tt_glm_par: Train-Test a GLM ensemble in parallel

In alexWhitworth/glmEnsemble: Builds GLM ensemble models in parallel

Description

Takes a list of training datasets and a single test dataset and builds an ensemble of GLMs in parallel. Additionally calculates ensemble weights based on element accuracy.

Usage

tt_glm_par(train_list, test_dat, out_vec, direction, family = binomial(link =
  "logit"), leave_cores = 1)

Arguments

train_list	A list of training data.frames for ensemble training
test_dat	A data.frame for calculating error rates from ensemble elements.
out_vec	A named vector "backbone" on which to place ensemble coefficients.
direction	A character string for the direction used in [stats]step
family	Used to specify the details of the glm methods. See [stats]family
leave_cores	An integer for number of cores to leave unused. Defaults to 1L.

alexWhitworth/glmEnsemble documentation built on Nov. 5, 2021, 6:55 a.m.