Working with models
Models enable storing and exporting computation results within DataSphere projects.
Creating a model
-
Select the project in your community or on the DataSphere home page in the Recent projects tab.
-
Open your project.
-
Select or create a notebook containing code to initialize a model variable in the system memory.
-
Run the code in the notebook with the selected configuration.
-
In the right-hand panel, select . In the window that opens, click Create model.
-
Select the name of the variable to build your model from.
-
Give your model a name and add a description as needed.
-
Click Create.
The new model will appear in the list of available project models. Creating a model may take some time.
Loading a model
You can load the saved model into the notebook interpreter state and use it in your computations:
-
Select the project in your community or on the DataSphere home page in the Recent projects tab.
-
Open your project.
-
In the right-hand panel, select . In the window that opens, select the model to load and click .
-
Select Load.
-
Enter the name of the variable to load the model into and click Load.
Once loaded, the model will be available in your code via the variable you provided.
Deleting a model
You can delete a model in the JupyterLab interface or on the project page under Resources.
- Open the JupyterLab interface and select in the right-hand panel.
- In the list of models, select the one you want to delete, click and then Delete.
- Click Confirm.
-
Select the project in your community or on the DataSphere home page in the Recent projects tab.
- Under Project resources, click Model.
- In the list of models, select the one you want to delete.
- On the model view page, click More and select Delete.
- Click Confirm.
Warning
In fact, resource deletion can take up to 72 hours.