deepboost.formula: Main function for deepboost model creation, using a formula

In deepboost: Deep Boosting Ensemble Modeling

Description

Main function for deepboost model creation, using a formula

Usage

deepboost.formula(formula, data, instance_weights = NULL, tree_depth = 5,
  num_iter = 1, beta = 0, lambda = 0.05, loss_type = "l",
  verbose = TRUE)

Arguments

formula	A R Formula object see : ?formula
data	A data.frame of samples to train on
instance_weights	The weight of each example
tree_depth	maximum depth for a single decision tree in the model
num_iter	number of iterations = number of trees in ensemble
beta	regularisation for scores (L1)
lambda	regularisation for tree depth
loss_type	- "l" logistic, "e" exponential
verbose	- print extra data while training TRUE / FALSE

Value

A trained Deepbost model

Examples

deepboost.formula(y ~ .,
 data.frame(x1=rep(c(0,0,1,1),2),x2=rep(c(0,1,0,1),2),y=factor(rep(c(0,0,0,1),2))),
 num_iter=1)
deepboost.formula(y ~ .,
 data.frame(x1=rep(c(0,0,1,1),2),x2=rep(c(0,1,0,1),2),y=factor(rep(c(0,0,0,1),2))),
 num_iter=2, beta=0.1, lambda=0.00125)

Example output

Iteration: 1, error: 0.25, avg tree size: 1, num trees: 1
[1] "Model error: 0.25"
[1] "Average tree size: 1"
[1] "Number of trees: 1"
Iteration: 1, error: 0.25, avg tree size: 1, num trees: 1
Iteration: 2, error: 0, avg tree size: 3, num trees: 2
[1] "Model error: 0"
[1] "Average tree size: 3"
[1] "Number of trees: 2"

deepboost documentation built on May 2, 2019, 8:35 a.m.