Implements a greedy strategy to add one rule at a time which maximizes/minimizes a metric.
# S3 method for rulelist
reorder(x, metric = "cumulative_coverage", minimize = FALSE, init = NULL, ...)A rulelist
(character vector or named list) Name of metrics or a custom function(s). See calculate. The 'n+1'th metric is used when there is a match at 'nth' level, similar to base::order. If there is a match at final level, row order of the rulelist comes into play.
(logical vector) Whether to minimize. Either TRUE/FALSE or a logical vector of same length as metric
(positive integer) Initial number of rows after which reordering should begin
passed to calculate
library("magrittr")
att = modeldata::attrition
tidy_c5 =
C50::C5.0(Attrition ~., data = att, rules = TRUE) %>%
tidy() %>%
set_validation_data(att, "Attrition") %>%
set_keys(NULL) %>%
head(5)
# with defaults
reorder(tidy_c5)
#> ---- Rulelist --------------------------------
#> ▶ Keys: NULL
#> ▶ Number of rules: 5
#> ▶ Model type: C5
#> ▶ Estimation type: classification
#> ▶ Is validation data set: TRUE
#>
#>
#> rule_nbr trial_nbr LHS RHS support confidence lift cumulative_coverage
#> <int> <int> <chr> <fct> <int> <dbl> <dbl> <dbl>
#> 1 3 1 ( Daily… Yes 13 0.933 5.8 13
#> 2 4 1 ( JobRo… No 195 0.924 1.1 208
#> 3 2 1 ( Envir… No 521 0.941 1.1 645
#> 4 1 1 ( JobLe… Yes 16 0.944 5.9 656
#> 5 5 1 ( Envir… Yes 9 0.909 5.6 664
#> ----------------------------------------------
# use 'cumulative_overlap' to break ties (if any)
reorder(tidy_c5, metric = c("cumulative_coverage", "cumulative_overlap"))
#> ---- Rulelist --------------------------------
#> ▶ Keys: NULL
#> ▶ Number of rules: 5
#> ▶ Model type: C5
#> ▶ Estimation type: classification
#> ▶ Is validation data set: TRUE
#>
#>
#> rule_nbr trial_nbr LHS RHS support confidence lift cumulative_coverage
#> <int> <int> <chr> <fct> <int> <dbl> <dbl> <dbl>
#> 1 3 1 ( Daily… Yes 13 0.933 5.8 13
#> 2 4 1 ( JobRo… No 195 0.924 1.1 208
#> 3 2 1 ( Envir… No 521 0.941 1.1 645
#> 4 1 1 ( JobLe… Yes 16 0.944 5.9 656
#> 5 5 1 ( Envir… Yes 9 0.909 5.6 664
#> # ℹ 1 more variable: cumulative_overlap <dbl>
#> ----------------------------------------------
# reorder after 2 rules
reorder(tidy_c5, init = 2)
#> ---- Rulelist --------------------------------
#> ▶ Keys: NULL
#> ▶ Number of rules: 5
#> ▶ Model type: C5
#> ▶ Estimation type: classification
#> ▶ Is validation data set: TRUE
#>
#>
#> rule_nbr trial_nbr LHS RHS support confidence lift cumulative_coverage
#> <int> <int> <chr> <fct> <int> <dbl> <dbl> <dbl>
#> 1 1 1 ( JobLe… Yes 16 0.944 5.9 16
#> 2 2 1 ( Envir… No 521 0.941 1.1 537
#> 3 4 1 ( JobRo… No 195 0.924 1.1 648
#> 4 3 1 ( Daily… Yes 13 0.933 5.8 656
#> 5 5 1 ( Envir… Yes 9 0.909 5.6 664
#> ----------------------------------------------