Error using h2o.randomForest

[tressoldi]

With this syntax:

data=h2o.uploadFile("RIC2Simone.csv", header = TRUE,sep=";",
destination_frame = "data")
data[,1] = as.factor(data[,1])

splits <- h2o.splitFrame(data = data,
ratios = c(0.50, 0.25), #partition data into 50%, 25%, 25% chunks
seed = 1) #setting a seed will guarantee reproducibility
train <- h2o.assign(splits[[1]], "train.hex")
valid <- h2o.assign(splits[[2]], "valid.hex")
test <- h2o.assign(splits[[3]],"test.hex")

response <- "Stimolo"

predictors<-setdiff(names(data),response)

m1 <- h2o.deeplearning(
model_id="dl_model_first",
training_frame=train,
validation_frame=valid,
x=predictors,
y=response,
hidden=c(32,32,32),
epochs=1000000,
score_validation_samples=10000,
stopping_rounds=2,
stopping_metric="misclassification",
stopping_tolerance=0.01,
nfolds=5,
fold_assignment="Stratified",
variable_importances=T
)

I got the following error message:

Illegal argument(s) for DRF model: DRF_model_R_1487947076967_1. Details: ERRR on field: _train: Training data must have at least 2 features (incl. response).

[ledell]

This is not the right place to file bug reports for H2O. This repository is for issues related to h2o-tutorials only. Please post to h2ostream or StackOverflow. That being said, it looks like H2O seems to think that you only have one column in your training data, so you should double check that your predictors and response variables are valid and that your data object was imported correctly.