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

Use aliased column names for cross joins #1250

Closed
wants to merge 1 commit into from
Closed

Use aliased column names for cross joins #1250

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
19 changes: 11 additions & 8 deletions dask_sql/physical/rel/logical/cross_join.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,18 +25,21 @@ class DaskCrossJoinPlugin(BaseRelPlugin):
def convert(self, rel: "LogicalPlan", context: "dask_sql.Context") -> DataContainer:
# We now have two inputs (from left and right), so we fetch them both
dc_lhs, dc_rhs = self.assert_inputs(rel, 2, context)
cc_lhs = dc_lhs.column_container
cc_rhs = dc_rhs.column_container

df_lhs = dc_lhs.df
df_rhs = dc_rhs.df
# Rename the columns of the left and right inputs
df_lhs_renamed = DataContainer(dc_lhs.df, cc_lhs.make_unique("lhs")).assign()
df_rhs_renamed = DataContainer(dc_rhs.df, cc_rhs.make_unique("rhs")).assign()

# Create a 'key' column in both DataFrames to join on
cross_join_key = utils.new_temporary_column(df_lhs)
df_lhs[cross_join_key] = 1
df_rhs[cross_join_key] = 1
cross_join_key = utils.new_temporary_column(df_lhs_renamed)
df_lhs_renamed[cross_join_key] = 1
df_rhs_renamed[cross_join_key] = 1

result = df_lhs.merge(df_rhs, on=cross_join_key, suffixes=("", "0")).drop(
cross_join_key, 1
)
result = df_lhs_renamed.merge(
df_rhs_renamed, on=cross_join_key, suffixes=("", "0")
).drop(cross_join_key, 1)
cc = ColumnContainer(result.columns)

# Rename columns like the rel specifies
Expand Down
11 changes: 11 additions & 0 deletions tests/integration/test_join.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -588,3 +588,14 @@ def test_null_key_join(c):
expected_df = pd.DataFrame({"a": [], "b": []})

assert_eq(result_df, expected_df)


def test_cross_join_duplicate_column_names(c):
c.create_table("df1", pd.DataFrame({"a": [1]}))
c.create_table("df2", pd.DataFrame({"a": [2]}))
c.create_table("df3", pd.DataFrame({"a": [3]}))

result_df = c.sql("SELECT * FROM df1, df2, df3")
expected_df = pd.DataFrame({"df1.a": [1], "df2.a": [2], "df3.a": [3]})

assert_eq(result_df, expected_df)
Loading