Skip to content

BUG: pivot_table dropna=False drops columns/index names #12650

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

Closed
wants to merge 1 commit into from
Closed

BUG: pivot_table dropna=False drops columns/index names #12650

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions doc/source/whatsnew/v0.18.1.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,8 @@ Bug Fixes


- Bug in ``pivot_table`` when ``margins=True`` and ``dropna=True`` where nulls still contributed to margin count (:issue:`12577`)
- Bug in ``pivot_table`` when ``dropna=False`` where table index/column names disappear (:issue:`12133`)
- Bug in ``crosstab`` when ``margins=True`` and ``dropna=False`` raises ``level`` is ``none`` failure (:issue:`12642`)

- Bug in ``Series.name`` when ``name`` attribute can be a hashable type (:issue:`12610`)
- Bug in ``.describe()`` resets categorical columns information (:issue:`11558`)
Expand Down
6 changes: 4 additions & 2 deletions pandas/tools/pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,13 +128,15 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',

if not dropna:
try:
m = MultiIndex.from_arrays(cartesian_product(table.index.levels))
m = MultiIndex.from_arrays(cartesian_product(table.index.levels),
names=table.index.names)
table = table.reindex_axis(m, axis=0)
except AttributeError:
pass # it's a single level

try:
m = MultiIndex.from_arrays(cartesian_product(table.columns.levels))
m = MultiIndex.from_arrays(cartesian_product(table.columns.levels),
names=table.columns.names)
table = table.reindex_axis(m, axis=1)
except AttributeError:
pass # it's a single level or a series
Expand Down
62 changes: 59 additions & 3 deletions pandas/tools/tests/test_pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -899,8 +899,8 @@ def test_crosstab_dropna(self):
'two', 'two', 'two'], dtype=object)
c = np.array(['dull', 'dull', 'dull', 'dull',
'dull', 'shiny', 'shiny'], dtype=object)
res = crosstab(a, [b, c], rownames=['a'],
colnames=['b', 'c'], dropna=False)
res = pd.crosstab(a, [b, c], rownames=['a'],
colnames=['b', 'c'], dropna=False)
m = MultiIndex.from_tuples([('one', 'dull'), ('one', 'shiny'),
('two', 'dull'), ('two', 'shiny')])
assert_equal(res.columns.values, m.values)
Expand Down Expand Up @@ -936,7 +936,7 @@ def test_crosstab_no_overlap(self):

tm.assert_frame_equal(actual, expected)

def test_margin_ignore_dropna_bug(self):
def test_margin_dropna(self):
# GH 12577
# pivot_table counts null into margin ('All')
# when margins=true and dropna=true
Expand Down Expand Up @@ -965,6 +965,62 @@ def test_margin_ignore_dropna_bug(self):
expected.columns = Index([3, 4, 'All'], name='b')
tm.assert_frame_equal(actual, expected)

# GH 12642
Copy link
Contributor

Choose a reason for hiding this comment

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

add this to the whatsnew (as a separate bug fix line)

# _add_margins raises KeyError: Level None not found
# when margins=True and dropna=False
df = pd.DataFrame({'a': [1, 2, 2, 2, 2, np.nan],
'b': [3, 3, 4, 4, 4, 4]})
actual = pd.crosstab(df.a, df.b, margins=True, dropna=False)
expected = pd.DataFrame([[1, 0, 1], [1, 3, 4], [2, 4, 6]])
expected.index = Index([1.0, 2.0, 'All'], name='a')
expected.columns = Index([3, 4, 'All'], name='b')
tm.assert_frame_equal(actual, expected)

df = DataFrame({'a': [1, np.nan, np.nan, np.nan, 2, np.nan],
'b': [3, np.nan, 4, 4, 4, 4]})
actual = pd.crosstab(df.a, df.b, margins=True, dropna=False)
expected = pd.DataFrame([[1, 0, 1], [0, 1, 1], [1, 4, 6]])
expected.index = Index([1.0, 2.0, 'All'], name='a')
expected.columns = Index([3.0, 4.0, 'All'], name='b')
tm.assert_frame_equal(actual, expected)

a = np.array(['foo', 'foo', 'foo', 'bar',
'bar', 'foo', 'foo'], dtype=object)
b = np.array(['one', 'one', 'two', 'one',
'two', np.nan, 'two'], dtype=object)
c = np.array(['dull', 'dull', 'dull', 'dull',
'dull', 'shiny', 'shiny'], dtype=object)

actual = pd.crosstab(a, [b, c], rownames=['a'],
colnames=['b', 'c'], margins=True, dropna=False)
m = MultiIndex.from_arrays([['one', 'one', 'two', 'two', 'All'],
['dull', 'shiny', 'dull', 'shiny', '']],
names=['b', 'c'])
expected = DataFrame([[1, 0, 1, 0, 2], [2, 0, 1, 1, 5],
[3, 0, 2, 1, 7]], columns=m)
expected.index = Index(['bar', 'foo', 'All'], name='a')
tm.assert_frame_equal(actual, expected)

actual = pd.crosstab([a, b], c, rownames=['a', 'b'],
colnames=['c'], margins=True, dropna=False)
m = MultiIndex.from_arrays([['bar', 'bar', 'foo', 'foo', 'All'],
['one', 'two', 'one', 'two', '']],
names=['a', 'b'])
expected = DataFrame([[1, 0, 1], [1, 0, 1], [2, 0, 2], [1, 1, 2],
[5, 2, 7]], index=m)
expected.columns = Index(['dull', 'shiny', 'All'], name='c')
tm.assert_frame_equal(actual, expected)

actual = pd.crosstab([a, b], c, rownames=['a', 'b'],
colnames=['c'], margins=True, dropna=True)
m = MultiIndex.from_arrays([['bar', 'bar', 'foo', 'foo', 'All'],
['one', 'two', 'one', 'two', '']],
names=['a', 'b'])
expected = DataFrame([[1, 0, 1], [1, 0, 1], [2, 0, 2], [1, 1, 2],
[5, 1, 6]], index=m)
expected.columns = Index(['dull', 'shiny', 'All'], name='c')
tm.assert_frame_equal(actual, expected)

if __name__ == '__main__':
import nose
nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
Expand Down