Skip to content

Fixing lazy polars execution on query result #18749

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

Merged
Mytherin merged 3 commits into from
Aug 27, 2025
Merged

Fixing lazy polars execution on query result #18749

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
754d108
Gather client properties from either relation or result
pdet Aug 27, 2025
a7e3645
Fix test
pdet Aug 27, 2025
8ca56c8
Make query result a shared_ptr so pyrelation is copyable
pdet Aug 27, 2025
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 src/include/duckdb/main/client_properties.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ struct ClientProperties {
arrow_lossless_conversion(lossless_conversion), arrow_output_version(arrow_output_version),
client_context(client_context) {
}
ClientProperties() {};

string time_zone = "UTC";
ArrowOffsetSize arrow_offset_size = ArrowOffsetSize::REGULAR;
Expand Down
4 changes: 2 additions & 2 deletions tools/pythonpkg/src/include/duckdb_python/pyrelation.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ namespace duckdb {
struct DuckDBPyRelation {
public:
explicit DuckDBPyRelation(shared_ptr<Relation> rel);
explicit DuckDBPyRelation(unique_ptr<DuckDBPyResult> result);
explicit DuckDBPyRelation(shared_ptr<DuckDBPyResult> result);
~DuckDBPyRelation();

public:
Expand Down Expand Up @@ -288,7 +288,7 @@ struct DuckDBPyRelation {
shared_ptr<Relation> rel;
vector<LogicalType> types;
vector<string> names;
unique_ptr<DuckDBPyResult> result;
shared_ptr<DuckDBPyResult> result;
std::string rendered_result;
};

Expand Down
2 changes: 2 additions & 0 deletions tools/pythonpkg/src/include/duckdb_python/pyresult.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,8 @@ struct DuckDBPyResult {
const vector<string> &GetNames();
const vector<LogicalType> &GetTypes();

ClientProperties GetClientProperties();

private:
void FillNumpy(py::dict &res, idx_t col_idx, NumpyResultConversion &conversion, const char *name);

Expand Down
11 changes: 9 additions & 2 deletions tools/pythonpkg/src/pyrelation.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ DuckDBPyRelation::~DuckDBPyRelation() {
rel.reset();
}

DuckDBPyRelation::DuckDBPyRelation(unique_ptr<DuckDBPyResult> result_p) : rel(nullptr), result(std::move(result_p)) {
DuckDBPyRelation::DuckDBPyRelation(shared_ptr<DuckDBPyResult> result_p) : rel(nullptr), result(std::move(result_p)) {
if (!result) {
throw InternalException("DuckDBPyRelation created without a result");
}
Expand Down Expand Up @@ -984,7 +984,14 @@ PolarsDataFrame DuckDBPyRelation::ToPolars(idx_t batch_size, bool lazy) {
ArrowSchema arrow_schema;
auto result_names = names;
QueryResult::DeduplicateColumns(result_names);
auto client_properties = rel->context->GetContext()->GetClientProperties();
ClientProperties client_properties;
if (rel) {
client_properties = rel->context->GetContext()->GetClientProperties();
} else if (result) {
client_properties = result->GetClientProperties();
} else {
throw InternalException("DuckDBPyRelation To Polars must have a valid relation or result");
}
ArrowConverter::ToArrowSchema(&arrow_schema, types, result_names, client_properties);
py::list batches;
// Now we create an empty arrow table
Expand Down
4 changes: 4 additions & 0 deletions tools/pythonpkg/src/pyresult.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,10 @@ DuckDBPyResult::~DuckDBPyResult() {
}
}

ClientProperties DuckDBPyResult::GetClientProperties() {
return result->client_properties;
}

const vector<string> &DuckDBPyResult::GetNames() {
if (!result) {
throw InternalException("Calling GetNames without a result object");
Expand Down
8 changes: 8 additions & 0 deletions tools/pythonpkg/tests/fast/arrow/test_polars.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,14 @@ def test_polars_from_json_error(self, duckdb_cursor):
my_res = duckdb.query("select my_str from my_table where my_str != 'y'")
assert my_res.fetchall() == [('x',)]

def test_polars_lazy_from_conn(self, duckdb_cursor):
duckdb_conn = duckdb.connect()

result = duckdb_conn.execute("SELECT 42 as bla")

lazy_df = result.pl(lazy=True)
assert lazy_df.collect().to_dicts() == [{'bla': 42}]

def test_polars_lazy(self, duckdb_cursor):
con = duckdb.connect()
con.execute("Create table names (a varchar, b integer)")
Expand Down
Loading