H2O Grid Support

Source: R/grid.R

Provides a set of functions to launch a grid search and get its results.

h2o.grid(
  algorithm,
  grid_id,
  x,
  y,
  training_frame,
  ...,
  hyper_params = list(),
  is_supervised = NULL,
  do_hyper_params_check = FALSE,
  search_criteria = NULL,
  export_checkpoints_dir = NULL,
  recovery_dir = NULL,
  parallelism = 1
)

Arguments

algorithm

Name of algorithm to use in grid search (gbm, randomForest, kmeans, glm, deeplearning, naivebayes, pca).
grid_id

(Optional) ID for resulting grid search. If it is not specified then it is autogenerated.
x

(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.
y

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.
training_frame

Id of the training data frame.
...

arguments describing parameters to use with algorithm (i.e., x, y, training_frame). Look at the specific algorithm - h2o.gbm, h2o.glm, h2o.kmeans, h2o.deepLearning - for available parameters.
hyper_params

List of lists of hyper parameters (i.e., list(ntrees=c(1,2), max_depth=c(5,7))).
is_supervised

(Optional) If specified then override the default heuristic which decides if the given algorithm name and parameters specify a supervised or unsupervised algorithm.
do_hyper_params_check

Perform client check for specified hyper parameters. It can be time expensive for large hyper space.
search_criteria

(Optional) List of control parameters for smarter hyperparameter search. The list can include values for: strategy, max_models, max_runtime_secs, stopping_metric, stopping_tolerance, stopping_rounds and seed. The default strategy 'Cartesian' covers the entire space of hyperparameter combinations. If you want to use cartesian grid search, you can leave the search_criteria argument unspecified. Specify the "RandomDiscrete" strategy to get random search of all the combinations of your hyperparameters with three ways of specifying when to stop the search: max number of models, max time, and metric-based early stopping (e.g., stop if MSE has not improved by 0.0001 over the 5 best models). Examples below: list(strategy = "RandomDiscrete", max_runtime_secs = 600, max_models = 100, stopping_metric = "AUTO", stopping_tolerance = 0.00001, stopping_rounds = 5, seed = 123456) or list(strategy = "RandomDiscrete", max_models = 42, max_runtime_secs = 28800) or list(strategy = "RandomDiscrete", stopping_metric = "AUTO", stopping_tolerance = 0.001, stopping_rounds = 10) or list(strategy = "RandomDiscrete", stopping_metric = "misclassification", stopping_tolerance = 0.00001, stopping_rounds = 5).
export_checkpoints_dir

Directory to automatically export grid and its models to.
recovery_dir

When specified the grid and all necessary data (frames, models) will be saved to this directory (use HDFS or other distributed file-system). Should the cluster crash during training, the grid can be reloaded from this directory via h2o.loadGrid and training can be resumed
parallelism

Level of Parallelism during grid model building. 1 = sequential building (default). Use the value of 0 for adaptive parallelism - decided by H2O. Any number > 1 sets the exact number of models built in parallel.

Details

Launch grid search with given algorithm and parameters.

Examples

# NOT RUN {
library(h2o)
library(jsonlite)
h2o.init()
iris_hf <- as.h2o(iris)
grid <- h2o.grid("gbm", x = c(1:4), y = 5, training_frame = iris_hf,
                 hyper_params = list(ntrees = c(1, 2, 3)))
# Get grid summary
summary(grid)
# Fetch grid models
model_ids <- grid@model_ids
models <- lapply(model_ids, function(id) { h2o.getModel(id)})
# }