Fits the best model (output of selectBestModel()).
fitBestModel(final_mod, train_data)Best model workflow (output of selectBestModel())
The part of the pangenome data designated for ML model
training. This can be the output of
rsample::training(splitMLInputTibble(ml_input_tibble)).
Best model fit
data(demo_ml_tibble)
data_split <- splitMLInputTibble(demo_ml_tibble, split = c(1, 0), seed = 1)
train <- rsample::training(data_split)
wflow <- buildWflow(buildLRModel(), buildRecipe(train))
set.seed(1)
tune_res <- tuneGrid(wflow, data_split,
buildTuningGrid("LR", 10^c(-3, -1), c(0, 0.5, 1)),
n_fold = 2
)
best_wflow <- selectBestModel(tune_res, wflow, "mcc")
fitBestModel(best_wflow, train)
#> ══ Workflow [trained] ══════════════════════════════════════════════════════════
#> Preprocessor: Recipe
#> Model: logistic_reg()
#>
#> ── Preprocessor ────────────────────────────────────────────────────────────────
#> 2 Recipe Steps
#>
#> • step_zv()
#> • step_normalize()
#>
#> ── Model ───────────────────────────────────────────────────────────────────────
#>
#> Call: glmnet::glmnet(x = maybe_matrix(x), y = y, family = "binomial", alpha = ~0)
#>
#> Df %Dev Lambda
#> 1 41 0.00 206.600
#> 2 41 0.25 188.200
#> 3 41 0.27 171.500
#> 4 41 0.30 156.300
#> 5 41 0.33 142.400
#> 6 41 0.36 129.700
#> 7 41 0.39 118.200
#> 8 41 0.43 107.700
#> 9 41 0.47 98.150
#> 10 41 0.51 89.430
#> 11 41 0.56 81.490
#> 12 41 0.62 74.250
#> 13 41 0.67 67.650
#> 14 41 0.74 61.640
#> 15 41 0.81 56.170
#> 16 41 0.88 51.180
#> 17 41 0.97 46.630
#> 18 41 1.06 42.490
#> 19 41 1.15 38.710
#> 20 41 1.26 35.270
#> 21 41 1.37 32.140
#> 22 41 1.50 29.280
#> 23 41 1.64 26.680
#> 24 41 1.78 24.310
#> 25 41 1.94 22.150
#> 26 41 2.12 20.180
#> 27 41 2.30 18.390
#> 28 41 2.50 16.760
#> 29 41 2.72 15.270
#> 30 41 2.96 13.910
#> 31 41 3.21 12.680
#> 32 41 3.48 11.550
#> 33 41 3.77 10.520
#> 34 41 4.08 9.589
#> 35 41 4.41 8.738
#> 36 41 4.77 7.961
#> 37 41 5.14 7.254
#> 38 41 5.55 6.610
#> 39 41 5.97 6.022
#> 40 41 6.43 5.487
#> 41 41 6.91 5.000
#> 42 41 7.42 4.556
#> 43 41 7.96 4.151
#> 44 41 8.53 3.782
#> 45 41 9.13 3.446
#> 46 41 9.77 3.140
#>
#> ...
#> and 54 more lines.