Model

class Model(object)

This namespace represents a model in a project. Multiple Model objects can belong to a single project.

init()

__init__(info, user)

Parmeters

  • info (str): Information about the current AI model in a project corresponding to the object.

  • user (str): User for creating, modifying, deleting the model.

Fields

  • id: Model ID.

  • url: DS2 API url information.

  • user: User information.

  • user_token: User token information.

  • app_url: Service app url.

repr()

Returns the Model ID in a Click AI's project as a printable format.

__repr__()

Return type

  • str

get_project()

Getter for current project's Project object.

get_project(project_id)

Parmeters

  • project_id : Project id as an int.

Return type

  • Project object

get_dataconnector()

Getter for the current project's data connector.

get_dataconnector(dataconnector_id)

Parmeters

  • dataconnector_id : Data connector's id as an int.

Return type

  • Dataconnector object

predict()

Predict the result using the input data and the model by calling self.utilClass.

predict(data, return_type="info")

Parmeters

  • data : Data needed for prediction.

Return type

  • requests

delete()

Delete the current model.

delete()

Return type

  • None

Reference

  • You can find the corresponding model deleted.

get_app_url()

Returns the app_url to predict and analyze outside of DS2.AI.

   get_app_url()

Return type

  • Link

  • URL

Reference

  • Link helps you predict and analyze data with the model.

deploy()

Deploy the model according to the cloud type, region, server type and project name if needed.

    deploy(cloud_type="AWS", region="us-west-1", server_type="g4dn.xlarge", project_name=None)

Parmeters

  • cloud_type (str): DS2.ai supports AWS, Google Cloud, MS Azure and the default is set as "AWS".

  • region (str): Region of the desired server and "us-west-1" is default.

  • server_type (str): Type of the server and "g4dn.xlarge" is default.

  • project_name (str): Name of the project in deploying process using SKYHUB AI and can be left None.

Return type

  • class Opsproject

  • Ops project id

Reference

  • You can find the deployed model in SKYHUB AI.

Last updated