Skip to content

TST: xfail incorrect test_empty_groupby #41341

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 1 commit into from
May 6, 2021
Merged

TST: xfail incorrect test_empty_groupby #41341

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
69 changes: 62 additions & 7 deletions pandas/tests/groupby/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1724,27 +1724,82 @@ def test_pivot_table_values_key_error():
[0],
[0.0],
["a"],
[Categorical([0])],
Categorical([0]),
[to_datetime(0)],
[date_range(0, 1, 1, tz="US/Eastern")],
[pd.array([0], dtype="Int64")],
[pd.array([0], dtype="Float64")],
[pd.array([False], dtype="boolean")],
date_range(0, 1, 1, tz="US/Eastern"),
pd.array([0], dtype="Int64"),
pd.array([0], dtype="Float64"),
pd.array([False], dtype="boolean"),
],
)
@pytest.mark.parametrize("method", ["attr", "agg", "apply"])
@pytest.mark.parametrize(
"op", ["idxmax", "idxmin", "mad", "min", "max", "sum", "prod", "skew"]
)
def test_empty_groupby(columns, keys, values, method, op):
def test_empty_groupby(columns, keys, values, method, op, request):
# GH8093 & GH26411

if isinstance(values, Categorical) and len(keys) == 1 and method == "apply":
Copy link
Contributor

Choose a reason for hiding this comment

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

ok, plan is to address the root cause and unxfail these as appropriate at some point?

Copy link
Member Author

Choose a reason for hiding this comment

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

yes, immediately xref #41342

Copy link
Member Author

Choose a reason for hiding this comment

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

(will need to rebase #41342 after this)

mark = pytest.mark.xfail(raises=TypeError, match="'str' object is not callable")
request.node.add_marker(mark)
elif (
isinstance(values, Categorical)
and len(keys) == 1
and op in ["idxmax", "idxmin"]
):
mark = pytest.mark.xfail(
raises=ValueError, match="attempt to get arg(min|max) of an empty sequence"
)
request.node.add_marker(mark)
elif (
isinstance(values, Categorical)
and len(keys) == 1
and not isinstance(columns, list)
):
mark = pytest.mark.xfail(
raises=TypeError, match="'Categorical' does not implement"
)
request.node.add_marker(mark)
elif (
isinstance(values, Categorical)
and len(keys) == 1
and op in ["mad", "min", "max", "sum", "prod", "skew"]
):
mark = pytest.mark.xfail(
raises=AssertionError, match="(DataFrame|Series) are different"
)
request.node.add_marker(mark)
elif (
isinstance(values, Categorical)
and len(keys) == 2
and op in ["min", "max", "sum"]
and method != "apply"
):
mark = pytest.mark.xfail(
raises=AssertionError, match="(DataFrame|Series) are different"
)
request.node.add_marker(mark)
elif (
isinstance(values, pd.core.arrays.BooleanArray)
and op in ["sum", "prod"]
and method != "apply"
):
mark = pytest.mark.xfail(
raises=AssertionError, match="(DataFrame|Series) are different"
)
request.node.add_marker(mark)

override_dtype = None
if isinstance(values[0], bool) and op in ("prod", "sum") and method != "apply":
# sum/product of bools is an integer
override_dtype = "int64"

df = DataFrame([3 * values], columns=list("ABC"))
df = DataFrame({"A": values, "B": values, "C": values}, columns=list("ABC"))

if hasattr(values, "dtype"):
# check that we did the construction right
assert (df.dtypes == values.dtype).all()

df = df.iloc[:0]

gb = df.groupby(keys)[columns]
Expand Down