Systematic data science process and model development
R is constantly evolving through its active community and its efficient package system. This session does not only include new functionalities and new machine learning models, but also better ways of writing more efficient code for your data science project. The key take away from this talk, is the importance of structuring your data science process and aligning it with your code development. By using new package ecosystems such as tidyverse and tidymodels, we will see how you can structure your data science project and write efficient code in R that will save you substantial time and make better models.
In this lecture, we will talk about the importance of the R community and structuring your data science process. Then we will move on the look closer at how you can build models using the tidymodels package. Thus, you will learn to use tidymodels to make systematic modeling in R.
About the Speaker:
Jens is an assistant professor in Computer Science at Roskilde University with a background in mathematics and philosophy. Prior to joining Roskilde University Jens worked as a data scientist in industry for four year, where he picked up R and worked with it professionally for the entire time. At Roskilde University Jens teaches various courses and supervise projects within Data Science and AI, often with R as the go to tool, as well as R courses for other researchers.
Agenda:
17:00 – 17:05 Welcome
17:05 – 17:55 R for Advanced Analytics
17:55 – 18:05 Q&A