buildEnsembleModel: Build ensemble model based on h2o platform

In ProfessionalFarmer/loonR: Common function in bioinformatics analysis

Build ensemble model based on h2o platform

Description

Build ensemble model based on h2o platform

Usage

buildEnsembleModel(
  train.df = NULL,
  train.group = NULL,
  val.df = NULL,
  val.group = NULL,
  candidates = NULL,
  nfolds = 5,
  seed = 1,
  type = "run",
  metalearner_algorithm = "glm",
  glm = TRUE,
  xg = TRUE,
  dl = TRUE,
  nb = TRUE,
  gbm = TRUE,
  rf = TRUE
)

Arguments

train.df	row is sample, column is feature
train.group	a vector
val.df	Default NULL, not to evaluate in validation dataset. row is sample, column is feature
val.group	a vector
candidates	if not specify candidates feature, all column names will be used
nfolds	Default 5. Used in internal model construction
seed	Default 1
type	Description for this run. Default "run"
metalearner_algorithm	Default glm. Could be "AUTO", "deeplearning", "drf", "gbm", "glm", "naivebayes", "xgboost". If AUTO, (GLM with non negative weights; if validation_frame is present, a lambda search is performed
glm	TRUE. Default included glm
xg	TRUE. Default included xgboost
dl	TRUE. Default included deep learning
nb	TRUE. Default included NaiveBayes
gbm	TRUE. Default included gbm
rf	TRUE. Default included random forests

Value

A list include fits, training risk score, aucs

ProfessionalFarmer/loonR documentation built on Oct. 9, 2024, 9:56 p.m.