Ensbl: An ensemble of xgboosts

In Gibbsdavidl/robencla: A robust ensemble of XGBoosts and data transformations.

An ensemble of xgboosts

Description

Each member of the ensemble is an xgboost, and contains a random sample of the data.

Details

The ensbl object contains a list of xgboost objects

Methods

Public methods

• Ensbl$new()

• Ensbl$print()

• Ensbl$sample_data()

• Ensbl$train_models()

• Ensbl$ensemble_combine()

• Ensbl$final_ensemble_combine()

• Ensbl$member_predict()

• Ensbl$print_error()

• Ensbl$clone()

---

Method new()

Usage

Ensbl$new(name, obj_mode, size, data, label, params)

---

Method print()

Usage

Ensbl$print(...)

---

Method sample_data()

Usage

Ensbl$sample_data(perc)

---

Method train_models()

Usage

Ensbl$train_models(perc)

---

Method ensemble_combine()

Usage

Ensbl$ensemble_combine(combine_function)

---

Method final_ensemble_combine()

Usage

Ensbl$final_ensemble_combine(combine_function)

---

Method member_predict()

Usage

Ensbl$member_predict(data, combine_function)

---

Method print_error()

Usage

Ensbl$print_error(label, threshold)

---

Method clone()

The objects of this class are cloneable with this method.

Usage

Ensbl$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Gibbsdavidl/robencla documentation built on Dec. 25, 2024, 12:44 a.m.