CatBoost

About this page

This is an API reference for CatBoost in BentoML. Please refer to CatBoost guides for more information about how to use CatBoost in BentoML.

bentoml.catboost.save_model(name: Tag | str, model: cb.CatBoost, *, signatures: dict[str, ModelSignatureDict] | None = None, labels: dict[str, str] | None = None, custom_objects: dict[str, t.Any] | None = None, external_modules: t.List[ModuleType] | None = None, metadata: dict[str, t.Any] | None = None) → bentoml.Model

Save an CatBoost model instance to the BentoML model store.

Parameters:

• name – The name to give to the model in the BentoML store. This must be a valid Tag name.

• model – The CatBoost model to be saved.

• signatures – Signatures of predict methods to be used. If not provided, the signatures default to {"predict": {"batchable": False}}. See ModelSignature for more details.

• labels – A default set of management labels to be associated with the model. An example is {"training-set": "data-1"}.

• custom_objects –

  Custom objects to be saved with the model. An example is {"my-normalizer": normalizer}.

  Custom objects are currently serialized with cloudpickle, but this implementation is subject to change.

• external_modules (List[ModuleType], optional, default to None) – user-defined additional python modules to be saved alongside the model or custom objects, e.g. a tokenizer module, preprocessor module, model configuration module

• metadata –

  Metadata to be associated with the model. An example is {"max_depth": 2}.

  Metadata is intended for display in model management UI and therefore must be a default Python type, such as str or int.

Returns:

A tag with a format name:version where name is the user-defined model’s name, and a generated version by BentoML.

Return type:

Tag

Example:

import bentoml
import numpy as np

from catboost import CatBoostClassifier, Pool

# initialize data
train_data = np.random.randint(0, 100, size=(100, 10))

train_labels = np.random.randint(0, 2, size=(100))

test_data = catboost_pool = Pool(train_data, train_labels)

model = CatBoostClassifier(iterations=2,
                           depth=2,
                           learning_rate=1,
                           loss_function='Logloss',
                           verbose=True)
# train the model
model.fit(train_data, train_labels)

# save the model to the BentoML model store
bento_model = bentoml.catboost.save_model("my_catboost_model", model)

bentoml.catboost.load_model(bento_model: str | Tag | Model) → catboost.CatBoost

Load the CatBoost model with the given tag from the local BentoML model store.

Parameters:

bento_model (str | Tag | Model) – Either the tag of the model to get from the store, or a BentoML ~bentoml.Model instance to load the model from.

Returns:

The CatBoost model loaded from the model store or BentoML Model.

Return type:

CatBoost

Example:

import bentoml
# target model must be from the BentoML model store
booster = bentoml.catboost.load_model("my_catboost_model")

bentoml.catboost.get(tag: t.Union[Tag, str], *, _model_store: ModelStore = <simple_di.providers.SingletonFactory object>, model_aliases: t.Dict[str, str] = <simple_di.providers.Static object>) → Model

Get a model by tag. If the tag is a string, it will be looked up in the model_aliases dict.

bentoml.catboost.get_service(model_name: str, **config: Unpack[ServiceConfig]) → Service[t.Any]

Get a BentoML service for the catboost model given by name.

Parameters:

• model_name (str) – The name of the model to get the service for.

• **config (Unpack[ServiceConfig]) – Configuration options for the service.

Returns:

A BentoML service instance that wraps the CatBoost model.

Example:

import bentoml

service = bentoml.catboost.get_service("my_catboost_model")