Downloading a Machine Learning model

Before you begin

For this task, you must have an IBM Cloud Pak® for Data account. You download a Machine Learning model from this resource. If you do not have an account, contact your IBM® representative.

In your IBM Cloud Pak for Data account, create the following resources:

• Cloud Object Storage
• Watson Machine Learning
• Watson Studio

Note: In IBM Cloud Pak for Data, you must set your region to Dallas(us-south) for this example.

To download the model:

1. Open IBM Cloud Pak for Data , and set your IBM Cloud® region to Dallas(us-south).
2. Open the Navigation Menu in the top left corner, and click Projects > View all projects.
3. Click New project.
4. Click Sample.
5. Click the tile named Evaluate an ML model.
6. Click the Create button to create the project with the ML model. View the import summary and ensure that the project is created successfully.
7. Click Mortgage Approval Prediction Model, which is available in the Asset section.
8. Click the Promote to deployment space button to deploy the model.
9. Choose an existing deployment space, or name a new one, in the Target space field.
10. From the Navigation Menu in the top left corner, choose Deployments.
11. Select your deployment space.
12. Choose Mortgage Approval Prediction Model.
13. Click the New deployment button.
14. Give the deployment a name and choose Online as the type.
15. Click the Create button.
16. Click your deployment in the list.
17. On the API reference page, the public and private endpoint of the deployment are displayed.
18. Copy the value of the public endpoint field. You use this value later to make a separate note of this part of the URL:

    https://us-south.ml.cloud.ibm.com/ml/v4/deployments/
    30d8221b-47ad-48d1-8b68-2f042474ff91
    predictions?version=2021-05-01

    Note: The shown endpoint value is an example. You get a different value when you do this task.
19. Note down the deployment ID. In this example, the ID is 30d8221b-47ad-48d1-8b68-2f042474ff91.
20. Click your deployment space in the breadcrumbs at the top of the browser window: Deployments / <your deployment space>.
21. Click the arrow button above the tray at the top right.
22. Choose Export space.
23. Click the New export file button.
24. Give a name for your export file and select the check box next to Mortgage Approval Prediction Model.
25. Click the Create button.
26. From the entry that appears in the table, hover over it and click the Download button to the right of the entry.
27. Open the download directory on your computer and locate the file with the name you chose. Open the compressed (.zip) file.
28. Inside the compressed file, navigate to assets/.METADATA.
29. Extract the file wml_model in the directory. It contains the details of your data model. It is not well formatted. To view it, you can use it any JSON formatter of your choice. It can be left unformatted if you do not want to inspect it.