h2o.make_leaderboard function

Create a leaderboard from a list of models, grids and/or automls.

Create a leaderboard from a list of models, grids and/or automls.

h2o.make_leaderboard( object, leaderboard_frame, sort_metric = "AUTO", extra_columns = c(), scoring_data = c("AUTO", "train", "valid", "xval") )

Arguments

  • object: List of models, automls, or grids; or just single automl/grid object.
  • leaderboard_frame: Frame used for generating the metrics (optional).
  • sort_metric: Metric used for sorting the leaderboard.
  • extra_columns: What extra columns should be calculated (might require leaderboard_frame). Use "ALL" for all available or list of extra columns.
  • scoring_data: Metrics to be reported in the leaderboard ("xval", "train", or "valid"). Used if no leaderboard_frame is provided.

Returns

data.frame

Examples

## Not run: library(h2o) 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))) h2o.make_leaderboard(grid, iris_hf) ## End(Not run)
  • Maintainer: Tomas Fryda
  • License: Apache License (== 2.0)
  • Last published: 2024-01-11