library(tidymodels) # Create Recipe model_recipe <- recipes::recipe(what-to-predict ~ data-features, data = your-data) # Define model using parsnip (e.x. linear regression) model_type <- parsnip::linear_reg() # Combine the two to create a workflow model_wflow <- workflows::workflow(model_recipe, model_type) # Fit workflow to data using parsnip model_fit <- parsnip::fit(model_wflow, your-data)library(tidymodels) # Create Recipe model_recipe <- recipes::recipe(what-to-predict ~ data-features, data = your-data) # Define model using parsnip (e.x. linear regression) model_type <- parsnip::linear_reg() # Combine the two to create a workflow model_wflow <- workflows::workflow(model_recipe, model_type) # Fit workflow to data using parsnip model_fit <- parsnip::fit(model_wflow, your-data)library(tidymodels) # Create Recipe model_recipe <- recipes::recipe(what-to-predict ~ data-features, data = your-data) # Define model using parsnip (e.x. linear regression) model_type <- parsnip::linear_reg() # Combine the two to create a workflow model_wflow <- workflows::workflow(model_recipe, model_type) # Fit workflow to data using parsnip model_fit <- parsnip::fit(model_wflow, your-data)library(tidymodels) # Create Recipe model_recipe <- recipes::recipe(what-to-predict ~ data-features, data = your-data) # Define model using parsnip (e.x. linear regression) model_type <- parsnip::linear_reg() # Combine the two to create a workflow model_wflow <- workflows::workflow(model_recipe, model_type) # Fit workflow to data using parsnip model_fit <- parsnip::fit(model_wflow, your-data)
Tidymodels and Vetiver
Section Agenda
Goal of Ferry Delay Prediction Model
Tidymodels
- Assignment - Create a tidymodel
Vetiver
- Pins and Plumber
- Assignment - Deploy and monitor your tidymodel
Disclaimer
THIS IS NOT A MODELING WORKSHOP!
… but modeling is still super cool 😎 !
Review
What’s the Goal?
What we have:
A beautiful - tidy - validated dataset
Ferry information and history
Weather data
What do we want:
- A MODEL that can predict if a ferry will have a delayed departure
Where are we going
Review - Washington State Ferry
⛴️ WSF is the largest operating public ferry system in the US! 🤯
🐋 21 ferries across Puget Sound and the Salish Sea
Question and Answer
The Question
Can we help inform travelers about possible ferry delays?
The Answer
Use the ferry-weather (validated) data to create a model that will predict delay status!
Introduction to Tidymodels
✋ If you have used tidymodels before?
Introduction to Tidymodels
Steps to create (most) models:
- Data - preprocessing?
- Create a formula - what does the model do?
- Define your model type - Linear regression, decision tree, xgboost, etc?
- Train
- Test
- Predict
Introduction to Tidymodels
Introduction to Tidymodels
Activity Time!
Activity
- Open the project
materials/04-tidymodels-vetiver/04-tidymodels-vetiver.Rproj - Open the file
04-tidymodels-vetiver.qmd
Complete Tasks 0 & 1 only!
Goal
Build a model using tidymodels.
We have a model…now what 🤷 ?
We have two questions:
- How can we save our model so others can use it?
- How can we serve our model so others can interact with it?
How do you save/share models?
Vetiver
- Open source R (and Python) package.
- Deploy and maintain machine learning models –> MLOps
- Provides tools to version, deploy, and monitor a trained model.
Introduction to Pins & Plumber
🧰 Pins
- Open source R (and Python) package.
- Publishes data, models, and other R objects, making it easy to share them across projects and with your colleagues.
- Interoperability –> You can share an object built in R with Python users (and vice versa)!
- For our workflow:
- How can we save our model so that others (or other content) can use it?
Activity
Activity
- Open the project
materials/04-tidymodels-vetiver/04-tidymodels-vetiver.Rproj - Open the file
04-tidymodels-vetiver.qmd
Complete Task 2 only!
Goal
Use vetiver to pin model to Posit Connect.
🧰 Plumber
- Open source R package.
- Create a web Application Programming Interface (API) using only R code!
- Interoperability –> You can interact with a Plumber API using Python (or any other language/HTTP client).
- For our workflow:
- How can we serve our model as an API?
Activity
Activity
- Open the project
materials/04-tidymodels-vetiver/04-tidymodels-vetiver.Rproj - Open the file
04-tidymodels-vetiver.qmd
Complete Task 3 only!
Goal
Use vetiver to serve the pinned model as an API to Posit Connect.
Version and Monitor your models
- Data changes over time
- Models change over time
- How can I ensure I’m using the best model for the job?
Activity
- Open the project
materials/04-tidymodels-vetiver/04-tidymodels-vetiver.Rproj - Open the file
04-tidymodels-vetiver.qmd
Complete Task 4
Goal
Use vetiver to version and monitor your ferry predict model.
Summary - Pins/Plumber
Ferry Delay Prediction Model
Training this model is relatively fast
What if the model training is slow or the data is REALLY big?
Workbench Jobs allows you to run R/Python scripts in new sessions independent of your current RStudio Pro/VSCode session
![]()
If you create a model, you should create a model card!
- Check out a basic model card here!
Review
Click to go back to Data Science Workflows with Posit Tools - R Focus website ↩︎
Tidymodels and Vetiver