fix: only do row identity based joins when joining by index (#356)

Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly: - [x] Make sure to open an issue as a [bug/issue](https://togithub.com/googleapis/python-bigquery-dataframes/issues/new/choose) before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) Fixes #355 🦕

Author: DLT1412

bigframes/core/__init__.py

@@ -349,7 +349,7 @@ def join(
  self,
  other: ArrayValue,
  join_def: join_def.JoinDefinition,
- allow_row_identity_join: bool = True,
+ allow_row_identity_join: bool = False,
  ):
  return ArrayValue(
  nodes.JoinNode(

bigframes/core/compile/single_column.py

@@ -33,7 +33,7 @@ def join_by_column_ordered(
  left: compiled.OrderedIR,
  right: compiled.OrderedIR,
  join: join_defs.JoinDefinition,
- allow_row_identity_join: bool = True,
+ allow_row_identity_join: bool = False,
 ) -> compiled.OrderedIR:
  """Join two expressions by column equality.
 
@@ -134,7 +134,7 @@ def join_by_column_unordered(
  left: compiled.UnorderedIR,
  right: compiled.UnorderedIR,
  join: join_defs.JoinDefinition,
- allow_row_identity_join: bool = True,
+ allow_row_identity_join: bool = False,
 ) -> compiled.UnorderedIR:
  """Join two expressions by column equality.
 

bigframes/core/nodes.py

@@ -115,7 +115,7 @@ class JoinNode(BigFrameNode):
  left_child: BigFrameNode
  right_child: BigFrameNode
  join: JoinDefinition
- allow_row_identity_join: bool = True
+ allow_row_identity_join: bool = False
 
  @property
  def row_preserving(self) -> bool:

tests/system/conftest.py

@@ -285,6 +285,13 @@ def scalars_table_id(test_data_tables) -> str:
  return test_data_tables["scalars"]
 
 
+@pytest.fixture(scope="session")
+def baseball_schedules_df(session: bigframes.Session) -> bigframes.dataframe.DataFrame:
+ """Public BQ table"""
+ df = session.read_gbq("bigquery-public-data.baseball.schedules")
+ return df
+
+
 @pytest.fixture(scope="session")
 def hockey_table_id(test_data_tables) -> str:
  return test_data_tables["hockey_players"]

tests/system/small/regression/test_issue355_merge_after_filter.py

@@ -0,0 +1,70 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import pandas as pd
+import pytest
+
+from tests.system.utils import assert_pandas_df_equal
+
+
+@pytest.mark.parametrize(
+ ("merge_how",),
+ [
+ ("inner",),
+ ("outer",),
+ ("left",),
+ ("right",),
+ ],
+)
+def test_merge_after_filter(baseball_schedules_df, merge_how):
+ on = ["awayTeamName"]
+ left_columns = [
+ "gameId",
+ "year",
+ "homeTeamName",
+ "awayTeamName",
+ "duration_minutes",
+ ]
+ right_columns = [
+ "gameId",
+ "year",
+ "homeTeamName",
+ "awayTeamName",
+ "duration_minutes",
+ ]
+
+ left = baseball_schedules_df[left_columns]
+ left = left[left["homeTeamName"] == "Rays"]
+ # Offset the rows somewhat so that outer join can have an effect.
+ right = baseball_schedules_df[right_columns]
+ right = right[right["homeTeamName"] == "White Sox"]
+
+ df = left.merge(right, on=on, how=merge_how)
+ bf_result = df.to_pandas()
+
+ left_pandas = baseball_schedules_df.to_pandas()[left_columns]
+ left_pandas = left_pandas[left_pandas["homeTeamName"] == "Rays"]
+
+ right_pandas = baseball_schedules_df.to_pandas()[right_columns]
+ right_pandas = right_pandas[right_pandas["homeTeamName"] == "White Sox"]
+
+ pd_result = pd.merge(
+ left_pandas,
+ right_pandas,
+ merge_how,
+ on,
+ sort=True,
+ )
+
+ assert_pandas_df_equal(bf_result, pd_result, ignore_order=True)