Settings of the out-of-bag tuning

What rpf(tune = ) searches. The search is coordinate-wise, so that it needs few forests (9 to 11 with the defaults):

1. the points search of ladder at the first min_leaf_rows;

2. every min_leaf_rows at the point chosen in step 1 (skipped if only one is given);

3. the two ladder neighbours of that point at the min_leaf_rows chosen in step 2 (if neighbours).

Usage

tune_control(
  ladder = greediness_ladder(),
  search = 3:8,
  min_leaf_rows = c(1, 5, 20, 100),
  neighbours = TRUE
)

Arguments

ladder

[data.frame: greediness_ladder()]: The points of greediness, greediest first: columns n_try_split_points (whole numbers, at least 1) and share_candidates (in (0, 1]). The column names of 0.5.0, split_try and t_try, still work, with a deprecation warning.

search

[integer: 3:8]: The rows of ladder searched in step 1 (on the default ladder from 10 / 0.4 to 1 / 0.0125).

min_leaf_rows

[integer: c(1, 5, 20, 100)]: The values of rpf()'s min_leaf_rows searched in step 2; the first one is that of step 1.

neighbours

[logical(1): TRUE]: Whether to run step 3.

Value

An object of class rpf_tune_control, a list with the four settings, for rpf(tune = ).

Details

Every forest has its number of splits chosen out of bag while it grows (as rpf(n_splits = NULL)) and is pruned by prune_components() with its defaults, without the display. A step chooses, among all forests grown at the coordinate it varies, the one whose pruned model has the lowest corrected out-of-bag RMSE (ties: the greedier point, the larger min_leaf_rows). Step 3 chooses among every forest grown at the chosen min_leaf_rows, so with min_leaf_rows 1 it also compares step 1's.

rpf(tune = TRUE) is tune_control(), and rpf(tune = "quick") is tune_control(search = c(5, 7), min_leaf_rows = 1, neighbours = FALSE): two forests, 3 / 0.1 and 1 / 0.025.

See also

greediness_ladder(), rpf()

Examples

# The full search and the quick preset
tune_control()
#> $ladder
#>    n_try_split_points share_candidates
#> 1                  40         1.000000
#> 2                  20         0.800000
#> 3                  10         0.400000
#> 4                   5         0.200000
#> 5                   3         0.100000
#> 6                   2         0.050000
#> 7                   1         0.025000
#> 8                   1         0.012500
#> 9                   1         0.006250
#> 10                  1         0.003125
#> 
#> $search
#> [1] 3 4 5 6 7 8
#> 
#> $min_leaf_rows
#> [1]   1   5  20 100
#> 
#> $neighbours
#> [1] TRUE
#> 
#> attr(,"class")
#> [1] "rpf_tune_control"
tune_control(search = c(5, 7), min_leaf_rows = 1, neighbours = FALSE)
#> $ladder
#>    n_try_split_points share_candidates
#> 1                  40         1.000000
#> 2                  20         0.800000
#> 3                  10         0.400000
#> 4                   5         0.200000
#> 5                   3         0.100000
#> 6                   2         0.050000
#> 7                   1         0.025000
#> 8                   1         0.012500
#> 9                   1         0.006250
#> 10                  1         0.003125
#> 
#> $search
#> [1] 5 7
#> 
#> $min_leaf_rows
#> [1] 1
#> 
#> $neighbours
#> [1] FALSE
#> 
#> attr(,"class")
#> [1] "rpf_tune_control"

# \donttest{
# A small search: two points of greediness, then two leaf sizes
set.seed(1)
x <- matrix(runif(400 * 4, -1, 1), ncol = 4, dimnames = list(NULL, paste0("x", 1:4)))
y <- x[, 1] + 2 * x[, 2] * x[, 3] + rnorm(400, sd = 0.3)
tuned <- rpf(
  x,
  y,
  max_interaction = 2,
  n_families = 10,
  tune = tune_control(search = c(3, 5), min_leaf_rows = c(1, 20), neighbours = FALSE)
)
tuned$tune$search
#>   step n_try_split_points share_candidates min_leaf_rows n_splits stopped_at
#> 1    1                 10              0.4             1       84        100
#> 2    1                  3              0.1             1       59         71
#> 3    2                 10              0.4            20      168        200
#>   capped oob_rmse_forest rule tau n_kept  oob_rmse seconds chosen_step1
#> 1  FALSE       0.4844060    R 0.1      2 0.3666121   0.076         TRUE
#> 2  FALSE       0.4459042    R 0.1      2 0.3752002   0.043        FALSE
#> 3  FALSE       0.3832057    R 0.1      2 0.3539268   0.167           NA
#>   chosen_step2 chosen_step3 final
#> 1        FALSE           NA FALSE
#> 2           NA           NA FALSE
#> 3         TRUE           NA  TRUE
# }