Skip to content

feat(dataframe): improve DataFrame::from_columns input types (#24630) #24633

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

Open
cj-zhukov wants to merge 2 commits into
base: main
Choose a base branch
from
+41 −33
Open

feat(dataframe): improve DataFrame::from_columns input types (#24630) #24633

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
e5fea8d
feat(dataframe): improve DataFrame::from_columns input types (#24630)
cj-zhukov Aug 24, 2026
41020b6
fix cargo clippy in test_dataframe_from_columns
cj-zhukov Aug 24, 2026
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
27 changes: 15 additions & 12 deletions datafusion/core/src/dataframe/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2614,7 +2614,7 @@ impl DataFrame {
/// # async fn main() -> Result<()> {
/// let id: ArrayRef = Arc::new(Int32Array::from(vec![1, 2, 3]));
/// let name: ArrayRef = Arc::new(StringArray::from(vec!["foo", "bar", "baz"]));
/// let df = DataFrame::from_columns(vec![("id", id), ("name", name)])?;
/// let df = DataFrame::from_columns([("id", id), ("name", name)])?;
/// let expected = vec![
/// "+----+------+",
/// "| id | name |",
Expand All @@ -2628,17 +2628,20 @@ impl DataFrame {
/// # Ok(())
/// # }
/// ```
pub fn from_columns(columns: Vec<(&str, ArrayRef)>) -> Result<Self> {
let fields = columns
.iter()
.map(|(name, array)| Field::new(*name, array.data_type().clone(), true))
.collect::<Vec<_>>();

let arrays = columns
pub fn from_columns<I, S>(columns: I) -> Result<Self>
where
I: IntoIterator<Item = (S, ArrayRef)>,
S: AsRef<str>,
{
let (fields, arrays): (Vec<_>, Vec<_>) = columns
.into_iter()
.map(|(_, array)| array)
.collect::<Vec<_>>();

.map(|(name, array)| {
(
Field::new(name.as_ref(), array.data_type().clone(), true),
array,
)
})
.unzip();
let schema = Arc::new(Schema::new(fields));
let batch = RecordBatch::try_new(schema, arrays)?;
let ctx = SessionContext::new();
Expand Down Expand Up @@ -2695,7 +2698,7 @@ macro_rules! dataframe {
use datafusion::prelude::DataFrame;
use datafusion::common::test_util::IntoArrayRef;

let columns = vec![
let columns = [
$(
($name, $data.into_array_ref()),
)+
Expand Down
47 changes: 26 additions & 21 deletions datafusion/core/tests/dataframe/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6968,7 +6968,7 @@ async fn test_dataframe_from_columns() -> Result<()> {
let strings: ArrayRef =
Arc::new(StringArray::from(vec![Some("foo"), Some("bar"), None]));

let df = DataFrame::from_columns(vec![
let columns = [
("bool", bools),
("i8", i8s),
("i16", i16s),
Expand All @@ -6982,10 +6982,10 @@ async fn test_dataframe_from_columns() -> Result<()> {
("f32", f32s),
("f64", f64s),
("str", strings),
])?;
];

assert_eq!(df.schema().fields().len(), 13);
assert_eq!(df.clone().count().await?, 3);
let df1 = DataFrame::from_columns(columns.clone())?;
let df2 = DataFrame::from_columns(columns.to_vec())?;

let expected_types = [
("bool", DataType::Boolean),
Expand All @@ -7003,26 +7003,31 @@ async fn test_dataframe_from_columns() -> Result<()> {
("str", DataType::Utf8),
];

let schema = df.schema();
for df in [df1, df2] {
assert_eq!(df.schema().fields().len(), expected_types.len());
assert_eq!(df.clone().count().await?, 3);

for (name, data_type) in expected_types {
assert_eq!(schema.field_with_name(None, name)?.data_type(), &data_type);
}
let schema = df.schema();

let rows = df.sort(vec![col("i32").sort(true, true)])?;
for (name, data_type) in &expected_types {
assert_eq!(schema.field_with_name(None, name)?.data_type(), data_type);
}

assert_batches_eq!(
&[
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
"| bool | i8 | i16 | i32 | i64 | u8 | u16 | u32 | u64 | f16 | f32 | f64 | str |",
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
"| true | -1 | -1 | -1 | -1 | 0 | 0 | 0 | 0 | 1 | 1.0 | 1.0 | foo |",
"| false | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 2 | 2.0 | 2.0 | bar |",
"| true | 1 | 1 | 1 | 1 | 2 | 2 | 2 | 2 | 3 | 3.0 | 3.0 | |",
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
],
&rows.collect().await?
);
let rows = df.sort(vec![col("i32").sort(true, true)])?;

assert_batches_eq!(
&[
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
"| bool | i8 | i16 | i32 | i64 | u8 | u16 | u32 | u64 | f16 | f32 | f64 | str |",
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
"| true | -1 | -1 | -1 | -1 | 0 | 0 | 0 | 0 | 1 | 1.0 | 1.0 | foo |",
"| false | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 2 | 2.0 | 2.0 | bar |",
"| true | 1 | 1 | 1 | 1 | 2 | 2 | 2 | 2 | 3 | 3.0 | 3.0 | |",
"+-------+----+-----+-----+-----+----+-----+-----+-----+-----+-----+-----+-----+",
],
&rows.collect().await?
);
}

Ok(())
}
Expand Down