Build a stacked ensemble (aka. Super Learner) using the H2O base learning algorithms specified by the user.

  model_id = NULL,
  validation_frame = NULL,
  blending_frame = NULL,
  base_models = list(),
  metalearner_algorithm = c("AUTO", "deeplearning", "drf", "gbm", "glm", "naivebayes",
  metalearner_nfolds = 0,
  metalearner_fold_assignment = c("AUTO", "Random", "Modulo", "Stratified"),
  metalearner_fold_column = NULL,
  metalearner_params = NULL,
  metalearner_transform = c("NONE", "Logit"),
  max_runtime_secs = 0,
  weights_column = NULL,
  offset_column = NULL,
  custom_metric_func = NULL,
  seed = -1,
  score_training_samples = 10000,
  keep_levelone_frame = FALSE,
  export_checkpoints_dir = NULL,
  gainslift_bins = -1



(Optional). A vector containing the names or indices of the predictor variables to use in building the model. If x is missing, then all columns except y are used. Training frame is used only to compute ensemble training metrics.


The name or column index of the response variable in the data. The response must be either a numeric or a categorical/factor variable. If the response is numeric, then a regression model will be trained, otherwise it will train a classification model.


Id of the training data frame.


Destination id for this model; auto-generated if not specified.


Id of the validation data frame.


Frame used to compute the predictions that serve as the training frame for the metalearner (triggers blending mode if provided)


List of models or grids (or their ids) to ensemble/stack together. Grids are expanded to individual models. If not using blending frame, then models must have been cross-validated using nfolds > 1, and folds must be identical across models.


Type of algorithm to use as the metalearner. Options include 'AUTO' (GLM with non negative weights; if validation_frame is present, a lambda search is performed), 'deeplearning' (Deep Learning with default parameters), 'drf' (Random Forest with default parameters), 'gbm' (GBM with default parameters), 'glm' (GLM with default parameters), 'naivebayes' (NaiveBayes with default parameters), or 'xgboost' (if available, XGBoost with default parameters). Must be one of: "AUTO", "deeplearning", "drf", "gbm", "glm", "naivebayes", "xgboost". Defaults to AUTO.


Number of folds for K-fold cross-validation of the metalearner algorithm (0 to disable or >= 2). Defaults to 0.


Cross-validation fold assignment scheme for metalearner cross-validation. Defaults to AUTO (which is currently set to Random). The 'Stratified' option will stratify the folds based on the response variable, for classification problems. Must be one of: "AUTO", "Random", "Modulo", "Stratified".


Column with cross-validation fold index assignment per observation for cross-validation of the metalearner.


Parameters for metalearner algorithm


Transformation used for the level one frame. Must be one of: "NONE", "Logit". Defaults to NONE.


Maximum allowed runtime in seconds for model training. Use 0 to disable. Defaults to 0.


Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from the dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the data frame. This is typically the number of times a row is repeated, but non-integer values are supported as well. During training, rows with higher weights matter more, due to the larger loss function pre-factor. If you set weight = 0 for a row, the returned prediction frame at that row is zero and this is incorrect. To get an accurate prediction, remove all rows with weight == 0.


Offset column. This will be added to the combination of columns before applying the link function.


Reference to custom evaluation function, format: `language:keyName=funcName`


Seed for random numbers; passed through to the metalearner algorithm. Defaults to -1 (time-based random number).


Specify the number of training set samples for scoring. The value must be >= 0. To use all training samples, enter 0. Defaults to 10000.


Logical. Keep level one frame used for metalearner training. Defaults to FALSE.


Automatically export generated models to this directory.


Set default multinomial AUC type. Must be one of: "AUTO", "NONE", "MACRO_OVR", "WEIGHTED_OVR", "MACRO_OVO", "WEIGHTED_OVO". Defaults to AUTO.


Gains/Lift table number of bins. 0 means disabled.. Default value -1 means automatic binning. Defaults to -1.


if (FALSE) {

# Import a sample binary outcome train/test set
train <- h2o.importFile("")
test <- h2o.importFile("")

# Identify predictors and response
y <- "response"
x <- setdiff(names(train), y)

# For binary classification, response should be a factor
train[, y] <- as.factor(train[, y])
test[, y] <- as.factor(test[, y])

# Number of CV folds
nfolds <- 5

# Train & Cross-validate a GBM
my_gbm <- h2o.gbm(x = x,
                  y = y,
                  training_frame = train,
                  distribution = "bernoulli",
                  ntrees = 10,
                  max_depth = 3,
                  min_rows = 2,
                  learn_rate = 0.2,
                  nfolds = nfolds,
                  fold_assignment = "Modulo",
                  keep_cross_validation_predictions = TRUE,
                  seed = 1)

# Train & Cross-validate a RF
my_rf <- h2o.randomForest(x = x,
                          y = y,
                          training_frame = train,
                          ntrees = 50,
                          nfolds = nfolds,
                          fold_assignment = "Modulo",
                          keep_cross_validation_predictions = TRUE,
                          seed = 1)

# Train a stacked ensemble using the GBM and RF above
ensemble <- h2o.stackedEnsemble(x = x,
                                y = y,
                                training_frame = train,
                                model_id = "my_ensemble_binomial",
                                base_models = list(my_gbm, my_rf))