ניהול של סשנים וקלט/פלט של BigQuery DataFrames

import bigframes
import bigframes.pandas as bpd

# Create session object
context = bigframes.BigQueryOptions(
    project=YOUR_PROJECT_ID,
    location=YOUR_LOCATION,
)
session = bigframes.Session(context)

# Load a BigQuery table into a dataframe
df1 = session.read_gbq("bigquery-public-data.ml_datasets.penguins")

# Create a dataframe with local data:
df2 = bpd.DataFrame({"my_col": [1, 2, 3]}, session=session)

import bigframes
import bigframes.pandas as bpd

context = bigframes.BigQueryOptions(location=YOUR_LOCATION, project=YOUR_PROJECT_ID)

session1 = bigframes.Session(context)
session2 = bigframes.Session(context)

series1 = bpd.Series([1, 2, 3, 4, 5], session=session1)
series2 = bpd.Series([1, 2, 3, 4, 5], session=session2)

try:
    series1 + series2
except ValueError as e:
    print(e)  # Error message: Cannot use combine sources from multiple sessions

import bigframes.pandas as bpd

# Set project ID for the global session
bpd.options.bigquery.project = YOUR_PROJECT_ID
# Update the global default session location
bpd.options.bigquery.location = YOUR_LOCATION

# The following two statements are essentially the same
df = bpd.read_gbq("bigquery-public-data.ml_datasets.penguins")
df = bpd.get_global_session().read_gbq("bigquery-public-data.ml_datasets.penguins")

import numpy as np

import bigframes.pandas as bpd

s = bpd.Series([1, 2, 3])

# Create a dataframe with Python dict
df = bpd.DataFrame(
    {
        "col_1": [1, 2, 3],
        "col_2": [4, 5, 6],
    }
)

# Create a series with Numpy
s = bpd.Series(np.arange(10))

import numpy as np
import pandas as pd

import bigframes.pandas as bpd

pd_df = pd.DataFrame(np.random.randn(4, 2))

# Convert Pandas dataframe to BigQuery DataFrame with read_pandas()
df_1 = bpd.read_pandas(pd_df)
# Convert Pandas dataframe to BigQuery DataFrame with the dataframe constructor
df_2 = bpd.DataFrame(pd_df)

import bigframes.pandas as bpd

bf_df = bpd.DataFrame({"my_col": [1, 2, 3]})
# Returns a Pandas Dataframe
bf_df.to_pandas()

bf_s = bpd.Series([1, 2, 3])
# Returns a Pandas Series
bf_s.to_pandas()

import bigframes.pandas as bpd

df = bpd.read_gbq("bigquery-public-data.ml_datasets.penguins")

# Returns a Pandas series with dry run stats
df.to_pandas(dry_run=True)

import bigframes.pandas as bpd

# Read a CSV file from GCS
df = bpd.read_csv("gs://cloud-samples-data/bigquery/us-states/us-states.csv")

import bigframes.pandas as bpd

df = bpd.DataFrame({"my_col": [1, 2, 3]})
# Write a dataframe to a CSV file in GCS
df.to_csv(f"gs://{YOUR_BUCKET}/myfile*.csv")

import bigframes.pandas as bpd

df = bpd.read_gbq("bigquery-public-data.ml_datasets.penguins")

import bigframes.pandas as bpd

sql = """
SELECT species, island, body_mass_g
FROM bigquery-public-data.ml_datasets.penguins
WHERE sex = 'MALE'
"""

df = bpd.read_gbq(sql)

import bigframes.pandas as bpd

df = bpd.DataFrame({"my_col": [1, 2, 3]})

df.to_gbq(f"{YOUR_PROJECT_ID}.{YOUR_DATASET_ID}.{YOUR_TABLE_NAME}")