VetiverModel

VetiverModel(self, model, model_name, prototype_data=None, versioned=None, description=None, metadata=None, **kwargs)

Create VetiverModel class for serving.

Parameters

Name	Type	Description	Default
model		A trained model, such as an sklearn or torch model	required
model_name	string	Model name or ID	required
prototype_data	(pd.DataFrame, np.array)	Sample of data model should expect when it is being served	None
versioned		Should the model be versioned when created?	None
description	str	A detailed description of the model. If omitted, a brief description will be generated.	None
metadata	dict	Other details to be saved and accessed for serving	None
**kwargs		Deprecated parameters.	{}

Attributes

Name	Type	Description
prototype	vetiver.Prototype	Data prototype
handler_predict	Callable	Method to make predictions from a trained model

Notes

VetiverModel can also take an initialized custom VetiverHandler as a model, for advanced use cases or non-supported model types. Parameter ptype_data was changed to prototype_data. Handling of ptype_data will be removed in a future version.

Examples

>>> from vetiver import mock, VetiverModel
>>> X, y = mock.get_mock_data()
>>> model = mock.get_mock_model().fit(X, y)
>>> v = VetiverModel(model = model, model_name = "my_model", prototype_data = X)
>>> v.description
'A scikit-learn DummyRegressor model'

Methods

Name	Description
from_pin	Create VetiverModel from pinned model.

from_pin

VetiverModel.from_pin(board, name, version=None)

Create VetiverModel from pinned model.

Parameters

Name	Type	Description	Default
board		pins board where model is located	required
name	str	Model name inside pins board	required
version	str	What model version should be loaded	None