abacusai.prediction_operator

Classes

PredictionOperator

A prediction operator.

Module Contents

class abacusai.prediction_operator.PredictionOperator(client, name=None, predictionOperatorId=None, createdAt=None, updatedAt=None, projectId=None, predictFunctionName=None, sourceCode=None, initializeFunctionName=None, notebookId=None, memory=None, useGpu=None, featureGroupIds=None, featureGroupTableNames=None, codeSource={}, refreshSchedules={}, latestPredictionOperatorVersion={})

Bases: abacusai.return_class.AbstractApiClass

A prediction operator.

Parameters:

client (ApiClient) – An authenticated API Client instance
name (str) – The name for the prediction operator.
predictionOperatorId (str) – The unique identifier of the prediction operator.
createdAt (str) – Date and time at which the prediction operator was created.
updatedAt (str) – Date and time at which the prediction operator was updated.
projectId (str) – The project this prediction operator belongs to.
predictFunctionName (str) – Name of the function found in the source code that will be executed to run predictions.
sourceCode (str) – Python code used to make the prediction operator.
initializeFunctionName (str) – Name of the optional initialize function found in the source code. This function will generate anything used by predictions, based on input feature groups.
notebookId (str) – The unique string identifier of the notebook used to create or edit the prediction operator.
memory (int) – Memory in GB specified for the prediction operator.
useGpu (bool) – Whether this prediction operator is using gpu.
featureGroupIds (list) – A list of Feature Group IDs used for initializing.
featureGroupTableNames (list) – A list of Feature Group table names used for initializing.
codeSource (CodeSource) – If a python model, information on the source code.
latestPredictionOperatorVersion (PredictionOperatorVersion) – The unique string identifier of the latest version.
refreshSchedules (RefreshSchedule) – List of refresh schedules that indicate when the next prediction operator version will be processed

name = None

prediction_operator_id = None

created_at = None

updated_at = None

project_id = None

predict_function_name = None

source_code = None

initialize_function_name = None

notebook_id = None

memory = None

use_gpu = None

feature_group_ids = None

feature_group_table_names = None

code_source

refresh_schedules

latest_prediction_operator_version

deprecated_keys

__repr__()

to_dict()

Get a dict representation of the parameters in this class

Returns:: The dict value representation of the class parameters
Return type:: dict

refresh()

Calls describe and refreshes the current object’s fields

Returns:: The current object
Return type:: PredictionOperator

describe()

Describe an existing prediction operator.

Parameters:: prediction_operator_id (str) – The unique ID of the prediction operator.
Returns:: The requested prediction operator object.
Return type:: PredictionOperator

update(name=None, feature_group_ids=None, source_code=None, initialize_function_name=None, predict_function_name=None, cpu_size=None, memory=None, package_requirements=None, use_gpu=None)

Update an existing prediction operator. This does not create a new version.

Parameters:

name (str) – Name of the prediction operator.
feature_group_ids (List) – List of feature groups that are supplied to the initialize function as parameters. Each of the parameters are materialized Dataframes. The order should match the initialize function’s parameters.
source_code (str) – Contents of a valid Python source code file. The source code should contain the function predictFunctionName, and the function ‘initializeFunctionName’ if defined.
initialize_function_name (str) – Name of the optional initialize function found in the source code. This function will generate anything used by predictions, based on input feature groups.
predict_function_name (str) – Name of the function found in the source code that will be executed to run predictions.
cpu_size (str) – Size of the CPU for the prediction operator.
memory (int) – Memory (in GB) for the prediction operator.
package_requirements (list) – List of package requirement strings. For example: [‘numpy==1.2.3’, ‘pandas>=1.4.0’]
use_gpu (bool) – Whether this prediction operator needs gpu.

Returns:

The updated prediction operator object.

Return type:

PredictionOperator

delete()

Delete an existing prediction operator.

Parameters:: prediction_operator_id (str) – The unique ID of the prediction operator.

deploy(auto_deploy=True)

Deploy the prediction operator.

Parameters:: auto_deploy (bool) – Flag to enable the automatic deployment when a new prediction operator version is created.
Returns:: The created deployment object.
Return type:: Deployment

create_version()

Create a new version of the prediction operator.

Parameters:: prediction_operator_id (str) – The unique ID of the prediction operator.
Returns:: The created prediction operator version object.
Return type:: PredictionOperatorVersion

list_versions()

List all the prediction operator versions for a prediction operator.

Parameters:: prediction_operator_id (str) – The unique ID of the prediction operator.
Returns:: A list of prediction operator version objects.
Return type:: list[PredictionOperatorVersion]