Reorders levels of factor columns by the frequencies for the individual levels.

The levels of a factor are reordered so that the most frequency level is at level 0, remaining levels are ordered from the second most frequent to the least frequent.

h2o.relevel_by_frequency(x, weights_column = NULL, top_n = -1)

Arguments

x

H2O frame with some factor columns

weights_column

optional name of weights column

top_n

optional number of most frequent levels to move to the top (eg.: for top_n=1 move only the most frequent level)

Value

new reordered frame

Examples

if (FALSE) { # \dontrun{
library(h2o)
h2o.init()

# Convert iris dataset to an H2OFrame
iris_hf <- as.h2o(iris)
# Look at current ordering of the Species column levels
h2o.levels(iris_hf["Species"])
# "setosa"     "versicolor" "virginica" 
# Change the reference level to "virginica"
iris_hf["Species"] <- h2o.relevel_by_frequency(x = iris_hf["Species"])
# Observe new ordering
h2o.levels(iris_hf["Species"])
# "virginica"  "versicolor" "setosa"
} # }