OpenADMET Models documentation

openadmet-models

XGBoost

XGBoost model implementations.

class openadmet.models.architecture.xgboost.XGBClassifierModel(**extra_data: Any)

Bases: XGBoostModelBase

XGBoost classification model.

Common parameters for XGBoost models can be found at: https://xgboost.readthedocs.io/en/stable/python/python_api.html Common parameters that you might want to set include: - n_estimators: Number of trees in the ensemble - max_depth: Maximum depth of a tree - max_leaves: Maximum number of leaves in a tree - learning_rate: Step size shrinkage used in update to prevent overfitting - objective: Specify the learning task and corresponding objective function - booster: Specify which booster to use, options are gbtree, gblinear or dart - tree_method: Specify the tree construction algorithm used in XGBoost

mod_class

alias of XGBClassifier

model_config: ClassVar[ConfigDict] = {'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_post_init(context: Any, /) → None

This function is meant to behave like a BaseModel method to initialize private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Args:

self: The BaseModel instance. context: The context.

predict_proba(X: ndarray) → ndarray

Predict using the model, returning probabilities for each class.

Parameters:

X (np.ndarray) – Data to predict on

Returns:

Probabilities for each class from the model

Return type:

np.ndarray

type: ClassVar[str] = 'XGBoostClaXGBClassifierModelssifierModel'

class openadmet.models.architecture.xgboost.XGBRegressorModel(**extra_data: Any)

Bases: XGBoostModelBase

XGBoost regression model.

Common parameters for XGBoost models can be found at: https://xgboost.readthedocs.io/en/stable/python/python_api.html

Common parameters that you might want to set include: - n_estimators: Number of trees in the ensemble - max_depth: Maximum depth of a tree - max_leaves: Maximum number of leaves in a tree - learning_rate: Step size shrinkage used in update to prevent overfitting - objective: Specify the learning task and corresponding objective function - booster: Specify which booster to use, options are gbtree, gblinear or dart - tree_method: Specify the tree construction algorithm used in XGBoost

mod_class

alias of XGBRegressor

model_config: ClassVar[ConfigDict] = {'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_post_init(context: Any, /) → None

This function is meant to behave like a BaseModel method to initialize private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Args:

self: The BaseModel instance. context: The context.

type: ClassVar[str] = 'XGBRegressorModel'

class openadmet.models.architecture.xgboost.XGBoostModelBase(**extra_data: Any)

Bases: PickleableModelBase

Base class for XGBoost models.

build()

Prepare the model.

mod_class: ClassVar[type]

model_config: ClassVar[ConfigDict] = {'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_post_init(context: Any, /) → None

This function is meant to behave like a BaseModel method to initialize private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Args:

self: The BaseModel instance. context: The context.

predict(X: ndarray, **kwargs) → ndarray

Predict using the model.

Parameters:

• X (np.ndarray) – Data to predict on

• kwargs (Dict) – Keyword arguments for model

Returns:

Predictions from the model

Return type:

np.ndarray

train(X: ndarray, y: ndarray)

Train the model.

Parameters:

• X (np.ndarray) – Training data features

• y (np.ndarray) – Training data labels

type: ClassVar[str]