google.cloud.bigquery.model.Model¶
-
class
google.cloud.bigquery.model.
Model
(model_ref)[source]¶ Model represents a machine learning model resource.
See https://cloud.google.com/bigquery/docs/reference/rest/v2/models
- Parameters
model_ref (Union[google.cloud.bigquery.model.ModelReference, str]) – A pointer to a model. If
model_ref
is a string, it must included a project ID, dataset ID, and model ID, each separated by.
.
Methods
__init__
(model_ref)Initialize self.
from_api_repr
(resource)Factory: construct a model resource given its API representation
Attributes
Datetime at which the model was created (
None
until set from the server).ID of dataset containing the model.
Description of the model (defaults to
None
).Custom encryption configuration for the model.
ETag for the model resource (
None
until set from the server).The datetime when this model expires.
Input feature columns that were used to train this model.
Title of the table (defaults to
None
).Label columns that were used to train this model.
Labels for the table.
The geographic location where the model resides.
The model ID.
Type of the model resource.
Datetime at which the model was last modified (
None
until set from the server).URL path for the model’s APIs.
Project bound to the model
A
ModelReference
pointing to this model.Information for all training runs in increasing order of start time.
-
property
created
¶ Datetime at which the model was created (
None
until set from the server).Read-only.
- Type
Union[datetime.datetime, None]
-
property
encryption_configuration
¶ Custom encryption configuration for the model.
Custom encryption configuration (e.g., Cloud KMS keys) or
None
if using default encryption.See protecting data with Cloud KMS keys in the BigQuery documentation.
-
property
expires
¶ The datetime when this model expires. If not present, the model will persist indefinitely. Expired models will be deleted and their storage reclaimed.
- Type
Union[datetime.datetime, None]
-
property
feature_columns
¶ Input feature columns that were used to train this model.
Read-only.
An iterable of
StandardSqlField
.- Type
Sequence[google.cloud.bigquery_v2.types.StandardSqlField]
-
property
friendly_name
¶ Title of the table (defaults to
None
).- Raises
ValueError – For invalid value types.
- Type
Optional[str]
-
classmethod
from_api_repr
(resource)[source]¶ Factory: construct a model resource given its API representation
-
property
label_columns
¶ Label columns that were used to train this model. The output of the model will have a
predicted_
prefix to these columns.Read-only.
An iterable of
StandardSqlField
.- Type
Sequence[google.cloud.bigquery_v2.types.StandardSqlField]
-
property
labels
¶ Labels for the table.
This method always returns a dict. To change a model’s labels, modify the dict, then call
Client.update_model
. To delete a label, set its value toNone
before updating.
-
property
location
¶ The geographic location where the model resides. This value is inherited from the dataset.
Read-only.
- Type
-
property
model_type
¶ Type of the model resource.
Read-only.
The value is one of elements of the
ModelType
enumeration.
-
property
modified
¶ Datetime at which the model was last modified (
None
until set from the server).Read-only.
- Type
Union[datetime.datetime, None]
-
property
reference
¶ A
ModelReference
pointing to this model.Read-only.
- Returns
pointer to this model.
- Return type
-
property
training_runs
¶ Information for all training runs in increasing order of start time.
Read-only.
An iterable of
TrainingRun
.- Type
Sequence[google.cloud.bigquery_v2.types.Model.TrainingRun]