Skip to contents

Determine Weights Appropriately for Super Learner given Binary Outcomes

Source: R/determine_weights.R
determine_weights_for_binary_outcomes.Rd

Determine Weights Appropriately for Super Learner given Binary Outcomes

Usage

determine_weights_for_binary_outcomes(
  data,
  y_variable,
  obs_weights = NULL,
  bound_eps = 0.001
)

Arguments

data

A data.frame with columns corresponding to predicted probabilities of 1 from each learner and the true y_variable from held-out data

y_variable

A character indicating the outcome variable in the data.frame.

obs_weights

A vector of weights for each observation that dictate how prediction should be more targeted to higher weighted observations.

bound_eps

A numeric value used to truncate probabilities away from 0 and 1.

Value

A vector of weights to be used for each of the learners.

Examples

predicted_probabilities <- data.frame(
  logistic = lnr_logistic(mtcars, am ~ hp)(mtcars),
  nnet = lnr_nnet(mtcars, am ~ hp)(mtcars),
  am = mtcars$am
)
determine_weights_for_binary_outcomes(predicted_probabilities, y_variable = "am")
#> [1] 0.8330272 0.1669728