Different results in csv outputs after running kuenm_ceval

[joaolemoslima]

I ran the kuenm_ceval function on my data, it ran smoothly (except for the mutate_ function error in dplyr, but from what I saw here that should not be a problem).

So, I ran the function and got the results. I explored them a bit and noticed that the model presented in the "best_candidate_models_OR_AICc.csv" is not coincident with the data for that model from the "calibration_results.csv" file.

The "best candidate model" has a deltaAICc value of 0, but on the "calibration_results.csv" file that same model has a deltaAICc value different from 0.

Which file should I trust?

The code that I used:

occ_joint <- "prover_joint.csv"
occ_tra <- "prover_train.csv"
M_var_dir <- "M_variables"
batch_cal <- "Candidate_models"
out_dir <- "Candidate_Models"
reg_mult <- c(0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4)
f_clas <- "basic"
args <- NULL
maxent_path <- "C:/Users/biodeserts/Documents/joaolima/kuenm/prover"
wait <- FALSE
run <- TRUE

kuenm_cal(occ.joint = occ_joint, occ.tra = occ_tra, M.var.dir = M_var_dir, batch = batch_cal,
out.dir = out_dir, reg.mult = reg_mult, f.clas = f_clas, args = args, maxent.path = maxent_path,
wait = wait, run = run)

occ_test <- "prover_test.csv"
out_eval <- "Calibration_results"
threshold <- 10
rand_percent <- 50
iterations <- 100
kept <- TRUE
selection <- "OR_AICc"
paral_proc <- FALSE

cal_eval <- kuenm_ceval(path = out_dir, occ.joint = occ_joint, occ.tra = occ_tra, occ.test = occ_test, batch = batch_cal,
out.eval = out_eval, threshold = threshold, rand.percent = rand_percent, iterations = iterations,
kept = kept, selection = selection, parallel.proc = paral_proc)