Skip to contents

Evaluate an SDM

Source: R/evaluate_sdm.R
evaluate_sdm.Rd

Returns various evaluation metrics from predicts::pa_evaluate() and flexsdm::sdm_eval().

Usage

evaluate_sdm(m, p_test, b_test, do_gc = FALSE, ...)

Arguments

m

SDM result within tune_sdm()

p_test

Presence test data generated within tune_sdm()

b_test

Background test data generated within tune_sdm()

do_gc

Logical. Run base::rm(list = ls) and base::gc() at end of function? Useful when running SDMs for many, many taxa, especially if done in parallel. Note, actually usees rm(list = ls(pattern = "^[^e$]")).

...

Passed to both terra::predict() and predicts::pa_evaluate()

Value

paModelEvaluation (see predicts::pa_evaluate()) with extra metrics from flexsdm::sdm_eval(): AUC as auc_po_flexsdm; BOYCE as CBI; CBI_rescale (CBI is -1 to 1, CBI_rescale is 0 to 1); and IMAE.

Examples


  out_dir <- file.path(system.file(package = "envSDM"), "examples")

  source(fs::path(out_dir, "tune_sdm_ex.R")) # make sure following prep file exists

  prep <- rio::import(fs::path(out_dir, "acaule", "prep.rds")
                      , trust = TRUE
                      )

  model <- tune_sdm(prep = prep
                    , out_dir = FALSE
                    , return_val = "object"
                    , algo = "rf"
                    , trees = 500
                    , mtry = 2
                    , nodesize = 1
                    , keep_model = TRUE
                    )
#> tuning acaule with algorithms: rf
#> out_dir is C:/temp/nige\Rtmpmcu61r\file66b8b79fd4
#> rf tune

  presences <- prep$testing[prep$testing$pa == 1, ]
  background <- prep$testing[prep$testing$pa == 0, ]

  evaluate_sdm(model$tune_rf$m[[1]]
               , p_test = presences
               , b_test = background
               )
#> @stats
#>    np   na prevalence   auc   cor pcor  ODP auc_po auc_po_flexsdm   CBI
#> 1 319 1675       0.16 0.995 0.938    0 0.84  0.995          0.995 0.899
#>   CBI_rescale  IMAE
#> 1       0.949 0.963
#> 
#> @thresholds
#>   max_kappa max_spec_sens no_omission equal_prevalence equal_sens_spec  or10
#> 1      0.58         0.242           0            0.159           0.347 0.744
#> 
#> @tr_stats
#>     treshold kappa  CCR  TPR  TNR  FPR  FNR  PPP  NPP  MCR     OR
#> 1          0     0 0.16    1    0    1    0 0.16  NaN 0.84    NaN
#> 2          0  0.34 0.68    1 0.62 0.38    0 0.33    1 0.32 520.82
#> 3          0  0.34 0.68    1 0.62 0.38    0 0.33    1 0.32 520.82
#> 4        ...   ...  ...  ...  ...  ...  ...  ...  ...  ...    ...
#> 175        1  0.77 0.95 0.67    1    0 0.33    1 0.94 0.05    Inf
#> 176        1  0.77 0.95 0.67    1    0 0.33    1 0.94 0.05    Inf
#> 177        1     0 0.84    0    1    0    1  NaN 0.84 0.16    NaN