h2o.automl: Automatic Machine Learning

the models that were trained in the process, ranked by a default model performance metric.
Usage
h2o.automl(

h2o.pareto_front: Plot Pareto front

<- splits[[2]]
# Build and train the model:
aml <- h2o.automl(y = response,

h2o.get_automl: Get an R object that is a subclass of H2OAutoML

<- h2o.automl(y = y, training_frame = prostate,
max_runtime_secs = 30, project_name = "prostate")
aml2 <- h2o.get_automl("prostate")

h2o.varimp: Retrieve the variable importance

"
predictors <- c("ID", "AGE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS")
aml <- h2o.automl(x = predictors, y = response

h2o.varimp-H2OAutoML-method: Retrieve the variable importance

<- c("ID", "AGE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS")
aml <- h2o.automl(x = predictors, y = response

h2o.varimp-H2OFrame-method: Retrieve the variable importance

", "VOL", "DPROS")
aml <- h2o.automl(x = predictors, y = response, training_frame = pros, max_runtime_secs = 60)
h2o.varimp(aml@leaderboard[1:5,])

h2o.get_leaderboard: Retrieve the leaderboard from the AutoML instance

<- h2o.automl(y = y, training_frame = prostate, max_runtime_secs = 30)
lb <- h2o.get_leaderboard(aml)
head(lb)

h2o.varimp_heatmap: Variable Importance Heatmap across multiple models

aml <- h2o.automl(y = response,
training_frame = train,
max_models = 10

h2o.get_best_model: Get best model of a given family/algorithm for a given

aml <- h2o.automl(y = y, training_frame = prostate, max_runtime_secs = 30)
gbm <- h2o.get_best_model(aml, "gbm")
## End(Not run)

h2o.model_correlation: Model Prediction Correlation

<- h2o.automl(y = response,
training_frame = train,
max_models = 10

h2o.disparate_analysis: Create a frame containing aggregations of intersectional

", EDUCATION = "2") # university educated man
favorable_class <- "0" # no default next month
aml <- h2o.automl(x, y

h2o.pd_multi_plot: Plot partial dependencies for a variable across multiple

the model:
aml <- h2o.automl(y = response,
training_frame = train,

h2o.model_correlation_heatmap: Model Prediction Correlation Heatmap

(df, ratios = 0.8, seed = 1)
train <- splits[[1]]
test <- splits[[2]]

h2o.infogram_train_subset_models: Train models over subsets selected using infogram

that creates models. This can be something like h2o.automl, h2o.gbm, etc.
training_frame
Training frame

h2o.explain: Generate Model Explanations

<- h2o.automl(y = response,
training_frame = train,
max_models = 10

h2o.explain_row: Generate Model Explanations for a single row

the model:
aml <- h2o.automl(y = response,
training_frame = train,

R/admissibleml.R:

#'
#' aml <- h2o.automl(x, y, training_frame = train, max_models = 3)
#'

R/automl.R:

to factor for classification
#' aml <- h2o.automl(y = y, training_frame = prostate, max_runtime_secs = 30)
#' lb

R/classes.R:

", "VOL", "DPROS")
#' aml <- h2o.automl(x = predictors, y = response, training_frame = pros, max_runtime_secs = 60

R/explain.R:

#' train <- splits[[1]]
#' test <- splits[[2]]
#'