def test_multiindex_objects(self):
mi = MultiIndex(levels=[['b', 'd', 'a'], [1, 2, 3]],
labels=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=['col1', 'col2'])
recons = mi._sort_levels_monotonic()
# these are equal
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# _hashed_values and hash_pandas_object(..., index=False)
# equivalency
expected = hash_pandas_object(mi, index=False).values
result = mi._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = hash_pandas_object(recons, index=False).values
result = recons._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = mi._hashed_values
result = recons._hashed_values
# values should match, but in different order
tm.assert_numpy_array_equal(np.sort(result), np.sort(expected))
def test_multiindex_objects(self):
mi = MultiIndex(levels=[['b', 'd', 'a'], [1, 2, 3]],
labels=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=['col1', 'col2'])
recons = mi._sort_levels_monotonic()
# these are equal
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# _hashed_values and hash_pandas_object(..., index=False)
# equivalency
expected = hash_pandas_object(
mi, index=False).values
result = mi._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = hash_pandas_object(
recons, index=False).values
result = recons._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = mi._hashed_values
result = recons._hashed_values
# values should match, but in different order
tm.assert_numpy_array_equal(np.sort(result),
np.sort(expected))
def test_reconstruct_sort():
# starts off lexsorted & monotonic
mi = MultiIndex.from_arrays([["A", "A", "B", "B", "B"], [1, 2, 1, 2, 3]])
assert mi.is_monotonic_increasing
recons = mi._sort_levels_monotonic()
assert recons.is_monotonic_increasing
assert mi is recons
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = MultiIndex.from_tuples(
[("z", "a"), ("x", "a"), ("y", "b"), ("x", "b"), ("y", "a"),
("z", "b")],
names=["one", "two"],
)
assert not mi.is_monotonic_increasing
recons = mi._sort_levels_monotonic()
assert not recons.is_monotonic_increasing
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = MultiIndex(
levels=[["b", "d", "a"], [1, 2, 3]],
codes=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=["col1", "col2"],
)
assert not mi.is_monotonic_increasing
recons = mi._sort_levels_monotonic()
assert not recons.is_monotonic_increasing
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
def test_multiindex_objects():
mi = MultiIndex(
levels=[["b", "d", "a"], [1, 2, 3]],
codes=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=["col1", "col2"],
)
recons = mi._sort_levels_monotonic()
# These are equal.
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# _hashed_values and hash_pandas_object(..., index=False) equivalency.
expected = hash_pandas_object(mi, index=False).values
result = mi._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = hash_pandas_object(recons, index=False).values
result = recons._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = mi._hashed_values
result = recons._hashed_values
# Values should match, but in different order.
tm.assert_numpy_array_equal(np.sort(result), np.sort(expected))
def test_multiindex_objects():
mi = MultiIndex(levels=[["b", "d", "a"], [1, 2, 3]],
codes=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=["col1", "col2"])
recons = mi._sort_levels_monotonic()
# These are equal.
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# _hashed_values and hash_pandas_object(..., index=False) equivalency.
expected = hash_pandas_object(mi, index=False).values
result = mi._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = hash_pandas_object(recons, index=False).values
result = recons._hashed_values
tm.assert_numpy_array_equal(result, expected)
expected = mi._hashed_values
result = recons._hashed_values
# Values should match, but in different order.
tm.assert_numpy_array_equal(np.sort(result), np.sort(expected))
def mi_intersection(left: pd.MultiIndex,
right: pd.MultiIndex) -> pd.MultiIndex: # pragma: no cover
"""Intersection of MultiIndexes, preserving order.
Fix https://github.com/pandas-dev/pandas/issues/31325
"""
if left.equals(right):
return left
lvals = left._ndarray_values
rvals = right._ndarray_values
uniq_tuples = None # flag whether _inner_indexer was successful
if left.is_monotonic and right.is_monotonic:
try:
uniq_tuples = left._inner_indexer(lvals, rvals)[0]
except TypeError:
pass # noqa:WPS420
if uniq_tuples is None:
right_uniq = set(rvals)
seen: Set[Tuple] = set()
uniq_tuples = [
x for x in lvals if x in right_uniq
and not (x in seen or seen.add(x)) # type: ignore
]
names = left.names if left.names == right.names else None
if len(uniq_tuples) == 0:
return pd.MultiIndex(
levels=left.levels,
codes=[[]] * left.nlevels,
names=names,
verify_integrity=False,
)
return pd.MultiIndex.from_tuples(uniq_tuples, sortorder=0, names=names)
def test_multiindex_objects():
mi = MultiIndex(
levels=[["b", "d", "a"], [1, 2, 3]],
codes=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=["col1", "col2"],
)
recons = mi._sort_levels_monotonic()
# These are equal.
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
def test_equals_multi(idx):
assert idx.equals(idx)
assert not idx.equals(idx.values)
assert idx.equals(Index(idx.values))
assert idx.equal_levels(idx)
assert not idx.equals(idx[:-1])
assert not idx.equals(idx[-1])
# different number of levels
index = MultiIndex(
levels=[
Index(list(range(4))),
Index(list(range(4))),
Index(list(range(4)))
],
codes=[
np.array([0, 0, 1, 2, 2, 2, 3, 3]),
np.array([0, 1, 0, 0, 0, 1, 0, 1]),
np.array([1, 0, 1, 1, 0, 0, 1, 0]),
],
)
index2 = MultiIndex(levels=index.levels[:-1], codes=index.codes[:-1])
assert not index.equals(index2)
assert not index.equal_levels(index2)
# levels are different
major_axis = Index(list(range(4)))
minor_axis = Index(list(range(2)))
major_codes = np.array([0, 0, 1, 2, 2, 3])
minor_codes = np.array([0, 1, 0, 0, 1, 0])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
assert not idx.equal_levels(index)
# some of the labels are different
major_axis = Index(["foo", "bar", "baz", "qux"])
minor_axis = Index(["one", "two"])
major_codes = np.array([0, 0, 2, 2, 3, 3])
minor_codes = np.array([0, 1, 0, 1, 0, 1])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
def test_equals_multi(idx):
assert idx.equals(idx)
assert not idx.equals(idx.values)
assert idx.equals(Index(idx.values))
assert idx.equal_levels(idx)
assert not idx.equals(idx[:-1])
assert not idx.equals(idx[-1])
# different number of levels
index = MultiIndex(
levels=[Index(lrange(4)),
Index(lrange(4)),
Index(lrange(4))],
codes=[
np.array([0, 0, 1, 2, 2, 2, 3, 3]),
np.array([0, 1, 0, 0, 0, 1, 0, 1]),
np.array([1, 0, 1, 1, 0, 0, 1, 0])
])
index2 = MultiIndex(levels=index.levels[:-1], codes=index.codes[:-1])
assert not index.equals(index2)
assert not index.equal_levels(index2)
# levels are different
major_axis = Index(lrange(4))
minor_axis = Index(lrange(2))
major_codes = np.array([0, 0, 1, 2, 2, 3])
minor_codes = np.array([0, 1, 0, 0, 1, 0])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
assert not idx.equal_levels(index)
# some of the labels are different
major_axis = Index(['foo', 'bar', 'baz', 'qux'])
minor_axis = Index(['one', 'two'])
major_codes = np.array([0, 0, 2, 2, 3, 3])
minor_codes = np.array([0, 1, 0, 1, 0, 1])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
def test_reconstruct_sort():
# starts off lexsorted & monotonic
mi = MultiIndex.from_arrays([
['A', 'A', 'B', 'B', 'B'], [1, 2, 1, 2, 3]
])
assert mi.is_lexsorted()
assert mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert recons.is_lexsorted()
assert recons.is_monotonic
assert mi is recons
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = pd.MultiIndex.from_tuples([('z', 'a'), ('x', 'a'), ('y', 'b'),
('x', 'b'), ('y', 'a'), ('z', 'b')],
names=['one', 'two'])
assert not mi.is_lexsorted()
assert not mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert not recons.is_lexsorted()
assert not recons.is_monotonic
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = MultiIndex(levels=[['b', 'd', 'a'], [1, 2, 3]],
labels=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=['col1', 'col2'])
assert not mi.is_lexsorted()
assert not mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert not recons.is_lexsorted()
assert not recons.is_monotonic
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
def test_reconstruct_sort():
# starts off lexsorted & monotonic
mi = MultiIndex.from_arrays([
['A', 'A', 'B', 'B', 'B'], [1, 2, 1, 2, 3]
])
assert mi.is_lexsorted()
assert mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert recons.is_lexsorted()
assert recons.is_monotonic
assert mi is recons
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = pd.MultiIndex.from_tuples([('z', 'a'), ('x', 'a'), ('y', 'b'),
('x', 'b'), ('y', 'a'), ('z', 'b')],
names=['one', 'two'])
assert not mi.is_lexsorted()
assert not mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert not recons.is_lexsorted()
assert not recons.is_monotonic
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
# cannot convert to lexsorted
mi = MultiIndex(levels=[['b', 'd', 'a'], [1, 2, 3]],
codes=[[0, 1, 0, 2], [2, 0, 0, 1]],
names=['col1', 'col2'])
assert not mi.is_lexsorted()
assert not mi.is_monotonic
recons = mi._sort_levels_monotonic()
assert not recons.is_lexsorted()
assert not recons.is_monotonic
assert mi.equals(recons)
assert Index(mi.values).equals(Index(recons.values))
def test_equals_multi(idx):
assert idx.equals(idx)
assert not idx.equals(idx.values)
assert idx.equals(Index(idx.values))
assert idx.equal_levels(idx)
assert not idx.equals(idx[:-1])
assert not idx.equals(idx[-1])
# different number of levels
index = MultiIndex(levels=[Index(list(range(4))),
Index(list(range(4))),
Index(list(range(4)))],
codes=[np.array([0, 0, 1, 2, 2, 2, 3, 3]),
np.array([0, 1, 0, 0, 0, 1, 0, 1]),
np.array([1, 0, 1, 1, 0, 0, 1, 0])],
)
index2 = MultiIndex(levels=index.levels[:-1], codes=index.codes[:-1])
assert not index.equals(index2)
assert not index.equal_levels(index2)
# levels are different
major_axis = Index(list(range(4)))
minor_axis = Index(list(range(2)))
major_codes = np.array([0, 0, 1, 2, 2, 3])
minor_codes = np.array([0, 1, 0, 0, 1, 0])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
assert not idx.equal_levels(index)
# some of the labels are different
major_axis = Index(['foo', 'bar', 'baz', 'qux'])
minor_axis = Index(['one', 'two'])
major_codes = np.array([0, 0, 2, 2, 3, 3])
minor_codes = np.array([0, 1, 0, 1, 0, 1])
index = MultiIndex(levels=[major_axis, minor_axis],
codes=[major_codes, minor_codes])
assert not idx.equals(index)
