Skip to content

DEPR: Silent dropping of nuisance columns in transform_dict_like #43743

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.

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
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions doc/source/whatsnew/v1.4.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -337,6 +337,7 @@ Other Deprecations
- Deprecated the ``squeeze`` argument to :meth:`read_csv`, :meth:`read_table`, and :meth:`read_excel`. Users should squeeze the DataFrame afterwards with ``.squeeze("columns")`` instead. (:issue:`43242`)
- Deprecated the ``index`` argument to :class:`SparseArray` construction (:issue:`23089`)
- Deprecated :meth:`.Rolling.validate`, :meth:`.Expanding.validate`, and :meth:`.ExponentialMovingWindow.validate` (:issue:`43665`)
- Deprecated silent dropping of columns that raised a ``TypeError`` in :class:`Series.transform` and :class:`DataFrame.transform` when used with a dictionary (:issue:`43740`)
Copy link
Member

Choose a reason for hiding this comment

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

is GroupBy.transform also affected? (same question for the agg PR)

Copy link
Member Author

Choose a reason for hiding this comment

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

No - groupby.transform does not accept dictionaries (or lists)


.. ---------------------------------------------------------------------------

Expand Down
13 changes: 7 additions & 6 deletions pandas/core/apply.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
FrameOrSeries,
)
from pandas.util._decorators import cache_readonly
from pandas.util._exceptions import find_stack_level

from pandas.core.dtypes.cast import is_nested_object
from pandas.core.dtypes.common import (
Expand Down Expand Up @@ -271,21 +272,21 @@ def transform_dict_like(self, func):
"No transform functions were provided",
}:
raise err
elif not isinstance(err, TypeError):
all_type_errors = False
else:
if not isinstance(err, TypeError):
all_type_errors = False
failed_names.append(name)
# combine results
if not results:
klass = TypeError if all_type_errors else ValueError
raise klass("Transform function failed")
if len(failed_names) > 0:
warnings.warn(
f"{failed_names} did not transform successfully and did not raise "
f"a TypeError. If any error is raised except for TypeError, "
f"this will raise in a future version of pandas. "
f"{failed_names} did not transform successfully. If any error is "
f"raised, this will raise in a future version of pandas. "
f"Drop these columns/ops to avoid this warning.",
FutureWarning,
stacklevel=4,
stacklevel=find_stack_level(),
)
return concat(results, axis=1)

Expand Down
21 changes: 14 additions & 7 deletions pandas/tests/apply/test_frame_transform.py
Original file line number Diff line number Diff line change
Expand Up @@ -160,33 +160,40 @@ def test_transform_bad_dtype(op, frame_or_series, request):
@pytest.mark.parametrize("op", frame_kernels_raise)
def test_transform_partial_failure_typeerror(op):
# GH 35964

if op == "rank":
pytest.skip("GH 40418: rank does not raise a TypeError")

# Using object makes most transform kernels fail
df = DataFrame({"A": 3 * [object], "B": [1, 2, 3]})

expected = df[["B"]].transform([op])
result = df.transform([op])
match = r"\['A'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = df.transform([op])
tm.assert_equal(result, expected)

expected = df[["B"]].transform({"B": op})
result = df.transform({"A": op, "B": op})
match = r"\['A'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = df.transform({"A": op, "B": op})
tm.assert_equal(result, expected)

expected = df[["B"]].transform({"B": [op]})
result = df.transform({"A": [op], "B": [op]})
match = r"\['A'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = df.transform({"A": [op], "B": [op]})
tm.assert_equal(result, expected)

expected = df.transform({"A": ["shift"], "B": [op]})
result = df.transform({"A": [op, "shift"], "B": [op]})
match = rf"\['{op}'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = df.transform({"A": [op, "shift"], "B": [op]})
tm.assert_equal(result, expected)


def test_transform_partial_failure_valueerror():
# GH 40211
match = ".*did not transform successfully and did not raise a TypeError"
match = ".*did not transform successfully"

def op(x):
if np.sum(np.sum(x)) < 10:
Expand All @@ -211,7 +218,7 @@ def op(x):
tm.assert_equal(result, expected)

expected = df.transform({"A": ["shift"], "B": [op]})
with tm.assert_produces_warning(FutureWarning, match=match, check_stacklevel=False):
with tm.assert_produces_warning(FutureWarning, match=match):
result = df.transform({"A": [op, "shift"], "B": [op]})
tm.assert_equal(result, expected)

Expand Down
24 changes: 17 additions & 7 deletions pandas/tests/apply/test_series_apply.py
Original file line number Diff line number Diff line change
Expand Up @@ -291,25 +291,35 @@ def test_transform_partial_failure(op, request):
ser = Series(3 * [object])

expected = ser.transform(["shift"])
result = ser.transform([op, "shift"])
match = rf"\['{op}'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = ser.transform([op, "shift"])
tm.assert_equal(result, expected)

expected = ser.transform({"B": "shift"})
result = ser.transform({"A": op, "B": "shift"})
match = r"\['A'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = ser.transform({"A": op, "B": "shift"})
tm.assert_equal(result, expected)

expected = ser.transform({"B": ["shift"]})
result = ser.transform({"A": [op], "B": ["shift"]})
match = r"\['A'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = ser.transform({"A": [op], "B": ["shift"]})
tm.assert_equal(result, expected)

expected = ser.transform({"A": ["shift"], "B": [op]})
result = ser.transform({"A": [op, "shift"], "B": [op]})
match = r"\['B'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
expected = ser.transform({"A": ["shift"], "B": [op]})
match = rf"\['{op}'\] did not transform successfully"
with tm.assert_produces_warning(FutureWarning, match=match):
result = ser.transform({"A": [op, "shift"], "B": [op]})
tm.assert_equal(result, expected)


def test_transform_partial_failure_valueerror():
# GH 40211
match = ".*did not transform successfully and did not raise a TypeError"
match = ".*did not transform successfully"

def noop(x):
return x
Expand All @@ -335,7 +345,7 @@ def raising_op(_):
tm.assert_equal(result, expected)

expected = ser.transform({"A": [noop], "B": [noop]})
with tm.assert_produces_warning(FutureWarning, match=match, check_stacklevel=False):
with tm.assert_produces_warning(FutureWarning, match=match):
result = ser.transform({"A": [noop, raising_op], "B": [noop]})
tm.assert_equal(result, expected)

Expand Down