https://blog.smarttechventures.au/tags/dotnet-data-science/Recent content in Dotnet Data-Science on Chris McKelt - Remembering ThoughtsHugo -- 0.147.2enFri, 03 Aug 2018 00:00:00 +0800https://blog.smarttechventures.au/articles/posts/charge-id-deploying-to-a-ml-net-model-to-azure-part-6/Fri, 03 Aug 2018 00:00:00 +0800https://blog.smarttechventures.au/articles/posts/charge-id-deploying-to-a-ml-net-model-to-azure-part-6/<p>In the previous post we built a machine learning model using <a href="http://dot.net/ml" target="_blank">ML.Net</a>, in this post we will deploy the model to an Azure app and allow it to be used via a HTTP API</p> <p>Using the output model in zip format ‘vita-model-1.zip’ we can include this in our web application as an embedded resource or simply include the file for deployment.</p> <p>To use the file from a HTTP endpoint:</p> <ol> <li>Include the zip file in your deployment – embedded resource/content/read from blob storage etc..</li> <li>Initialise the model as a singleton during application start up by using a file path or stream</li> <li>Call the model using the function PredictionModel.Predict(‘my data from which to predict’)</li> </ol> <p>Sample below that logs to <a href="https://logz.io/" target="_blank">Logz.io</a></p>