Vetiver:v0.2.3

Version

VetiverModel Create VetiverModel class for serving.
vetiver_pin_write Pin a trained VetiverModel along with other model metadata.
vetiver_create_prototype Create zero row structure to save data types
model_card.model_card Create a model card for documentation

Deploy

VetiverAPI Create model aware API
VetiverAPI.run Start API
VetiverAPI.vetiver_post Create new POST endpoint that is aware of model input data
vetiver_endpoint Wrap url where VetiverModel will be deployed
predict Make a prediction from model endpoint
write_app Write VetiverAPI app to a file
prepare_docker Create all files needed for Docker
write_docker.write_docker Writes a Dockerfile to run VetiverAPI in a container
deploy_rsconnect Deploy to Posit Connect

Monitor

compute_metrics Compute metrics for given time period
pin_metrics Update an existing pin storing model metrics over time
plot_metrics Plot metrics over a given time period

Model Handlers

BaseHandler Base handler class for creating VetiverModel of different type.
SKLearnHandler Handler class for creating VetiverModels with sklearn.
TorchHandler Handler class for creating VetiverModels with torch.
StatsmodelsHandler Handler class for creating VetiverModels with statsmodels.
XGBoostHandler Handler class for creating VetiverModels with xgboost.
SpacyHandler Handler class for creating VetiverModels with spacy.