Introduction to Model Deployment

Peter Hurford


Deployment is the central hub for users to deploy, manage and monitor their models.

Manage Deployments

The following commands can be used to manage deployments.

Create a Deployment

When creating a new deployment, a DataRobot model_id and label must be provided. A description can be optionally provided to document the purpose of the deployment.

The default prediction server is used when making predictions against the deployment, and is a requirement for creating a deployment on DataRobot cloud. For on-prem installations, a user must not provide a default prediction server and a pre-configured prediction server will be used instead. Refer to ListPredictionServers for more information on retrieving available prediction servers.

project <- GetProject("5506fcd38bd88f5953219da0")
model <- ListModels(project)[[1]]
predictionServer <- ListPredictionServers()[[1]]
deployment <- CreateDeployment(model,
                               label = "New Deployment",
                               description = "A new deployment for demo purposes",
                               defaultPredictionServerId = predictionServer)

List Deployments

Use the following command to list deployments a user can view.


Retrieve a Deployment

It is possible to retrieve a single deployment with its identifier, rather than list all deployments.


Delete a Deployment

To mark a deployment as deleted, use the following command.

deployment <- GetDeployment("5e319d2e422fbd6b58a5edad")

Model Replacement

The model of a deployment can be replaced effortlessly with zero interruption of predictions.

Model replacement is an asynchronous process, which means there are some preparatory works to complete before the process is fully finished. However, predictions made against this deployment will start using the new model as soon as you initiate the process. The ReplaceDeployedModel function won’t return until this asynchronous process is fully finished.

Alongside the identifier of the new model, a reason is also required. The reason is stored in model history of the deployment for bookkeeping purpose. An enum ModelReplacementReason is provided for convenience, all possible values are documented below:

Here is an example of model replacement:

project <- GetProject("5506fcd38bd88f5953219da0")
newModel <- ListModels(project)[[2]]
deployment <- GetDeployment("5e319d2e422fbd6b58a5edad")
ReplaceDeployedModel(deployment, newModel, ModelReplacementReason$Accuracy)


Before initiating the model replacement request, it is usually a good idea to use the ValidateReplaceDeployedModel function to validate if the new model can be used as a replacement.

The ValidateReplaceDeployedModel function returns the validation status, a message and a list with details on each check. If the status is “passing” or “warning”, use ReplaceDeployedModel to perform model the replacement. If status is “failing”, refer to the checks list for more details on why the new model cannot be used as a replacement.

project <- GetProject("5506fcd38bd88f5953219da0")
newModel <- ListModels(project)[[2]]
deployment <- GetDeployment("5e319d2e422fbd6b58a5edad")
validation <- ValidateReplaceDeployedModel(deployment, newModel)
print(validation$status)  # Look here to see if passing
print(validation$checks)  # Look here if not passing to see why

Drift Tracking Setting

Drift tracking is used to help analyze and monitor the performance of a model after it is deployed. When the model of a deployment is replaced drift tracking status will not be altered.

Use GetDeploymentDriftTrackingSettings to retrieve the current tracking status for target drift and feature drift:

deployment <- GetDeployment("5e319d2e422fbd6b58a5edad")

Use UpdateDeploymentDriftTrackingSettings to update target drift and feature drift tracking status.

deployment <- GetDeployment("5e319d2e422fbd6b58a5edad")
UpdateDeploymentDriftTrackingSettings(deployment, targetDriftEnabled = TRUE)