R6 Class for Scikit-learn Regressors

An R6 Class that provides an interface to scikit-learn regression models.

Public fields

model

The underlying sklearn model

residuals

Model residuals

df.residual

Degrees of freedom of residuals

Methods

Public methods

• Regressor$new()

• Regressor$fit()

• Regressor$predict()

• Regressor$clone()

---

Method new()

Create a new Regressor object

Usage

Regressor$new(model_name, ...)

Arguments

model_name

Name of the sklearn model to use

...

Additional parameters passed to the sklearn model

---

Method fit()

Fit the model to training data

Usage

Regressor$fit(x, y, calibration = FALSE, seed = 42L, ...)

Arguments

x

Feature matrix

y

Target vector

calibration

Logical flag to indicate if calibration of residuals should be used

seed

Seed for random number generator

---

Method predict()

Make predictions on new data

Usage

Regressor$predict(
  newdata,
  method = c("none", "splitconformal", "surrogate", "bootstrap", "tsbootstrap",
    "bayesian"),
  nsim = 250L,
  level = 95,
  seed = 123
)

Arguments

newdata

New data to predict on

method

Method for computing prediction intervals

nsim

Number of simulations for bootstrap/tsbootstrap

level

Confidence level for prediction intervals

seed

Random seed

---

Method clone()

The objects of this class are cloneable with this method.

Usage

Regressor$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.