def test_take_preserve_name(self):
index = RangeIndex(1, 5, name='foo')
taken = index.take([3, 0, 1])
self.assertEqual(index.name, taken.name)
def test_intersection(self, sort):
# intersect with Int64Index
other = Index(np.arange(1, 6))
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(self.index, sort=sort)
expected = Index(
np.sort(np.asarray(np.intersect1d(self.index.values,
other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
# reversed (GH 17296)
result = other.intersection(self.index, sort=sort)
tm.assert_index_equal(result, expected)
# GH 17296: intersect two decreasing RangeIndexes
first = RangeIndex(10, -2, -2)
other = RangeIndex(5, -4, -1)
expected = first.astype(int).intersection(other.astype(int), sort=sort)
result = first.intersection(other, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
# reversed
result = other.intersection(first, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name='asdf')
assert idx.name == idx[1:].name
def create_index(self):
return RangeIndex(5)
def test_get_indexer_backfill(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='backfill')
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_constructor(self):
index = RangeIndex(5)
expected = np.arange(5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 5
assert index._step == 1
assert index.name is None
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5)
expected = np.arange(1, 5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 1
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5, 2)
expected = np.arange(1, 5, 2, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._step == 2
tm.assert_index_equal(Index(expected), index)
msg = "RangeIndex\\(\\.\\.\\.\\) must be called with integers"
with tm.assert_raises_regex(TypeError, msg):
RangeIndex()
for index in [RangeIndex(0), RangeIndex(start=0), RangeIndex(stop=0),
RangeIndex(0, 0)]:
expected = np.empty(0, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 0
assert index._step == 1
tm.assert_index_equal(Index(expected), index)
with tm.assert_raises_regex(TypeError, msg):
RangeIndex(name='Foo')
for index in [RangeIndex(0, name='Foo'),
RangeIndex(start=0, name='Foo'),
RangeIndex(stop=0, name='Foo'),
RangeIndex(0, 0, name='Foo')]:
assert isinstance(index, RangeIndex)
assert index.name == 'Foo'
# we don't allow on a bare Index
pytest.raises(TypeError, lambda: Index(0, 1000))
# invalid args
for i in [Index(['a', 'b']), Series(['a', 'b']), np.array(['a', 'b']),
[], 'foo', datetime(2000, 1, 1, 0, 0), np.arange(0, 10),
np.array([1]), [1]]:
pytest.raises(TypeError, lambda: RangeIndex(i))
def _get_index_loc(self, key, base_index=None):
"""
Get the location of a specific key in an index
Parameters
----------
key : label
The key for which to find the location if the underlying index is
a DateIndex or a location if the underlying index is a RangeIndex
or an Int64Index.
base_index : pd.Index, optional
Optionally the base index to search. If None, the model's index is
searched.
Returns
-------
loc : int
The location of the key
index : pd.Index
The index including the key; this is a copy of the original index
unless the index had to be expanded to accomodate `key`.
index_was_expanded : bool
Whether or not the index was expanded to accomodate `key`.
Notes
-----
If `key` is past the end of of the given index, and the index is either
an Int64Index or a date index, this function extends the index up to
and including key, and then returns the location in the new index.
"""
if base_index is None:
base_index = self._index
index = base_index
date_index = isinstance(base_index, (PeriodIndex, DatetimeIndex))
int_index = isinstance(base_index, Int64Index)
range_index = isinstance(base_index, RangeIndex)
index_class = type(base_index)
nobs = len(index)
# Special handling for RangeIndex
if range_index and isinstance(key, (int, long, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > nobs - 1:
# See gh5835. Remove the except after pandas 0.25 required.
try:
base_index_start = base_index.start
base_index_step = base_index.step
except AttributeError:
base_index_start = base_index._start
base_index_step = base_index._step
stop = base_index_start + (key + 1) * base_index_step
index = RangeIndex(start=base_index_start,
stop=stop,
step=base_index_step)
# Special handling for Int64Index
if (not range_index and int_index and not date_index
and isinstance(key, (int, long, np.integer))):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > base_index[-1]:
index = Int64Index(np.arange(base_index[0], int(key + 1)))
# Special handling for date indexes
if date_index:
# Use index type to choose creation function
if index_class is DatetimeIndex:
index_fn = date_range
else:
index_fn = period_range
# Integer key (i.e. already given a location)
if isinstance(key, (int, long, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key < nobs:
key = index[nobs + key]
# Out-of-sample (note that we include key itself in the new
# index)
elif key > len(base_index) - 1:
index = index_fn(start=base_index[0],
periods=int(key + 1),
freq=base_index.freq)
key = index[-1]
else:
key = index[key]
# Other key types (i.e. string date or some datetime-like object)
else:
# Covert the key to the appropriate date-like object
if index_class is PeriodIndex:
date_key = Period(key, freq=base_index.freq)
else:
date_key = Timestamp(key)
# Out-of-sample
if date_key > base_index[-1]:
# First create an index that may not always include `key`
index = index_fn(start=base_index[0],
end=date_key,
freq=base_index.freq)
# Now make sure we include `key`
if not index[-1] == date_key:
index = index_fn(start=base_index[0],
periods=len(index) + 1,
freq=base_index.freq)
# Get the location
if date_index:
# (note that get_loc will throw a KeyError if key is invalid)
loc = index.get_loc(key)
elif int_index or range_index:
# For Int64Index and RangeIndex, key is assumed to be the location
# and not an index value (this assumption is required to support
# RangeIndex)
try:
index[key]
# We want to raise a KeyError in this case, to keep the exception
# consistent across index types.
# - Attempting to index with an out-of-bound location (e.g.
# index[10] on an index of length 9) will raise an IndexError
# (as of Pandas 0.22)
# - Attemtping to index with a type that cannot be cast to integer
# (e.g. a non-numeric string) will raise a ValueError if the
# index is RangeIndex (otherwise will raise an IndexError)
# (as of Pandas 0.22)
except (IndexError, ValueError) as e:
raise KeyError(str(e))
loc = key
else:
loc = index.get_loc(key)
# Check if we now have a modified index
index_was_expanded = index is not base_index
# Return the index through the end of the loc / slice
if isinstance(loc, slice):
end = loc.stop
else:
end = loc
return loc, index[:end + 1], index_was_expanded
class TestRangeIndex(Numeric):
_holder = RangeIndex
_compat_props = ["shape", "ndim", "size"]
@pytest.fixture(
params=[
RangeIndex(start=0, stop=20, step=2, name="foo"),
RangeIndex(start=18, stop=-1, step=-2, name="bar"),
],
ids=["index_inc", "index_dec"],
)
def indices(self, request):
return request.param
def create_index(self):
return RangeIndex(start=0, stop=20, step=2)
def test_can_hold_identifiers(self):
idx = self.create_index()
key = idx[0]
assert idx._can_hold_identifiers_and_holds_name(key) is False
def test_too_many_names(self):
index = self.create_index()
with pytest.raises(ValueError, match="^Length"):
index.names = ["roger", "harold"]
@pytest.mark.parametrize(
"index, start, stop, step",
[
(RangeIndex(5), 0, 5, 1),
(RangeIndex(0, 5), 0, 5, 1),
(RangeIndex(5, step=2), 0, 5, 2),
(RangeIndex(1, 5, 2), 1, 5, 2),
],
)
def test_start_stop_step_attrs(self, index, start, stop, step):
# GH 25710
assert index.start == start
assert index.stop == stop
assert index.step == step
@pytest.mark.parametrize("attr_name", ["_start", "_stop", "_step"])
def test_deprecated_start_stop_step_attrs(self, attr_name):
# GH 26581
idx = self.create_index()
with tm.assert_produces_warning(FutureWarning):
getattr(idx, attr_name)
def test_copy(self):
i = RangeIndex(5, name="Foo")
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._range == range(0, 5, 1)
assert i_copy.name == "Foo"
def test_repr(self):
i = RangeIndex(5, name="Foo")
result = repr(i)
expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
i = RangeIndex(5, 0, -1)
result = repr(i)
expected = "RangeIndex(start=5, stop=0, step=-1)"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
def test_insert(self):
idx = RangeIndex(5, name="Foo")
result = idx[1:4]
# test 0th element
tm.assert_index_equal(idx[0:4], result.insert(0, idx[0]))
# GH 18295 (test missing)
expected = Float64Index([0, np.nan, 1, 2, 3, 4])
for na in (np.nan, pd.NaT, None):
result = RangeIndex(5).insert(1, na)
tm.assert_index_equal(result, expected)
def test_delete(self):
idx = RangeIndex(5, name="Foo")
expected = idx[1:].astype(int)
result = idx.delete(0)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
expected = idx[:-1].astype(int)
result = idx.delete(-1)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
with pytest.raises((IndexError, ValueError)):
# either depending on numpy version
result = idx.delete(len(idx))
def test_view(self):
i = RangeIndex(0, name="Foo")
i_view = i.view()
assert i_view.name == "Foo"
i_view = i.view("i8")
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_dtype(self):
index = self.create_index()
assert index.dtype == np.int64
def test_cached_data(self):
# GH 26565, GH26617
# Calling RangeIndex._data caches an int64 array of the same length at
# self._cached_data. This test checks whether _cached_data has been set
idx = RangeIndex(0, 100, 10)
assert idx._cached_data is None
repr(idx)
assert idx._cached_data is None
str(idx)
assert idx._cached_data is None
idx.get_loc(20)
assert idx._cached_data is None
90 in idx
assert idx._cached_data is None
91 in idx
assert idx._cached_data is None
idx.all()
assert idx._cached_data is None
idx.any()
assert idx._cached_data is None
df = pd.DataFrame({"a": range(10)}, index=idx)
df.loc[50]
assert idx._cached_data is None
with pytest.raises(KeyError, match="51"):
df.loc[51]
assert idx._cached_data is None
df.loc[10:50]
assert idx._cached_data is None
df.iloc[5:10]
assert idx._cached_data is None
# actually calling idx._data
assert isinstance(idx._data, np.ndarray)
assert isinstance(idx._cached_data, np.ndarray)
def test_is_monotonic(self):
index = RangeIndex(0, 20, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is False
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is False
index = RangeIndex(4, 0, -1)
assert index.is_monotonic is False
assert index._is_strictly_monotonic_increasing is False
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(2, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
def test_equals_range(self):
equiv_pairs = [
(RangeIndex(0, 9, 2), RangeIndex(0, 10, 2)),
(RangeIndex(0), RangeIndex(1, -1, 3)),
(RangeIndex(1, 2, 3), RangeIndex(1, 3, 4)),
(RangeIndex(0, -9, -2), RangeIndex(0, -10, -2)),
]
for left, right in equiv_pairs:
assert left.equals(right)
assert right.equals(left)
def test_logical_compat(self):
idx = self.create_index()
assert idx.all() == idx.values.all()
assert idx.any() == idx.values.any()
def test_identical(self):
index = self.create_index()
i = Index(index.copy())
assert i.identical(index)
# we don't allow object dtype for RangeIndex
if isinstance(index, RangeIndex):
return
same_values_different_type = Index(i, dtype=object)
assert not i.identical(same_values_different_type)
i = index.copy(dtype=object)
i = i.rename("foo")
same_values = Index(i, dtype=object)
assert same_values.identical(index.copy(dtype=object))
assert not i.identical(index)
assert Index(same_values, name="foo", dtype=object).identical(i)
assert not index.copy(dtype=object).identical(
index.copy(dtype="int64"))
def test_get_indexer(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_pad(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="pad")
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_backfill(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="backfill")
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_limit(self):
# GH 28631
idx = RangeIndex(4)
target = RangeIndex(6)
result = idx.get_indexer(target, method="pad", limit=1)
expected = np.array([0, 1, 2, 3, 3, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("stop", [0, -1, -2])
def test_get_indexer_decreasing(self, stop):
# GH 28678
index = RangeIndex(7, stop, -3)
result = index.get_indexer(range(9))
expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
def test_join_outer(self):
# join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="outer", return_indexers=True)
noidx_res = index.join(other, how="outer")
tm.assert_index_equal(res, noidx_res)
eres = Int64Index([
0, 2, 4, 6, 8, 10, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
25
])
elidx = np.array(
[0, 1, 2, 3, 4, 5, 6, 7, -1, 8, -1, 9, -1, -1, -1, -1, -1, -1, -1],
dtype=np.intp,
)
eridx = np.array(
[-1, -1, -1, -1, -1, -1, -1, -1, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0],
dtype=np.intp,
)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# join with RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="outer", return_indexers=True)
noidx_res = index.join(other, how="outer")
tm.assert_index_equal(res, noidx_res)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_inner(self):
# Join with non-RangeIndex
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="inner", return_indexers=True)
# no guarantee of sortedness, so sort for comparison purposes
ind = res.argsort()
res = res.take(ind)
lidx = lidx.take(ind)
ridx = ridx.take(ind)
eres = Int64Index([16, 18])
elidx = np.array([8, 9], dtype=np.intp)
eridx = np.array([9, 7], dtype=np.intp)
assert isinstance(res, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# Join two RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="inner", return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_left(self):
# Join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="left", return_indexers=True)
eres = index
eridx = np.array([-1, -1, -1, -1, -1, -1, -1, -1, 9, 7], dtype=np.intp)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
# Join withRangeIndex
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="left", return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_right(self):
# Join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="right", return_indexers=True)
eres = other
elidx = np.array([-1, -1, -1, -1, -1, -1, -1, 9, -1, 8, -1],
dtype=np.intp)
assert isinstance(other, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
# Join withRangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="right", return_indexers=True)
eres = other
assert isinstance(other, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
def test_join_non_int_index(self):
index = self.create_index()
other = Index([3, 6, 7, 8, 10], dtype=object)
outer = index.join(other, how="outer")
outer2 = other.join(index, how="outer")
expected = Index([0, 2, 3, 4, 6, 7, 8, 10, 12, 14, 16, 18])
tm.assert_index_equal(outer, outer2)
tm.assert_index_equal(outer, expected)
inner = index.join(other, how="inner")
inner2 = other.join(index, how="inner")
expected = Index([6, 8, 10])
tm.assert_index_equal(inner, inner2)
tm.assert_index_equal(inner, expected)
left = index.join(other, how="left")
tm.assert_index_equal(left, index.astype(object))
left2 = other.join(index, how="left")
tm.assert_index_equal(left2, other)
right = index.join(other, how="right")
tm.assert_index_equal(right, other)
right2 = other.join(index, how="right")
tm.assert_index_equal(right2, index.astype(object))
def test_join_non_unique(self):
index = self.create_index()
other = Index([4, 4, 3, 3])
res, lidx, ridx = index.join(other, return_indexers=True)
eres = Int64Index([0, 2, 4, 4, 6, 8, 10, 12, 14, 16, 18])
elidx = np.array([0, 1, 2, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.intp)
eridx = np.array([-1, -1, 0, 1, -1, -1, -1, -1, -1, -1, -1],
dtype=np.intp)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_self(self, join_type):
index = self.create_index()
joined = index.join(index, how=join_type)
assert index is joined
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
assert i.nbytes < i._int64index.nbytes / 10
# constant memory usage
i2 = RangeIndex(0, 10)
assert i.nbytes == i2.nbytes
def test_cant_or_shouldnt_cast(self):
# can't
with pytest.raises(TypeError):
RangeIndex("foo", "bar", "baz")
# shouldn't
with pytest.raises(TypeError):
RangeIndex("0", "1", "2")
def test_view_index(self):
index = self.create_index()
index.view(Index)
def test_prevent_casting(self):
index = self.create_index()
result = index.astype("O")
assert result.dtype == np.object_
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name="foo")
taken = index.take([3, 0, 1])
assert index.name == taken.name
def test_take_fill_value(self):
# GH 12631
idx = pd.RangeIndex(1, 4, name="xxx")
result = idx.take(np.array([1, 0, -1]))
expected = pd.Int64Index([2, 1, 3], name="xxx")
tm.assert_index_equal(result, expected)
# fill_value
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -1]), fill_value=True)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = pd.Int64Index([2, 1, 3], name="xxx")
tm.assert_index_equal(result, expected)
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
idx.take(np.array([1, -5]))
def test_print_unicode_columns(self):
df = pd.DataFrame({
"\u05d0": [1, 2, 3],
"\u05d1": [4, 5, 6],
"c": [7, 8, 9]
})
repr(df.columns) # should not raise UnicodeDecodeError
def test_repr_roundtrip(self):
index = self.create_index()
tm.assert_index_equal(eval(repr(index)), index)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name="asdf")
assert idx.name == idx[1:].name
def test_explicit_conversions(self):
# GH 8608
# add/sub are overridden explicitly for Float/Int Index
idx = RangeIndex(5)
# float conversions
arr = np.arange(5, dtype="int64") * 3.2
expected = Float64Index(arr)
fidx = idx * 3.2
tm.assert_index_equal(fidx, expected)
fidx = 3.2 * idx
tm.assert_index_equal(fidx, expected)
# interops with numpy arrays
expected = Float64Index(arr)
a = np.zeros(5, dtype="float64")
result = fidx - a
tm.assert_index_equal(result, expected)
expected = Float64Index(-arr)
a = np.zeros(5, dtype="float64")
result = a - fidx
tm.assert_index_equal(result, expected)
def test_has_duplicates(self, indices):
assert indices.is_unique
assert not indices.has_duplicates
def test_extended_gcd(self):
index = self.create_index()
result = index._extended_gcd(6, 10)
assert result[0] == result[1] * 6 + result[2] * 10
assert 2 == result[0]
result = index._extended_gcd(10, 6)
assert 2 == result[1] * 10 + result[2] * 6
assert 2 == result[0]
def test_min_fitting_element(self):
result = RangeIndex(0, 20, 2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(1, 6)._min_fitting_element(1)
assert 1 == result
result = RangeIndex(18, -2, -2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(5, 0, -1)._min_fitting_element(1)
assert 1 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._min_fitting_element(big_num)
assert big_num == result
def test_max_fitting_element(self):
result = RangeIndex(0, 20, 2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(1, 6)._max_fitting_element(4)
assert 4 == result
result = RangeIndex(18, -2, -2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(5, 0, -1)._max_fitting_element(4)
assert 4 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._max_fitting_element(big_num)
assert big_num == result
def test_pickle_compat_construction(self):
# RangeIndex() is a valid constructor
pass
def test_slice_specialised(self):
index = self.create_index()
index.name = "foo"
# scalar indexing
res = index[1]
expected = 2
assert res == expected
res = index[-1]
expected = 18
assert res == expected
# slicing
# slice value completion
index_slice = index[:]
expected = index
tm.assert_index_equal(index_slice, expected)
# positive slice values
index_slice = index[7:10:2]
expected = Index(np.array([14, 18]), name="foo")
tm.assert_index_equal(index_slice, expected)
# negative slice values
index_slice = index[-1:-5:-2]
expected = Index(np.array([18, 14]), name="foo")
tm.assert_index_equal(index_slice, expected)
# stop overshoot
index_slice = index[2:100:4]
expected = Index(np.array([4, 12]), name="foo")
tm.assert_index_equal(index_slice, expected)
# reverse
index_slice = index[::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-8::-1]
expected = Index(np.array([4, 2, 0]), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-40::-1]
expected = Index(np.array([], dtype=np.int64), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[40::-1]
expected = Index(index.values[40::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[10::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
@pytest.mark.parametrize("step", set(range(-5, 6)) - {0})
def test_len_specialised(self, step):
# make sure that our len is the same as np.arange calc
start, stop = (0, 5) if step > 0 else (5, 0)
arr = np.arange(start, stop, step)
index = RangeIndex(start, stop, step)
assert len(index) == len(arr)
index = RangeIndex(stop, start, step)
assert len(index) == 0
@pytest.fixture(params=[
([RI(1, 12, 5)], RI(1, 12, 5)),
([RI(0, 6, 4)], RI(0, 6, 4)),
([RI(1, 3), RI(3, 7)], RI(1, 7)),
([RI(1, 5, 2), RI(5, 6)], RI(1, 6, 2)),
([RI(1, 3, 2), RI(4, 7, 3)], RI(1, 7, 3)),
([RI(-4, 3, 2), RI(4, 7, 2)], RI(-4, 7, 2)),
([RI(-4, -8), RI(-8, -12)], RI(0, 0)),
([RI(-4, -8), RI(3, -4)], RI(0, 0)),
([RI(-4, -8), RI(3, 5)], RI(3, 5)),
([RI(-4, -2), RI(3, 5)], I64([-4, -3, 3, 4])),
([RI(-2), RI(3, 5)], RI(3, 5)),
([RI(2), RI(2)], I64([0, 1, 0, 1])),
([RI(2), RI(2, 5), RI(5, 8, 4)], RI(0, 6)),
([RI(2), RI(3, 5), RI(5, 8, 4)], I64([0, 1, 3, 4, 5])),
([RI(-2, 2), RI(2, 5), RI(5, 8, 4)], RI(-2, 6)),
([RI(3), I64([-1, 3, 15])], I64([0, 1, 2, -1, 3, 15])),
([RI(3), F64([-1, 3.1, 15.0])], F64([0, 1, 2, -1, 3.1, 15.0])),
([RI(3), OI(["a", None, 14])], OI([0, 1, 2, "a", None, 14])),
([RI(3, 1), OI(["a", None, 14])], OI(["a", None, 14])),
])
def appends(self, request):
"""Inputs and expected outputs for RangeIndex.append test"""
return request.param
def test_append(self, appends):
# GH16212
indices, expected = appends
result = indices[0].append(indices[1:])
tm.assert_index_equal(result, expected, exact=True)
if len(indices) == 2:
# Append single item rather than list
result2 = indices[0].append(indices[1])
tm.assert_index_equal(result2, expected, exact=True)
def test_engineless_lookup(self):
# GH 16685
# Standard lookup on RangeIndex should not require the engine to be
# created
idx = RangeIndex(2, 10, 3)
assert idx.get_loc(5) == 1
tm.assert_numpy_array_equal(idx.get_indexer([2, 8]),
ensure_platform_int(np.array([0, 2])))
with pytest.raises(KeyError, match="3"):
idx.get_loc(3)
assert "_engine" not in idx._cache
# The engine is still required for lookup of a different dtype scalar:
with pytest.raises(KeyError, match="'a'"):
assert idx.get_loc("a") == -1
assert "_engine" in idx._cache
def test_get_indexer_pad(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="pad")
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_cant_or_shouldnt_cast(self, start, stop, step):
msg = f"Wrong type {type(start)} for value {start}"
with pytest.raises(TypeError, match=msg):
RangeIndex(start, stop, step)
def test_isin_range(self, base):
# GH#41151
values = RangeIndex(0, 1)
result = base.isin(values)
expected = np.array([True, False])
tm.assert_numpy_array_equal(result, expected)
class TestRangeIndex(NumericBase):
_index_cls = RangeIndex
@pytest.fixture
def dtype(self):
return np.int64
@pytest.fixture(
params=["uint64", "float64", "category", "datetime64", "object"],
)
def invalid_dtype(self, request):
return request.param
@pytest.fixture
def simple_index(self) -> Index:
return self._index_cls(start=0, stop=20, step=2)
@pytest.fixture(
params=[
RangeIndex(start=0, stop=20, step=2, name="foo"),
RangeIndex(start=18, stop=-1, step=-2, name="bar"),
],
ids=["index_inc", "index_dec"],
)
def index(self, request):
return request.param
def test_constructor_unwraps_index(self, dtype):
result = self._index_cls(1, 3)
expected = np.array([1, 2], dtype=dtype)
tm.assert_numpy_array_equal(result._data, expected)
def test_can_hold_identifiers(self, simple_index):
idx = simple_index
key = idx[0]
assert idx._can_hold_identifiers_and_holds_name(key) is False
def test_too_many_names(self, simple_index):
index = simple_index
with pytest.raises(ValueError, match="^Length"):
index.names = ["roger", "harold"]
@pytest.mark.parametrize(
"index, start, stop, step",
[
(RangeIndex(5), 0, 5, 1),
(RangeIndex(0, 5), 0, 5, 1),
(RangeIndex(5, step=2), 0, 5, 2),
(RangeIndex(1, 5, 2), 1, 5, 2),
],
)
def test_start_stop_step_attrs(self, index, start, stop, step):
# GH 25710
assert index.start == start
assert index.stop == stop
assert index.step == step
@pytest.mark.parametrize("attr_name", ["_start", "_stop", "_step"])
def test_deprecated_start_stop_step_attrs(self, attr_name, simple_index):
# GH 26581
idx = simple_index
with tm.assert_produces_warning(FutureWarning):
getattr(idx, attr_name)
def test_copy(self):
i = RangeIndex(5, name="Foo")
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._range == range(0, 5, 1)
assert i_copy.name == "Foo"
def test_repr(self):
i = RangeIndex(5, name="Foo")
result = repr(i)
expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
i = RangeIndex(5, 0, -1)
result = repr(i)
expected = "RangeIndex(start=5, stop=0, step=-1)"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
def test_insert(self):
idx = RangeIndex(5, name="Foo")
result = idx[1:4]
# test 0th element
tm.assert_index_equal(idx[0:4], result.insert(0, idx[0]))
# GH 18295 (test missing)
expected = Float64Index([0, np.nan, 1, 2, 3, 4])
for na in [np.nan, None, pd.NA]:
result = RangeIndex(5).insert(1, na)
tm.assert_index_equal(result, expected)
result = RangeIndex(5).insert(1, pd.NaT)
expected = Index([0, pd.NaT, 1, 2, 3, 4], dtype=object)
tm.assert_index_equal(result, expected)
def test_delete(self):
idx = RangeIndex(5, name="Foo")
expected = idx[1:].astype(int)
result = idx.delete(0)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
expected = idx[:-1].astype(int)
result = idx.delete(-1)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
msg = "index 5 is out of bounds for axis 0 with size 5"
with pytest.raises((IndexError, ValueError), match=msg):
# either depending on numpy version
result = idx.delete(len(idx))
def test_view(self):
i = RangeIndex(0, name="Foo")
i_view = i.view()
assert i_view.name == "Foo"
i_view = i.view("i8")
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_dtype(self, simple_index):
index = simple_index
assert index.dtype == np.int64
def test_cache(self):
# GH 26565, GH26617, GH35432
# This test checks whether _cache has been set.
# Calling RangeIndex._cache["_data"] creates an int64 array of the same length
# as the RangeIndex and stores it in _cache.
idx = RangeIndex(0, 100, 10)
assert idx._cache == {}
repr(idx)
assert idx._cache == {}
str(idx)
assert idx._cache == {}
idx.get_loc(20)
assert idx._cache == {}
90 in idx # True
assert idx._cache == {}
91 in idx # False
assert idx._cache == {}
idx.all()
assert idx._cache == {}
idx.any()
assert idx._cache == {}
for _ in idx:
pass
assert idx._cache == {}
idx.format()
assert idx._cache == {}
df = pd.DataFrame({"a": range(10)}, index=idx)
str(df)
assert idx._cache == {}
df.loc[50]
assert idx._cache == {}
with pytest.raises(KeyError, match="51"):
df.loc[51]
assert idx._cache == {}
df.loc[10:50]
assert idx._cache == {}
df.iloc[5:10]
assert idx._cache == {}
# idx._cache should contain a _data entry after call to idx._data
idx._data
assert isinstance(idx._data, np.ndarray)
assert idx._data is idx._data # check cached value is reused
assert len(idx._cache) == 1
expected = np.arange(0, 100, 10, dtype="int64")
tm.assert_numpy_array_equal(idx._cache["_data"], expected)
def test_is_monotonic(self):
index = RangeIndex(0, 20, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is False
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is False
index = RangeIndex(4, 0, -1)
assert index.is_monotonic is False
assert index._is_strictly_monotonic_increasing is False
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(2, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
def test_equals_range(self):
equiv_pairs = [
(RangeIndex(0, 9, 2), RangeIndex(0, 10, 2)),
(RangeIndex(0), RangeIndex(1, -1, 3)),
(RangeIndex(1, 2, 3), RangeIndex(1, 3, 4)),
(RangeIndex(0, -9, -2), RangeIndex(0, -10, -2)),
]
for left, right in equiv_pairs:
assert left.equals(right)
assert right.equals(left)
def test_logical_compat(self, simple_index):
idx = simple_index
assert idx.all() == idx.values.all()
assert idx.any() == idx.values.any()
def test_identical(self, simple_index):
index = simple_index
i = Index(index.copy())
assert i.identical(index)
# we don't allow object dtype for RangeIndex
if isinstance(index, RangeIndex):
return
same_values_different_type = Index(i, dtype=object)
assert not i.identical(same_values_different_type)
i = index.copy(dtype=object)
i = i.rename("foo")
same_values = Index(i, dtype=object)
assert same_values.identical(index.copy(dtype=object))
assert not i.identical(index)
assert Index(same_values, name="foo", dtype=object).identical(i)
assert not index.copy(dtype=object).identical(index.copy(dtype="int64"))
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
assert i.nbytes < i._int64index.nbytes / 10
# constant memory usage
i2 = RangeIndex(0, 10)
assert i.nbytes == i2.nbytes
@pytest.mark.parametrize(
"start,stop,step",
[
# can't
("foo", "bar", "baz"),
# shouldn't
("0", "1", "2"),
],
)
def test_cant_or_shouldnt_cast(self, start, stop, step):
msg = f"Wrong type {type(start)} for value {start}"
with pytest.raises(TypeError, match=msg):
RangeIndex(start, stop, step)
def test_view_index(self, simple_index):
index = simple_index
index.view(Index)
def test_prevent_casting(self, simple_index):
index = simple_index
result = index.astype("O")
assert result.dtype == np.object_
def test_repr_roundtrip(self, simple_index):
index = simple_index
tm.assert_index_equal(eval(repr(index)), index)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name="asdf")
assert idx.name == idx[1:].name
def test_has_duplicates(self, index):
assert index.is_unique
assert not index.has_duplicates
def test_extended_gcd(self, simple_index):
index = simple_index
result = index._extended_gcd(6, 10)
assert result[0] == result[1] * 6 + result[2] * 10
assert 2 == result[0]
result = index._extended_gcd(10, 6)
assert 2 == result[1] * 10 + result[2] * 6
assert 2 == result[0]
def test_min_fitting_element(self):
result = RangeIndex(0, 20, 2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(1, 6)._min_fitting_element(1)
assert 1 == result
result = RangeIndex(18, -2, -2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(5, 0, -1)._min_fitting_element(1)
assert 1 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._min_fitting_element(big_num)
assert big_num == result
def test_max_fitting_element(self):
result = RangeIndex(0, 20, 2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(1, 6)._max_fitting_element(4)
assert 4 == result
result = RangeIndex(18, -2, -2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(5, 0, -1)._max_fitting_element(4)
assert 4 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._max_fitting_element(big_num)
assert big_num == result
def test_pickle_compat_construction(self):
# RangeIndex() is a valid constructor
pass
def test_slice_specialised(self, simple_index):
index = simple_index
index.name = "foo"
# scalar indexing
res = index[1]
expected = 2
assert res == expected
res = index[-1]
expected = 18
assert res == expected
# slicing
# slice value completion
index_slice = index[:]
expected = index
tm.assert_index_equal(index_slice, expected)
# positive slice values
index_slice = index[7:10:2]
expected = Index(np.array([14, 18]), name="foo")
tm.assert_index_equal(index_slice, expected)
# negative slice values
index_slice = index[-1:-5:-2]
expected = Index(np.array([18, 14]), name="foo")
tm.assert_index_equal(index_slice, expected)
# stop overshoot
index_slice = index[2:100:4]
expected = Index(np.array([4, 12]), name="foo")
tm.assert_index_equal(index_slice, expected)
# reverse
index_slice = index[::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-8::-1]
expected = Index(np.array([4, 2, 0]), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-40::-1]
expected = Index(np.array([], dtype=np.int64), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[40::-1]
expected = Index(index.values[40::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[10::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
@pytest.mark.parametrize("step", set(range(-5, 6)) - {0})
def test_len_specialised(self, step):
# make sure that our len is the same as np.arange calc
start, stop = (0, 5) if step > 0 else (5, 0)
arr = np.arange(start, stop, step)
index = RangeIndex(start, stop, step)
assert len(index) == len(arr)
index = RangeIndex(stop, start, step)
assert len(index) == 0
@pytest.fixture(
params=[
([RI(1, 12, 5)], RI(1, 12, 5)),
([RI(0, 6, 4)], RI(0, 6, 4)),
([RI(1, 3), RI(3, 7)], RI(1, 7)),
([RI(1, 5, 2), RI(5, 6)], RI(1, 6, 2)),
([RI(1, 3, 2), RI(4, 7, 3)], RI(1, 7, 3)),
([RI(-4, 3, 2), RI(4, 7, 2)], RI(-4, 7, 2)),
([RI(-4, -8), RI(-8, -12)], RI(0, 0)),
([RI(-4, -8), RI(3, -4)], RI(0, 0)),
([RI(-4, -8), RI(3, 5)], RI(3, 5)),
([RI(-4, -2), RI(3, 5)], I64([-4, -3, 3, 4])),
([RI(-2), RI(3, 5)], RI(3, 5)),
([RI(2), RI(2)], I64([0, 1, 0, 1])),
([RI(2), RI(2, 5), RI(5, 8, 4)], RI(0, 6)),
([RI(2), RI(3, 5), RI(5, 8, 4)], I64([0, 1, 3, 4, 5])),
([RI(-2, 2), RI(2, 5), RI(5, 8, 4)], RI(-2, 6)),
([RI(3), I64([-1, 3, 15])], I64([0, 1, 2, -1, 3, 15])),
([RI(3), F64([-1, 3.1, 15.0])], F64([0, 1, 2, -1, 3.1, 15.0])),
([RI(3), OI(["a", None, 14])], OI([0, 1, 2, "a", None, 14])),
([RI(3, 1), OI(["a", None, 14])], OI(["a", None, 14])),
]
)
def appends(self, request):
"""Inputs and expected outputs for RangeIndex.append test"""
return request.param
def test_append(self, appends):
# GH16212
indices, expected = appends
result = indices[0].append(indices[1:])
tm.assert_index_equal(result, expected, exact=True)
if len(indices) == 2:
# Append single item rather than list
result2 = indices[0].append(indices[1])
tm.assert_index_equal(result2, expected, exact=True)
def test_engineless_lookup(self):
# GH 16685
# Standard lookup on RangeIndex should not require the engine to be
# created
idx = RangeIndex(2, 10, 3)
assert idx.get_loc(5) == 1
tm.assert_numpy_array_equal(
idx.get_indexer([2, 8]), ensure_platform_int(np.array([0, 2]))
)
with pytest.raises(KeyError, match="3"):
idx.get_loc(3)
assert "_engine" not in idx._cache
# Different types of scalars can be excluded immediately, no need to
# use the _engine
with pytest.raises(KeyError, match="'a'"):
idx.get_loc("a")
assert "_engine" not in idx._cache
def test_format_empty(self):
# GH35712
empty_idx = self._index_cls(0)
assert empty_idx.format() == []
assert empty_idx.format(name=True) == [""]
@pytest.mark.parametrize(
"RI",
[
RangeIndex(0, -1, -1),
RangeIndex(0, 1, 1),
RangeIndex(1, 3, 2),
RangeIndex(0, -1, -2),
RangeIndex(-3, -5, -2),
],
)
def test_append_len_one(self, RI):
# GH39401
result = RI.append([])
tm.assert_index_equal(result, RI, exact=True)
@pytest.mark.parametrize("base", [RangeIndex(0, 2), Index([0, 1])])
def test_isin_range(self, base):
# GH#41151
values = RangeIndex(0, 1)
result = base.isin(values)
expected = np.array([True, False])
tm.assert_numpy_array_equal(result, expected)
def test_cache(self):
# GH 26565, GH26617, GH35432
# This test checks whether _cache has been set.
# Calling RangeIndex._cache["_data"] creates an int64 array of the same length
# as the RangeIndex and stores it in _cache.
idx = RangeIndex(0, 100, 10)
assert idx._cache == {}
repr(idx)
assert idx._cache == {}
str(idx)
assert idx._cache == {}
idx.get_loc(20)
assert idx._cache == {}
90 in idx # True
assert idx._cache == {}
91 in idx # False
assert idx._cache == {}
idx.all()
assert idx._cache == {}
idx.any()
assert idx._cache == {}
for _ in idx:
pass
assert idx._cache == {}
idx.format()
assert idx._cache == {}
df = pd.DataFrame({"a": range(10)}, index=idx)
str(df)
assert idx._cache == {}
df.loc[50]
assert idx._cache == {}
with pytest.raises(KeyError, match="51"):
df.loc[51]
assert idx._cache == {}
df.loc[10:50]
assert idx._cache == {}
df.iloc[5:10]
assert idx._cache == {}
# idx._cache should contain a _data entry after call to idx._data
idx._data
assert isinstance(idx._data, np.ndarray)
assert idx._data is idx._data # check cached value is reused
assert len(idx._cache) == 1
expected = np.arange(0, 100, 10, dtype="int64")
tm.assert_numpy_array_equal(idx._cache["_data"], expected)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name='asdf')
self.assertEqual(idx.name, idx[1:].name)
def setup_method(self, method):
self.indices = dict(index=RangeIndex(0, 20, 2, name='foo'))
self.setup_indices()
def test_get_indexer_decreasing(self, stop):
# GH 28678
index = RangeIndex(7, stop, -3)
result = index.get_indexer(range(9))
expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
def test_intersection(self):
# intersect with Int64Index
other = Index(np.arange(1, 6))
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(self.index)
expected = Index(np.sort(np.asarray(np.intersect1d(self.index.values,
other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def create_index(self):
return RangeIndex(start=0, stop=20, step=2)
def test_ufunc_compat(self):
idx = RangeIndex(5)
result = np.sin(idx)
expected = Float64Index(np.sin(np.arange(5, dtype='int64')))
tm.assert_index_equal(result, expected)
def test_constructor_additional_invalid_args(self, args):
msg = f"Value needs to be a scalar value, was type {type(args).__name__}"
with pytest.raises(TypeError, match=msg):
RangeIndex(args)
def setup_method(self, method):
self.indices = dict(index=RangeIndex(0, 20, 2, name='foo'),
index_dec=RangeIndex(18, -1, -2, name='bar'))
self.setup_indices()
def test_constructor_invalid_args_wrong_type(self, args):
msg = f"Wrong type {type(args)} for value {args}"
with pytest.raises(TypeError, match=msg):
RangeIndex(args)
def test_get_indexer(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_index_equal_class(exact):
idx1 = Index([0, 1, 2])
idx2 = RangeIndex(3)
tm.assert_index_equal(idx1, idx2, exact=exact)
def test_constructor(self):
index = RangeIndex(5)
expected = np.arange(5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 5
assert index._step == 1
assert index.name is None
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5)
expected = np.arange(1, 5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 1
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5, 2)
expected = np.arange(1, 5, 2, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._step == 2
tm.assert_index_equal(Index(expected), index)
for index in [
RangeIndex(0),
RangeIndex(start=0),
RangeIndex(stop=0),
RangeIndex(0, 0)
]:
expected = np.empty(0, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 0
assert index._step == 1
tm.assert_index_equal(Index(expected), index)
for index in [
RangeIndex(0, name='Foo'),
RangeIndex(start=0, name='Foo'),
RangeIndex(stop=0, name='Foo'),
RangeIndex(0, 0, name='Foo')
]:
assert isinstance(index, RangeIndex)
assert index.name == 'Foo'
# we don't allow on a bare Index
with pytest.raises(TypeError):
Index(0, 1000)
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name='foo')
taken = index.take([3, 0, 1])
assert index.name == taken.name
def test_numeric_compat2(self):
# validate that we are handling the RangeIndex overrides to numeric ops
# and returning RangeIndex where possible
idx = RangeIndex(0, 10, 2)
result = idx * 2
expected = RangeIndex(0, 20, 4)
tm.assert_index_equal(result, expected, exact=True)
result = idx + 2
expected = RangeIndex(2, 12, 2)
tm.assert_index_equal(result, expected, exact=True)
result = idx - 2
expected = RangeIndex(-2, 8, 2)
tm.assert_index_equal(result, expected, exact=True)
# truediv under PY3
result = idx / 2
if PY3:
expected = RangeIndex(0, 5, 1).astype('float64')
else:
expected = RangeIndex(0, 5, 1)
tm.assert_index_equal(result, expected, exact=True)
result = idx / 4
expected = RangeIndex(0, 10, 2) / 4
tm.assert_index_equal(result, expected, exact=True)
result = idx // 1
expected = idx
tm.assert_index_equal(result, expected, exact=True)
# __mul__
result = idx * idx
expected = Index(idx.values * idx.values)
tm.assert_index_equal(result, expected, exact=True)
# __pow__
idx = RangeIndex(0, 1000, 2)
result = idx ** 2
expected = idx._int64index ** 2
tm.assert_index_equal(Index(result.values), expected, exact=True)
# __floordiv__
cases_exact = [(RangeIndex(0, 1000, 2), 2, RangeIndex(0, 500, 1)),
(RangeIndex(-99, -201, -3), -3, RangeIndex(33, 67, 1)),
(RangeIndex(0, 1000, 1), 2,
RangeIndex(0, 1000, 1)._int64index // 2),
(RangeIndex(0, 100, 1), 2.0,
RangeIndex(0, 100, 1)._int64index // 2.0),
(RangeIndex(0), 50, RangeIndex(0)),
(RangeIndex(2, 4, 2), 3, RangeIndex(0, 1, 1)),
(RangeIndex(-5, -10, -6), 4, RangeIndex(-2, -1, 1)),
(RangeIndex(-100, -200, 3), 2, RangeIndex(0))]
for idx, div, expected in cases_exact:
tm.assert_index_equal(idx // div, expected, exact=True)
def makeRangeIndex(k=10, name=None, **kwargs):
return RangeIndex(0, k, 1, name=name, **kwargs)
def test_get_indexer_pad(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='pad')
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4])
self.assert_numpy_array_equal(indexer, expected)
