In this hands-on lab, you are working as a data scientist for Sam’s Taxi, a taxi cab company. You’ve been asked to come up with a model that can be used to predict fare prices based on length of drive and time it takes to drive there. You’ll use Azure Machine Learning studio and Azure automated machine learning to create a regression model that will predict fare prices. You’ll also get a chance to deploy your model to a real-time endpoint.
Successfully complete this lab by achieving the following learning objectives:
- Open the Azure ML Studio and Create a New Dataset
In the Azure ML studio, create a new dataset using the taxi fare data file from Microsoft.
- Configure and Start the Automated ML Run
Change the timeout of the run to 30 minutes by clicking on View additional configuration settings, expanding Exit criterion, and setting the Training job time (hours) to 0.5, so it will stop after approximately 30 minutes.
- Review Results
Take a look at some of the metrics for the run, like the R2 score or the root mean squared error.
- Deploy the Model to a Real-Time Endpoint
During the deployment process on the compute step, make sure the VM is set to standard_DS2_v2 and change the instance count to 1. Otherwise, the resources will be deleted.
- Test Your Newly Deployed Model
Use some values from the CSV file and see how accurate the predicted value is compared to the actual value.