mlr (version 1.1-18)

predict.WrappedModel: Predict new data.

Description

Predict the target variable of new data using a fitted model. What is stored exactly in the [Prediction] object depends on the predict.type setting of the Learner.

Usage

## S3 method for class 'WrappedModel':
predict(object, task, newdata,
    subset, ...)

Value

[Prediction].

Examples

## split iris data in training and test set
n <- nrow(iris)
mixed.set <- sample(1:n)
training.set <- mixed.set[1:(n/2)]
test.set <- mixed.set[(n/2 + 1):n]

## use linear discriminant analysis as learner for classification task
task <- makeClassifTask(data = iris, target = "Species")
learner <- makeLearner("classif.lda", method = "mle")
mod <- train(learner, task, subset = training.set)

## predict class labels for test data
pred <- predict(mod, newdata = iris[test.set,])
head(pred$data)

## predict now probabiliies instead of class labels
learner <- makeLearner("classif.lda", method = "mle", predict.type = "prob")
mod <- train(learner, task, subset = training.set)
pred <- predict(mod, newdata = iris[test.set, ])
head(pred$data)