As of January 1, 2020 this library no longer supports Python 2 on the latest released version. Library versions released prior to that date will continue to be available. For more information please visit Python 2 support on Google Cloud.

Managing Tables¶

Tables exist within datasets. See BigQuery documentation for more information on Tables.

Listing Tables¶

List the tables belonging to a dataset with the list_tables() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set dataset_id to the ID of the dataset that contains
#                  the tables you are listing.
# dataset_id = 'your-project.your_dataset'

tables = client.list_tables(dataset_id)  # Make an API request.

print("Tables contained in '{}':".format(dataset_id))
for table in tables:
    print("{}.{}.{}".format(table.project, table.dataset_id, table.table_id))

Getting a Table¶

Get a table resource with the get_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the model to fetch.
# table_id = 'your-project.your_dataset.your_table'

table = client.get_table(table_id)  # Make an API request.

# View table properties
print(
    "Got table '{}.{}.{}'.".format(table.project, table.dataset_id, table.table_id)
)
print("Table schema: {}".format(table.schema))
print("Table description: {}".format(table.description))
print("Table has {} rows".format(table.num_rows))

Determine if a table exists with the get_table() method:

from google.cloud import bigquery
from google.cloud.exceptions import NotFound

client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to determine existence.
# table_id = "your-project.your_dataset.your_table"

try:
    client.get_table(table_id)  # Make an API request.
    print("Table {} already exists.".format(table_id))
except NotFound:
    print("Table {} is not found.".format(table_id))

Browse data rows in a table with the list_rows() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to browse data rows.
# table_id = "your-project.your_dataset.your_table_name"

# Download all rows from a table.
rows_iter = client.list_rows(table_id)  # Make an API request.

# Iterate over rows to make the API requests to fetch row data.
rows = list(rows_iter)
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Download at most 10 rows.
rows_iter = client.list_rows(table_id, max_results=10)
rows = list(rows_iter)
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Specify selected fields to limit the results to certain columns.
table = client.get_table(table_id)  # Make an API request.
fields = table.schema[:2]  # First two columns.
rows_iter = client.list_rows(table_id, selected_fields=fields, max_results=10)
rows = list(rows_iter)
print("Selected {} columns from table {}.".format(len(rows_iter.schema), table_id))
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Print row data in tabular format.
rows = client.list_rows(table, max_results=10)
format_string = "{!s:<16} " * len(rows.schema)
field_names = [field.name for field in rows.schema]
print(format_string.format(*field_names))  # Prints column headers.
for row in rows:
    print(format_string.format(*row))  # Prints row data.

Creating a Table¶

Create an empty table with the create_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

schema = [
    bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
    bigquery.SchemaField("age", "INTEGER", mode="REQUIRED"),
]

table = bigquery.Table(table_id, schema=schema)
table = client.create_table(table)  # Make an API request.
print(
    "Created table {}.{}.{}".format(table.project, table.dataset_id, table.table_id)
)

Create an integer range partitioned table with the create_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

schema = [
    bigquery.SchemaField("full_name", "STRING"),
    bigquery.SchemaField("city", "STRING"),
    bigquery.SchemaField("zipcode", "INTEGER"),
]

table = bigquery.Table(table_id, schema=schema)
table.range_partitioning = bigquery.RangePartitioning(
    # To use integer range partitioning, select a top-level REQUIRED /
    # NULLABLE column with INTEGER / INT64 data type.
    field="zipcode",
    range_=bigquery.PartitionRange(start=0, end=100000, interval=10),
)
table = client.create_table(table)  # Make an API request.
print(
    "Created table {}.{}.{}".format(table.project, table.dataset_id, table.table_id)
)

Load table data from a file with the load_table_from_file() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(
    source_format=bigquery.SourceFormat.CSV, skip_leading_rows=1, autodetect=True,
)

with open(file_path, "rb") as source_file:
    job = client.load_table_from_file(source_file, table_id, job_config=job_config)

job.result()  # Waits for the job to complete.

table = client.get_table(table_id)  # Make an API request.
print(
    "Loaded {} rows and {} columns to {}".format(
        table.num_rows, len(table.schema), table_id
    )
)

Load a CSV file from Cloud Storage with the load_table_from_uri() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
    skip_leading_rows=1,
    # The source format defaults to CSV, so the line below is optional.
    source_format=bigquery.SourceFormat.CSV,
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"

load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)  # Make an API request.
print("Loaded {} rows.".format(destination_table.num_rows))

Load a JSON file from Cloud Storage:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
    source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"

load_job = client.load_table_from_uri(
    uri,
    table_id,
    location="US",  # Must match the destination dataset location.
    job_config=job_config,
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Load a Parquet file from Cloud Storage:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(source_format=bigquery.SourceFormat.PARQUET,)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet"

load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Load an Avro file from Cloud Storage:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(source_format=bigquery.SourceFormat.AVRO)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.avro"

load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Load an ORC file from Cloud Storage:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(source_format=bigquery.SourceFormat.ORC)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.orc"

load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Load a CSV file from Cloud Storage and auto-detect schema:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

# Set the encryption key to use for the destination.
# TODO: Replace this key with a key you have created in KMS.
# kms_key_name = "projects/{}/locations/{}/keyRings/{}/cryptoKeys/{}".format(
#     "cloud-samples-tests", "us", "test", "test"
# )
job_config = bigquery.LoadJobConfig(
    autodetect=True,
    skip_leading_rows=1,
    # The source format defaults to CSV, so the line below is optional.
    source_format=bigquery.SourceFormat.CSV,
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.
load_job.result()  # Waits for the job to complete.
destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Load a JSON file from Cloud Storage and auto-detect schema:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

# Set the encryption key to use for the destination.
# TODO: Replace this key with a key you have created in KMS.
# kms_key_name = "projects/{}/locations/{}/keyRings/{}/cryptoKeys/{}".format(
#     "cloud-samples-tests", "us", "test", "test"
# )
job_config = bigquery.LoadJobConfig(
    autodetect=True, source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.
load_job.result()  # Waits for the job to complete.
destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Updating a Table¶

Update a property in a table’s metadata with the update_table() method:

# from google.cloud import bigquery
# client = bigquery.Client()
# project = client.project
# dataset_ref = bigquery.DatasetReference(project, dataset_id)
# table_ref = dataset_ref.table('my_table')
# table = client.get_table(table_ref)  # API request

assert table.description == "Original description."
table.description = "Updated description."

table = client.update_table(table, ["description"])  # API request

assert table.description == "Updated description."

Insert rows into a table’s data with the insert_rows() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the model to fetch.
# table_id = "your-project.your_dataset.your_table"

table = client.get_table(table_id)  # Make an API request.
rows_to_insert = [(u"Phred Phlyntstone", 32), (u"Wylma Phlyntstone", 29)]

errors = client.insert_rows(table, rows_to_insert)  # Make an API request.
if errors == []:
    print("New rows have been added.")

Insert rows into a table’s data with the insert_rows() method, achieving higher write limit:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the model to fetch.
# table_id = "your-project.your_dataset.your_table"

table = client.get_table(table_id)  # Make an API request.
rows_to_insert = [(u"Phred Phlyntstone", 32), (u"Wylma Phlyntstone", 29)]

errors = client.insert_rows(
    table, rows_to_insert, row_ids=[None] * len(rows_to_insert)
)  # Make an API request.
if errors == []:
    print("New rows have been added.")

Mind that inserting data with None row insert IDs can come at the expense of more duplicate inserts. See also: Streaming inserts.

Add an empty column to the existing table with the update_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table
#                  to add an empty column.
# table_id = "your-project.your_dataset.your_table_name"

table = client.get_table(table_id)  # Make an API request.

original_schema = table.schema
new_schema = original_schema[:]  # Creates a copy of the schema.
new_schema.append(bigquery.SchemaField("phone", "STRING"))

table.schema = new_schema
table = client.update_table(table, ["schema"])  # Make an API request.

if len(table.schema) == len(original_schema) + 1 == len(new_schema):
    print("A new column has been added.")
else:
    print("The column has not been added.")

Copying a Table¶

Copy a table with the copy_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set source_table_id to the ID of the original table.
# source_table_id = "your-project.source_dataset.source_table"

# TODO(developer): Set destination_table_id to the ID of the destination table.
# destination_table_id = "your-project.destination_dataset.destination_table"

job = client.copy_table(source_table_id, destination_table_id)
job.result()  # Wait for the job to complete.

print("A copy of the table created.")

Copy table data to Google Cloud Storage with the extract_table() method:

# from google.cloud import bigquery
# client = bigquery.Client()
# bucket_name = 'my-bucket'
project = "bigquery-public-data"
dataset_id = "samples"
table_id = "shakespeare"

destination_uri = "gs://{}/{}".format(bucket_name, "shakespeare.csv")
dataset_ref = bigquery.DatasetReference(project, dataset_id)
table_ref = dataset_ref.table(table_id)

extract_job = client.extract_table(
    table_ref,
    destination_uri,
    # Location must match that of the source table.
    location="US",
)  # API request
extract_job.result()  # Waits for job to complete.

print(
    "Exported {}:{}.{} to {}".format(project, dataset_id, table_id, destination_uri)
)

Deleting a Table¶

Delete a table with the delete_table() method:

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to fetch.
# table_id = 'your-project.your_dataset.your_table'

# If the table does not exist, delete_table raises
# google.api_core.exceptions.NotFound unless not_found_ok is True.
client.delete_table(table_id, not_found_ok=True)  # Make an API request.
print("Deleted table '{}'.".format(table_id))

Restoring a Deleted Table¶

Restore a deleted table from a snapshot by using the copy_table() method:

import time

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Choose a table to recover.
# table_id = "your-project.your_dataset.your_table"

# TODO(developer): Choose a new table ID for the recovered table data.
# recovery_table_id = "your-project.your_dataset.your_table_recovered"

# TODO(developer): Choose an appropriate snapshot point as epoch
# milliseconds. For this example, we choose the current time as we're about
# to delete the table immediately afterwards.
snapshot_epoch = int(time.time() * 1000)

# [START_EXCLUDE]
# Due to very short lifecycle of the table, ensure we're not picking a time
# prior to the table creation due to time drift between backend and client.
table = client.get_table(table_id)
created_epoch = datetime_helpers.to_milliseconds(table.created)
if created_epoch > snapshot_epoch:
    snapshot_epoch = created_epoch
# [END_EXCLUDE]

# "Accidentally" delete the table.
client.delete_table(table_id)  # Make an API request.

# Construct the restore-from table ID using a snapshot decorator.
snapshot_table_id = "{}@{}".format(table_id, snapshot_epoch)

# Construct and run a copy job.
job = client.copy_table(
    snapshot_table_id,
    recovered_table_id,
    # Must match the source and destination tables location.
    location="US",
)  # Make an API request.

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

print(
    "Copied data from deleted table {} to {}".format(table_id, recovered_table_id)
)

Overwrite a Table¶

Replace the table data with an Avro file from Cloud Storage:

import six

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.AVRO,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.avro"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Replace the table data with a CSV file from Cloud Storage:

import six

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.CSV,
    skip_leading_rows=1,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Replace the table data with a JSON file from Cloud Storage:

import six

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Replace the table data with an ORC file from Cloud Storage:

import six

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.ORC,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.orc"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Replace the table data with a Parquet file from Cloud Storage:

import six

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.PARQUET,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Waits for the job to complete.

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

Managing Tables¶

Listing Tables¶

Getting a Table¶

Creating a Table¶

Updating a Table¶

Copying a Table¶

Deleting a Table¶

Restoring a Deleted Table¶

Overwrite a Table¶

google-cloud-bigquery

Navigation

Related Topics