Prediction on Test Data using Unsupervised VarPro

Obtain predicted values on test data for unsupervised forests.

predict.unsupv(object, newdata, ...)

Arguments

object

Unsupervised VarPro object from previous call to unsupv. Only applies if method="auto" was used.

newdata

Test data. If not provided the training data is used.

...

Additional options.

Details

Applies to unsupervised VarPro objects built using autoencoder (method="auto"). The unsupervised object contains a multivariate random forest which is used to predict on test data.

Returns a matrix containing predicted values where each column is predicted value for a feature (hot-encoding is applied) and with attributes:

1. mse: standardized mean-squared error averaged across feature.

2. mse.all: standardized mean-squared error for each feature.

Author

Min Lu and Hemant Ishwaran

See also

unsupv.varpro

Examples

# \donttest{
## ------------------------------------------------------------
##
## boston housing
## obtain predicted values for the training data
##
## ------------------------------------------------------------

## unsupervised varpro on boston housing
data(BostonHousing, package = "mlbench")
o <- unsupv(data=BostonHousing)

## predicted values for the training features
print(head(predict(o)))

## ------------------------------------------------------------
##
## mtcars
## obtain predicted values for test data
## also illustrates hot-encoding working on test data
##
## ------------------------------------------------------------

## mtcars with some factors
d <- data.frame(mpg=mtcars$mpg,lapply(mtcars[, c("cyl", "vs", "carb")], as.factor))

## training 
o <- unsupv(d[1:20,])

## predicted values on test data
print(predict(o, d[-(1:20),]))

## predicted values on bad test data with strange factor values 
dbad <- d[-(1:20),]
dbad$carb <- as.character(dbad$carb)
dbad$carb <-  sample(LETTERS, size = nrow(dbad))
print(predict(o, dbad))

# }