Skip to content

BUG: Fix error for boxplot when using a pre-grouped DataFrame with more than one grouping #57985

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 9 commits into from
Mar 31, 2024
Merged
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v3.0.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -409,7 +409,7 @@ Period

Plotting
^^^^^^^^
-
- Bug in :meth:`.DataFrameGroupBy.boxplot` failed when there were multiple groupings (:issue:`14701`)
-

Groupby/resample/rolling
Expand Down
6 changes: 3 additions & 3 deletions pandas/plotting/_matplotlib/boxplot.py
Original file line number Diff line number Diff line change
Expand Up @@ -533,14 +533,14 @@ def boxplot_frame_groupby(
)
axes = flatten_axes(axes)

ret = pd.Series(dtype=object)

data = {}
for (key, group), ax in zip(grouped, axes):
d = group.boxplot(
ax=ax, column=column, fontsize=fontsize, rot=rot, grid=grid, **kwds
)
ax.set_title(pprint_thing(key))
ret.loc[key] = d
data[key] = d
ret = pd.Series(data)
maybe_adjust_figure(fig, bottom=0.15, top=0.9, left=0.1, right=0.9, wspace=0.2)
else:
keys, frames = zip(*grouped)
Expand Down
14 changes: 14 additions & 0 deletions pandas/tests/plotting/test_boxplot_method.py
Original file line number Diff line number Diff line change
Expand Up @@ -740,3 +740,17 @@ def test_boxplot_multiindex_column(self):
expected_xticklabel = ["(bar, one)", "(bar, two)"]
result_xticklabel = [x.get_text() for x in axes.get_xticklabels()]
assert expected_xticklabel == result_xticklabel

@pytest.mark.parametrize("group", ["X", ["X", "Y"]])
def test_boxplot_multi_groupby_groups(self, group):
# GH 14701
rows = 20
df = DataFrame(
np.random.default_rng(12).normal(size=(rows, 2)), columns=["Col1", "Col2"]
)
df["X"] = Series(np.repeat(["A", "B"], int(rows / 2)))
df["Y"] = Series(np.tile(["C", "D"], int(rows / 2)))
grouped = df.groupby(group)
_check_plot_works(df.boxplot, by=group, default_axes=True)
_check_plot_works(df.plot.box, by=group, default_axes=True)
_check_plot_works(grouped.boxplot, default_axes=True)
Loading