8000 BUG: DatetimeIndex slicing with boolean Index raises TypeError by sinhrks · Pull Request #22852 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

BUG: DatetimeIndex slicing with boolean Index raises TypeError #22852

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 7, 2018
Merged

BUG: DatetimeIndex slicing with boolean Index raises TypeError #22852

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
04de511
BUG: DatetimeIndex slicing with boolean Index raises TypeError
sinhrks Sep 27, 2018
420e5c4
remove duplicated tesets
sinhrks Nov 1, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
BUG: DatetimeIndex slicing with boolean Index raises TypeError
  • Loading branch information
@sinhrks
sinhrks committed Nov 7, 2018
commit 04de5118a8c92c8baa6ed38af48b20523664cbda
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v0.24.0.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1221,7 +1221,7 @@ Indexing
- Bug in `MultiIndex.set_levels` when levels value is not subscriptable (:issue:`23273`)
- Bug where setting a timedelta column by ``Index`` causes it to be casted to double, and therefore lose precision (:issue:`23511`)
- Bug in :func:`Index.union` and :func:`Index.intersection` where name of the ``Index`` of the result was not computed correctly for certain cases (:issue:`9943`, :issue:`9862`)

- Bug in :class:`Index` slicing with boolean :class:`Index` may raise ``TypeError`` (:issue:`22533`)

Missing
^^^^^^^
Expand Down
2 changes: 1 addition & 1 deletion pandas/core/arrays/datetimelike.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,7 +161,7 @@ def __getitem__(self, key):
return self._box_func(val)

if com.is_bool_indexer(key):
key = np.asarray(key)
key = np.asarray(key, dtype=bool)
if key.all():
key = slice(0, None, None)
else:
Expand Down
2 changes: 1 addition & 1 deletion pandas/core/indexes/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2078,7 +2078,7 @@ def __getitem__(self, key):
return promote(getitem(key))

if com.is_bool_indexer(key):
key = np.asarray(key)
key = np.asarray(key, dtype=bool)

key = com.values_from_object(key)
result = getitem(key)
Expand Down
2 changes: 1 addition & 1 deletion pandas/core/indexes/multi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1614,7 +1614,7 @@ def __getitem__(self, key):
return tuple(retval)
else:
if com.is_bool_indexer(key):
key = np.asarray(key)
key = np.asarray(key, dtype=bool)
sortorder = self.sortorder
else:
# cannot be sure whether the result will be sorted
Expand Down
22 changes: 22 additions & 0 deletions pandas/tests/indexes/datetimes/test_indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -603,3 +603,25 @@ def test_get_loc_nat(self):
# GH#20464
index = DatetimeIndex(['1/3/2000', 'NaT'])
assert index.get_loc(pd.NaT) == 1

@pytest.mark.parametrize('ind1', [[True] * 5, pd.Index([True] * 5)])
@pytest.mark.parametrize('ind2', [[True, False, True, False, False],
pd.Index([True, False, True, False,
False])])
def test_getitem_bool_index_all(self, ind1, ind2):
# GH#22533
idx = pd.date_range('2011-01-01', '2011-01-05', freq='D', name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.DatetimeIndex(['2011-01-01', '2011-01-03'], name='idx')
tm.assert_index_equal(idx[ind2], expected)

@pytest.mark.parametrize('ind1', [[True], pd.Index([True])])
@pytest.mark.parametrize('ind2', [[False], pd.Index([False])])
def test_getitem_bool_index_single(self, ind1, ind2):
# GH#22533
idx = pd.DatetimeIndex(['2011-01-01'], name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.DatetimeIndex([], name='idx')
tm.assert_index_equal(idx[ind2], expected)
27 changes: 27 additions & 0 deletions pandas/tests/indexes/multi/test_indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,33 @@ def test_get_indexer_consistency(idx):
assert indexer.dtype == np.intp


@pytest.mark.parametrize('ind1', [[True] * 5, pd.Index([True] * 5)])
@pytest.mark.parametrize('ind2', [[True, False, True, False, False],
pd.Index([True, False, True, False,
False])])
def test_getitem_bool_index_all(ind1, ind2):
# GH#22533
idx = MultiIndex.from_tuples([(10, 1), (20, 2), (30, 3),
(40, 4), (50, 5)])
tm.assert_index_equal(idx[ind1], idx)

expected = MultiIndex.from_tuples([(10, 1), (30, 3)])
tm.assert_index_equal(idx[ind2], expected)


@pytest.mark.parametrize('ind1', [[True], pd.Index([True])])
@pytest.mark.parametrize('ind2', [[False], pd.Index([False])])
def test_getitem_bool_index_single(ind1, ind2):
# GH#22533
idx = MultiIndex.from_tuples([(10, 1)])
tm.assert_index_equal(idx[ind1], idx)

expected = pd.MultiIndex(levels=[np.array([], dtype=np.int64),
np.array([], dtype=np.int64)],
labels=[[], []])
tm.assert_index_equal(idx[ind2], expected)


def test_get_loc(idx):
assert idx.get_loc(('foo', 'two')) == 1
assert idx.get_loc(('baz', 'two')) == 3
Expand Down
22 changes: 22 additions & 0 deletions pandas/tests/indexes/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,6 +718,28 @@ def test_getitem_error(self, indices, itm):
with pytest.raises(IndexError):
indices[itm]

@pytest.mark.parametrize('ind1', [[True] * 5, pd.Index([True] * 5)])
@pytest.mark.parametrize('ind2', [[True, False, True, False, False],
pd.Index([True, False, True, False,
False])])
def test_getitem_bool_index_all(self, ind1, ind2):
# GH#22533
idx = pd.Index(['a', 'b', 'c', 'd', 'e'], name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.Index(['a', 'c'], name='idx')
tm.assert_index_equal(idx[ind2], expected)

@pytest.mark.parametrize('ind1', [[True], pd.Index([True])])
@pytest.mark.parametrize('ind2', [[False], pd.Index([False])])
def test_getitem_bool_index_single(self, ind1, ind2):
# GH#22533
idx = pd.Index(['a'], name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.Index([], name='idx')
tm.assert_index_equal(idx[ind2], expected)

def test_intersection(self):
first = self.strIndex[:20]
second = self.strIndex[:10]
Expand Down
22 changes: 22 additions & 0 deletions pandas/tests/indexes/test_numeric.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -839,6 +839,28 @@ def test_join_outer(self):
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)

@pytest.mark.parametrize('ind1', [[True] * 5, pd.Index([True] * 5)])
@pytest.mark.parametrize('ind2', [[True, False, True, False, False],
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you just add these all to TestIndexOps to get overage on all index (and series) for this. Note that there is an open issue to fixture this ;<

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK, added some tests to TestIndexOps.

pd.Index([True, False, True, False,
False])])
def test_getitem_bool_index_all(self, ind1, ind2):
# GH#22533
idx = pd.Int64Index([1, 2, 3, 4, 5], name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.Int64Index([1, 3], name='idx')
tm.assert_index_equal(idx[ind2], expected)

@pytest.mark.parametrize('ind1', [[True], pd.Index([True])])
@pytest.mark.parametrize('ind2', [[False], pd.Index([False])])
def test_getitem_bool_index_single(self, ind1, ind2):
# GH#22533
idx = pd.Int64Index([1], name='idx')
tm.assert_index_equal(idx[ind1], idx)

expected = pd.Int64Index([], name='idx')
tm.assert_index_equal(idx[ind2], expected)


class TestUInt64Index(NumericInt):

Expand Down
34 changes: 30 additions & 4 deletions pandas/tests/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,19 +178,20 @@ def setup_method(self, method):
self.unicode_index = tm.makeUnicodeIndex(10, name='a')

DD9C arr = np.random.randn(10)
self.bool_series = Series(arr, index=self.bool_index, name='a')
self.int_series = Series(arr, index=self.int_index, name='a')
self.float_series = Series(arr, index=self.float_index, name='a')
self.dt_series = Series(arr, index=self.dt_index, name='a')
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index, name='a')
self.string_series = Series(arr, index=self.string_index, name='a')
self.unicode_series = Series(arr, index=self.unicode_index, name='a')

types = ['bool', 'int', 'float', 'dt', 'dt_tz', 'period', 'string',
'unicode']
fmts = ["{0}_{1}".format(t, f)
for t in types for f in ['index', 'series']]
self.objs = [getattr(self, f)
for f in fmts if getattr(self, f, None) is not None]
self.indexes = [getattr(self, '{}_index'.format(t)) for t in types]
self.series = [getattr(self, '{}_series'.format(t)) for t in types]
self.objs = self.indexes + self.series

def check_ops_properties(self, props, filter=None, ignore_failures=False):
for op in props:
Expand Down Expand Up @@ -997,6 +998,31 @@ def test_validate_bool_args(self):
with pytest.raises(ValueError):
self.int_series.drop_duplicates(inplace=value)

def test_getitem(self):
for i in self.indexes:
s = pd.Series(i)

assert i[0] == s.iloc[0]
assert i[5] == s.iloc[5]
assert i[-1] == s.iloc[-1]

assert i[-1] == i[9]

pytest.raises(IndexError, i.__getitem__, 20)
pytest.raises(IndexError, s.iloc.__getitem__, 20)

@pytest.mark.parametrize('indexer_klass', [list, pd.Index])
@pytest.mark.parametrize('indexer', [[True] * 10, [False] * 10,
[True, False, True, True, False,
False, True, True, False, True]])
def test_bool_indexing(self, indexer_klass, indexer):
# GH 22533
for idx in self.indexes:
exp_idx = [i for i in range(len(indexer)) if indexer[i]]
tm.assert_index_equal(idx[indexer_klass(indexer)], idx[exp_idx])
s = pd.Series(idx)
tm.assert_series_equal(s[indexer_klass(indexer)], s.iloc[exp_idx])


class TestTranspose(Ops):
errmsg = "the 'axes' parameter is not supported"
Expand Down
0