8000 fix: Fix error loading local dataframes into bigquery by TrevorBergeron · Pull Request #1165 · googleapis/python-bigquery-dataframes · GitHub
[go: up one dir, main page]
Skip to content

fix: Fix error loading local dataframes into bigquery #1165

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
TrevorBergeron merged 1 commit into from
Nov 21, 2024
Merged

fix: Fix error loading local dataframes into bigquery #1165

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
2 changes: 2 additions & 0 deletions bigframes/session/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,10 +158,12 @@ def read_pandas_load_job(
ordering_col = f"rowid_{suffix}"
suffix += 1

# Maybe should just convert to pyarrow or parquet?
pandas_dataframe_copy = pandas_dataframe.copy()
pandas_dataframe_copy.index.names = new_idx_ids
pandas_dataframe_copy.columns = pandas.Index(new_col_ids)
pandas_dataframe_copy[ordering_col] = np.arange(pandas_dataframe_copy.shape[0])
pandas_dataframe_copy = pandas_dataframe_copy.reset_index(drop=False)

job_config = bigquery.LoadJobConfig()
# Specify the datetime dtypes, which is auto-detected as timestamp types.
Expand Down
14 changes: 14 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 @@ -99,6 +99,20 @@ def test_df_construct_pandas_load_job(scalars_dfs_maybe_ordered):
assert_dfs_equivalent(pd_result, bf_result)


def test_df_construct_structs(session):
pd_frame = pd.Series(
[
{"version": 1, "project": "pandas"},
{"version": 2, "project": "pandas"},
{"version": 1, "project": "numpy"},
]
).to_frame()
bf_series = session.read_pandas(pd_frame)
pd.testing.assert_frame_equal(
bf_series.to_pandas(), pd_frame, check_index_type=False, check_dtype=False
)


def test_df_construct_pandas_set_dtype(scalars_dfs):
columns = [
"int64_too",
Expand Down
0