Xgboost h2o error on WIndows OS?

Question

I tried to run xgboost on my local machine with Windows OS. But the following error :

Error in .h2o.doSafeREST(h2oRestApiVersion = h2oRestApiVersion, urlSuffix = page,  : 


ERROR MESSAGE:

java.lang.AssertionError: Unregistered algorithm xgboost

here is my code sample :

library(h2o)
h2o.init(enable_assertions = TRUE)
localH2O=h2o.init(nthreads = 8)

train.h2o <- h2o.importFile("train.csv")
test.h2o <- h2o.importFile("test.csv")

# Number of CV folds (to generate level-one data for stacking)
nfolds <- 5

y <- get_index(train.h2o,"loss")
x <- setdiff(1:length(train.h2o), y)
x=h2o.colnames(train.h2o[,x])
y=h2o.colnames(train.h2o[,y])


my_xgb1 <- h2o.xgboost(x = x,
                       y = y,
                       training_frame = train.h2o,
                       ntrees = 50,
                       max_depth = 3,
                       min_rows = 2,
                       learn_rate = 0.2,
                       nfolds = nfolds,
                       fold_assignment = "Modulo",
                       keep_cross_validation_predictions = TRUE,
                       seed = 1)

when I run it, I get the following error :

ERROR: Unexpected HTTP Status code: 500 Server Error (url = http://localhost:54321/3/ModelBuilders/xgboost)

java.lang.AssertionError [1] "java.lang.AssertionError: Unregistered algorithm xgboost"
[2] " hex.ModelBuilder.make(ModelBuilder.java:149)"
[3] "
water.api.ModelBuildersHandler.fetch(ModelBuildersHandler.java:35)"
[4] " sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)"

....

I found here that xgboost for h2o work on some specific dev environments.

MY QUESTION is: how can I make it work on Windows OS ?

Thank you.

George George · Accepted Answer · 2018-04-10T12:32:43

H2o xgboost is not currently supported in Windows.

Please see the attached screenshot from the latest docs page for h2o xgboost.

Xgboost h2o error on WIndows OS?

3 Answers