Model deployment
Before publishing your model as a web service, create a scoring experiment and make sure that the Web service input and the Web service output modules are properly connected. Also, process the model if you want your output in a proper format, for example, outputting only the scored label and input to the score model may not contain the label column; in this case, you can also filter the ArrDelay15 column along with the others in the Project Columns module connected to the Score Model module. Let's take a look at the following screenshot:
Then, publish your scoring experiment, so that it would be available as a web service in the ...
Get Microsoft Azure Machine Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
