Skip to content

feat: include index columns in DataFrame.sql if they are named #788

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
merged 1 commit into from
Jun 14, 2024
Merged

feat: include index columns in DataFrame.sql if they are named #788

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
3 changes: 2 additions & 1 deletion bigframes/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -379,7 +379,8 @@ def _to_sql_query(
@property
def sql(self) -> str:
"""Compiles this DataFrame's expression tree to SQL."""
sql, _, _ = self._to_sql_query(include_index=False)
include_index = self.index.name is not None or len(self.index.names) > 1
sql, _, _ = self._to_sql_query(include_index=include_index)
return sql

@property
Expand Down
97 changes: 97 additions & 0 deletions tests/system/small/test_dataframe_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@

import google.api_core.exceptions
import pandas as pd
import pandas.testing
import pyarrow as pa
import pytest

Expand All @@ -35,6 +36,102 @@
import bigframes.pandas as bpd


def test_sql_executes(scalars_df_default_index, bigquery_client):
"""Test that DataFrame.sql returns executable SQL.

DF.sql is used in public documentation such as
https://cloud.google.com/blog/products/data-analytics/using-bigquery-dataframes-with-carto-geospatial-tools
as a way to pass a DataFrame on to carto without executing the SQL
immediately.

Make sure that this SQL can be run outside of BigQuery DataFrames (assuming
similar credentials / access to the referenced tables).
"""
# Do some operations to make for more complex SQL.
df = (
scalars_df_default_index.drop(columns=["geography_col"])
.groupby("string_col")
.max()
)
df.index.name = None # Don't include unnamed indexes.
query = df.sql

bf_result = df.to_pandas().sort_values("rowindex").reset_index(drop=True)
bq_result = (
bigquery_client.query_and_wait(query)
.to_dataframe()
.sort_values("rowindex")
.reset_index(drop=True)
)
pandas.testing.assert_frame_equal(bf_result, bq_result, check_dtype=False)


def test_sql_executes_and_includes_named_index(
scalars_df_default_index, bigquery_client
):
"""Test that DataFrame.sql returns executable SQL.

DF.sql is used in public documentation such as
https://cloud.google.com/blog/products/data-analytics/using-bigquery-dataframes-with-carto-geospatial-tools
as a way to pass a DataFrame on to carto without executing the SQL
immediately.

Make sure that this SQL can be run outside of BigQuery DataFrames (assuming
similar credentials / access to the referenced tables).
"""
# Do some operations to make for more complex SQL.
df = (
scalars_df_default_index.drop(columns=["geography_col"])
.groupby("string_col")
.max()
)
query = df.sql

bf_result = df.to_pandas().sort_values("rowindex")
bq_result = (
bigquery_client.query_and_wait(query)
.to_dataframe()
.set_index("string_col")
.sort_values("rowindex")
)
pandas.testing.assert_frame_equal(
bf_result, bq_result, check_dtype=False, check_index_type=False
)


def test_sql_executes_and_includes_named_multiindex(
scalars_df_default_index, bigquery_client
):
"""Test that DataFrame.sql returns executable SQL.

DF.sql is used in public documentation such as
https://cloud.google.com/blog/products/data-analytics/using-bigquery-dataframes-with-carto-geospatial-tools
as a way to pass a DataFrame on to carto without executing the SQL
immediately.

Make sure that this SQL can be run outside of BigQuery DataFrames (assuming
similar credentials / access to the referenced tables).
"""
# Do some operations to make for more complex SQL.
df = (
scalars_df_default_index.drop(columns=["geography_col"])
.groupby(["string_col", "bool_col"])
.max()
)
query = df.sql

bf_result = df.to_pandas().sort_values("rowindex")
bq_result = (
bigquery_client.query_and_wait(query)
.to_dataframe()
.set_index(["string_col", "bool_col"])
.sort_values("rowindex")
)
pandas.testing.assert_frame_equal(
bf_result, bq_result, check_dtype=False, check_index_type=False
)


def test_to_pandas_w_correct_dtypes(scalars_df_default_index):
"""Verify to_pandas() APIs returns the expected dtypes."""
actual = scalars_df_default_index.to_pandas().dtypes
Expand Down