l2boost {boost} | R Documentation |
An implementation of the LogitBoost algorithm for binary classification
l2boost(xlearn, ylearn, xtest, presel = 200, mfinal = 100)
xlearn |
A (n x p)-matrix, where rows correspond to training instances and columns contain the predictor variables. |
ylearn |
A vector of length n containing the class labels, which need to be coded by 0 and 1. |
xtest |
A (m x p)-matrix, where rows correspond to test instances and columns contain the predictor variables. |
presel |
An integer, giving the number of features to be pre-selected according to the Wilcoxon test statistic. Default is presel=200 features. If presel=0, no feature preselection is carried out. |
mfinal |
An integer, the number of iterations for which boosting is run. Defaults to mfinal=100 iterations |
The function outputs an array, whose rows contain out-of-sample probabilities that the class labels are predicted as being of class 1, for every boosting iteration.
Marcel Dettling
data(leukemia, package = "boost") ## Dividing the leukemia dataset into training and test data xlearn <- leukemia.x[c(1:20, 34:38),] ylearn <- leukemia.y[c(1:20, 34:38)] xtest <- leukemia.x[21:33,] ytest <- leukemia.y[21:33] ## Classification with l2boost fit <- l2boost(xlearn, ylearn, xtest, presel=50, mfinal=20) summarize(fit, ytest)