vetiver
Contents
vetiver#
The goal of vetiver is to provide fluent tooling to version, share, deploy, and monitor a trained model. Functions handle both recording and checking the model’s input data prototype, and predicting from a remote API endpoint. You can use vetiver with:
You can install the released version of vetiver from PyPI:
python -m pip install vetiver
And the development version from GitHub with:
python -m pip install git+https://github.com/rstudio/vetiver-python
This website documents the public API of Vetiver (for Python). See vetiver.rstudio.com for more on how to get started.
Version#
|
Create VetiverModel class for serving. |
|
Pin a trained VetiverModel along with other model metadata. |
|
|
|
Create a model card for documentation |
Deploy#
|
Create model aware API |
|
Start API |
|
Create new POST endpoint that is aware of model input data |
|
Wrap url where VetiverModel will be deployed |
|
Make a prediction from model endpoint |
|
Write VetiverAPI app to a file |
|
Writes a Dockerfile to run VetiverAPI in a container |
|
Load packages necessary for predictions |
|
Create all files needed for Docker |
|
Deploy to Posit Connect |
Monitor#
|
Compute metrics for given time period |
|
Update an existing pin storing model metrics over time |
|
Plot metrics over a given time period |
Model Handlers#
|
Base handler class for creating VetiverModel of different type. |
|
Handler class for creating VetiverModels with sklearn. |
|
Handler class for creating VetiverModels with torch. |
|
Handler class for creating VetiverModels with statsmodels. |
|
Handler class for creating VetiverModels with xgboost. |
Advanced Usage#
Advanced Usage