From the course: Docker for Data Engineers
Unlock this course with a free trial
Join today to access over 24,900 courses taught by industry experts.
Making predictions using the containerized application - Docker Tutorial
From the course: Docker for Data Engineers
Making predictions using the containerized application
Let's confirm that our container has been successfully deployed. We can do this from the command line by running the az container show command. We specify the resource group, loony-deployment-rg, the name of the container, churn-prediction-app, and we want the fully qualified domain name and the provisioning state of the container. We want the output in a table format. And here is our fully qualified domain name of the container. The provisioning state is succeeded. Looks like the container deployed successfully. Let's head over to the Azure portal. Search for container instances. And there you should find our churn-prediction-app. Click through to this to view the details of the running container. Observe the fully qualified domain name of the container, the FQDN. We'll use this fully qualified domain name when we reference this container in our HTTP request to get predictions from the deployed model. Let's copy this over and let's make a curl request to our containerized app. Here…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
(Locked)
Azure Container Instances1m 34s
-
(Locked)
Training an ML model and serializing to a pickle file5m 7s
-
(Locked)
Setting up the Dockerfile for model prediction5m 45s
-
(Locked)
Running a containerized app locally for churn prediction2m 23s
-
(Locked)
Authenticating to Azure using the Azure CLI1m 35s
-
(Locked)
Creating an Azure Container Registry and pushing the image3m 58s
-
(Locked)
Deploying a container to Azure Container Instances4m 9s
-
(Locked)
Making predictions using the containerized application2m 44s
-
(Locked)
-