graboo_reg: Function that builds weak model on Gradient Boosting for...
In StevenBoys/Ensemblelearn: Use Ensemble learning to better prediction.

Description Usage Arguments Value Examples

Function that builds weak model on Gradient Boosting for regression task

1	graboo_reg(x, y, last_est, loss = mse, eta = 0.1)

`x`	- input independent variables x for the training
`y`	- input dependent variable y for the traisning
`last_est`	- the output estimate from the last step
`loss`	- the loss function used, its default value is the mean of the square error
`eta`	- the step size we use to update the total estimate each time, its default value is 0.1

The trained results of weak model on Gradient Boosting.

x <- matrix(rnorm(4000), 200, 20)
beta <- rnorm(5)
y <- x[, 1:length(beta)] %*% beta + rnorm(200)
last_est <- rep(0, ncol(x))
graboo_reg(x, y, last_est)