DataFrame에서 데이터 로드

Pandas DataFrame의 콘텐츠를 테이블에 로드합니다.

코드 샘플

Python

이 샘플을 사용해 보기 전에 BigQuery 빠른 시작: 클라이언트 라이브러리 사용의 Python 설정 안내를 따르세요. 자세한 내용은 BigQuery Python API 참고 문서를 확인하세요.

BigQuery에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 클라이언트 라이브러리의 인증 설정을 참조하세요.

import datetime
from zoneinfo import ZoneInfo

import bigframes.pandas as bpd
import pandas as pd
import pandas_gbq

# Set partial ordering mode for BigQuery DataFrames.
bpd.options.bigquery.ordering_mode = "partial"


def load_table_dataframe_bigframes(
    table_id: str = "your-project.your_dataset.your_table_name",
) -> None:
    """Loads a pandas DataFrame into a BigQuery table using BigQuery DataFrames."""
    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"),
    )

    bq_df = bpd.read_pandas(dataframe)
    bq_df.to_gbq(table_id, if_exists="replace", index=True)
    print(f"Loaded DataFrame to {table_id} using BigQuery DataFrames.")


def load_table_dataframe_pandas_gbq(
    table_id: str = "your-project.your_dataset.your_table_name",
) -> None:
    """Loads a pandas DataFrame into a BigQuery table using pandas-gbq."""
    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"),
    )

    pandas_gbq.to_gbq(dataframe, table_id, if_exists="replace")
    print(f"Loaded DataFrame to {table_id} using pandas-gbq.")


# [Preferred] Run using BigQuery DataFrames:
# load_table_dataframe_bigframes("your-project.your_dataset.your_table_name")

# Alternatively, run using pandas-gbq:
# load_table_dataframe_pandas_gbq("your-project.your_dataset.your_table_name")

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저 참조하기