def test_is_non_overlapping_monotonic(self):
# Should be True in all cases
tpls = [(0, 1), (2, 3), (4, 5), (6, 7)]
for closed in ('left', 'right', 'neither', 'both'):
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is True
idx = IntervalIndex.from_tuples(reversed(tpls), 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)]
for closed in ('left', 'right', 'neither', 'both'):
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(reversed(tpls), 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)]
for closed in ('left', 'right', 'neither', 'both'):
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(reversed(tpls), closed=closed)
assert idx.is_non_overlapping_monotonic is False
# Should be False for closed='both', overwise True (GH16560)
idx = IntervalIndex.from_breaks(range(4), closed='both')
assert idx.is_non_overlapping_monotonic is False
for closed in ('left', 'right', 'neither'):
idx = IntervalIndex.from_breaks(range(4), closed=closed)
assert idx.is_non_overlapping_monotonic is True
def test_constructors_errors_string(self, data):
# GH 19016
left, right = data[:-1], data[1:]
tuples = lzip(left, right)
ivs = [Interval(l, r) for l, r in tuples] or data
msg = ('category, object, and string subtypes are not supported '
'for IntervalIndex')
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex(ivs)
with tm.assert_raises_regex(TypeError, msg):
Index(ivs)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_intervals(ivs)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_breaks(data)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_arrays(left, right)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_tuples(tuples)
def slice_locs_cases(self, breaks):
# TODO: same tests for more index types
index = IntervalIndex.from_breaks([0, 1, 2], closed='right')
self.assertEqual(index.slice_locs(), (0, 2))
self.assertEqual(index.slice_locs(0, 1), (0, 1))
self.assertEqual(index.slice_locs(1, 1), (0, 1))
self.assertEqual(index.slice_locs(0, 2), (0, 2))
self.assertEqual(index.slice_locs(0.5, 1.5), (0, 2))
self.assertEqual(index.slice_locs(0, 0.5), (0, 1))
self.assertEqual(index.slice_locs(start=1), (0, 2))
self.assertEqual(index.slice_locs(start=1.2), (1, 2))
self.assertEqual(index.slice_locs(end=1), (0, 1))
self.assertEqual(index.slice_locs(end=1.1), (0, 2))
self.assertEqual(index.slice_locs(end=1.0), (0, 1))
self.assertEqual(*index.slice_locs(-1, -1))
index = IntervalIndex.from_breaks([0, 1, 2], closed='neither')
self.assertEqual(index.slice_locs(0, 1), (0, 1))
self.assertEqual(index.slice_locs(0, 2), (0, 2))
self.assertEqual(index.slice_locs(0.5, 1.5), (0, 2))
self.assertEqual(index.slice_locs(1, 1), (1, 1))
self.assertEqual(index.slice_locs(1, 2), (1, 2))
index = IntervalIndex.from_breaks([0, 1, 2], closed='both')
self.assertEqual(index.slice_locs(1, 1), (0, 2))
self.assertEqual(index.slice_locs(1, 2), (0, 2))
def test_constructors_errors(self):
# scalar
with pytest.raises(TypeError):
IntervalIndex(5)
# not an interval
with pytest.raises(TypeError):
IntervalIndex([0, 1])
with pytest.raises(TypeError):
IntervalIndex.from_intervals([0, 1])
# invalid closed
with pytest.raises(ValueError):
IntervalIndex.from_arrays([0, 1], [1, 2], closed='invalid')
# mismatched closed
with pytest.raises(ValueError):
IntervalIndex.from_intervals([Interval(0, 1),
Interval(1, 2, closed='left')])
with pytest.raises(ValueError):
IntervalIndex.from_arrays([0, 10], [3, 5])
with pytest.raises(ValueError):
Index([Interval(0, 1), Interval(2, 3, closed='left')])
# no point in nesting periods in an IntervalIndex
with pytest.raises(ValueError):
IntervalIndex.from_breaks(
pd.period_range('2000-01-01', periods=3))
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
def test_constructor_errors(self):
# GH 19016: categorical data
data = Categorical(list('01234abcde'), ordered=True)
msg = ('category, object, and string subtypes are not supported '
'for IntervalIndex')
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_breaks(data)
def slice_locs_cases(self, breaks):
# TODO: same tests for more index types
index = IntervalIndex.from_breaks([0, 1, 2], closed='right')
assert index.slice_locs() == (0, 2)
assert index.slice_locs(0, 1) == (0, 1)
assert index.slice_locs(1, 1) == (0, 1)
assert index.slice_locs(0, 2) == (0, 2)
assert index.slice_locs(0.5, 1.5) == (0, 2)
assert index.slice_locs(0, 0.5) == (0, 1)
assert index.slice_locs(start=1) == (0, 2)
assert index.slice_locs(start=1.2) == (1, 2)
assert index.slice_locs(end=1) == (0, 1)
assert index.slice_locs(end=1.1) == (0, 2)
assert index.slice_locs(end=1.0) == (0, 1)
assert index.slice_locs(-1, -1) == (0, 0)
index = IntervalIndex.from_breaks([0, 1, 2], closed='neither')
assert index.slice_locs(0, 1) == (0, 1)
assert index.slice_locs(0, 2) == (0, 2)
assert index.slice_locs(0.5, 1.5) == (0, 2)
assert index.slice_locs(1, 1) == (1, 1)
assert index.slice_locs(1, 2) == (1, 2)
index = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)],
closed='both')
assert index.slice_locs(1, 1) == (0, 1)
assert index.slice_locs(1, 2) == (0, 2)
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)
def test_constructors(self):
expected = self.index
actual = IntervalIndex.from_breaks(np.arange(3), closed='right')
self.assertTrue(expected.equals(actual))
alternate = IntervalIndex.from_breaks(np.arange(3), closed='left')
self.assertFalse(expected.equals(alternate))
actual = IntervalIndex.from_intervals([Interval(0, 1), Interval(1, 2)])
self.assertTrue(expected.equals(actual))
actual = IntervalIndex([Interval(0, 1), Interval(1, 2)])
self.assertTrue(expected.equals(actual))
actual = IntervalIndex.from_arrays(np.arange(2), np.arange(2) + 1,
closed='right')
self.assertTrue(expected.equals(actual))
actual = Index([Interval(0, 1), Interval(1, 2)])
assert isinstance(actual, IntervalIndex)
self.assertTrue(expected.equals(actual))
actual = Index(expected)
assert isinstance(actual, IntervalIndex)
self.assertTrue(expected.equals(actual))
def test_constructors(self, data, closed, name):
left, right = data[:-1], data[1:]
ivs = [Interval(l, r, closed=closed) for l, r in lzip(left, right)]
expected = IntervalIndex._simple_new(
left=left, right=right, closed=closed, name=name)
# validate expected
assert expected.closed == closed
assert expected.name == name
assert expected.dtype.subtype == data.dtype
tm.assert_index_equal(expected.left, data[:-1])
tm.assert_index_equal(expected.right, data[1:])
# validated constructors
result = IntervalIndex(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_breaks(data, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_arrays(
left, right, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
lzip(left, right), closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = Index(ivs, name=name)
assert isinstance(result, IntervalIndex)
tm.assert_index_equal(result, expected)
# idempotent
tm.assert_index_equal(Index(expected), expected)
tm.assert_index_equal(IntervalIndex(expected), expected)
result = IntervalIndex.from_intervals(expected)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(
expected.values, name=expected.name)
tm.assert_index_equal(result, expected)
left, right = expected.left, expected.right
result = IntervalIndex.from_arrays(
left, right, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
expected.to_tuples(), closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
breaks = expected.left.tolist() + [expected.right[-1]]
result = IntervalIndex.from_breaks(
breaks, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
def test_intersection(self):
other = IntervalIndex.from_breaks([1, 2, 3])
expected = IntervalIndex.from_breaks([1, 2])
actual = self.index.intersection(other)
self.assertTrue(expected.equals(actual))
tm.assert_index_equal(self.index.intersection(self.index),
self.index)
def test_intersection(self, closed):
idx = self.create_index(closed=closed)
other = IntervalIndex.from_breaks([1, 2, 3], closed=closed)
expected = IntervalIndex.from_breaks([1, 2], closed=closed)
actual = idx.intersection(other)
assert expected.equals(actual)
tm.assert_index_equal(idx.intersection(idx), idx)
def setup(self, N):
left = np.append(np.arange(N), np.array(0))
right = np.append(np.arange(1, N + 1), np.array(1))
self.intv = IntervalIndex.from_arrays(left, right)
self.intv._engine
self.left = IntervalIndex.from_breaks(np.arange(N))
self.right = IntervalIndex.from_breaks(np.arange(N - 3, 2 * N - 3))
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True)
ex_levels = IntervalIndex.from_breaks([-1e-3, 0.25, 0.5, 0.75, 1])
tm.assert_index_equal(result.categories, ex_levels)
result, bins = cut(arr, 4, retbins=True, right=False)
ex_levels = IntervalIndex.from_breaks([0, 0.25, 0.5, 0.75, 1 + 1e-3],
closed='left')
tm.assert_index_equal(result.categories, ex_levels)
def test_basic_dtype(self):
assert is_interval_dtype('interval[int64]')
assert is_interval_dtype(IntervalIndex.from_tuples([(0, 1)]))
assert is_interval_dtype(IntervalIndex.from_breaks(np.arange(4)))
assert is_interval_dtype(IntervalIndex.from_breaks(
date_range('20130101', periods=3)))
assert not is_interval_dtype('U')
assert not is_interval_dtype('S')
assert not is_interval_dtype('foo')
assert not is_interval_dtype(np.object_)
assert not is_interval_dtype(np.int64)
assert not is_interval_dtype(np.float64)
def test_constructors_datetimelike(self, closed):
# DTI / TDI
for idx in [pd.date_range('20130101', periods=5),
pd.timedelta_range('1 day', periods=5)]:
result = IntervalIndex.from_breaks(idx, closed=closed)
expected = IntervalIndex.from_breaks(idx.values, closed=closed)
tm.assert_index_equal(result, expected)
expected_scalar_type = type(idx[0])
i = result[0]
assert isinstance(i.left, expected_scalar_type)
assert isinstance(i.right, expected_scalar_type)
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
expected = Series(IntervalIndex.from_breaks(
[-0.003, 1.5, 3], closed='right').repeat(2)).astype(
CDT(ordered=True))
tm.assert_series_equal(result, expected)
result, bins = qcut(s, 2, retbins=True)
expected = Series(IntervalIndex.from_breaks(
[-0.001, 1.5, 3], closed='right').repeat(2)).astype(
CDT(ordered=True))
tm.assert_series_equal(result, expected)
def test_constructors(self, closed, name):
left, right = Index([0, 1, 2, 3]), Index([1, 2, 3, 4])
ivs = [Interval(l, r, closed=closed) for l, r in zip(left, right)]
expected = IntervalIndex._simple_new(
left=left, right=right, closed=closed, name=name)
result = IntervalIndex(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_breaks(
np.arange(5), closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_arrays(
left.values, right.values, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
zip(left, right), closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = Index(ivs, name=name)
assert isinstance(result, IntervalIndex)
tm.assert_index_equal(result, expected)
# idempotent
tm.assert_index_equal(Index(expected), expected)
tm.assert_index_equal(IntervalIndex(expected), expected)
result = IntervalIndex.from_intervals(
expected.values, name=expected.name)
tm.assert_index_equal(result, expected)
left, right = expected.left, expected.right
result = IntervalIndex.from_arrays(
left, right, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
expected.to_tuples(), closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
breaks = expected.left.tolist() + [expected.right[-1]]
result = IntervalIndex.from_breaks(
breaks, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
def _format_labels(bins, precision, right=True,
include_lowest=False, dtype=None):
""" based on the dtype, return our labels """
closed = 'right' if right else 'left'
if is_datetime64_dtype(dtype):
formatter = Timestamp
adjust = lambda x: x - Timedelta('1ns')
elif is_timedelta64_dtype(dtype):
formatter = Timedelta
adjust = lambda x: x - Timedelta('1ns')
else:
precision = _infer_precision(precision, bins)
formatter = lambda x: _round_frac(x, precision)
adjust = lambda x: x - 10 ** (-precision)
breaks = [formatter(b) for b in bins]
labels = IntervalIndex.from_breaks(breaks, closed=closed)
if right and include_lowest:
# we will adjust the left hand side by precision to
# account that we are all right closed
v = adjust(labels[0].left)
i = IntervalIndex.from_intervals(
[Interval(v, labels[0].right, closed='right')])
labels = i.append(labels[1:])
return labels
def test_constructors_nan(self, closed, data):
# GH 18421
expected_values = np.array(data, dtype=object)
expected_idx = IntervalIndex(data, closed=closed)
# validate the expected index
assert expected_idx.closed == closed
tm.assert_numpy_array_equal(expected_idx.values, expected_values)
result = IntervalIndex.from_tuples(data, closed=closed)
tm.assert_index_equal(result, expected_idx)
tm.assert_numpy_array_equal(result.values, expected_values)
result = IntervalIndex.from_breaks([np.nan] + data, closed=closed)
tm.assert_index_equal(result, expected_idx)
tm.assert_numpy_array_equal(result.values, expected_values)
result = IntervalIndex.from_arrays(data, data, closed=closed)
tm.assert_index_equal(result, expected_idx)
tm.assert_numpy_array_equal(result.values, expected_values)
if closed == 'right':
# Can't specify closed for IntervalIndex.from_intervals
result = IntervalIndex.from_intervals(data)
tm.assert_index_equal(result, expected_idx)
tm.assert_numpy_array_equal(result.values, expected_values)
def test_constructors_empty(self, data, closed):
# GH 18421
expected_dtype = getattr(data, 'dtype', np.int64)
expected_values = np.array([], dtype=object)
expected_index = IntervalIndex(data, closed=closed)
# validate the expected index
assert expected_index.empty
assert expected_index.closed == closed
assert expected_index.dtype.subtype == expected_dtype
tm.assert_numpy_array_equal(expected_index.values, expected_values)
result = IntervalIndex.from_tuples(data, closed=closed)
tm.assert_index_equal(result, expected_index)
tm.assert_numpy_array_equal(result.values, expected_values)
result = IntervalIndex.from_breaks(data, closed=closed)
tm.assert_index_equal(result, expected_index)
tm.assert_numpy_array_equal(result.values, expected_values)
result = IntervalIndex.from_arrays(data, data, closed=closed)
tm.assert_index_equal(result, expected_index)
tm.assert_numpy_array_equal(result.values, expected_values)
if closed == 'right':
# Can't specify closed for IntervalIndex.from_intervals
result = IntervalIndex.from_intervals(data)
tm.assert_index_equal(result, expected_index)
tm.assert_numpy_array_equal(result.values, expected_values)
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_constructors_errors_tz(self, tz_left, tz_right):
# GH 18537
left = date_range('2017-01-01', periods=4, tz=tz_left)
right = date_range('2017-01-02', periods=4, tz=tz_right)
# don't need to check IntervalIndex(...) or from_intervals, since
# mixed tz are disallowed at the Interval level
with pytest.raises(ValueError):
IntervalIndex.from_arrays(left, right)
with pytest.raises(ValueError):
IntervalIndex.from_tuples(lzip(left, right))
with pytest.raises(ValueError):
breaks = left.tolist() + [right[-1]]
IntervalIndex.from_breaks(breaks)
def test_label_precision(self):
arr = np.arange(0, 0.73, 0.01)
result = cut(arr, 4, precision=2)
ex_levels = IntervalIndex.from_breaks([-0.00072, 0.18, 0.36,
0.54, 0.72])
tm.assert_index_equal(result.categories, ex_levels)
def test_constructor_timestamp(self, closed, name, freq, periods, tz):
start, end = Timestamp('20180101', tz=tz), Timestamp('20181231', tz=tz)
breaks = date_range(start=start, end=end, freq=freq)
expected = IntervalIndex.from_breaks(breaks, name=name, closed=closed)
# defined from start/end/freq
result = interval_range(
start=start, end=end, freq=freq, name=name, closed=closed)
tm.assert_index_equal(result, expected)
# defined from start/periods/freq
result = interval_range(
start=start, periods=periods, freq=freq, name=name, closed=closed)
tm.assert_index_equal(result, expected)
# defined from end/periods/freq
result = interval_range(
end=end, periods=periods, freq=freq, name=name, closed=closed)
tm.assert_index_equal(result, expected)
# GH 20976: linspace behavior defined from start/end/periods
if not breaks.freq.isAnchored() and tz is None:
# matches expected only for non-anchored offsets and tz naive
# (anchored/DST transitions cause unequal spacing in expected)
result = interval_range(start=start, end=end, periods=periods,
name=name, closed=closed)
tm.assert_index_equal(result, expected)
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
def test_insert(self):
expected = IntervalIndex.from_breaks(range(4))
actual = self.index.insert(2, Interval(2, 3))
assert expected.equals(actual)
pytest.raises(ValueError, self.index.insert, 0, 1)
pytest.raises(ValueError, self.index.insert, 0,
Interval(2, 3, closed='left'))
def test_series_ret_bins():
# see gh-8589
ser = Series(np.arange(4))
result, bins = cut(ser, 2, retbins=True)
expected = Series(IntervalIndex.from_breaks(
[-0.003, 1.5, 3], closed="right").repeat(2)).astype(CDT(ordered=True))
tm.assert_series_equal(result, expected)
def test_cut_return_intervals(self):
s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
res = cut(s, 3)
exp_bins = np.linspace(0, 8, num=4).round(3)
exp_bins[0] -= 0.008
exp = Series(IntervalIndex.from_breaks(exp_bins, closed='right').take(
[0, 0, 0, 1, 1, 1, 2, 2, 2])).astype(CDT(ordered=True))
tm.assert_series_equal(res, exp)
def test_constructors_errors(self):
# scalar
msg = ('IntervalIndex(...) must be called with a collection of '
'some kind, 5 was passed')
with pytest.raises(TypeError, message=msg):
IntervalIndex(5)
# not an interval
msg = "type <class 'numpy.int32'> with value 0 is not an interval"
with pytest.raises(TypeError, message=msg):
IntervalIndex([0, 1])
with pytest.raises(TypeError, message=msg):
IntervalIndex.from_intervals([0, 1])
# invalid closed
msg = "invalid options for 'closed': invalid"
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_arrays([0, 1], [1, 2], closed='invalid')
# mismatched closed
msg = 'intervals must all be closed on the same side'
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_intervals([Interval(0, 1),
Interval(1, 2, closed='left')])
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_arrays([0, 10], [3, 5])
with pytest.raises(ValueError, message=msg):
Index([Interval(0, 1), Interval(2, 3, closed='left')])
# no point in nesting periods in an IntervalIndex
msg = 'Period dtypes are not supported, use a PeriodIndex instead'
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_breaks(
pd.period_range('2000-01-01', periods=3))
# decreasing breaks/arrays
msg = 'left side of interval must be <= right side'
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_breaks(range(10, -1, -1))
with pytest.raises(ValueError, message=msg):
IntervalIndex.from_arrays(range(10, -1, -1), range(9, -2, -1))
def test_value_counts_bins(self):
klasses = [Index, Series]
for klass in klasses:
s_values = ['a', 'b', 'b', 'b', 'b', 'c', 'd', 'd', 'a', 'a']
s = klass(s_values)
# bins
pytest.raises(TypeError, lambda bins: s.value_counts(bins=bins), 1)
s1 = Series([1, 1, 2, 3])
res1 = s1.value_counts(bins=1)
exp1 = Series({Interval(0.997, 3.0): 4})
tm.assert_series_equal(res1, exp1)
res1n = s1.value_counts(bins=1, normalize=True)
exp1n = Series({Interval(0.997, 3.0): 1.0})
tm.assert_series_equal(res1n, exp1n)
if isinstance(s1, Index):
tm.assert_index_equal(s1.unique(), Index([1, 2, 3]))
else:
exp = np.array([1, 2, 3], dtype=np.int64)
tm.assert_numpy_array_equal(s1.unique(), exp)
assert s1.nunique() == 3
# these return the same
res4 = s1.value_counts(bins=4, dropna=True)
intervals = IntervalIndex.from_breaks([0.997, 1.5, 2.0, 2.5, 3.0])
exp4 = Series([2, 1, 1, 0], index=intervals.take([0, 3, 1, 2]))
tm.assert_series_equal(res4, exp4)
res4 = s1.value_counts(bins=4, dropna=False)
intervals = IntervalIndex.from_breaks([0.997, 1.5, 2.0, 2.5, 3.0])
exp4 = Series([2, 1, 1, 0], index=intervals.take([0, 3, 1, 2]))
tm.assert_series_equal(res4, exp4)
res4n = s1.value_counts(bins=4, normalize=True)
exp4n = Series([0.5, 0.25, 0.25, 0],
index=intervals.take([0, 3, 1, 2]))
tm.assert_series_equal(res4n, exp4n)
# handle NA's properly
s_values = [
'a', 'b', 'b', 'b', np.nan, np.nan, 'd', 'd', 'a', 'a', 'b'
]
s = klass(s_values)
expected = Series([4, 3, 2], index=['b', 'a', 'd'])
tm.assert_series_equal(s.value_counts(), expected)
if isinstance(s, Index):
exp = Index(['a', 'b', np.nan, 'd'])
tm.assert_index_equal(s.unique(), exp)
else:
exp = np.array(['a', 'b', np.nan, 'd'], dtype=object)
tm.assert_numpy_array_equal(s.unique(), exp)
assert s.nunique() == 3
s = klass({})
expected = Series([], dtype=np.int64)
tm.assert_series_equal(s.value_counts(),
expected,
check_index_type=False)
# returned dtype differs depending on original
if isinstance(s, Index):
tm.assert_index_equal(s.unique(), Index([]), exact=False)
else:
tm.assert_numpy_array_equal(s.unique(),
np.array([]),
check_dtype=False)
assert s.nunique() == 0
def test_length_one(self):
"""breaks of length one produce an empty IntervalIndex"""
breaks = [0]
result = IntervalIndex.from_breaks(breaks)
expected = IntervalIndex.from_breaks([])
tm.assert_index_equal(result, expected)
def test_repr_matches():
idx = IntervalIndex.from_breaks([1, 2, 3])
a = repr(idx)
b = repr(idx.values)
assert a.replace("Index", "Array") == b
def test_left_right_dont_share_data(self):
# GH#36310
breaks = np.arange(5)
result = IntervalIndex.from_breaks(breaks)._data
assert result._left.base is None or result._left.base is not result._right.base
def test_label_precision():
arr = np.arange(0, 0.73, 0.01)
result = cut(arr, 4, precision=2)
ex_levels = IntervalIndex.from_breaks([-0.00072, 0.18, 0.36, 0.54, 0.72])
tm.assert_index_equal(result.categories, ex_levels)
def makeIntervalIndex(k=10, name=None, **kwargs):
"""make a length k IntervalIndex"""
x = np.linspace(0, 100, num=(k + 1))
return IntervalIndex.from_breaks(x, name=name, **kwargs)
def monotonic_index(start, end, dtype="int64", inclusive="right"):
return IntervalIndex.from_breaks(np.arange(start, end, dtype=dtype),
inclusive=inclusive)
def test_interval_can_hold_element_emptylist(self, dtype, element):
arr = np.array([1, 3, 4], dtype=dtype)
ii = IntervalIndex.from_breaks(arr)
blk = new_block(ii._data, [1], ndim=2)
assert blk._can_hold_element([])
def create_index(self, *, inclusive="right"):
return IntervalIndex.from_breaks(range(11), inclusive=inclusive)
def test_delete(self):
expected = IntervalIndex.from_breaks([1, 2])
actual = self.index.delete(0)
self.assertTrue(expected.equals(actual))
def create_index(self):
return IntervalIndex.from_breaks(np.arange(10))
def test_set_operation_errors(self):
pytest.raises(ValueError, self.index.union, self.index.left)
other = IntervalIndex.from_breaks([0, 1, 2], closed='neither')
pytest.raises(ValueError, self.index.union, other)
def test_construction(self):
result = interval_range(0, 5, name='foo', closed='both')
expected = IntervalIndex.from_breaks(np.arange(0, 5),
name='foo',
closed='both')
tm.assert_index_equal(result, expected)
def setup_cache(self):
idx = IntervalIndex.from_breaks(np.arange(1000001))
monotonic = Series(np.arange(1000000), index=idx)
return monotonic
def test_value_counts_bins(index_or_series):
klass = index_or_series
s_values = ["a", "b", "b", "b", "b", "c", "d", "d", "a", "a"]
s = klass(s_values)
# bins
msg = "bins argument only works with numeric data"
with pytest.raises(TypeError, match=msg):
s.value_counts(bins=1)
s1 = Series([1, 1, 2, 3])
res1 = s1.value_counts(bins=1)
exp1 = Series({Interval(0.997, 3.0): 4})
tm.assert_series_equal(res1, exp1)
res1n = s1.value_counts(bins=1, normalize=True)
exp1n = Series({Interval(0.997, 3.0): 1.0})
tm.assert_series_equal(res1n, exp1n)
if isinstance(s1, Index):
tm.assert_index_equal(s1.unique(), Index([1, 2, 3]))
else:
exp = np.array([1, 2, 3], dtype=np.int64)
tm.assert_numpy_array_equal(s1.unique(), exp)
assert s1.nunique() == 3
# these return the same
res4 = s1.value_counts(bins=4, dropna=True)
intervals = IntervalIndex.from_breaks([0.997, 1.5, 2.0, 2.5, 3.0])
exp4 = Series([2, 1, 1, 0], index=intervals.take([0, 1, 3, 2]))
tm.assert_series_equal(res4, exp4)
res4 = s1.value_counts(bins=4, dropna=False)
intervals = IntervalIndex.from_breaks([0.997, 1.5, 2.0, 2.5, 3.0])
exp4 = Series([2, 1, 1, 0], index=intervals.take([0, 1, 3, 2]))
tm.assert_series_equal(res4, exp4)
res4n = s1.value_counts(bins=4, normalize=True)
exp4n = Series([0.5, 0.25, 0.25, 0], index=intervals.take([0, 1, 3, 2]))
tm.assert_series_equal(res4n, exp4n)
# handle NA's properly
s_values = ["a", "b", "b", "b", np.nan, np.nan, "d", "d", "a", "a", "b"]
s = klass(s_values)
expected = Series([4, 3, 2], index=["b", "a", "d"])
tm.assert_series_equal(s.value_counts(), expected)
if isinstance(s, Index):
exp = Index(["a", "b", np.nan, "d"])
tm.assert_index_equal(s.unique(), exp)
else:
exp = np.array(["a", "b", np.nan, "d"], dtype=object)
tm.assert_numpy_array_equal(s.unique(), exp)
assert s.nunique() == 3
s = klass({}) if klass is dict else klass({}, dtype=object)
expected = Series([], dtype=np.int64)
tm.assert_series_equal(s.value_counts(), expected, check_index_type=False)
# returned dtype differs depending on original
if isinstance(s, Index):
tm.assert_index_equal(s.unique(), Index([]), exact=False)
else:
tm.assert_numpy_array_equal(s.unique(), np.array([]), check_dtype=False)
assert s.nunique() == 0
def test_constructors_errors(self):
# scalar
msg = (r'IntervalIndex\(...\) must be called with a collection of '
'some kind, 5 was passed')
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex(5)
# not an interval
msg = ("type <(class|type) 'numpy.int64'> with value 0 "
"is not an interval")
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex([0, 1])
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_intervals([0, 1])
# invalid closed
msg = "invalid options for 'closed': invalid"
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex.from_arrays([0, 1], [1, 2], closed='invalid')
# mismatched closed within intervals
msg = 'intervals must all be closed on the same side'
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex.from_intervals([Interval(0, 1),
Interval(1, 2, closed='left')])
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex([Interval(0, 1), Interval(2, 3, closed='left')])
with tm.assert_raises_regex(ValueError, msg):
Index([Interval(0, 1), Interval(2, 3, closed='left')])
# mismatched closed inferred from intervals vs constructor.
msg = 'conflicting values for closed'
with tm.assert_raises_regex(ValueError, msg):
iv = [Interval(0, 1, closed='both'), Interval(1, 2, closed='both')]
IntervalIndex(iv, closed='neither')
# no point in nesting periods in an IntervalIndex
msg = 'Period dtypes are not supported, use a PeriodIndex instead'
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex.from_breaks(
pd.period_range('2000-01-01', periods=3))
# decreasing breaks/arrays
msg = 'left side of interval must be <= right side'
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex.from_breaks(range(10, -1, -1))
with tm.assert_raises_regex(ValueError, msg):
IntervalIndex.from_arrays(range(10, -1, -1), range(9, -2, -1))
# GH 19016: categorical data
data = Categorical(list('01234abcde'), ordered=True)
msg = ('category, object, and string subtypes are not supported '
'for IntervalIndex')
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_breaks(data)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_arrays(data[:-1], data[1:])
def test_constructor_interval_values_mismatched_dtype(self):
dti = date_range("2016-01-01", periods=3)
ii = IntervalIndex.from_breaks(dti)
result = Index(ii, dtype="category")
expected = CategoricalIndex(ii)
tm.assert_index_equal(result, expected)
def series_with_interval_index(self):
return Series(np.arange(5), IntervalIndex.from_breaks(np.arange(6)))
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 = "|".join([
"not supported between instances of 'int' and '.*.Interval'",
r"Invalid comparison between dtype=interval\[int64\] and ",
])
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_linspace_dst_transition(self, start, mid, end):
# GH 20976: linspace behavior defined from start/end/periods
# accounts for the hour gained/lost during DST transition
result = interval_range(start=start, end=end, periods=2)
expected = IntervalIndex.from_breaks([start, mid, end])
tm.assert_index_equal(result, expected)
def setup_method(self, method):
self.s = Series(np.arange(5), IntervalIndex.from_breaks(np.arange(6)))
def create_index(self, closed="right"):
return IntervalIndex.from_breaks(range(11), closed=closed)
def monotonic_index(start, end, dtype="int64", closed="right"):
return IntervalIndex.from_breaks(np.arange(start, end, dtype=dtype),
closed=closed)
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)
class TestClassConstructors(ConstructorTests):
"""Tests specific to the IntervalIndex/Index constructors"""
@pytest.fixture(
params=[IntervalIndex, partial(Index, dtype="interval")],
ids=["IntervalIndex", "Index"],
)
def constructor(self, request):
return request.param
def get_kwargs_from_breaks(self, breaks, closed="right"):
"""
converts intervals in breaks format to a dictionary of kwargs to
specific to the format expected by the IntervalIndex/Index constructors
"""
if len(breaks) == 0:
return {"data": breaks}
ivs = [
Interval(left, right, closed) if notna(left) else left
for left, right in zip(breaks[:-1], breaks[1:])
]
if isinstance(breaks, list):
return {"data": ivs}
elif is_categorical_dtype(breaks):
return {"data": breaks._constructor(ivs)}
return {"data": np.array(ivs, dtype=object)}
def test_generic_errors(self, constructor):
"""
override the base class implementation since errors are handled
differently; checks unnecessary since caught at the Interval level
"""
pass
def test_constructor_string(self):
# GH23013
# When forming the interval from breaks,
# the interval of strings is already forbidden.
pass
def test_constructor_errors(self, constructor):
# mismatched closed within intervals with no constructor override
ivs = [Interval(0, 1, closed="right"), Interval(2, 3, closed="left")]
msg = "intervals must all be closed on the same side"
with pytest.raises(ValueError, match=msg):
constructor(ivs)
# scalar
msg = (
r"IntervalIndex\(...\) must be called with a collection of "
"some kind, 5 was passed"
)
with pytest.raises(TypeError, match=msg):
constructor(5)
# not an interval; dtype depends on 32bit/windows builds
msg = "type <class 'numpy.int(32|64)'> with value 0 is not an interval"
with pytest.raises(TypeError, match=msg):
constructor([0, 1])
@pytest.mark.filterwarnings("ignore:Passing keywords other:FutureWarning")
@pytest.mark.parametrize(
"data, closed",
[
([], "both"),
([np.nan, np.nan], "neither"),
(
[Interval(0, 3, closed="neither"), Interval(2, 5, closed="neither")],
"left",
),
(
[Interval(0, 3, closed="left"), Interval(2, 5, closed="right")],
"neither",
),
(IntervalIndex.from_breaks(range(5), closed="both"), "right"),
],
)
def test_override_inferred_closed(self, constructor, data, closed):
# GH 19370
if isinstance(data, IntervalIndex):
tuples = data.to_tuples()
else:
tuples = [(iv.left, iv.right) if notna(iv) else iv for iv in data]
expected = IntervalIndex.from_tuples(tuples, closed=closed)
result = constructor(data, closed=closed)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
"values_constructor", [list, np.array, IntervalIndex, IntervalArray]
)
def test_index_object_dtype(self, values_constructor):
# Index(intervals, dtype=object) is an Index (not an IntervalIndex)
intervals = [Interval(0, 1), Interval(1, 2), Interval(2, 3)]
values = values_constructor(intervals)
result = Index(values, dtype=object)
assert type(result) is Index
tm.assert_numpy_array_equal(result.values, np.array(values))
def test_index_mixed_closed(self):
# GH27172
intervals = [
Interval(0, 1, closed="left"),
Interval(1, 2, closed="right"),
Interval(2, 3, closed="neither"),
Interval(3, 4, closed="both"),
]
result = Index(intervals)
expected = Index(intervals, dtype=object)
tm.assert_index_equal(result, expected)
class TestClassConstructors(Base):
"""Tests specific to the IntervalIndex/Index constructors"""
@pytest.fixture(params=[IntervalIndex,
partial(Index, dtype='interval')],
ids=['IntervalIndex', 'Index'])
def constructor(self, request):
return request.param
def get_kwargs_from_breaks(self, breaks, closed='right'):
"""
converts intervals in breaks format to a dictionary of kwargs to
specific to the format expected by the IntervalIndex/Index constructors
"""
if len(breaks) == 0:
return {'data': breaks}
ivs = [
Interval(l, r, closed) if notna(l) else l
for l, r in zip(breaks[:-1], breaks[1:])
]
if isinstance(breaks, list):
return {'data': ivs}
elif is_categorical_dtype(breaks):
return {'data': breaks._constructor(ivs)}
return {'data': np.array(ivs, dtype=object)}
def test_generic_errors(self, constructor):
"""
override the base class implementation since errors are handled
differently; checks unnecessary since caught at the Interval level
"""
pass
def test_constructor_string(self):
# GH23013
# When forming the interval from breaks,
# the interval of strings is already forbidden.
pass
def test_constructor_errors(self, constructor):
# mismatched closed within intervals with no constructor override
ivs = [Interval(0, 1, closed='right'), Interval(2, 3, closed='left')]
msg = 'intervals must all be closed on the same side'
with pytest.raises(ValueError, match=msg):
constructor(ivs)
# scalar
msg = (r'IntervalIndex\(...\) must be called with a collection of '
'some kind, 5 was passed')
with pytest.raises(TypeError, match=msg):
constructor(5)
# not an interval
msg = "type <class 'numpy.int64'> with value 0 is not an interval"
with pytest.raises(TypeError, match=msg):
constructor([0, 1])
@pytest.mark.parametrize(
'data, closed',
[([], 'both'), ([np.nan, np.nan], 'neither'),
([Interval(0, 3, closed='neither'),
Interval(2, 5, closed='neither')], 'left'),
([Interval(0, 3, closed='left'),
Interval(2, 5, closed='right')], 'neither'),
(IntervalIndex.from_breaks(range(5), closed='both'), 'right')])
def test_override_inferred_closed(self, constructor, data, closed):
# GH 19370
if isinstance(data, IntervalIndex):
tuples = data.to_tuples()
else:
tuples = [(iv.left, iv.right) if notna(iv) else iv for iv in data]
expected = IntervalIndex.from_tuples(tuples, closed=closed)
result = constructor(data, closed=closed)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('values_constructor',
[list, np.array, IntervalIndex, IntervalArray])
def test_index_object_dtype(self, values_constructor):
# Index(intervals, dtype=object) is an Index (not an IntervalIndex)
intervals = [Interval(0, 1), Interval(1, 2), Interval(2, 3)]
values = values_constructor(intervals)
result = Index(values, dtype=object)
assert type(result) is Index
tm.assert_numpy_array_equal(result.values, np.array(values))
def obj(self):
idx = IntervalIndex.from_breaks(range(4))
return Series(idx)
def test_labels(right, breaks, closed):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True, right=right)
ex_levels = IntervalIndex.from_breaks(breaks, closed=closed)
tm.assert_index_equal(result.categories, ex_levels)
def test_contains_interval(self, item, expected):
# GH 23705
ci = CategoricalIndex(IntervalIndex.from_breaks(range(3)))
result = item in ci
assert result is expected
def test_constructors(self, data, closed, name):
left, right = data[:-1], data[1:]
ivs = [Interval(l, r, closed=closed) for l, r in lzip(left, right)]
expected = IntervalIndex._simple_new(left=left,
right=right,
closed=closed,
name=name)
# validate expected
assert expected.closed == closed
assert expected.name == name
assert expected.dtype.subtype == data.dtype
tm.assert_index_equal(expected.left, data[:-1])
tm.assert_index_equal(expected.right, data[1:])
# validated constructors
result = IntervalIndex(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_breaks(data, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_arrays(left,
right,
closed=closed,
name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(lzip(left, right),
closed=closed,
name=name)
tm.assert_index_equal(result, expected)
result = Index(ivs, name=name)
assert isinstance(result, IntervalIndex)
tm.assert_index_equal(result, expected)
# idempotent
tm.assert_index_equal(Index(expected), expected)
tm.assert_index_equal(IntervalIndex(expected), expected)
result = IntervalIndex.from_intervals(expected)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(expected.values,
name=expected.name)
tm.assert_index_equal(result, expected)
left, right = expected.left, expected.right
result = IntervalIndex.from_arrays(left,
right,
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(expected.to_tuples(),
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
breaks = expected.left.tolist() + [expected.right[-1]]
result = IntervalIndex.from_breaks(breaks,
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
