שימוש בספריות Python בקוד פתוח

import bigframes.pandas as bpd

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


def query_standard_sql(project_id: str = "your-project-id") -> bpd.DataFrame:
    """Runs a standard SQL query using BigQuery DataFrames."""
    sql = """
    SELECT name FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = 'TX'
    LIMIT 100
    """

    # Run a query alongside existing SQL. The project will be determined from
    # default credentials.
    df = bpd.read_gbq(sql)

    # Run a query after explicitly specifying a project.
    bpd.close_session()
    bpd.options.bigquery.project = project_id
    df = bpd.read_gbq(sql)
    return df


# Run the sample:
# df = query_standard_sql("your-project-id")
# print(df.head())

import pandas

sql = """
    SELECT name
    FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = 'TX'
    LIMIT 100
"""

# Run a Standard SQL query using the environment's default project
df = pandas.read_gbq(sql, dialect="standard")

# Run a Standard SQL query with the project set explicitly
project_id = "your-project-id"
df = pandas.read_gbq(sql, project_id=project_id, dialect="standard")

from google.cloud import bigquery

client = bigquery.Client()
sql = """
    SELECT name
    FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = 'TX'
    LIMIT 100
"""

# Run a Standard SQL query using the environment's default project
df = client.query(sql).to_dataframe()

# Run a Standard SQL query with the project set explicitly
project_id = "your-project-id"
df = client.query(sql, project=project_id).to_dataframe()

import pandas

sql = """
    SELECT name
    FROM [bigquery-public-data:usa_names.usa_1910_current]
    WHERE state = 'TX'
    LIMIT 100
"""

df = pandas.read_gbq(sql, dialect="legacy")

from google.cloud import bigquery

client = bigquery.Client()
sql = """
    SELECT name
    FROM [bigquery-public-data:usa_names.usa_1910_current]
    WHERE state = 'TX'
    LIMIT 100
"""
query_config = bigquery.QueryJobConfig(use_legacy_sql=True)

df = client.query(sql, job_config=query_config).to_dataframe()

import bigframes.pandas as bpd
import pandas as pd

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


def query_bqstorage() -> pd.DataFrame:
    """Queries BigQuery and downloads results using the BigQuery Storage API."""
    sql = """
    SELECT name FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = 'TX'
    LIMIT 100
    """

    # Read query results into a server-side DataFrame without downloading data.
    df = bpd.read_gbq(sql)

    # When downloading results to an in-memory pandas DataFrame,
    # bigquery-dataframes automatically uses the BigQuery Storage API if
    # installed.
    pandas_df = df.to_pandas()
    return pandas_df


# Run the sample:
# pandas_df = query_bqstorage()
# print(pandas_df.head())

import pandas

sql = "SELECT * FROM `bigquery-public-data.irs_990.irs_990_2012`"

# Use the BigQuery Storage API to download results more quickly.
df = pandas.read_gbq(sql, dialect="standard", use_bqstorage_api=True)

from google.cloud import bigquery

client = bigquery.Client()
sql = "SELECT * FROM `bigquery-public-data.irs_990.irs_990_2012`"

# The client library uses the BigQuery Storage API to download results to a
# pandas dataframe if the API is enabled on the project, the
# `google-cloud-bigquery-storage` package is installed, and the `pyarrow`
# package is installed.
df = client.query(sql).to_dataframe()

import bigframes.pandas as bpd

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


def query_parameters() -> bpd.DataFrame:
    """Queries BigQuery using BigQuery DataFrames with query parameters."""
    sql = """
    SELECT name FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = @state
    LIMIT 100
    """

    query_config = {
        "query": {
            "parameterMode": "NAMED",
            "queryParameters": [
                {
                    "name": "state",
                    "parameterType": {"type": "STRING"},
                    "parameterValue": {"value": "TX"},
                }
            ],
        }
    }

    df = bpd.read_gbq(sql, configuration=query_config)
    return df


# Run the sample:
# df = query_parameters()
# print(df.head())

import pandas

sql = """
    SELECT name
    FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = @state
    LIMIT @limit
"""
query_config = {
    "query": {
        "parameterMode": "NAMED",
        "queryParameters": [
            {
                "name": "state",
                "parameterType": {"type": "STRING"},
                "parameterValue": {"value": "TX"},
            },
            {
                "name": "limit",
                "parameterType": {"type": "INTEGER"},
                "parameterValue": {"value": 100},
            },
        ],
    }
}

df = pandas.read_gbq(sql, configuration=query_config)

from google.cloud import bigquery

client = bigquery.Client()
sql = """
    SELECT name
    FROM `bigquery-public-data.usa_names.usa_1910_current`
    WHERE state = @state
    LIMIT @limit
"""
query_config = bigquery.QueryJobConfig(
    query_parameters=[
        bigquery.ScalarQueryParameter("state", "STRING", "TX"),
        bigquery.ScalarQueryParameter("limit", "INTEGER", 100),
    ]
)

df = client.query(sql, job_config=query_config).to_dataframe()

import bigframes.pandas as bpd
import pandas as pd

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


def upload_from_dataframe(
    table_id: str = "your-project.your_dataset.your_table_name",
) -> bpd.DataFrame:
    """Uploads an in-memory pandas DataFrame to a BigQuery table using BigQuery DataFrames."""
    # Create a local pandas DataFrame.
    df = pd.DataFrame(
        {
            "my_string": ["a", "b", "c"],
            "my_int64": [1, 2, 3],
            "my_float64": [4.0, 5.0, 6.0],
        }
    )

    # Convert the local pandas DataFrame to a BigQuery DataFrame.
    bq_df = bpd.read_pandas(df)

    # Write the DataFrame to a BigQuery table.
    bq_df.to_gbq(table_id, if_exists="replace")
    return bq_df


# Run the sample:
# bq_df = upload_from_dataframe("your-project.your_dataset.your_table_name")
# print(bq_df.head())

import pandas

df = pandas.DataFrame(
    {
        "my_string": ["a", "b", "c"],
        "my_int64": [1, 2, 3],
        "my_float64": [4.0, 5.0, 6.0],
        "my_timestamp": [
            pandas.Timestamp("1998-09-04T16:03:14"),
            pandas.Timestamp("2010-09-13T12:03:45"),
            pandas.Timestamp("2015-10-02T16:00:00"),
        ],
    }
)
table_id = "my_dataset.new_table"

df.to_gbq(table_id)

from google.cloud import bigquery
import pandas

df = pandas.DataFrame(
    {
        "my_string": ["a", "b", "c"],
        "my_int64": [1, 2, 3],
        "my_float64": [4.0, 5.0, 6.0],
        "my_timestamp": [
            pandas.Timestamp("1998-09-04T16:03:14"),
            pandas.Timestamp("2010-09-13T12:03:45"),
            pandas.Timestamp("2015-10-02T16:00:00"),
        ],
    }
)
client = bigquery.Client()
table_id = "my_dataset.new_table"
# Since string columns use the "object" dtype, pass in a (partial) schema
# to ensure the correct BigQuery data type.
job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("my_string", "STRING"),
    ]
)

job = client.load_table_from_dataframe(df, table_id, job_config=job_config)

# Wait for the load job to complete.
job.result()