MLOPS and Azure Machine Learning Service
<p>As a data engineer on Azure who works closely with data scientists and in data science projects, it’s my job to find and deploy the best tools for machine learning projects. Data science happens in notebooks, starts with a small idea and over the years has become more easy to use than ever before. What used to be a notebook full of code building custom models has (luckily for all of us) developed into a selection of import statements and open source models data scientist can use on demand.</p>
<p>Feed a model your labeled and prepped data and your are ready to go. So why do we need anything more than Jupyter and Python to do it?</p>
<p>A model in a notebook is a good start but not something you want to deploy into production. This is where MLOPS and all the wonderful machine learning tools we currently have come into play.</p>
<h1>MLOPS</h1>
<p>MLOPS stands for Machine Learning Operations and is the process of getting a model ready for production. It’s basically all the steps you need to take after the notebook phase.</p>
<p> </p>
<p>ML-Dev-Ops</p>
<p>Imagine you have a promising model and a good idea of what you need to do with the input data. The next step now is to automate the process of training, validating and deploying your model.</p>
<p><a href="https://medium.com/@marthalasia/mlops-and-azure-machine-learning-service-ed61a8c220e">Read More</a></p>