Skip to content

fix: dataframes to_gbq now creates dataset if it doesn't exist #222

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
Genesis929 merged 11 commits into from
Dec 18, 2023
Merged

fix: dataframes to_gbq now creates dataset if it doesn't exist #222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
9b47254
"fix: dataframes to_gbq now creates dataset if it doesn't exist
Genesis929 Nov 18, 2023
13a9dee
fix: dataframes to_gbq now creates dataset if it doesn't exist
Genesis929 Nov 18, 2023
82d47e8
fix: dataframes to_gbq now creates dataset if it doesn't exist
Genesis929 Nov 18, 2023
a4a2e50
update test
Genesis929 Nov 21, 2023
f776667
Merge branch 'main' into b295247521-to-gbq-create-dataset
Genesis929 Dec 12, 2023
75a1810
update create dataset method.
Genesis929 Dec 12, 2023
4eeec45
fix
Genesis929 Dec 12, 2023
d0161dc
Merge branch 'main' into b295247521-to-gbq-create-dataset
shobsi Dec 14, 2023
a2b2520
Merge branch 'main' into b295247521-to-gbq-create-dataset
shobsi Dec 14, 2023
509d9aa
Merge branch 'main' into b295247521-to-gbq-create-dataset
Genesis929 Dec 18, 2023
52c5f1d
Merge branch 'main' into b295247521-to-gbq-create-dataset
Genesis929 Dec 18, 2023
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
17 changes: 15 additions & 2 deletions bigframes/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
Union,
)

import google.api_core.exceptions
import google.cloud.bigquery as bigquery
import numpy
import pandas
Expand Down Expand Up @@ -2508,7 +2509,14 @@ def to_gbq(
)
if_exists = "replace"

if "." not in destination_table:
table_parts = destination_table.split(".")
default_project = self._block.expr.session.bqclient.project

if len(table_parts) == 2:
destination_dataset = f"{default_project}.{table_parts[0]}"
elif len(table_parts) == 3:
destination_dataset = f"{table_parts[0]}.{table_parts[1]}"
else:
raise ValueError(
f"Got invalid value for destination_table {repr(destination_table)}. "
"Should be of the form 'datasetId.tableId' or 'projectId.datasetId.tableId'."
Expand All @@ -2523,11 +2531,16 @@ def to_gbq(
f"Valid options include None or one of {dispositions.keys()}."
)

try:
self._session.bqclient.get_dataset(destination_dataset)
except google.api_core.exceptions.NotFound:
self._session.bqclient.create_dataset(destination_dataset, exists_ok=True)

job_config = bigquery.QueryJobConfig(
write_disposition=dispositions[if_exists],
destination=bigquery.table.TableReference.from_string(
destination_table,
default_project=self._block.expr.session.bqclient.project,
default_project=default_project,
),
)

Expand Down
15 changes: 15 additions & 0 deletions tests/system/small/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3683,3 +3683,18 @@ def test_to_pandas_downsampling_option_override(session):
total_memory_bytes = df.memory_usage(deep=True).sum()
total_memory_mb = total_memory_bytes / (1024 * 1024)
assert total_memory_mb == pytest.approx(download_size, rel=0.3)


def test_to_gbq_and_create_dataset(session, scalars_df_index, dataset_id_not_created):
dataset_id = dataset_id_not_created
destination_table = f"{dataset_id}.scalars_df"

result_table = scalars_df_index.to_gbq(destination_table)
assert (
result_table == destination_table
if destination_table
else result_table is not None
)

loaded_scalars_df_index = session.read_gbq(result_table)
assert not loaded_scalars_df_index.empty