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.

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

fix: Allow empty sort by columns #18774

Merged
merged 3 commits into from
Sep 18, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
7 changes: 6 additions & 1 deletion crates/polars-core/src/frame/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1796,7 +1796,12 @@ impl DataFrame {
slice: Option<(i64, usize)>,
) -> PolarsResult<Self> {
if by_column.is_empty() {
polars_bail!(ComputeError: "No columns selected for sorting");
// If no columns selected, any order (including original order) is correct.
return if let Some((offset, len)) = slice {
Ok(self.slice(offset, len))
} else {
Ok(self.clone())
};
}
// note that the by_column argument also contains evaluated expression from
// polars-lazy that may not even be present in this dataframe. therefore
Expand Down
4 changes: 4 additions & 0 deletions crates/polars-expr/src/expressions/sortby.rs
Original file line number Diff line number Diff line change
Expand Up @@ -201,6 +201,10 @@ impl PhysicalExpr for SortByExpr {
}
fn evaluate(&self, df: &DataFrame, state: &ExecutionState) -> PolarsResult<Series> {
let series_f = || self.input.evaluate(df, state);
if self.by.is_empty() {
// Sorting by 0 columns returns input unchanged.
return series_f();
}
let (series, sorted_idx) = if self.by.len() == 1 {
let sorted_idx_f = || {
let s_sort_by = self.by[0].evaluate(df, state)?;
Expand Down
1 change: 0 additions & 1 deletion crates/polars-expr/src/planner.rs
Original file line number Diff line number Diff line change
Expand Up @@ -338,7 +338,6 @@ fn create_physical_expr_inner(
by,
sort_options,
} => {
polars_ensure!(!by.is_empty(), InvalidOperation: "'sort_by' got an empty set");
let phys_expr = create_physical_expr_inner(*expr, ctxt, expr_arena, schema, state)?;
let phys_by =
create_physical_expressions_from_nodes(by, ctxt, expr_arena, schema, state)?;
Expand Down
7 changes: 2 additions & 5 deletions py-polars/tests/unit/dataframe/test_df.py
Original file line number Diff line number Diff line change
Expand Up @@ -360,11 +360,8 @@ def test_sort_multi_output_exprs_01() -> None:
):
df.sort("dts", "strs", nulls_last=[True, False, True])

with pytest.raises(
ComputeError,
match="No columns selected for sorting",
):
df.sort(pl.col("^xxx$"))
# No columns selected - return original input.
assert_frame_equal(df, df.sort(pl.col("^xxx$")))


@pytest.mark.parametrize(
Expand Down
7 changes: 3 additions & 4 deletions py-polars/tests/unit/test_empty.py
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
import pytest

import polars as pl
from polars.exceptions import InvalidOperationError
from polars.testing import assert_frame_equal, assert_series_equal


Expand Down Expand Up @@ -52,9 +51,9 @@ def test_empty_count_window() -> None:


def test_empty_sort_by_args() -> None:
df = pl.DataFrame([1, 2, 3])
with pytest.raises(InvalidOperationError):
df.select(pl.all().sort_by([]))
df = pl.DataFrame({"x": [2, 1, 3]})
assert_frame_equal(df, df.select(pl.col.x.sort_by([])))
assert_frame_equal(df, df.sort([]))


def test_empty_9137() -> None:
Expand Down