The output structure is analogous to the output of h2o.predict_leaf_node_assignment. For each tree t and class c there will be a column Tt.Cc (eg. T3.C1 for tree 3 and class 1). The value will be the corresponding predicted probability of this class by combining the raw contributions of trees T1.Cc,..,TtCc. Binomial models build the trees just for the first class and values in columns Tx.C1 thus correspond to the the probability p0.
staged_predict_proba.H2OModel(object, newdata, ...)h2o.staged_predict_proba(object, newdata, ...)
Returns an H2OFrame object with predicted probability for each tree in the model.
a fitted H2OModel object for which prediction is desired
An H2OFrame object in which to look for variables with which to predict.
additional arguments to pass on.
h2o.gbm
and h2o.randomForest
for model
generation in h2o.
if (FALSE) {
library(h2o)
h2o.init()
prostate_path <- system.file("extdata", "prostate.csv", package = "h2o")
prostate <- h2o.uploadFile(path = prostate_path)
prostate$CAPSULE <- as.factor(prostate$CAPSULE)
prostate_gbm <- h2o.gbm(3:9, "CAPSULE", prostate)
h2o.predict(prostate_gbm, prostate)
h2o.staged_predict_proba(prostate_gbm, prostate)
}
Run the code above in your browser using DataLab