Skip to content
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

Jump to bottom

feat(rust, python): Support zero fill null strategy for binary and string columns #13869

Merged
merged 4 commits into from
Jan 20, 2024
Merged

feat(rust, python): Support zero fill null strategy for binary and string columns #13869

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6f42103
implement fill null zero for binary dtype
edavisau Jan 20, 2024
5d0bd2d
add fill null tests
edavisau Jan 20, 2024
b21b3d8
add horizontal sum test for strings
edavisau Jan 20, 2024
1e87656
fmt
edavisau Jan 20, 2024
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
1 change: 1 addition & 0 deletions crates/polars-core/src/chunked_array/ops/fill_null.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -383,6 +383,7 @@ fn fill_null_binary(ca: &BinaryChunked, strategy: FillNullStrategy) -> PolarsRes
FillNullStrategy::Max => {
ca.fill_null_with_values(ca.max_binary().ok_or_else(err_fill_null)?)
},
FillNullStrategy::Zero => ca.fill_null_with_values(&[]),
strat => polars_bail!(InvalidOperation: "fill-null strategy {:?} is not supported", strat),
}
}
Expand Down
8 changes: 8 additions & 0 deletions py-polars/tests/unit/functions/aggregation/test_horizontal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,14 @@ def test_sum_max_min() -> None:
assert_series_equal(out["min"], pl.Series("min", [1.0, 2.0, 3.0]))


def test_str_sum_horizontal() -> None:
df = pl.DataFrame(
{"A": ["a", "b", None, "c", None], "B": ["f", "g", "h", None, None]}
)
out = df.select(pl.sum_horizontal("A", "B"))
assert_series_equal(out["A"], pl.Series("A", ["af", "bg", "h", "c", ""]))


def test_cum_sum_horizontal() -> None:
df = pl.DataFrame(
{
Expand Down
6 changes: 6 additions & 0 deletions py-polars/tests/unit/series/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1025,10 +1025,16 @@ def test_fill_null() -> None:
b = pl.Series("b", ["a", None, "c", None, "e"])
assert b.fill_null(strategy="min").to_list() == ["a", "a", "c", "a", "e"]
assert b.fill_null(strategy="max").to_list() == ["a", "e", "c", "e", "e"]
assert b.fill_null(strategy="zero").to_list() == ["a", "", "c", "", "e"]
assert b.fill_null(strategy="forward").to_list() == ["a", "a", "c", "c", "e"]
assert b.fill_null(strategy="backward").to_list() == ["a", "c", "c", "e", "e"]

c = pl.Series("c", [b"a", None, b"c", None, b"e"])
assert c.fill_null(strategy="min").to_list() == [b"a", b"a", b"c", b"a", b"e"]
assert c.fill_null(strategy="max").to_list() == [b"a", b"e", b"c", b"e", b"e"]
assert c.fill_null(strategy="zero").to_list() == [b"a", b"", b"c", b"", b"e"]
assert c.fill_null(strategy="forward").to_list() == [b"a", b"a", b"c", b"c", b"e"]
assert c.fill_null(strategy="backward").to_list() == [b"a", b"c", b"c", b"e", b"e"]

df = pl.DataFrame(
[
Expand Down