Information gain from a split, entropy criterion (Geron Ch 5, morie.fn hmigr)

Usage

morie_geron_information_gain_hmigr(y, split)

Arguments

y: Class labels.
split: Group assignment (same length as y).

Value

List with information_gain, parent_entropy, child_entropy, weighted_child_entropy, intrinsic_information, gain_ratio, estimate, n, method.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_geron_information_gain_hmigr(V, V)
#> $information_gain
#> [1] 3
#> 
#> $parent_entropy
#> [1] 3
#> 
#> $child_entropy
#> [1] 0 0 0 0 0 0 0 0
#> 
#> $weighted_child_entropy
#> [1] 0
#> 
#> $group_sizes
#> [1] 1 1 1 1 1 1 1 1
#> 
#> $n_groups
#> [1] 8
#> 
#> $intrinsic_information
#> [1] 3
#> 
#> $gain_ratio
#> [1] 1
#> 
#> $estimate
#> [1] 3
#> 
#> $n
#> [1] 8
#> 
#> $method
#> [1] "Information gain (entropy impurity decrease)"
#>