h2o.giniCoef(object, valid = FALSE, ...)
h2o.auc
for AUC, h2o.giniCoef
for the
GINI coefficient, and h2o.metric
for the various. See
h2o.performance
for creating H2OModelMetrics objects.
threshold metrics.library(h2o)
h2o.init()
prosPath <- system.file("extdata", "prostate.csv", package="h2o")
hex <- h2o.uploadFile(prosPath)
hex[,2] <- as.factor(hex[,2])
model <- h2o.gbm(x = 3:9, y = 2, training_frame = hex, distribution = "bernoulli")
perf <- h2o.performance(model, hex)
h2o.giniCoef(perf)
Run the code above in your browser using DataLab