Abstract: The Julia programming language is showing great promise by combining the power and flexibility of Python with the speed of C. The support of the community is phenomenal with multiple open source packages to help with development coming out daily. This talk is devoted to developing and entire workflow of data preparation, model building, and deploying through a REST API for consumption in production.
This talk will go through the data preparation phase, including, importing data, basic munging, and feature engineering. The next step of the process will go through building and testing machine-learning models. Through scikitlearn.jl, Julia has access to Python’s Scikit Learn package and all the underlying models available in addition to the numerous models written in Julia. This will go into the writing of a testing file to cross-validate and evaluate goodness of fit on the models for determination as to which model to use. Once the data scientist has a model that works well, the final (and most important step) is putting that model into production. The last step of this talk is on deploying the selected model within the Genie framework.
The Genie framework is a full stack web framework with a rich API. While it does a good job of building web applications, the focus of this talk is on building a RESTful API that can be easily integrated with the rest of any organizations tech stack. This framework allows machine learning models to be stored in memory, resulting in lightning fast response times on model scoring.
A basic understanding of building machine learning models is expected, but no knowledge of Julia or building an API is expected. All code will be available at the end of the talk with a template ready for starting their own projects!
Bio: Chase is currently a Data Scientist at Progressive Leasing in Draper, Utah working on variety of cool projects. Prior to the current position, he was an Assistant Professor of Finance and Economics at the University of South Carolina Upstate and holds a BS, MS, and PhD, all in Economics, from the University of Utah.