Skip to content

Fix fillna to handle NaN properly. #1572

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 2 commits into from
Jun 11, 2020
Merged

Fix fillna to handle NaN properly. #1572

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
03af9cc
Fix fillna to handle NaN properly.
ueshin Jun 10, 2020
d735263
More fix.
ueshin Jun 10, 2020
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
20 changes: 12 additions & 8 deletions databricks/koalas/series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1607,20 +1607,24 @@ def _fillna(self, value=None, method=None, axis=None, inplace=False, limit=None,
if (method is not None) and (method not in ["ffill", "pad", "backfill", "bfill"]):
raise ValueError("Expecting 'pad', 'ffill', 'backfill' or 'bfill'.")

if not self.spark.nullable:
if inplace:
return
else:
return self

scol = self.spark.column

if isinstance(self.spark.data_type, (FloatType, DoubleType)):
cond = scol.isNull() | F.isnan(scol)
else:
if not self.spark.nullable:
if inplace:
return
else:
return self
cond = scol.isNull()

if value is not None:
if not isinstance(value, (float, int, str, bool)):
raise TypeError("Unsupported type %s" % type(value))
if limit is not None:
raise ValueError("limit parameter for value is not support now")
scol = F.when(scol.isNull(), value).otherwise(scol)
scol = F.when(cond, value).otherwise(scol)
else:
if method in ["ffill", "pad"]:
func = F.last
Expand All @@ -1642,7 +1646,7 @@ def _fillna(self, value=None, method=None, axis=None, inplace=False, limit=None,
.orderBy(NATURAL_ORDER_COLUMN_NAME)
.rowsBetween(begin, end)
)
scol = F.when(scol.isNull(), func(scol, True).over(window)).otherwise(scol)
scol = F.when(cond, func(scol, True).over(window)).otherwise(scol)
kseries = self._with_new_scol(scol).rename(self.name)
if inplace:
self._internal = kseries._internal
Expand Down
11 changes: 11 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 @@ -210,6 +210,7 @@ def test_fillna(self):
kser = ks.from_pandas(pser)

self.assert_eq(kser.fillna(0), pser.fillna(0))
self.assert_eq(kser.fillna(np.nan).fillna(0), pser.fillna(np.nan).fillna(0))

kser.fillna(0, inplace=True)
pser.fillna(0, inplace=True)
Expand All @@ -220,6 +221,16 @@ def test_fillna(self):
pser.fillna(0, inplace=True)
self.assert_eq(kser, pser)

pser = pd.Series([1, 2, 3, 4, 5, 6], name="x")
kser = ks.from_pandas(pser)

pser.loc[3] = np.nan
kser.loc[3] = np.nan

self.assert_eq(kser.fillna(0), pser.fillna(0))
self.assert_eq(kser.fillna(method="ffill"), pser.fillna(method="ffill"))
self.assert_eq(kser.fillna(method="bfill"), pser.fillna(method="bfill"))

def test_dropna(self):
pser = pd.Series([np.nan, 2, 3, 4, np.nan, 6], name="x")

Expand Down