Skip to content

BUG: GH12558 where nulls contributed to normalized value_counts #12566

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: GH12558 where nulls contributed to normalized value_counts #12566

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 @@ -43,3 +43,5 @@ Performance Improvements

Bug Fixes
~~~~~~~~~

- Bug in ``value_counts`` when ``normalize=True`` and ``dropna=True`` where nulls still contributed to the normalized count (:issue:`12558`)
2 changes: 1 addition & 1 deletion pandas/core/algorithms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
result = result.sort_values(ascending=ascending)

if normalize:
result = result / float(values.size)
result = result / float(counts.sum())

return result

Expand Down
16 changes: 13 additions & 3 deletions pandas/core/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
callable, map
)
from pandas import compat

from pandas.compat.numpy_compat import _np_version_under1p8
from pandas.core.base import (PandasObject, SelectionMixin, GroupByError,
DataError, SpecificationError)
from pandas.core.categorical import Categorical
Expand Down Expand Up @@ -2949,8 +2949,18 @@ def value_counts(self, normalize=False, sort=True, ascending=False,

if normalize:
out = out.astype('float')
acc = rep(np.diff(np.r_[idx, len(ids)]))
out /= acc[mask] if dropna else acc
d = np.diff(np.r_[idx, len(ids)])
if dropna:
m = ids[lab == -1]
if _np_version_under1p8:
mi, ml = algos.factorize(m)
d[ml] = d[ml] - np.bincount(mi)
else:
np.add.at(d, m, -1)
acc = rep(d)[mask]
else:
acc = rep(d)
out /= acc

if sort and bins is None:
cat = ids[inc][mask] if dropna else ids[inc]
Expand Down
16 changes: 16 additions & 0 deletions pandas/tests/test_algos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -517,6 +517,22 @@ def test_dropna(self):
pd.Series([10.3, 5., 5., None]).value_counts(dropna=False),
pd.Series([2, 1, 1], index=[5., 10.3, np.nan]))

def test_value_counts_normalized(self):
# GH12558
s = Series([1, 2, np.nan, np.nan, np.nan])
dtypes = (np.float64, np.object, 'M8[ns]')
for t in dtypes:
s_typed = s.astype(t)
result = s_typed.value_counts(normalize=True, dropna=False)
Copy link
Contributor

Choose a reason for hiding this comment

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

maybe put right after tests for dropna

expected = Series([0.6, 0.2, 0.2],
index=Series([np.nan, 2.0, 1.0], dtype=t))
tm.assert_series_equal(result, expected)

result = s_typed.value_counts(normalize=True, dropna=True)
expected = Series([0.5, 0.5],
index=Series([2.0, 1.0], dtype=t))
tm.assert_series_equal(result, expected)


class GroupVarTestMixin(object):

Expand Down