Skip to content

pm_service_api_manage_deploy.md

Latest commit

 

History

History
86 lines (69 loc) · 2.42 KB

pm_service_api_manage_deploy.md

File metadata and controls

86 lines (69 loc) · 2.42 KB
copyright
years
2016, 2017
lastupdated 2017-11-16

{:new_window: target="_blank"} {:shortdesc: .shortdesc} {:screen: .screen} {:codeblock: .codeblock} {:pre: .pre}

Deploying or refreshing a predictive model

To deploy or refresh a predictive model by using the service, you use an API call to upload a file that contains the scoring branch that was developed by using IBM® SPSS® Modeler. It is made available for scoring data in your applications. Each model file is given a context ID as a convenient alias to use for referencing the deployed model in subsequent service calls. If a model exists for a context ID, it is replaced by this PUT call as a means of refreshing the predictive analytics in use by your applications. {: shortdesc}

PUT http://{PA Bluemix load balancer
URL}/pm/v1/model/{contextId}?accesskey={access_key for this bound
application}

{: codeblock}

Request example:

    Content-Type: multipart/form-data
    Parameters:
        Form parameters:
            model_file: the model file to upload
        Path parameters:
            contextId: the unique identifier to assign to your model or a reference to the deployed model to refresh
        Query Parameters:
            accesskey: access_key from env.VCAP_SERVICES

{: codeblock}

Response when the deployment succeeds:

    Content-Type: application/json
    Status code: 200
    body:
        {
           "flag":true, 
           "message":"detailed information"  
         }

{: codeblock}

Response when the deployment fails:

    Content-Type: application/json
    Status code: 200
    body:
        {
           "flag":false, 
           "message":"reason"
        }

{: codeblock}

Learn more

Ready to get started? To create an instance of a service or bind an application, see Using the service with Spark and Python models or Using the service with IBM® SPSS® models.

For more information about the API, see Service API for Spark and Python models or Service API for IBM® SPSS® models.

For more information about IBM® SPSS® Modeler and the modeling algorithms it provides, see IBM Knowledge Center.

For more information about IBM Data Science Experience and the modeling algorithms it provides, see https://datascience.ibm.com.