Skip to content

BUG: crosstab with margins=True and dropna=False #12643

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 8 commits into from
Closed

BUG: crosstab with margins=True and dropna=False #12643

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9c0d99b
Modified _generate_marginal_results
OXPHOS Mar 14, 2016
7c28949
change in pivot_table-if margin
Mar 14, 2016
0039da5
Documentaion
Mar 14, 2016
76fbacf
Fix stylistic errors
OXPHOS Mar 15, 2016
869a253
Fixed margin=true, dropna=false error
OXPHOS Mar 16, 2016
d3ed27a
Update what's new
OXPHOS Mar 16, 2016
e21c88a
Fixed margins=Ture, dropna=False issue
OXPHOS Mar 16, 2016
12608fd
Merge remote-tracking branch 'pydata/master'
OXPHOS Mar 16, 2016
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 @@ -89,3 +89,5 @@ Bug Fixes
~~~~~~~~~

- Bug in ``value_counts`` when ``normalize=True`` and ``dropna=True`` where nulls still contributed to the normalized count (:issue:`12558`)
- Bug in ``pivot_table`` when ``margins=True`` and ``dropna=True`` where nulls still contributed to margin count (:issue:`12577`)
- Bug in ``pivot_table`` when ``margins=True`` and ``dropna=False`` where column names result in KeyError (:issue:`12642`)
12 changes: 8 additions & 4 deletions pandas/tools/pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,6 +149,8 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
table = table.fillna(value=fill_value, downcast='infer')

if margins:
if dropna:
data = data[data.notnull().all(axis=1)]
table = _add_margins(table, data, values, rows=index,
cols=columns, aggfunc=aggfunc,
margins_name=margins_name)
Expand All @@ -173,16 +175,18 @@ def _add_margins(table, data, values, rows, cols, aggfunc,

exception_msg = 'Conflicting name "{0}" in margins'.format(margins_name)
for level in table.index.names:
if margins_name in table.index.get_level_values(level):
raise ValueError(exception_msg)
if level is not None:
if margins_name in table.index.get_level_values(level):
raise ValueError(exception_msg)

grand_margin = _compute_grand_margin(data, values, aggfunc, margins_name)

# could be passed a Series object with no 'columns'
if hasattr(table, 'columns'):
for level in table.columns.names[1:]:
if margins_name in table.columns.get_level_values(level):
raise ValueError(exception_msg)
if level is not None:
if margins_name in table.columns.get_level_values(level):
raise ValueError(exception_msg)

if len(rows) > 1:
key = (margins_name,) + ('',) * (len(rows) - 1)
Expand Down
78 changes: 78 additions & 0 deletions pandas/tools/tests/test_pivot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -936,6 +936,84 @@ def test_crosstab_no_overlap(self):

tm.assert_frame_equal(actual, expected)

def test_margin_ignore_dropna_bug(self):
# GH 12577
Copy link
Contributor

Choose a reason for hiding this comment

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

so rename to test_margin_dropna

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Trying to make sure I got this right -

I current have two test methods respectively for this one and #12614. They're both margins and dropna issues for sure.

And I should merge these two methods into one, and name it test_margin_dropna, correct?

And I'll keep the issue numbers in comments?

Thanks.

Copy link
Contributor

Choose a reason for hiding this comment

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

yes that sounds fine (and just add this number after the other one). Idea is to have same tests together even though they occurred via different issues.

# pivot_table counts null into margin ('All')
# when margins=true and dropna=true

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=True)
expected = pd.DataFrame([[1, 0, 1], [1, 3, 4], [2, 3, 5]])
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=True)
expected = pd.DataFrame([[1, 0, 1], [0, 1, 1], [1, 1, 2]])
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)

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

def test_marginsTrue_dropnaFalse_KeyError_bug(self):
# GH 12642
# _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'])
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'])
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)

res = crosstab(a, [b, c], rownames=['a'],
colnames=['b', 'c'], margins=True, dropna=False)
m = MultiIndex.from_tuples([('one', 'dull'), ('one', 'shiny'),
('two', 'dull'), ('two', 'shiny'),
('All', '')])
assert_equal(res.columns.values, m.values)

res = crosstab([a, b], c, rownames=['a', 'b'],
colnames=['c'], margins=True, dropna=False)
m = MultiIndex.from_tuples([('bar', 'one'), ('bar', 'two'),
('foo', 'one'), ('foo', 'two'),
('All', '')])
assert_equal(res.index.values, m.values)

res = crosstab([a, b], c, rownames=['a', 'b'],
colnames=['c'], margins=True, dropna=True)
m = MultiIndex.from_tuples([('bar', 'one'), ('bar', 'two'),
('foo', 'one'), ('foo', 'two'),
('All', '')])
assert_equal(res.index.values, m.values)

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