Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
104 changes: 104 additions & 0 deletions bigquery/bigframes/load_table_dataframe.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,104 @@
# Copyright 2026 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.

# [START bigquery_bigframes_load_table_dataframe]
import datetime

import bigframes.pandas as bpd

import pandas as pd

import pytz

# Set partial ordering mode as the default configuration for BigQuery
# DataFrames.
bpd.options.bigquery.ordering_mode = "partial"


def load_table_dataframe(
table_id: str = "your-project.your_dataset.your_table_name",
) -> bpd.DataFrame:
records = [
{
"title": "The Meaning of Life",
"release_year": 1983,
"length_minutes": 112.5,
"release_date": pytz.timezone("Europe/Paris")
.localize(datetime.datetime(1983, 5, 9, 13, 0, 0))
.astimezone(pytz.utc),
# Assume UTC timezone when a datetime object contains no timezone.
"dvd_release": datetime.datetime(2002, 1, 22, 7, 0, 0),
},
{
"title": "Monty Python and the Holy Grail",
"release_year": 1975,
"length_minutes": 91.5,
"release_date": pytz.timezone("Europe/London")
.localize(datetime.datetime(1975, 4, 9, 23, 59, 2))
.astimezone(pytz.utc),
"dvd_release": datetime.datetime(2002, 7, 16, 9, 0, 0),
},
{
"title": "Life of Brian",
"release_year": 1979,
"length_minutes": 94.25,
"release_date": pytz.timezone("America/New_York")
.localize(datetime.datetime(1979, 8, 17, 23, 59, 5))
.astimezone(pytz.utc),
"dvd_release": datetime.datetime(2008, 1, 14, 8, 0, 0),
},
{
"title": "And Now for Something Completely Different",
"release_year": 1971,
"length_minutes": 88.0,
"release_date": pytz.timezone("Europe/London")
.localize(datetime.datetime(1971, 9, 28, 23, 59, 7))
.astimezone(pytz.utc),
"dvd_release": datetime.datetime(2003, 10, 22, 10, 0, 0),
},
]
Comment on lines +32 to +70

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Use standard library zoneinfo.ZoneInfo and datetime.timezone.utc instead of pytz to localize the datetimes. This is cleaner, more idiomatic, and avoids the deprecated pytz library.

    records = [
        {
            "title": "The Meaning of Life",
            "release_year": 1983,
            "length_minutes": 112.5,
            "release_date": datetime.datetime(
                1983, 5, 9, 13, 0, 0, tzinfo=ZoneInfo("Europe/Paris")
            ).astimezone(datetime.timezone.utc),
            # Assume UTC timezone when a datetime object contains no timezone.
            "dvd_release": datetime.datetime(2002, 1, 22, 7, 0, 0),
        },
        {
            "title": "Monty Python and the Holy Grail",
            "release_year": 1975,
            "length_minutes": 91.5,
            "release_date": datetime.datetime(
                1975, 4, 9, 23, 59, 2, tzinfo=ZoneInfo("Europe/London")
            ).astimezone(datetime.timezone.utc),
            "dvd_release": datetime.datetime(2002, 7, 16, 9, 0, 0),
        },
        {
            "title": "Life of Brian",
            "release_year": 1979,
            "length_minutes": 94.25,
            "release_date": datetime.datetime(
                1979, 8, 17, 23, 59, 5, tzinfo=ZoneInfo("America/New_York")
            ).astimezone(datetime.timezone.utc),
            "dvd_release": datetime.datetime(2008, 1, 14, 8, 0, 0),
        },
        {
            "title": "And Now for Something Completely Different",
            "release_year": 1971,
            "length_minutes": 88.0,
            "release_date": datetime.datetime(
                1971, 9, 28, 23, 59, 7, tzinfo=ZoneInfo("Europe/London")
            ).astimezone(datetime.timezone.utc),
            "dvd_release": datetime.datetime(2003, 10, 22, 10, 0, 0),
        },
    ]

dataframe = pd.DataFrame(
records,
# In the loaded table, the column order reflects the order of the
# columns in the DataFrame.
columns=[
"title",
"release_year",
"length_minutes",
"release_date",
"dvd_release",
],
# Optionally, set a named index, which can also be written to the
# BigQuery table.
index=pd.Index(
["Q24980", "Q25043", "Q24953", "Q16403"], name="wikidata_id"
),
)

# Convert the local pandas DataFrame into a BigQuery DataFrame.
bq_df = bpd.read_pandas(dataframe)

# Write the DataFrame to a BigQuery table.
bq_df.to_gbq(table_id, if_exists="replace", index=True)
return bq_df
# [END bigquery_bigframes_load_table_dataframe]


if __name__ == "__main__":
import os

table_id = os.environ.get(
"TABLE_ID", "your-project.your_dataset.your_table_name"
)
print(load_table_dataframe(table_id=table_id))
27 changes: 27 additions & 0 deletions bigquery/bigframes/load_table_dataframe_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Copyright 2026 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 load_table_dataframe


def test_load_table_dataframe(project_id: str, dataset_id: str) -> None:
table_id = f"{project_id}.{dataset_id}.load_table_dataframe"
import bigframes.pandas as bpd

bq_df = load_table_dataframe.load_table_dataframe(table_id=table_id)
assert bq_df is not None

# Verify that the rows were actually written to BigQuery
df_loaded = bpd.read_gbq(table_id)
assert len(df_loaded) == 4