Plots training set (and validation set if available) scoring history for an H2O Model
# S3 method for H2OModel plot(x, timestep = "AUTO", metric = "AUTO", ...)
x | A fitted H2OModel object for which the scoring history plot is desired. |
---|---|
timestep | A unit of measurement for the x-axis. |
metric | A unit of measurement for the y-axis. |
... | additional arguments to pass on. |
Returns a scoring history plot.
This method dispatches on the type of H2O model to select the correct
scoring history. The timestep
and metric
arguments are restricted to what is
available in the scoring history for a particular type of model.
h2o.deeplearning
, h2o.gbm
,
h2o.glm
, h2o.randomForest
for model
generation in h2o.
# NOT RUN { if (requireNamespace("mlbench", quietly=TRUE)) { library(h2o) h2o.init() df <- as.h2o(mlbench::mlbench.friedman1(10000, 1)) rng <- h2o.runif(df, seed = 1234) train <- df[rng < 0.8,] valid <- df[rng >= 0.8,] gbm <- h2o.gbm(x = 1:10, y = "y", training_frame = train, validation_frame = valid, ntrees = 500, learn_rate = 0.01, score_each_iteration = TRUE) plot(gbm) plot(gbm, timestep = "duration", metric = "deviance") plot(gbm, timestep = "number_of_trees", metric = "deviance") plot(gbm, timestep = "number_of_trees", metric = "rmse") plot(gbm, timestep = "number_of_trees", metric = "mae") } # }