In this week's #TidyTuesday video, I go over the Palmer Penguins dataset. I then briefly describe each #TidyModels packages and its main functions. I use the Rsample package to create a train and test set as well as a validation set using kfolds crossvalidation. I also preprocess the data using the Recipes package as well as use Knn to impute missing data. I then create two models: an XGBoost model and a Knearest neighbor model using the Parsnip package. After that, I use the Dials package to create a grid of parameters for both models and then train the models using the Tune package. Finally, I use the Workflow package to train the models and evaluate the models using the Yardstick package. After modeling, I create an R Shiny App using shinydashboard and deploy the previously created model for realtime predictions.
Connect with me on LinkedIn: / andrewcouch
Q&A Submission Form: https://forms.gle/6EzU4GCR9VnJx8gg7
Code for this video: https://github.com/andrewcouch/Tidy...
TidyTuesday: https://github.com/rfordatascience/ti...
PC Setup (Amazon Affiliates)
Keyboard: https://amzn.to/3Bbbk3T
Mouse: https://amzn.to/3BcRGVo
Microphone: https://amzn.to/3ePo9JS
Audio Interface: https://amzn.to/3qTAmjz
Webcam: https://amzn.to/3L9Ql6j
CPU: https://amzn.to/3qGa6Zu
GPU: https://amzn.to/3DnhMHL
RAM: https://amzn.to/3LdTxh7