make.predictions {SIAMCAT} | R Documentation |
This function takes a siamcat-class-object containing a model trained by train.model and performs predictions on a given test-set.
make.predictions(siamcat, siamcat.holdout = NULL, normalize.holdout = TRUE, verbose = 1)
siamcat |
object of class siamcat-class |
siamcat.holdout |
optional, object of class siamcat-class on
which to make predictions, defaults to |
normalize.holdout |
boolean, should the holdout features be normalized
with a frozen normalization (see normalize.features) using the
normalization parameters in |
verbose |
control output: for only information about progress and success, |
This functions uses the model in the model_list
-slot of the
siamcat
object to make predictions on a given test set. The
test set can either consist of the test instances in the cross-
validation, saved in the data_split
-slot of the same
siamcat
object, or a completely external feature set, given in
the form of another siamcat
object (siamcat.holdout
).
object of class siamcat-class with the slot pred_matrix
filled or a matrix containing the predictions for the holdout set
data(siamcat_example) # Simple example siamcat.pred <- make.predictions(siamcat_example) # Predictions on a holdout-set ## Not run: pred.mat <- make.predictions(siamcat.trained, siamcat.holdout, normalize.holdout=TRUE) ## End(Not run)