Managing Datasets#

A dataset represents a collection of tables, and applies several default policies to tables as they are created:

  • An access control list (ACL). When created, a dataset has an ACL which maps to the ACL inherited from its project.

  • A default table expiration period. If set, tables created within the dataset will have the value as their expiration period.

See BigQuery documentation for more information on Datasets.

Listing Datasets#

List datasets for a project with the list_datasets() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

datasets = list(client.list_datasets())  # Make an API request.
project = client.project

if datasets:
    print("Datasets in project {}:".format(project))
    for dataset in datasets:
        print("\t{}".format(dataset.dataset_id))
else:
    print("{} project does not contain any datasets.".format(project))

List datasets by label for a project with the list_datasets() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

label_filter = "labels.color:green"
datasets = list(client.list_datasets(filter=label_filter))  # Make an API request.

if datasets:
    print("Datasets filtered by {}:".format(label_filter))
    for dataset in datasets:
        print("\t{}.{}".format(dataset.project, dataset.dataset_id))
else:
    print("No datasets found with this filter.")

Getting a Dataset#

Get a dataset resource (to pick up changes made by another client) with the get_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = 'your-project.your_dataset'

dataset = client.get_dataset(dataset_id)  # Make an API request.

full_dataset_id = "{}.{}".format(dataset.project, dataset.dataset_id)
friendly_name = dataset.friendly_name
print(
    "Got dataset '{}' with friendly_name '{}'.".format(
        full_dataset_id, friendly_name
    )
)

# View dataset properties
print("Description: {}".format(dataset.description))
print("Labels:")
labels = dataset.labels
if labels:
    for label, value in labels.items():
        print("\t{}: {}".format(label, value))
else:
    print("\tDataset has no labels defined.")

# View tables in dataset
print("Tables:")
tables = list(client.list_tables(dataset))  # API request(s)
if tables:
    for table in tables:
        print("\t{}".format(table.table_id))
else:
    print("\tThis dataset does not contain any tables.")

Determine if a dataset exists with the get_dataset() method:

from google.cloud.exceptions import NotFound

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

try:
    client.get_dataset(dataset_id)  # Make an API request.
    print("Dataset {} already exists".format(dataset_id))
except NotFound:
    print("Dataset {} is not found".format(dataset_id))

Creating a Dataset#

Create a new dataset with the create_dataset() method:

from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to create.
# dataset_id = "{}.your_dataset".format(client.project)

# Construct a full Dataset object to send to the API.
dataset = bigquery.Dataset(dataset_id)

# TODO(developer): Specify the geographic location where the dataset should reside.
dataset.location = "US"

# Send the dataset to the API for creation.
# Raises google.api_core.exceptions.Conflict if the Dataset already
# exists within the project.
dataset = client.create_dataset(dataset)  # Make an API request.
print("Created dataset {}.{}".format(client.project, dataset.dataset_id))

Updating a Dataset#

Update a property in a dataset’s metadata with the update_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = 'your-project.your_dataset'

dataset = client.get_dataset(dataset_id)  # Make an API request.
dataset.description = "Updated description."
dataset = client.update_dataset(dataset, ["description"])  # Make an API request.

full_dataset_id = "{}.{}".format(dataset.project, dataset.dataset_id)
print(
    "Updated dataset '{}' with description '{}'.".format(
        full_dataset_id, dataset.description
    )
)

Modify user permissions on a dataset with the update_dataset() method:

from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = 'your-project.your_dataset'

dataset = client.get_dataset(dataset_id)  # Make an API request.

entry = bigquery.AccessEntry(
    role="READER",
    entity_type="userByEmail",
    entity_id="sample.bigquery.dev@gmail.com",
)

entries = list(dataset.access_entries)
entries.append(entry)
dataset.access_entries = entries

dataset = client.update_dataset(dataset, ["access_entries"])  # Make an API request.

full_dataset_id = "{}.{}".format(dataset.project, dataset.dataset_id)
print(
    "Updated dataset '{}' with modified user permissions.".format(full_dataset_id)
)

Manage Dataset labels#

Add labels to a dataset with the update_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = "your-project.your_dataset"

dataset = client.get_dataset(dataset_id)  # Make an API request.
dataset.labels = {"color": "green"}
dataset = client.update_dataset(dataset, ["labels"])  # Make an API request.

print("Labels added to {}".format(dataset_id))

Get dataset’s labels with the get_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = "your-project.your_dataset"

dataset = client.get_dataset(dataset_id)  # Make an API request.

# View dataset labels
print("Dataset ID: {}".format(dataset_id))
print("Labels:")
if dataset.labels:
    for label, value in dataset.labels.items():
        print("\t{}: {}".format(label, value))
else:
    print("\tDataset has no labels defined.")

Delete dataset’s labels with the update_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

# TODO(developer): Set dataset_id to the ID of the dataset to fetch.
# dataset_id = "your-project.your_dataset"

dataset = client.get_dataset(dataset_id)  # Make an API request.

# To delete a label from a dataset, set its value to None
dataset.labels["color"] = None

dataset = client.update_dataset(dataset, ["labels"])  # Make an API request.
print("Labels deleted from {}".format(dataset_id))

Deleting a Dataset#

Delete a dataset with the delete_dataset() method:

# TODO(developer): Import the client library.
# from google.cloud import bigquery

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

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

# Use the delete_contents parameter to delete a dataset and its contents
# Use the not_found_ok parameter to not receive an error if the dataset has already been deleted.
client.delete_dataset(
    dataset_id, delete_contents=True, not_found_ok=True
)  # Make an API request.

print("Deleted dataset '{}'.".format(dataset_id))