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): guarantee schema-stable col(dtype) selection #6674

Merged
merged 2 commits into from
Feb 5, 2023
Merged

feat(rust): guarantee schema-stable col(dtype) selection #6674

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6e5b9f9
feat(rust): guarantee schema-stable dtype column selection
alexander-beedie Feb 4, 2023
26bb0f7
slightly cleaner filter, and add note about stable return order
alexander-beedie Feb 5, 2023
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
9 changes: 3 additions & 6 deletions polars/polars-lazy/polars-plan/src/logical_plan/projection.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,15 +208,12 @@ fn expand_dtypes(
dtypes: &[DataType],
exclude: &[Arc<str>],
) -> PolarsResult<()> {
for dtype in dtypes {
for field in schema.iter_fields().filter(|f| f.data_type() == dtype) {
for field in schema.iter_fields() {
alexander-beedie marked this conversation as resolved.
Show resolved Hide resolved
if dtypes.contains(&field.dtype) {
let name = field.name();

// skip excluded names
if exclude.iter().any(|excl| excl.as_ref() == name.as_str()) {
continue;
continue; // skip excluded names
}

let new_expr = expr.clone();
let new_expr = replace_dtype_with_column(new_expr, Arc::from(name.as_str()));
let new_expr = rewrite_special_aliases(new_expr)?;
Expand Down
2 changes: 1 addition & 1 deletion polars/polars-lazy/src/tests/queries.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1590,7 +1590,7 @@ pub fn test_select_by_dtypes() -> PolarsResult<()> {
.lazy()
.select([dtype_cols([DataType::Float32, DataType::Utf8])])
.collect()?;
assert_eq!(out.dtypes(), &[DataType::Float32, DataType::Utf8]);
assert_eq!(out.dtypes(), &[DataType::Utf8, DataType::Float32]);

Ok(())
}
Expand Down
2 changes: 1 addition & 1 deletion py-polars/tests/unit/test_df.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1578,7 +1578,7 @@ def test_select_by_dtype(df: pl.DataFrame) -> None:
out = df.select(pl.col(pl.Utf8))
assert out.columns == ["strings", "strings_nulls"]
out = df.select(pl.col([pl.Utf8, pl.Boolean]))
assert out.columns == ["strings", "strings_nulls", "bools", "bools_nulls"]
assert out.columns == ["bools", "bools_nulls", "strings", "strings_nulls"]
out = df.select(pl.col(INTEGER_DTYPES))
assert out.columns == ["int", "int_nulls"]

Expand Down
22 changes: 11 additions & 11 deletions py-polars/tests/unit/test_exprs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,7 +215,7 @@ def test_dtype_col_selection() -> None:
"n": pl.UInt64,
},
)
assert set(df.select(pl.col(INTEGER_DTYPES)).columns) == {
assert df.select(pl.col(INTEGER_DTYPES)).columns == [
"e",
"f",
"g",
Expand All @@ -224,9 +224,9 @@ def test_dtype_col_selection() -> None:
"l",
"m",
"n",
}
assert set(df.select(pl.col(FLOAT_DTYPES)).columns) == {"i", "j"}
assert set(df.select(pl.col(NUMERIC_DTYPES)).columns) == {
]
assert df.select(pl.col(FLOAT_DTYPES)).columns == ["i", "j"]
assert df.select(pl.col(NUMERIC_DTYPES)).columns == [
"e",
"f",
"g",
Expand All @@ -237,8 +237,8 @@ def test_dtype_col_selection() -> None:
"l",
"m",
"n",
}
assert set(df.select(pl.col(TEMPORAL_DTYPES)).columns) == {
]
assert df.select(pl.col(TEMPORAL_DTYPES)).columns == [
"a1",
"a2",
"a3",
Expand All @@ -249,19 +249,19 @@ def test_dtype_col_selection() -> None:
"d2",
"d3",
"d4",
}
assert set(df.select(pl.col(DATETIME_DTYPES)).columns) == {
]
assert df.select(pl.col(DATETIME_DTYPES)).columns == [
"a1",
"a2",
"a3",
"a4",
}
assert set(df.select(pl.col(DURATION_DTYPES)).columns) == {
]
assert df.select(pl.col(DURATION_DTYPES)).columns == [
"d1",
"d2",
"d3",
"d4",
}
]


def test_list_eval_expression() -> None:
Expand Down