predictResponseFromWeightedAverage: Predict a numeric response using (un)weighted averaging.

In boostr: A modular framework to bag or boost any estimation procedure.

Description

Process a matrix of predicted responses and form a column-wise estimate based on (un)weighted averaging.

Usage

predictResponseFromWeightedAverage(preds, weights, .parallel, ...)

Arguments

preds	is matrix of predicted classes
weights	is a vector of length equal to nrow(preds)
.parallel	is a boolean flag determining whether to work across columns of preds in parallel – need to register a parallel backend (e.g. doParallel, doRedis) for this to actually work.
...	additional arguments to pass to weighted.mean.

Details

Gives the prediction from row(i) in preds weight equal to weights[i]. Note that NA's are not removed. To have weighted.mean remove the NA's pass na.rm=TRUE to the function call.

Value

a vector of length equal to ncol(preds) containing the estimated response for each column of preds.

boostr documentation built on May 2, 2019, 1:42 p.m.