeIndex() which don't compare type equal
# but are just .equals
assert_series_equal(empty, empty2, check_index_type=False)
# With explicit dtype:
empty = Series(dtype='float64')
empty2 = Series(input_class(), dtype='float64')
assert_series_equal(empty, empty2, check_index_type=False)
# GH 18515 : with dtype=category:
empty = Series(dtype='category')
empty2 = Series(input_class(), dtype='category')
assert_series_equal(empty, empty2, check_index_type=False)
if input_class is not list:
# With index:
empty = Series(index=lrange(10))
empty2 = Series(input_class(), index=lrange(10))
assert_series_equal(empty, empty2)
# With index and dtype float64:
empty = Series(np.nan, index=lrange(10))
empty2 = Series(input_class(), index=lrange(10), dtype='float64')
assert_series_equal(empty, empty2)
# GH 19853 : with empty string, index and dtype str
empty = Series('', dtype=str, index=range(3))
empty2 = Series('', index=range(3))
assert_series_equal(empty, empty2)
@pytest.mark.parametrize('input_arg', [np.nan, float('nan')])
def test_constructor_nan(self, input_arg):
empty = Series(dtype='float64', index=lrange(10))
empty2 = Series(input_arg, index=lrange(10))
assert_series_equal(empty, empty2, check_index_type=False)
@pytest.mark.parametrize('dtype', [
'f8',
'i8',
'M8[ns]',
'm8[ns]',
'category',
'object',
'datetime64[ns, UTC]',
])
@pytest.mark.parametrize('index', [None, pd.Index([])])
def test_constructor_dtype_only(self, dtype, index):
# GH-20865
result = pd.Series(dtype=dtype, index=index)
assert result.dtype == dtype
assert len(result) == 0
def test_constructor_no_data_index_order(self):
result = pd.Series(index=['b', 'a', 'c'])
assert result.index.tolist() == ['b', 'a', 'c']
def test_constructor_dtype_str_na_values(self, string_dtype):
# https://github.com/pandas-dev/pandas/issues/21083
ser = Series(['x', None], dtype=string_dtype)
result = ser.isna()
expected = Series([False, True])
tm.assert_series_equal(result, expected)
assert ser.iloc[1] is None
ser = Series(['x', np.nan], dtype=string_dtype)
assert np.isnan(ser.iloc[1])
def test_constructor_series(self):
index1 = ['d', 'b', 'a', 'c']
index2 = sorted(index1)
s1 = Series([4, 7, -5, 3], index=index1)
s2 = Series(s1, index=index2)
assert_series_equal(s2, s1.sort_index())
def test_constructor_iterator(self):
expected = Series(list(range(10)), dtype='int64')
result = Series(range(10), dtype='int64')
assert_series_equal(result, expected)
def test_constructor_list_like(self):
# make sure that we are coercing different
# list-likes to standard dtypes and not
# platform specific
expected = Series([1, 2, 3], dtype='int64')
for obj in [[1, 2, 3], (1, 2, 3), np.array([1, 2, 3], dtype='int64')]:
result = Series(obj, index=[0, 1, 2])
assert_series_equal(result, expected)
@pytest.mark.parametrize('input_vals', [
([1, 2]),
(['1', '2']),
(list(pd.date_range('1/1/2011', periods=2, freq='H'))),
(list(pd.date_range('1/1/2011', periods=2, freq='H',
tz='US/Eastern'))),
([pd.Interval(left=0, right=5)]),
])
def test_constructor_list_str(self, input_vals, string_dtype):
# GH 16605
# Ensure that data elements from a list are converted to strings
# when dtype is str, 'str', or 'U'
result = Series(input_vals, dtype=string_dtype)
expected = Series(input_vals).astype(string_dtype)
assert_series_equal(result, expected)
def test_constructor_list_str_na(self, string_dtype):
result = Series([1.0, 2.0, np.nan], dtype=string_dtype)
expected = Series(['1.0', '2.0', np.nan], dtype=object)
assert_series_equal(result, expected)
assert np.isnan(result[2])
def test_constructor_generator(self):
gen = (i for i in range(10))
result = Series(gen)
exp = Series(lrange(10))
assert_series_equal(result, exp)
gen = (i for i in range(10))
result = Series(gen, index=lrange(10, 20))
exp.index = lrange(10, 20)
assert_series_equal(result, exp)
def test_constructor_map(self):
# GH8909
m = map(lambda x: x, range(10))
result = Series(m)
exp = Series(lrange(10))
assert_series_equal(result, exp)
m = map(lambda x: x, range(10))
result = Series(m, index=lrange(10, 20))
exp.index = lrange(10, 20)
assert_series_equal(result, exp)
def test_constructor_categorical(self):
cat = pd.Categorical([0, 1, 2, 0, 1, 2], ['a', 'b', 'c'],
fastpath=True)
res = Series(cat)
tm.assert_categorical_equal(res.values, cat)
# GH12574
pytest.raises(ValueError,
lambda: Series(pd.Categorical([1, 2, 3]), dtype='int64'))
cat = Series(pd.Categorical([1, 2, 3]), dtype='category')
assert is_categorical_dtype(cat)
assert is_categorical_dtype(cat.dtype)
s = Series([1, 2, 3], dtype='category')
assert is_categorical_dtype(s)
assert is_categorical_dtype(s.dtype)
def test_constructor_categorical_with_coercion(self):
factor = Categorical(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
# test basic creation / coercion of categoricals
s = Series(factor, name='A')
assert s.dtype == 'category'
assert len(s) == len(factor)
str(s.values)
str(s)
# in a frame
df = DataFrame({'A': factor})
result = df['A']
tm.assert_series_equal(result, s)
result = df.iloc[:, 0]
tm.assert_series_equal(result, s)
assert len(df) == len(factor)
str(df.values)
str(df)
df = DataFrame({'A': s})
result = df['A']
tm.assert_series_equal(result, s)
assert len(df) == len(factor)
str(df.values)
str(df)
# multiples
df = DataFrame({'A': s, 'B': s, 'C': 1})
result1 = df['A']
result2 = df['B']
tm.assert_series_equal(result1, s)
tm.assert_series_equal(result2, s, check_names=False)
assert result2.name == 'B'
assert len(df) == len(factor)
str(df.values)
str(df)
# GH8623
x = DataFrame(
[[1, 'John P. Doe'], [2, 'Jane Dove'], [1, 'John P. Doe']],
columns=['person_id', 'person_name'])
x['person_name'] = Categorical(
x.person_name) # doing this breaks transform
expected = x.iloc[0].person_name
result = x.person_name.iloc[0]
assert result == expected
result = x.person_name[0]
assert result == expected
result = x.person_name.loc[0]
assert result == expected
def test_constructor_categorical_dtype(self):
result = pd.Series(['a', 'b'],
dtype=CategoricalDtype(['a', 'b', 'c'],
ordered=True))
assert is_categorical_dtype(result) is True
tm.assert_index_equal(result.cat.categories, pd.Index(['a', 'b', 'c']))
assert result.cat.ordered
result = pd.Series(['a', 'b'], dtype=CategoricalDtype(['b', 'a']))
assert is_categorical_dtype(result)
tm.assert_index_equal(result.cat.categories, pd.Index(['b', 'a']))
assert result.cat.ordered is False
# GH 19565 - Check broadcasting of scalar with Categorical dtype
result = Series('a',
index=[0, 1],
dtype=CategoricalDtype(['a', 'b'], ordered=True))
expected = Series(['a', 'a'],
index=[0, 1],
dtype=CategoricalDtype(['a', 'b'], ordered=True))
tm.assert_series_equal(result, expected, check_categorical=True)
def test_categorical_sideeffects_free(self):
# Passing a categorical to a Series and then changing values in either
# the series or the categorical should not change the values in the
# other one, IF you specify copy!
cat = Categorical(["a", "b", "c", "a"])
s = Series(cat, copy=True)
assert s.cat is not cat
s.cat.categories = [1, 2, 3]
exp_s = np.array([1, 2, 3, 1], dtype=np.int64)
exp_cat = np.array(["a", "b", "c", "a"], dtype=np.object_)
tm.assert_numpy_array_equal(s.__array__(), exp_s)
tm.assert_numpy_array_equal(cat.__array__(), exp_cat)
# setting
s[0] = 2
exp_s2 = np.array([2, 2, 3, 1], dtype=np.int64)
tm.assert_numpy_array_equal(s.__array__(), exp_s2)
tm.assert_numpy_array_equal(cat.__array__(), exp_cat)
# however, copy is False by default
# so this WILL change values
cat = Categorical(["a", "b", "c", "a"])
s = Series(cat)
assert s.values is cat
s.cat.categories = [1, 2, 3]
exp_s = np.array([1, 2, 3, 1], dtype=np.int64)
tm.assert_numpy_array_equal(s.__array__(), exp_s)
tm.assert_numpy_array_equal(cat.__array__(), exp_s)
s[0] = 2
exp_s2 = np.array([2, 2, 3, 1], dtype=np.int64)
tm.assert_numpy_array_equal(s.__array__(), exp_s2)
tm.assert_numpy_array_equal(cat.__array__(), exp_s2)
def test_unordered_compare_equal(self):
left = pd.Series(['a', 'b', 'c'], dtype=CategoricalDtype(['a', 'b']))
right = pd.Series(
pd.Categorical(['a', 'b', np.nan], categories=['a', 'b']))
tm.assert_series_equal(left, right)
def test_constructor_maskedarray(self):
data = ma.masked_all((3, ), dtype=float)
result = Series(data)
expected = Series([nan, nan, nan])
assert_series_equal(result, expected)
data[0] = 0.0
data[2] = 2.0
index = ['a', 'b', 'c']
result = Series(data, index=index)
expected = Series([0.0, nan, 2.0], index=index)
assert_series_equal(result, expected)
data[1] = 1.0
result = Series(data, index=index)
expected = Series([0.0, 1.0, 2.0], index=index)
assert_series_equal(result, expected)
data = ma.masked_all((3, ), dtype=int)
result = Series(data)
expected = Series([nan, nan, nan], dtype=float)
assert_series_equal(result, expected)
data[0] = 0
data[2] = 2
index = ['a', 'b', 'c']
result = Series(data, index=index)
expected = Series([0, nan, 2], index=index, dtype=float)
assert_series_equal(result, expected)
data[1] = 1
result = Series(data, index=index)
expected = Series([0, 1, 2], index=index, dtype=int)
assert_series_equal(result, expected)
data = ma.masked_all((3, ), dtype=bool)
result = Series(data)
expected = Series([nan, nan, nan], dtype=object)
assert_series_equal(result, expected)
data[0] = True
data[2] = False
index = ['a', 'b', 'c']
result = Series(data, index=index)
expected = Series([True, nan, False], index=index, dtype=object)
assert_series_equal(result, expected)
data[1] = True
result = Series(data, index=index)
expected = Series([True, True, False], index=index, dtype=bool)
assert_series_equal(result, expected)
data = ma.masked_all((3, ), dtype='M8[ns]')
result = Series(data)
expected = Series([iNaT, iNaT, iNaT], dtype='M8[ns]')
assert_series_equal(result, expected)
data[0] = datetime(2001, 1, 1)
data[2] = datetime(2001, 1, 3)
index = ['a', 'b', 'c']
result = Series(data, index=index)
expected = Series([datetime(2001, 1, 1), iNaT,
datetime(2001, 1, 3)],
index=index,
dtype='M8[ns]')
assert_series_equal(result, expected)
data[1] = datetime(2001, 1, 2)
result = Series(data, index=index)
expected = Series(
[datetime(2001, 1, 1),
datetime(2001, 1, 2),
datetime(2001, 1, 3)],
index=index,
dtype='M8[ns]')
assert_series_equal(result, expected)
def test_series_ctor_plus_datetimeindex(self):
rng = date_range('20090415', '20090519', freq='B')
data = {k: 1 for k in rng}
result = Series(data, index=rng)
assert result.index is rng
def test_constructor_default_index(self):
s = Series([0, 1, 2])
tm.assert_index_equal(s.index, pd.Index(np.arange(3)))
@pytest.mark.parametrize('input', [[1, 2, 3], (1, 2, 3),
list(range(3)),
pd.Categorical(['a', 'b', 'a']),
(i for i in range(3)),
map(lambda x: x, range(3))])
def test_constructor_index_mismatch(self, input):
# GH 19342
# test that construction of a Series with an index of different length
# raises an error
msg = 'Length of passed values is 3, index implies 4'
with pytest.raises(ValueError, message=msg):
Series(input, index=np.arange(4))
def test_constructor_numpy_scalar(self):
# GH 19342
# construction with a numpy scalar
# should not raise
result = Series(np.array(100), index=np.arange(4), dtype='int64')
expected = Series(100, index=np.arange(4), dtype='int64')
tm.assert_series_equal(result, expected)
def test_constructor_broadcast_list(self):
# GH 19342
# construction with single-element container and index
# should raise
pytest.raises(ValueError, Series, ['foo'], index=['a', 'b', 'c'])
def test_constructor_corner(self):
df = tm.makeTimeDataFrame()
objs = [df, df]
s = Series(objs, index=[0, 1])
assert isinstance(s, Series)
def test_constructor_sanitize(self):
s = Series(np.array([1., 1., 8.]), dtype='i8')
assert s.dtype == np.dtype('i8')
s = Series(np.array([1., 1., np.nan]), copy=True, dtype='i8')
assert s.dtype == np.dtype('f8')
def test_constructor_copy(self):
# GH15125
# test dtype parameter has no side effects on copy=True
for data in [[1.], np.array([1.])]:
x = Series(data)
y = pd.Series(x, copy=True, dtype=float)
# copy=True maintains original data in Series
tm.assert_series_equal(x, y)
# changes to origin of copy does not affect the copy
x[0] = 2.
assert not x.equals(y)
assert x[0] == 2.
assert y[0] == 1.
@pytest.mark.parametrize("index", [
pd.date_range('20170101', periods=3, tz='US/Eastern'),
pd.date_range('20170101', periods=3),
pd.timedelta_range('1 day', periods=3),
pd.period_range('2012Q1', periods=3, freq='Q'),
pd.Index(list('abc')),
pd.Int64Index([1, 2, 3]),
pd.RangeIndex(0, 3)
],
ids=lambda x: type(x).__name__)
def test_constructor_limit_copies(self, index):
# GH 17449
# limit copies of input
s = pd.Series(index)
# we make 1 copy; this is just a smoke test here
assert s._data.blocks[0].values is not index
def test_constructor_pass_none(self):
s = Series(None, index=lrange(5))
assert s.dtype == np.float64
s = Series(None, index=lrange(5), dtype=object)
assert s.dtype == np.object_
# GH 7431
# inference on the index
s = Series(index=np.array([None]))
expected = Series(index=Index([None]))
assert_series_equal(s, expected)
def test_constructor_pass_nan_nat(self):
# GH 13467
exp = Series([np.nan, np.nan], dtype=np.float64)
assert exp.dtype == np.float64
tm.assert_series_equal(Series([np.nan, np.nan]), exp)
tm.assert_series_equal(Series(np.array([np.nan, np.nan])), exp)
exp = Series([pd.NaT, pd.NaT])
assert exp.dtype == 'datetime64[ns]'
tm.assert_series_equal(Series([pd.NaT, pd.NaT]), exp)
tm.assert_series_equal(Series(np.array([pd.NaT, pd.NaT])), exp)
tm.assert_series_equal(Series([pd.NaT, np.nan]), exp)
tm.assert_series_equal(Series(np.array([pd.NaT, np.nan])), exp)
tm.assert_series_equal(Series([np.nan, pd.NaT]), exp)
tm.assert_series_equal(Series(np.array([np.nan, pd.NaT])), exp)
def test_constructor_cast(self):
pytest.raises(ValueError, Series, ['a', 'b', 'c'], dtype=float)
def test_constructor_dtype_nocast(self):
# 1572
s = Series([1, 2, 3])
s2 = Series(s, dtype=np.int64)
s2[1] = 5
assert s[1] == 5
def test_constructor_datelike_coercion(self):
# GH 9477
# incorrectly inferring on dateimelike looking when object dtype is
# specified
s = Series([Timestamp('20130101'), 'NOV'], dtype=object)
assert s.iloc[0] == Timestamp('20130101')
assert s.iloc[1] == 'NOV'
assert s.dtype == object
# the dtype was being reset on the slicing and re-inferred to datetime
# even thought the blocks are mixed
belly = '216 3T19'.split()
wing1 = '2T15 4H19'.split()
wing2 = '416 4T20'.split()
mat = pd.to_datetime('2016-01-22 2019-09-07'.split())
df = pd.DataFrame({
'wing1': wing1,
'wing2': wing2,
'mat': mat
},
index=belly)
result = df.loc['3T19']
assert result.dtype == object
result = df.loc['216']
assert result.dtype == object
def test_constructor_datetimes_with_nulls(self):
# gh-15869
for arr in [
np.array([None, None, None, None,
datetime.now(), None]),
np.array([None, None, datetime.now(), None])
]:
result = Series(arr)
assert result.dtype == 'M8[ns]'
def test_constructor_dtype_datetime64(self):
s = Series(iNaT, dtype='M8[ns]', index=lrange(5))
assert isna(s).all()
# in theory this should be all nulls, but since
# we are not specifying a dtype is ambiguous
s = Series(iNaT, index=lrange(5))
assert not isna(s).all()
s = Series(nan, dtype='M8[ns]', index=lrange(5))
assert isna(s).all()
s = Series([datetime(2001, 1, 2, 0, 0), iNaT], dtype='M8[ns]')
assert isna(s[1])
assert s.dtype == 'M8[ns]'
s = Series([datetime(2001, 1, 2, 0, 0), nan], dtype='M8[ns]')
assert isna(s[1])
assert s.dtype == 'M8[ns]'
# GH3416
dates = [
np.datetime64(datetime(2013, 1, 1)),
np.datetime64(datetime(2013, 1, 2)),
np.datetime64(datetime(2013, 1, 3)),
]
s = Series(dates)
assert s.dtype == 'M8[ns]'
s.iloc[0] = np.nan
assert s.dtype == 'M8[ns]'
# GH3414 related
pytest.raises(
TypeError, lambda x: Series(Series(dates).astype('int') / 1000000,
dtype='M8[ms]'))
pytest.raises(TypeError, lambda x: Series(dates, dtype='datetime64'))
# invalid dates can be help as object
result = Series([datetime(2, 1, 1)])
assert result[0] == datetime(2, 1, 1, 0, 0)
result = Series([datetime(3000, 1, 1)])
assert result[0] == datetime(3000, 1, 1, 0, 0)
# don't mix types
result = Series([Timestamp('20130101'), 1], index=['a', 'b'])
assert result['a'] == Timestamp('20130101')
assert result['b'] == 1
# GH6529
# coerce datetime64 non-ns properly
dates = date_range('01-Jan-2015', '01-Dec-2015', freq='M')
values2 = dates.view(np.ndarray).astype('datetime64[ns]')
expected = Series(values2, index=dates)
for dtype in ['s', 'D', 'ms', 'us', 'ns']:
values1 = dates.view(np.ndarray).astype('M8[{0}]'.format(dtype))
result = Series(values1, dates)
assert_series_equal(result, expected)
# GH 13876
# coerce to non-ns to object properly
expected = Series(values2, index=dates, dtype=object)
for dtype in ['s', 'D', 'ms', 'us', 'ns']:
values1 = dates.view(np.ndarray).astype('M8[{0}]'.format(dtype))
result = Series(values1, index=dates, dtype=object)
assert_series_equal(result, expected)
# leave datetime.date alone
dates2 = np.array([d.date() for d in dates.to_pydatetime()],
dtype=object)
series1 = Series(dates2, dates)
tm.assert_numpy_array_equal(series1.values, dates2)
assert series1.dtype == object
# these will correctly infer a datetime
s = Series([None, pd.NaT, '2013-08-05 15:30:00.000001'])
assert s.dtype == 'datetime64[ns]'
s = Series([np.nan, pd.NaT, '2013-08-05 15:30:00.000001'])
assert s.dtype == 'datetime64[ns]'
s = Series([pd.NaT, None, '2013-08-05 15:30:00.000001'])
assert s.dtype == 'datetime64[ns]'
s = Series([pd.NaT, np.nan, '2013-08-05 15:30:00.000001'])
assert s.dtype == 'datetime64[ns]'
# tz-aware (UTC and other tz's)
# GH 8411
dr = date_range('20130101', periods=3)
assert Series(dr).iloc[0].tz is None
dr = date_range('20130101', periods=3, tz='UTC')
assert str(Series(dr).iloc[0].tz) == 'UTC'
dr = date_range('20130101', periods=3, tz='US/Eastern')
assert str(Series(dr).iloc[0].tz) == 'US/Eastern'
# non-convertible
s = Series([1479596223000, -1479590, pd.NaT])
assert s.dtype == 'object'
assert s[2] is pd.NaT
assert 'NaT' in str(s)
# if we passed a NaT it remains
s = Series([datetime(2010, 1, 1), datetime(2, 1, 1), pd.NaT])
assert s.dtype == 'object'
assert s[2] is pd.NaT
assert 'NaT' in str(s)
# if we passed a nan it remains
s = Series([datetime(2010, 1, 1), datetime(2, 1, 1), np.nan])
assert s.dtype == 'object'
assert s[2] is np.nan
assert 'NaN' in str(s)
def test_constructor_with_datetime_tz(self):
# 8260
# support datetime64 with tz
dr = date_range('20130101', periods=3, tz='US/Eastern')
s = Series(dr)
assert s.dtype.name == 'datetime64[ns, US/Eastern]'
assert s.dtype == 'datetime64[ns, US/Eastern]'
assert is_datetime64tz_dtype(s.dtype)
assert 'datetime64[ns, US/Eastern]' in str(s)
# export
result = s.values
assert isinstance(result, np.ndarray)
assert result.dtype == 'datetime64[ns]'
exp = pd.DatetimeIndex(result)
exp = exp.tz_localize('UTC').tz_convert(tz=s.dt.tz)
tm.assert_index_equal(dr, exp)
# indexing
result = s.iloc[0]
assert result == Timestamp('2013-01-01 00:00:00-0500',
tz='US/Eastern',
freq='D')
result = s[0]
assert result == Timestamp('2013-01-01 00:00:00-0500',
tz='US/Eastern',
freq='D')
result = s[Series([True, True, False], index=s.index)]
assert_series_equal(result, s[0:2])
result = s.iloc[0:1]
assert_series_equal(result, Series(dr[0:1]))
# concat
result = pd.concat([s.iloc[0:1], s.iloc[1:]])
assert_series_equal(result, s)
# short str
assert 'datetime64[ns, US/Eastern]' in str(s)
# formatting with NaT
result = s.shift()
assert 'datetime64[ns, US/Eastern]' in str(result)
assert 'NaT' in str(result)
# long str
t = Series(date_range('20130101', periods=1000, tz='US/Eastern'))
assert 'datetime64[ns, US/Eastern]' in str(t)
result = pd.DatetimeIndex(s, freq='infer')
tm.assert_index_equal(result, dr)
# inference
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Pacific')
])
assert s.dtype == 'datetime64[ns, US/Pacific]'
assert lib.infer_dtype(s) == 'datetime64'
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Eastern')
])
assert s.dtype == 'object'
assert lib.infer_dtype(s) == 'datetime'
# with all NaT
s = Series(pd.NaT, index=[0, 1], dtype='datetime64[ns, US/Eastern]')
expected = Series(pd.DatetimeIndex(['NaT', 'NaT'], tz='US/Eastern'))
assert_series_equal(s, expected)
@pytest.mark.parametrize("arr_dtype", [np.int64, np.float64])
@pytest.mark.parametrize("dtype", ["M8", "m8"])
@pytest.mark.parametrize("unit", ['ns', 'us', 'ms', 's', 'h', 'm', 'D'])
def test_construction_to_datetimelike_unit(self, arr_dtype, dtype, unit):
# tests all units
# gh-19223
dtype = "{}[{}]".format(dtype, unit)
arr = np.array([1, 2, 3], dtype=arr_dtype)
s = Series(arr)
result = s.astype(dtype)
expected = Series(arr.astype(dtype))
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize('arg',
['2013-01-01 00:00:00', pd.NaT, np.nan, None])
def test_constructor_with_naive_string_and_datetimetz_dtype(self, arg):
# GH 17415: With naive string
result = Series([arg], dtype='datetime64[ns, CET]')
expected = Series(pd.Timestamp(arg)).dt.tz_localize('CET')
assert_series_equal(result, expected)
def test_construction_interval(self):
# construction from interval & array of intervals
index = IntervalIndex.from_breaks(np.arange(3), closed='right')
result = Series(index)
repr(result)
str(result)
tm.assert_index_equal(Index(result.values), index)
result = Series(index.values)
tm.assert_index_equal(Index(result.values), index)
def test_construction_consistency(self):
# make sure that we are not re-localizing upon construction
# GH 14928
s = Series(pd.date_range('20130101', periods=3, tz='US/Eastern'))
result = Series(s, dtype=s.dtype)
tm.assert_series_equal(result, s)
result = Series(s.dt.tz_convert('UTC'), dtype=s.dtype)
tm.assert_series_equal(result, s)
result = Series(s.values, dtype=s.dtype)
tm.assert_series_equal(result, s)
def test_constructor_periodindex(self):
# GH7932
# converting a PeriodIndex when put in a Series
pi = period_range('20130101', periods=5, freq='D')
s = Series(pi)
expected = Series(pi.astype(object))
assert_series_equal(s, expected)
assert s.dtype == 'object'
def test_constructor_dict(self):
d = {'a': 0., 'b': 1., 'c': 2.}
result = Series(d, index=['b', 'c', 'd', 'a'])
expected = Series([1, 2, nan, 0], index=['b', 'c', 'd', 'a'])
assert_series_equal(result, expected)
pidx = tm.makePeriodIndex(100)
d = {pidx[0]: 0, pidx[1]: 1}
result = Series(d, index=pidx)
expected = Series(np.nan, pidx)
expected.iloc[0] = 0
expected.iloc[1] = 1
assert_series_equal(result, expected)
def test_constructor_dict_order(self):
# GH19018
# initialization ordering: by insertion order if python>= 3.6, else
# order by value
d = {'b': 1, 'a': 0, 'c': 2}
result = Series(d)
if PY36:
expected = Series([1, 0, 2], index=list('bac'))
else:
expected = Series([0, 1, 2], index=list('abc'))
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("value", [2, np.nan, None, float('nan')])
def test_constructor_dict_nan_key(self, value):
# GH 18480
d = {1: 'a', value: 'b', float('nan'): 'c', 4: 'd'}
result = Series(d).sort_values()
expected = Series(['a', 'b', 'c', 'd'], index=[1, value, np.nan, 4])
assert_series_equal(result, expected)
# MultiIndex:
d = {(1, 1): 'a', (2, np.nan): 'b', (3, value): 'c'}
result = Series(d).sort_values()
expected = Series(['a', 'b', 'c'],
index=Index([(1, 1), (2, np.nan), (3, value)]))
assert_series_equal(result, expected)
def test_constructor_dict_datetime64_index(self):
# GH 9456
dates_as_str = ['1984-02-19', '1988-11-06', '1989-12-03', '1990-03-15']
values = [42544017.198965244, 1234565, 40512335.181958228, -1]
def create_data(constructor):
return dict(zip((constructor(x) for x in dates_as_str), values))
data_datetime64 = create_data(np.datetime64)
data_datetime = create_data(lambda x: datetime.strptime(x, '%Y-%m-%d'))
data_Timestamp = create_data(Timestamp)
expected = Series(values, (Timestamp(x) for x in dates_as_str))
result_datetime64 = Series(data_datetime64)
result_datetime = Series(data_datetime)
result_Timestamp = Series(data_Timestamp)
assert_series_equal(result_datetime64, expected)
assert_series_equal(result_datetime, expected)
assert_series_equal(result_Timestamp, expected)
def test_constructor_list_of_tuples(self):
data = [(1, 1), (2, 2), (2, 3)]
s = Series(data)
assert list(s) == data
def test_constructor_tuple_of_tuples(self):
data = ((1, 1), (2, 2), (2, 3))
s = Series(data)
assert tuple(s) == data
def test_constructor_dict_of_tuples(self):
data = {(1, 2): 3, (None, 5): 6}
result = Series(data).sort_values()
expected = Series([3, 6],
index=MultiIndex.from_tuples([(1, 2), (None, 5)]))
tm.assert_series_equal(result, expected)
def test_constructor_set(self):
values = set([1, 2, 3, 4, 5])
pytest.raises(TypeError, Series, values)
values = frozenset(values)
pytest.raises(TypeError, Series, values)
def test_fromDict(self):
data = {'a': 0, 'b': 1, 'c': 2, 'd': 3}
series = Series(data)
assert tm.is_sorted(series.index)
data = {'a': 0, 'b': '1', 'c': '2', 'd': datetime.now()}
series = Series(data)
assert series.dtype == np.object_
data = {'a': 0, 'b': '1', 'c': '2', 'd': '3'}
series = Series(data)
assert series.dtype == np.object_
data = {'a': '0', 'b': '1'}
series = Series(data, dtype=float)
assert series.dtype == np.float64
def test_fromValue(self):
nans = Series(np.NaN, index=self.ts.index)
assert nans.dtype == np.float_
assert len(nans) == len(self.ts)
strings = Series('foo', index=self.ts.index)
assert strings.dtype == np.object_
assert len(strings) == len(self.ts)
d = datetime.now()
dates = Series(d, index=self.ts.index)
assert dates.dtype == 'M8[ns]'
assert len(dates) == len(self.ts)
# GH12336
# POJO.Test construction of categorical series from value
categorical = Series(0, index=self.ts.index, dtype="category")
expected = Series(0, index=self.ts.index).astype("category")
assert categorical.dtype == 'category'
assert len(categorical) == len(self.ts)
tm.assert_series_equal(categorical, expected)
def test_constructor_dtype_timedelta64(self):
# basic
td = Series([timedelta(days=i) for i in range(3)])
assert td.dtype == 'timedelta64[ns]'
td = Series([timedelta(days=1)])
assert td.dtype == 'timedelta64[ns]'
td = Series(
[timedelta(days=1),
timedelta(days=2),
np.timedelta64(1, 's')])
assert td.dtype == 'timedelta64[ns]'
# mixed with NaT
td = Series([timedelta(days=1), NaT], dtype='m8[ns]')
assert td.dtype == 'timedelta64[ns]'
td = Series([timedelta(days=1), np.nan], dtype='m8[ns]')
assert td.dtype == 'timedelta64[ns]'
td = Series([np.timedelta64(300000000), pd.NaT], dtype='m8[ns]')
assert td.dtype == 'timedelta64[ns]'
# improved inference
# GH5689
td = Series([np.timedelta64(300000000), NaT])
assert td.dtype == 'timedelta64[ns]'
# because iNaT is int, not coerced to timedelta
td = Series([np.timedelta64(300000000), iNaT])
assert td.dtype == 'object'
td = Series([np.timedelta64(300000000), np.nan])
assert td.dtype == 'timedelta64[ns]'
td = Series([pd.NaT, np.timedelta64(300000000)])
assert td.dtype == 'timedelta64[ns]'
td = Series([np.timedelta64(1, 's')])
assert td.dtype == 'timedelta64[ns]'
# these are frequency conversion astypes
# for t in ['s', 'D', 'us', 'ms']:
# pytest.raises(TypeError, td.astype, 'm8[%s]' % t)
# valid astype
td.astype('int64')
# invalid casting
pytest.raises(TypeError, td.astype, 'int32')
# this is an invalid casting
def f():
Series([timedelta(days=1), 'foo'], dtype='m8[ns]')
pytest.raises(Exception, f)
# leave as object here
td = Series([timedelta(days=i) for i in range(3)] + ['foo'])
assert td.dtype == 'object'
# these will correctly infer a timedelta
s = Series([None, pd.NaT, '1 Day'])
assert s.dtype == 'timedelta64[ns]'
s = Series([np.nan, pd.NaT, '1 Day'])
assert s.dtype == 'timedelta64[ns]'
s = Series([pd.NaT, None, '1 Day'])
assert s.dtype == 'timedelta64[ns]'
s = Series([pd.NaT, np.nan, '1 Day'])
assert s.dtype == 'timedelta64[ns]'
# GH 16406
def test_constructor_mixed_tz(self):
s = Series(
[Timestamp('20130101'),
Timestamp('20130101', tz='US/Eastern')])
expected = Series(
[Timestamp('20130101'),
Timestamp('20130101', tz='US/Eastern')],
dtype='object')
assert_series_equal(s, expected)
def test_NaT_scalar(self):
series = Series([0, 1000, 2000, iNaT], dtype='M8[ns]')
val = series[3]
assert isna(val)
series[2] = val
assert isna(series[2])
def test_NaT_cast(self):
# GH10747
result = Series([np.nan]).astype('M8[ns]')
expected = Series([NaT])
assert_series_equal(result, expected)
def test_constructor_name_hashable(self):
for n in [777, 777., 'name', datetime(2001, 11, 11), (1, ), u"\u05D0"]:
for data in [[1, 2, 3], np.ones(3), {'a': 0, 'b': 1}]:
s = Series(data, name=n)
assert s.name == n
def test_constructor_name_unhashable(self):
for n in [['name_list'], np.ones(2), {1: 2}]:
for data in [['name_list'], np.ones(2), {1: 2}]:
pytest.raises(TypeError, Series, data, name=n)
def test_auto_conversion(self):
series = Series(list(date_range('1/1/2000', periods=10)))
assert series.dtype == 'M8[ns]'
def test_convert_non_ns(self):
# convert from a numpy array of non-ns timedelta64
arr = np.array([1, 2, 3], dtype='timedelta64[s]')
s = Series(arr)
expected = Series(pd.timedelta_range('00:00:01', periods=3, freq='s'))
assert_series_equal(s, expected)
# convert from a numpy array of non-ns datetime64
# note that creating a numpy datetime64 is in LOCAL time!!!!
# seems to work for M8[D], but not for M8[s]
s = Series(
np.array(['2013-01-01', '2013-01-02', '2013-01-03'],
dtype='datetime64[D]'))
assert_series_equal(
s, Series(date_range('20130101', periods=3, freq='D')))
# s = Series(np.array(['2013-01-01 00:00:01','2013-01-01
# 00:00:02','2013-01-01 00:00:03'],dtype='datetime64[s]'))
# assert_series_equal(s,date_range('20130101
# 00:00:01',period=3,freq='s'))
@pytest.mark.parametrize("index", [
date_range('1/1/2000', periods=10),
timedelta_range('1 day', periods=10),
period_range('2000-Q1', periods=10, freq='Q')
],
ids=lambda x: type(x).__name__)
def test_constructor_cant_cast_datetimelike(self, index):
# floats are not ok
msg = "Cannot cast {} to ".format(type(index).__name__)
with tm.assert_raises_regex(TypeError, msg):
Series(index, dtype=float)
# ints are ok
# we test with np.int64 to get similar results on
# windows / 32-bit platforms
result = Series(index, dtype=np.int64)
expected = Series(index.astype(np.int64))
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("index", [
date_range('1/1/2000', periods=10),
timedelta_range('1 day', periods=10),
period_range('2000-Q1', periods=10, freq='Q')
],
ids=lambda x: type(x).__name__)
def test_constructor_cast_object(self, index):
s = Series(index, dtype=object)
exp = Series(index).astype(object)
tm.assert_series_equal(s, exp)
s = Series(pd.Index(index, dtype=object), dtype=object)
exp = Series(index).astype(object)
tm.assert_series_equal(s, exp)
s = Series(index.astype(object), dtype=object)
exp = Series(index).astype(object)
tm.assert_series_equal(s, exp)
def test_constructor_generic_timestamp_deprecated(self):
# see gh-15524
with tm.assert_produces_warning(FutureWarning):
dtype = np.timedelta64
s = Series([], dtype=dtype)
assert s.empty
assert s.dtype == 'm8[ns]'
with tm.assert_produces_warning(FutureWarning):
dtype = np.datetime64
s = Series([], dtype=dtype)
assert s.empty
assert s.dtype == 'M8[ns]'
# These timestamps have the wrong frequencies,
# so an Exception should be raised now.
msg = "cannot convert timedeltalike"
with tm.assert_raises_regex(TypeError, msg):
Series([], dtype='m8[ps]')
msg = "cannot convert datetimelike"
with tm.assert_raises_regex(TypeError, msg):
Series([], dtype='M8[ps]')
@pytest.mark.parametrize('dtype', [None, 'uint8', 'category'])
def test_constructor_range_dtype(self, dtype):
# GH 16804
expected = Series([0, 1, 2, 3, 4], dtype=dtype or 'int64')
result = Series(range(5), dtype=dtype)
tm.assert_series_equal(result, expected)
def test_infer_freq(self, freq):
# GH#11018
idx = pd.timedelta_range('1', freq=freq, periods=10)
result = pd.TimedeltaIndex(idx.asi8, freq='infer')
tm.assert_index_equal(idx, result)
assert result.freq == freq
class TestTableOrientReader:
@pytest.mark.parametrize(
"index_nm",
[
None, "idx",
pytest.param("index", marks=pytest.mark.xfail), "level_0"
],
)
@pytest.mark.parametrize(
"vals",
[
{
"ints": [1, 2, 3, 4]
},
{
"objects": ["a", "b", "c", "d"]
},
{
"objects": ["1", "2", "3", "4"]
},
{
"date_ranges": pd.date_range("2016-01-01", freq="d", periods=4)
},
{
"categoricals": pd.Series(pd.Categorical(["a", "b", "c", "c"]))
},
{
"ordered_cats":
pd.Series(pd.Categorical(["a", "b", "c", "c"], ordered=True))
},
{
"floats": [1.0, 2.0, 3.0, 4.0]
},
{
"floats": [1.1, 2.2, 3.3, 4.4]
},
{
"bools": [True, False, False, True]
},
],
)
def test_read_json_table_orient(self, index_nm, vals, recwarn):
df = DataFrame(vals, index=pd.Index(range(4), name=index_nm))
out = df.to_json(orient="table")
result = pd.read_json(out, orient="table")
tm.assert_frame_equal(df, result)
@pytest.mark.parametrize("index_nm", [None, "idx", "index"])
@pytest.mark.parametrize(
"vals",
[
{
"timedeltas": pd.timedelta_range("1H", periods=4, freq="T")
},
{
"timezones":
pd.date_range(
"2016-01-01", freq="d", periods=4, tz="US/Central")
},
],
)
def test_read_json_table_orient_raises(self, index_nm, vals, recwarn):
df = DataFrame(vals, index=pd.Index(range(4), name=index_nm))
out = df.to_json(orient="table")
with pytest.raises(NotImplementedError, match="can not yet read "):
pd.read_json(out, orient="table")
def test_comprehensive(self):
df = DataFrame(
{
"A": [1, 2, 3, 4],
"B": ["a", "b", "c", "c"],
"C": pd.date_range("2016-01-01", freq="d", periods=4),
# 'D': pd.timedelta_range('1H', periods=4, freq='T'),
"E": pd.Series(pd.Categorical(["a", "b", "c", "c"])),
"F": pd.Series(
pd.Categorical(["a", "b", "c", "c"], ordered=True)),
"G": [1.1, 2.2, 3.3, 4.4],
# 'H': pd.date_range('2016-01-01', freq='d', periods=4,
# tz='US/Central'),
"I": [True, False, False, True],
},
index=pd.Index(range(4), name="idx"),
)
out = df.to_json(orient="table")
result = pd.read_json(out, orient="table")
tm.assert_frame_equal(df, result)
@pytest.mark.parametrize(
"index_names",
[[None, None], ["foo", "bar"], ["foo", None], [None, "foo"],
["index", "foo"]],
)
def test_multiindex(self, index_names):
# GH 18912
df = pd.DataFrame(
[["Arr", "alpha", [1, 2, 3, 4]], ["Bee", "Beta", [10, 20, 30, 40]]
],
index=[["A", "B"], ["Null", "Eins"]],
columns=["Aussprache", "Griechisch", "Args"],
)
df.index.names = index_names
out = df.to_json(orient="table")
result = pd.read_json(out, orient="table")
tm.assert_frame_equal(df, result)
def test_empty_frame_roundtrip(self):
# GH 21287
df = pd.DataFrame(columns=["a", "b", "c"])
expected = df.copy()
out = df.to_json(orient="table")
result = pd.read_json(out, orient="table")
tm.assert_frame_equal(expected, result)
def create_data():
""" create the pickle/msgpack data """
data = {
u'A': [0., 1., 2., 3., np.nan],
u'B': [0, 1, 0, 1, 0],
u'C': [u'foo1', u'foo2', u'foo3', u'foo4', u'foo5'],
u'D': date_range('1/1/2009', periods=5),
u'E': [0., 1, Timestamp('20100101'), u'foo', 2.]
}
scalars = dict(timestamp=Timestamp('20130101'),
period=Period('2012', 'M'))
index = dict(int=Index(np.arange(10)),
date=date_range('20130101', periods=10),
period=period_range('2013-01-01', freq='M', periods=10),
float=Index(np.arange(10, dtype=np.float64)),
uint=Index(np.arange(10, dtype=np.uint64)),
timedelta=timedelta_range('00:00:00', freq='30T', periods=10))
if _loose_version >= LooseVersion('0.18'):
from pandas import RangeIndex
index['range'] = RangeIndex(10)
if _loose_version >= LooseVersion('0.21'):
from pandas import interval_range
index['interval'] = interval_range(0, periods=10)
mi = dict(reg2=MultiIndex.from_tuples(
tuple(zip(*[[u'bar', u'bar', u'baz', u'baz', u'foo',
u'foo', u'qux', u'qux'],
[u'one', u'two', u'one', u'two', u'one',
u'two', u'one', u'two']])),
names=[u'first', u'second']))
series = dict(float=Series(data[u'A']),
int=Series(data[u'B']),
mixed=Series(data[u'E']),
ts=Series(np.arange(10).astype(np.int64),
index=date_range('20130101', periods=10)),
mi=Series(np.arange(5).astype(np.float64),
index=MultiIndex.from_tuples(
tuple(zip(*[[1, 1, 2, 2, 2],
[3, 4, 3, 4, 5]])),
names=[u'one', u'two'])),
dup=Series(np.arange(5).astype(np.float64),
index=[u'A', u'B', u'C', u'D', u'A']),
cat=Series(Categorical([u'foo', u'bar', u'baz'])),
dt=Series(date_range('20130101', periods=5)),
dt_tz=Series(date_range('20130101', periods=5,
tz='US/Eastern')),
period=Series([Period('2000Q1')] * 5))
mixed_dup_df = DataFrame(data)
mixed_dup_df.columns = list(u"ABCDA")
frame = dict(float=DataFrame({u'A': series[u'float'],
u'B': series[u'float'] + 1}),
int=DataFrame({u'A': series[u'int'],
u'B': series[u'int'] + 1}),
mixed=DataFrame({k: data[k]
for k in [u'A', u'B', u'C', u'D']}),
mi=DataFrame({u'A': np.arange(5).astype(np.float64),
u'B': np.arange(5).astype(np.int64)},
index=MultiIndex.from_tuples(
tuple(zip(*[[u'bar', u'bar', u'baz',
u'baz', u'baz'],
[u'one', u'two', u'one',
u'two', u'three']])),
names=[u'first', u'second'])),
dup=DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=[u'A', u'B', u'A']),
cat_onecol=DataFrame({u'A': Categorical([u'foo', u'bar'])}),
cat_and_float=DataFrame({
u'A': Categorical([u'foo', u'bar', u'baz']),
u'B': np.arange(3).astype(np.int64)}),
mixed_dup=mixed_dup_df,
dt_mixed_tzs=DataFrame({
u'A': Timestamp('20130102', tz='US/Eastern'),
u'B': Timestamp('20130603', tz='CET')}, index=range(5)),
dt_mixed2_tzs=DataFrame({
u'A': Timestamp('20130102', tz='US/Eastern'),
u'B': Timestamp('20130603', tz='CET'),
u'C': Timestamp('20130603', tz='UTC')}, index=range(5))
)
with catch_warnings(record=True):
mixed_dup_panel = Panel({u'ItemA': frame[u'float'],
u'ItemB': frame[u'int']})
mixed_dup_panel.items = [u'ItemA', u'ItemA']
panel = dict(float=Panel({u'ItemA': frame[u'float'],
u'ItemB': frame[u'float'] + 1}),
dup=Panel(
np.arange(30).reshape(3, 5, 2).astype(np.float64),
items=[u'A', u'B', u'A']),
mixed_dup=mixed_dup_panel)
cat = dict(int8=Categorical(list('abcdefg')),
int16=Categorical(np.arange(1000)),
int32=Categorical(np.arange(10000)))
timestamp = dict(normal=Timestamp('2011-01-01'),
nat=NaT,
tz=Timestamp('2011-01-01', tz='US/Eastern'))
if _loose_version < LooseVersion('0.19.2'):
timestamp['freq'] = Timestamp('2011-01-01', offset='D')
timestamp['both'] = Timestamp('2011-01-01', tz='Asia/Tokyo',
offset='M')
else:
timestamp['freq'] = Timestamp('2011-01-01', freq='D')
timestamp['both'] = Timestamp('2011-01-01', tz='Asia/Tokyo',
freq='M')
off = {'DateOffset': DateOffset(years=1),
'DateOffset_h_ns': DateOffset(hour=6, nanoseconds=5824),
'BusinessDay': BusinessDay(offset=timedelta(seconds=9)),
'BusinessHour': BusinessHour(normalize=True, n=6, end='15:14'),
'CustomBusinessDay': CustomBusinessDay(weekmask='Mon Fri'),
'SemiMonthBegin': SemiMonthBegin(day_of_month=9),
'SemiMonthEnd': SemiMonthEnd(day_of_month=24),
'MonthBegin': MonthBegin(1),
'MonthEnd': MonthEnd(1),
'QuarterBegin': QuarterBegin(1),
'QuarterEnd': QuarterEnd(1),
'Day': Day(1),
'YearBegin': YearBegin(1),
'YearEnd': YearEnd(1),
'Week': Week(1),
'Week_Tues': Week(2, normalize=False, weekday=1),
'WeekOfMonth': WeekOfMonth(week=3, weekday=4),
'LastWeekOfMonth': LastWeekOfMonth(n=1, weekday=3),
'FY5253': FY5253(n=2, weekday=6, startingMonth=7, variation="last"),
'Easter': Easter(),
'Hour': Hour(1),
'Minute': Minute(1)}
return dict(series=series,
frame=frame,
panel=panel,
index=index,
scalars=scalars,
mi=mi,
sp_series=dict(float=_create_sp_series(),
ts=_create_sp_tsseries()),
sp_frame=dict(float=_create_sp_frame()),
cat=cat,
timestamp=timestamp,
offsets=off)
def test_timedelta_methods(method):
s = pd.Series(pd.timedelta_range("2000", periods=4))
s.attrs = {"a": 1}
result = method(s.dt)
assert result.attrs == {"a": 1}
def test_linspace_behavior(self, periods, freq):
# GH 20976
result = timedelta_range(start="0 days", end="4 days", periods=periods)
expected = timedelta_range(start="0 days", end="4 days", freq=freq)
tm.assert_index_equal(result, expected)
def test_constructor_timedelta64_values_mismatched_dtype(self):
# check we don't silently ignore the dtype keyword
tdi = timedelta_range("4 Days", periods=5)
result = Index(tdi, dtype="category")
expected = CategoricalIndex(tdi)
tm.assert_index_equal(result, expected)