Retrieve the Log Loss Value

Retrieves the log loss output for a H2OBinomialMetrics or H2OMultinomialMetrics object If "train", "valid", and "xval" parameters are FALSE (default), then the training Log Loss value is returned. If more than one parameter is set to TRUE, then a named vector of Log Losses are returned, where the names are "train", "valid" or "xval".

h2o.logloss(object, train = FALSE, valid = FALSE, xval = FALSE)

Arguments

object	a H2OModelMetrics object of the correct type.
train	Retrieve the training Log Loss
valid	Retrieve the validation Log Loss
xval	Retrieve the cross-validation Log Loss

Examples

# NOT RUN {
library(h2o)
h2o.init()

f <- "https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv"
cars <- h2o.importFile(f)
cars["economy_20mpg"] <- as.factor(cars["economy_20mpg"])
predictors <- c("displacement", "power", "weight", "acceleration", "year")
response <- "economy_20mpg"
cars_splits <- h2o.splitFrame(data =  cars, ratios = .8, seed = 1234)
train <- cars_splits[[1]]
valid <- cars_splits[[2]]
car_drf <- h2o.randomForest(x = predictors,
                            y = response,
                            training_frame = train,
                            validation_frame = valid)
h2o.logloss(car_drf, train = TRUE, valid = TRUE)
# }