Skip to content

Fix value_counts() to work properly when dropna is True #1116

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

Merged
merged 11 commits into from
Dec 18, 2019
Merged

Fix value_counts() to work properly when dropna is True #1116

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
37206db
fix
itholic Dec 11, 2019
21c8431
fix comment & rollback useless change
itholic Dec 11, 2019
f2f3df5
fix
itholic Dec 11, 2019
a895436
fix for index
itholic Dec 11, 2019
64d1fb6
fix & add tests
itholic Dec 12, 2019
0362cc2
support for pyspark2.3 with set option
itholic Dec 12, 2019
d2271db
fix
itholic Dec 12, 2019
1299d0e
fix
itholic Dec 12, 2019
0210ebe
fix test logic
itholic Dec 13, 2019
204976e
raise error only for multiindex
itholic Dec 13, 2019
c04be15
fix test more properly
itholic Dec 13, 2019
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
5 changes: 3 additions & 2 deletions databricks/koalas/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -945,11 +945,12 @@ def value_counts(self, normalize=False, sort=True, ascending=False, bins=None, d
raise NotImplementedError("value_counts currently does not support bins")

if dropna:
sdf_dropna = self._internal._sdf.dropna()
sdf_dropna = self._internal._sdf.select(self._scol).dropna()
else:
sdf_dropna = self._internal._sdf
index_name = SPARK_INDEX_NAME_FORMAT(0)
sdf = sdf_dropna.groupby(self._scol.alias(index_name)).count()
column_name = self._internal.data_columns[0]
sdf = sdf_dropna.groupby(sdf_dropna[column_name].alias(index_name)).count()
if sort:
if ascending:
sdf = sdf.orderBy(F.col('count'))
Expand Down
26 changes: 26 additions & 0 deletions databricks/koalas/tests/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,6 +269,32 @@ def test_value_counts(self):
kser.name = 'index'
self.assert_eq(kser.value_counts(), pser.value_counts(), almost=True)

# Series from DataFrame
pdf = pd.DataFrame({'a': [1, 2, 3], 'b': [None, 1, None]})
kdf = ks.from_pandas(pdf)

self.assert_eq(kdf.a.value_counts(normalize=True),
pdf.a.value_counts(normalize=True), almost=True)
self.assert_eq(kdf.a.value_counts(ascending=True),
pdf.a.value_counts(ascending=True), almost=True)
self.assert_eq(kdf.a.value_counts(normalize=True, dropna=False),
pdf.a.value_counts(normalize=True, dropna=False), almost=True)
self.assert_eq(kdf.a.value_counts(ascending=True, dropna=False),
pdf.a.value_counts(ascending=True, dropna=False), almost=True)

# Series with NaN index
pser = pd.Series([1, 2, 3], index=[2, None, 5])
kser = ks.from_pandas(pser)

self.assert_eq(kser.value_counts(normalize=True),
pser.value_counts(normalize=True), almost=True)
self.assert_eq(kser.value_counts(ascending=True),
pser.value_counts(ascending=True), almost=True)
self.assert_eq(kser.value_counts(normalize=True, dropna=False),
pser.value_counts(normalize=True, dropna=False), almost=True)
self.assert_eq(kser.value_counts(ascending=True, dropna=False),
pser.value_counts(ascending=True, dropna=False), almost=True)

def test_nsmallest(self):
sample_lst = [1, 2, 3, 4, np.nan, 6]
pser = pd.Series(sample_lst, name='x')
Expand Down