Skip to content

TST: expand tests for ExtensionArray setitem with nullable arrays #31741

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 9 commits into from
Feb 13, 2020
Merged

TST: expand tests for ExtensionArray setitem with nullable arrays #31741

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
a62dbda
TST: expand tests for ExtensionArray setitem with nullable arrays
jorisvandenbossche Feb 6, 2020
3d713ef
combine tests
jorisvandenbossche Feb 6, 2020
d2e1af5
fix numpy test
jorisvandenbossche Feb 7, 2020
af11ed0
test msg
jorisvandenbossche Feb 7, 2020
ceb1a3c
Merge remote-tracking branch 'upstream/master' into setitem-tests
jorisvandenbossche Feb 10, 2020
8796c6e
use xfail
jorisvandenbossche Feb 10, 2020
0be92b7
fix numpy test
jorisvandenbossche Feb 10, 2020
ac970c6
Merge remote-tracking branch 'upstream/master' into setitem-tests
jorisvandenbossche Feb 13, 2020
db73fff
add xfail reason
jorisvandenbossche Feb 13, 2020
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
99 changes: 87 additions & 12 deletions pandas/tests/extension/base/setitem.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
import pytest

import pandas as pd
from pandas.core.arrays.numpy_ import PandasDtype
import pandas._testing as tm

from .base import BaseExtensionTests

Expand Down Expand Up @@ -93,6 +93,92 @@ def test_setitem_iloc_scalar_multiple_homogoneous(self, data):
df.iloc[10, 1] = data[1]
assert df.loc[10, "B"] == data[1]

@pytest.mark.parametrize(
Copy link
Contributor

Choose a reason for hiding this comment

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

think about adding a new class here; these are specifically for setitem_mask (could be a followon)

Copy link
Member Author

Choose a reason for hiding this comment

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

think about adding a new class here; these are specifically for setitem_mask (could be a followon)

In general, changing names is annoying for downstream consumers of those tests (this are the base extension tests), so not worth here I think

Copy link
Contributor

Choose a reason for hiding this comment

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

ok, I don't buy your argument, these are experimental features where we actually to expand test coverage. its going to happen (but ok for now)

"mask",
[
np.array([True, True, True, False, False]),
pd.array([True, True, True, False, False], dtype="boolean"),
],
ids=["numpy-array", "boolean-array"],
)
def test_setitem_mask(self, data, mask, box_in_series):
arr = data[:5].copy()
expected = arr.take([0, 0, 0, 3, 4])
if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)
arr[mask] = data[0]
self.assert_equal(expected, arr)

def test_setitem_mask_raises(self, data, box_in_series):
# wrong length
mask = np.array([True, False])

if box_in_series:
data = pd.Series(data)

with pytest.raises(IndexError, match="wrong length"):
data[mask] = data[0]

mask = pd.array(mask, dtype="boolean")
with pytest.raises(IndexError, match="wrong length"):
data[mask] = data[0]

def test_setitem_mask_boolean_array_raises(self, data, box_in_series):
# missing values in mask
mask = pd.array(np.zeros(data.shape, dtype="bool"), dtype="boolean")
mask[:2] = pd.NA

if box_in_series:
data = pd.Series(data)

msg = (
"Cannot mask with a boolean indexer containing NA values|"
"cannot mask with array containing NA / NaN values"
)
with pytest.raises(ValueError, match=msg):
data[mask] = data[0]

@pytest.mark.parametrize(
"idx",
[[0, 1, 2], pd.array([0, 1, 2], dtype="Int64"), np.array([0, 1, 2])],
ids=["list", "integer-array", "numpy-array"],
Copy link
Contributor

Choose a reason for hiding this comment

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

labels should be: extension-integer-array, numpy-integer-array to be more informative

)
def test_setitem_integer_array(self, data, idx, box_in_series):
arr = data[:5].copy()
expected = data.take([0, 0, 0, 3, 4])

if box_in_series:
arr = pd.Series(arr)
expected = pd.Series(expected)

arr[idx] = arr[0]
self.assert_equal(arr, expected)

@pytest.mark.parametrize(
"idx, box_in_series",
[
([0, 1, 2, pd.NA], False),
pytest.param(
[0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
],
ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
)
def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
arr = data.copy()

# TODO(xfail) this raises KeyError about labels not found (it tries label-based)
# for list of labels with Series
if box_in_series:
arr = pd.Series(data, index=[tm.rands(4) for _ in range(len(data))])

msg = "Cannot index with an integer indexer containing NA values"
with pytest.raises(ValueError, match=msg):
arr[idx] = arr[0]

@pytest.mark.parametrize("as_callable", [True, False])
@pytest.mark.parametrize("setter", ["loc", None])
def test_setitem_mask_aligned(self, data, as_callable, setter):
Expand Down Expand Up @@ -219,14 +305,3 @@ def test_setitem_preserves_views(self, data):
data[0] = data[1]
assert view1[0] == data[1]
assert view2[0] == data[1]

def test_setitem_nullable_mask(self, data):
# GH 31446
# TODO: there is some issue with PandasArray, therefore,
# TODO: skip the setitem test for now, and fix it later
if data.dtype != PandasDtype("object"):
arr = data[:5]
expected = data.take([0, 0, 0, 3, 4])
mask = pd.array([True, True, True, False, False])
arr[mask] = data[0]
self.assert_extension_array_equal(expected, arr)
46 changes: 46 additions & 0 deletions pandas/tests/extension/test_numpy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,6 +396,52 @@ def test_setitem_scalar_key_sequence_raise(self, data):
# Failed: DID NOT RAISE <class 'ValueError'>
super().test_setitem_scalar_key_sequence_raise(data)

# TODO: there is some issue with PandasArray, therefore,
# skip the setitem test for now, and fix it later (GH 31446)

@skip_nested
@pytest.mark.parametrize(
"mask",
[
np.array([True, True, True, False, False]),
pd.array([True, True, True, False, False], dtype="boolean"),
],
ids=["numpy-array", "boolean-array"],
)
def test_setitem_mask(self, data, mask, box_in_series):
super().test_setitem_mask(data, mask, box_in_series)

@skip_nested
def test_setitem_mask_raises(self, data, box_in_series):
super().test_setitem_mask_raises(data, box_in_series)

@skip_nested
def test_setitem_mask_boolean_array_raises(self, data, box_in_series):
super().test_setitem_mask_boolean_array_raises(data, box_in_series)

@skip_nested
@pytest.mark.parametrize(
"idx",
[[0, 1, 2], pd.array([0, 1, 2], dtype="Int64"), np.array([0, 1, 2])],
ids=["list", "integer-array", "numpy-array"],
)
def test_setitem_integer_array(self, data, idx, box_in_series):
super().test_setitem_integer_array(data, idx, box_in_series)

@skip_nested
@pytest.mark.parametrize(
"idx, box_in_series",
[
([0, 1, 2, pd.NA], False),
pytest.param([0, 1, 2, pd.NA], True, marks=pytest.mark.xfail),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
(pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
],
ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
)
def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
super().test_setitem_integer_with_missing_raises(data, idx, box_in_series)

@skip_nested
def test_setitem_slice(self, data, box_in_series):
super().test_setitem_slice(data, box_in_series)
Expand Down