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

[BUG] Enable groupby with alias for native executor #2917

Merged
merged 4 commits into from
Sep 26, 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
28 changes: 17 additions & 11 deletions src/daft-local-execution/src/pipeline.rs
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ use daft_core::{
prelude::{Schema, SchemaRef},
utils::supertype,
};
use daft_dsl::{join::get_common_join_keys, Expr};
use daft_dsl::{col, join::get_common_join_keys, Expr};
use daft_micropartition::MicroPartition;
use daft_physical_plan::{
Filter, HashAggregate, HashJoin, InMemoryScan, Limit, LocalPhysicalPlan, Project, Sort,
Expand Down Expand Up @@ -186,17 +186,23 @@ pub fn physical_plan_to_pipeline(
}) => {
let (first_stage_aggs, second_stage_aggs, final_exprs) =
populate_aggregation_stages(aggregations, schema, group_by);
let first_stage_agg_op = AggregateOperator::new(
first_stage_aggs
.values()
.cloned()
.map(|e| Arc::new(Expr::Agg(e.clone())))
.collect(),
group_by.clone(),
);
let child_node = physical_plan_to_pipeline(input, psets)?;
let post_first_agg_node =
IntermediateNode::new(Arc::new(first_stage_agg_op), vec![child_node]).boxed();
let (post_first_agg_node, group_by) = if !first_stage_aggs.is_empty() {
let agg_op = AggregateOperator::new(
first_stage_aggs
.values()
.cloned()
.map(|e| Arc::new(Expr::Agg(e.clone())))
.collect(),
group_by.clone(),
);
(
IntermediateNode::new(Arc::new(agg_op), vec![child_node]).boxed(),
&group_by.iter().map(|e| col(e.name())).collect(),
)
} else {
(child_node, group_by)
};

let second_stage_agg_sink = AggregateSink::new(
second_stage_aggs
Expand Down
6 changes: 0 additions & 6 deletions tests/cookbook/test_aggregations.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,17 +6,11 @@
import pandas as pd
import pytest

from daft import context
from daft.datatype import DataType
from daft.expressions import col
from daft.udf import udf
from tests.conftest import assert_df_equals

pytestmark = pytest.mark.skipif(
context.get_context().daft_execution_config.enable_native_executor is True,
reason="Native executor fails for these tests",
)


def test_sum(daft_df, service_requests_csv_pd_df, repartition_nparts):
"""Sums across an entire column for the entire table"""
Expand Down
7 changes: 1 addition & 6 deletions tests/dataframe/test_aggregations.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,18 +7,13 @@
import pytest

import daft
from daft import col, context
from daft import col
from daft.context import get_context
from daft.datatype import DataType
from daft.errors import ExpressionTypeError
from daft.utils import freeze
from tests.utils import sort_arrow_table

pytestmark = pytest.mark.skipif(
context.get_context().daft_execution_config.enable_native_executor is True,
reason="Native executor fails for these tests",
)


@pytest.mark.parametrize("repartition_nparts", [1, 2, 4])
def test_agg_global(make_df, repartition_nparts):
Expand Down
7 changes: 1 addition & 6 deletions tests/dataframe/test_approx_percentiles_aggregations.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,7 @@
import pyarrow as pa
import pytest

from daft import col, context

pytestmark = pytest.mark.skipif(
context.get_context().daft_execution_config.enable_native_executor is True,
reason="Native executor fails for these tests",
)
from daft import col


@pytest.mark.parametrize("repartition_nparts", [1, 2, 4])
Expand Down
6 changes: 0 additions & 6 deletions tests/dataframe/test_distinct.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,9 @@
import pyarrow as pa
import pytest

from daft import context
from daft.datatype import DataType
from tests.utils import sort_arrow_table

pytestmark = pytest.mark.skipif(
context.get_context().daft_execution_config.enable_native_executor is True,
reason="Native executor fails for these tests",
)


@pytest.mark.parametrize("repartition_nparts", [1, 2, 5])
def test_distinct_with_nulls(make_df, repartition_nparts):
Expand Down
6 changes: 0 additions & 6 deletions tests/dataframe/test_map_groups.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,12 +3,6 @@
import pytest

import daft
from daft import context

pytestmark = pytest.mark.skipif(
context.get_context().daft_execution_config.enable_native_executor is True,
reason="Native executor fails for these tests",
)


@pytest.mark.parametrize("repartition_nparts", [1, 2, 4])
Expand Down
Loading