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

handle empty arrays when inferring schema #297

Merged
merged 1 commit into from
Nov 26, 2024
Merged

handle empty arrays when inferring schema #297

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 10 additions & 0 deletions __tests__/dataframe.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2008,6 +2008,16 @@ describe("create", () => {
string: pl.String,
});
});
test("from row objects, inferred schema, empty array", () => {
const df = pl.readRecords([
{ a: [], b: 0 },
{ a: [""], b: 0 },
]);
expect(df.schema).toStrictEqual({
a: pl.List(pl.String),
b: pl.Float64,
});
});
test("from row objects, with schema", () => {
const rows = [
{ num: 1, date: "foo", string: "foo1" },
Expand Down
33 changes: 19 additions & 14 deletions src/dataframe.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1657,21 +1657,26 @@ fn obj_to_pairs(rows: &Array, len: usize) -> impl '_ + Iterator<Item = Vec<(Stri
if val.is_array().unwrap() {
let arr: napi::JsObject = unsafe { val.cast() };
let len = arr.get_array_length().unwrap();
// dont compare too many items, as it could be expensive
let max_take = std::cmp::min(len as usize, 10);
let mut dtypes: Vec<DataType> =
Vec::with_capacity(len as usize);

for idx in 0..max_take {
let item: napi::JsUnknown =
arr.get_element(idx as u32).unwrap();
let ty = item.get_type().unwrap();
let dt: Wrap<DataType> = ty.into();
dtypes.push(dt.0)
}
let dtype = coerce_data_type(&dtypes);

DataType::List(dtype.into())
if len == 0 {
DataType::List(DataType::Null.into())
} else {
// dont compare too many items, as it could be expensive
let max_take = std::cmp::min(len as usize, 10);
let mut dtypes: Vec<DataType> =
Vec::with_capacity(len as usize);

for idx in 0..max_take {
let item: napi::JsUnknown =
arr.get_element(idx as u32).unwrap();
let ty = item.get_type().unwrap();
let dt: Wrap<DataType> = ty.into();
dtypes.push(dt.0)
}
let dtype = coerce_data_type(&dtypes);

DataType::List(dtype.into())
}
} else if val.is_date().unwrap() {
DataType::Datetime(TimeUnit::Milliseconds, None)
} else {
Expand Down