costsensitive (version 0.1.2.10)

regression.one.vs.rest: Regression One-Vs-Rest

Description

Creates a cost-sensitive classifier by creating one regressor per class to predict cost. Takes as input a regressor rather than a classifier. The objective is to create a model that would predict the class with the minimum cost.

Usage

regression.one.vs.rest(X, C, regressor, nthreads = 1, ...)

Arguments

X

The data (covariates/features).

C

matrix(n_samples, n_classes) Costs for each class for each observation.

regressor

function(X, y, ...) -> object, that would create regressor with method `predict`.

nthreads

Number of parallel threads to use (not available on Windows systems). Note that, unlike the Python version, this is not a shared memory model and each additional thread will require more memory from the system. Not recommended to use when the algorithm is itself parallelized.

...

Extra arguments to pass to `regressor`.

References

Beygelzimer, A., Langford, J., & Zadrozny, B. (2008). Machine learning techniques-reductions between prediction quality metrics.

Examples

# NOT RUN {
library(costsensitive)
wrapped.lm <- function(X, y, ...) {
	return(lm(y ~ ., data = X, ...))
}
set.seed(1)
X <- data.frame(feature1 = rnorm(100), feature2 = rnorm(100), feature3 = runif(100))
C <- data.frame(cost1 = rgamma(100, 1), cost2 = rgamma(100, 1), cost3 = rgamma(100, 1))
model <- regression.one.vs.rest(X, C, wrapped.lm)
predict(model, X, type = "class")
predict(model, X, type = "score")
print(model)
# }