Google BigQuery

要从 GBQ 读取或写入数据，需要额外的依赖项

Python

$ pip install google-cloud-bigquery

读取

我们可以这样将查询加载到 DataFrame 中

Python

from_arrow · fsspec 功能可用 · pyarrow 功能可用

import polars as pl
from google.cloud import bigquery

client = bigquery.Client()

# Perform a query.
QUERY = (
    'SELECT name FROM `bigquery-public-data.usa_names.usa_1910_2013` '
    'WHERE state = "TX" '
    'LIMIT 100')
query_job = client.query(QUERY)  # API request
rows = query_job.result()  # Waits for query to finish

df = pl.from_arrow(rows.to_arrow())

写入

Python

from google.cloud import bigquery

client = bigquery.Client()

# Write DataFrame to stream as parquet file; does not hit disk
with io.BytesIO() as stream:
    df.write_parquet(stream)
    stream.seek(0)
    parquet_options = bigquery.ParquetOptions()
    parquet_options.enable_list_inference = True
    job = client.load_table_from_file(
        stream,
        destination='tablename',
        project='projectname',
        job_config=bigquery.LoadJobConfig(
            source_format=bigquery.SourceFormat.PARQUET,
            parquet_options=parquet_options,
        ),
    )
job.result()  # Waits for the job to complete