def test_get_indexer_requires_unique(self):
np.random.seed(123456789)
ci = CategoricalIndex(list("aabbca"),
categories=list("cab"),
ordered=False)
oidx = Index(np.array(ci))
msg = "Reindexing only valid with uniquely valued Index objects"
for n in [1, 2, 5, len(ci)]:
finder = oidx[np.random.randint(0, len(ci), size=n)]
with pytest.raises(InvalidIndexError, match=msg):
ci.get_indexer(finder)
# see gh-17323
#
# Even when indexer is equal to the
# members in the index, we should
# respect duplicates instead of taking
# the fast-track path.
for finder in [list("aabbca"), list("aababca")]:
with pytest.raises(InvalidIndexError, match=msg):
ci.get_indexer(finder)
def test_get_indexer_non_unique(self):
np.random.seed(123456789)
ci = CategoricalIndex(list("aabbca"),
categories=list("cab"),
ordered=False)
oidx = Index(np.array(ci))
for n in [1, 2, 5, len(ci)]:
finder = oidx[np.random.randint(0, len(ci), size=n)]
expected = oidx.get_indexer_non_unique(finder)[0]
actual = ci.get_indexer(finder)
tm.assert_numpy_array_equal(expected, actual)
# see gh-17323
#
# Even when indexer is equal to the
# members in the index, we should
# respect duplicates instead of taking
# the fast-track path.
for finder in [list("aabbca"), list("aababca")]:
expected = oidx.get_indexer_non_unique(finder)[0]
actual = ci.get_indexer(finder)
tm.assert_numpy_array_equal(expected, actual)
def test_get_indexer_base(self):
# Determined by cat ordering.
idx = CategoricalIndex(list("cab"), categories=list("cab"))
expected = np.arange(len(idx), dtype=np.intp)
actual = idx.get_indexer(idx)
tm.assert_numpy_array_equal(expected, actual)
with pytest.raises(ValueError, match="Invalid fill method"):
idx.get_indexer(idx, method="invalid")
def test_get_indexer_nans_in_index_and_target(self):
# GH 45361
ci = CategoricalIndex([1, 2, np.nan, 3])
other1 = [2, 3, 4, np.nan]
res1 = ci.get_indexer(other1)
expected1 = np.array([1, 3, -1, 2], dtype=np.intp)
tm.assert_numpy_array_equal(res1, expected1)
other2 = [1, 4, 2, 3]
res2 = ci.get_indexer(other2)
expected2 = np.array([0, -1, 1, 3], dtype=np.intp)
tm.assert_numpy_array_equal(res2, expected2)
def test_get_indexer_non_unique(self):
idx1 = CategoricalIndex(list("aabcde"), categories=list("edabc"))
idx2 = CategoricalIndex(list("abf"))
for indexer in [idx2, list("abf"), Index(list("abf"))]:
msg = "Reindexing only valid with uniquely valued Index objects"
with pytest.raises(InvalidIndexError, match=msg):
idx1.get_indexer(indexer)
r1, _ = idx1.get_indexer_non_unique(indexer)
expected = np.array([0, 1, 2, -1], dtype=np.intp)
tm.assert_almost_equal(r1, expected)
def test_get_indexer_same_categories_same_order(self):
ci = CategoricalIndex(["a", "b"], categories=["a", "b"])
result = ci.get_indexer(
CategoricalIndex(["b", "b"], categories=["a", "b"]))
expected = np.array([1, 1], dtype="intp")
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_same_categories_different_order(self):
# https://github.com/pandas-dev/pandas/issues/19551
ci = CategoricalIndex(["a", "b"], categories=["a", "b"])
result = ci.get_indexer(CategoricalIndex(["b", "b"], categories=["b", "a"]))
expected = np.array([1, 1], dtype="intp")
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_same_categories_same_order(self):
ci = CategoricalIndex(['a', 'b'], categories=['a', 'b'])
result = ci.get_indexer(
CategoricalIndex(['b', 'b'], categories=['a', 'b']))
expected = np.array([1, 1], dtype='intp')
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_same_categories_same_order(self):
ci = CategoricalIndex(['a', 'b'], categories=['a', 'b'])
result = ci.get_indexer(CategoricalIndex(['b', 'b'],
categories=['a', 'b']))
expected = np.array([1, 1], dtype='intp')
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_same_categories_different_order(self):
# https://github.com/pandas-dev/pandas/issues/19551
ci = CategoricalIndex(['a', 'b'], categories=['a', 'b'])
result = ci.get_indexer(CategoricalIndex(['b', 'b'],
categories=['b', 'a']))
expected = np.array([1, 1], dtype='intp')
tm.assert_numpy_array_equal(result, expected)
class CategoricalIndexIndexing:
params = ["monotonic_incr", "monotonic_decr", "non_monotonic"]
param_names = ["index"]
def setup(self, index):
N = 10**5
values = list("a" * N + "b" * N + "c" * N)
indices = {
"monotonic_incr": CategoricalIndex(values),
"monotonic_decr": CategoricalIndex(reversed(values)),
"non_monotonic": CategoricalIndex(list("abc" * N)),
}
self.data = indices[index]
self.data_unique = CategoricalIndex([
"".join(perm)
for perm in itertools.permutations(string.printable, 3)
])
self.int_scalar = 10000
self.int_list = list(range(10000))
self.cat_scalar = "b"
self.cat_list = ["a", "c"]
def time_getitem_scalar(self, index):
self.data[self.int_scalar]
def time_getitem_slice(self, index):
self.data[:self.int_scalar]
def time_getitem_list_like(self, index):
self.data[[self.int_scalar]]
def time_getitem_list(self, index):
self.data[self.int_list]
def time_getitem_bool_array(self, index):
self.data[self.data == self.cat_scalar]
def time_get_loc_scalar(self, index):
self.data.get_loc(self.cat_scalar)
def time_get_indexer_list(self, index):
self.data_unique.get_indexer(self.cat_list)
def test_get_indexer_array(self):
arr = np.array(
[Timestamp("1999-12-31 00:00:00"), Timestamp("2000-12-31 00:00:00")],
dtype=object,
)
cats = [Timestamp("1999-12-31 00:00:00"), Timestamp("2000-12-31 00:00:00")]
ci = CategoricalIndex(cats, categories=cats, ordered=False, dtype="category")
result = ci.get_indexer(arr)
expected = np.array([0, 1], dtype="intp")
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_array(self):
arr = np.array([Timestamp('1999-12-31 00:00:00'),
Timestamp('2000-12-31 00:00:00')], dtype=object)
cats = [Timestamp('1999-12-31 00:00:00'),
Timestamp('2000-12-31 00:00:00')]
ci = CategoricalIndex(cats,
categories=cats,
ordered=False, dtype='category')
result = ci.get_indexer(arr)
expected = np.array([0, 1], dtype='intp')
tm.assert_numpy_array_equal(result, expected)
def test_get_indexer_method(self):
idx1 = CategoricalIndex(list("aabcde"), categories=list("edabc"))
idx2 = CategoricalIndex(list("abf"))
msg = "method pad not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="pad")
msg = "method backfill not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="backfill")
msg = "method nearest not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="nearest")
def test_get_indexer(self):
idx1 = CategoricalIndex(list("aabcde"), categories=list("edabc"))
idx2 = CategoricalIndex(list("abf"))
for indexer in [idx2, list("abf"), Index(list("abf"))]:
r1 = idx1.get_indexer(idx2)
tm.assert_almost_equal(r1, np.array([0, 1, 2, -1], dtype=np.intp))
msg = "method pad not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="pad")
msg = "method backfill not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="backfill")
msg = "method nearest not yet implemented for CategoricalIndex"
with pytest.raises(NotImplementedError, match=msg):
idx2.get_indexer(idx1, method="nearest")
