Skip to content
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

BUG: Categorical scatter plot has KeyError #16199 #16208

Merged
merged 2 commits into from
Jun 12, 2017
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/v0.20.3.txt
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ Performance Improvements

Bug Fixes
~~~~~~~~~
- Fixed issue with dataframe scatter plot for categorical data that reports incorrect column key not found when categorical data is used for plotting (:issue:`16199`)



Expand Down
5 changes: 5 additions & 0 deletions pandas/plotting/_core.py
Original file line number Diff line number Diff line change
Expand Up @@ -778,6 +778,11 @@ def __init__(self, data, x, y, **kwargs):
x = self.data.columns[x]
if is_integer(y) and not self.data.columns.holds_integer():
y = self.data.columns[y]
if len(self.data[x]._get_numeric_data()) == 0:
raise ValueError(self._kind + ' requires x column to be numeric')
if len(self.data[y]._get_numeric_data()) == 0:
raise ValueError(self._kind + ' requires y column to be numeric')

self.x = x
self.y = y

Expand Down
18 changes: 18 additions & 0 deletions pandas/tests/plotting/test_frame.py
Original file line number Diff line number Diff line change
Expand Up @@ -915,6 +915,24 @@ def test_plot_scatter(self):
axes = df.plot(x='x', y='y', kind='scatter', subplots=True)
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))

@slow
def test_plot_scatter_with_categorical_data(self):
# GH 16199
df = pd.DataFrame({'x': [1, 2, 3, 4],
'y': pd.Categorical(['a', 'b', 'a', 'c'])})

with pytest.raises(ValueError) as ve:
df.plot(x='x', y='y', kind='scatter')
ve.match('requires y column to be numeric')

with pytest.raises(ValueError) as ve:
df.plot(x='y', y='x', kind='scatter')
ve.match('requires x column to be numeric')

with pytest.raises(ValueError) as ve:
df.plot(x='y', y='y', kind='scatter')
ve.match('requires x column to be numeric')

@slow
def test_plot_scatter_with_c(self):
df = DataFrame(randn(6, 4),
Expand Down