fmeta.xgb: xgboost meta predictor

In fizlaz/DUN: Team DUN Kaggle milestone

Description

Creates probabilities for each class

Usage

fmeta.xgb(train, test = NULL, folds = 5, nrounds = 250, csv = FALSE,
  verbose = 1)

Arguments

train	Train set without ID and URL
test	Test set without ID and URL. If left empty then it the functions trains on train with 5 fold cross validation
folds	Number of cross validation folds
nrounds	Number of rounds per fold, default 250
csv	Boolean, default FALSE. If TRUE, saves csv output.
verbose	0(quiet),1(evaluation metric),2(+tree information), default 1

Value

A data frame with 5 probabilites for each row

fizlaz/DUN documentation built on May 16, 2019, 1:13 p.m.