kuenm_cal_swd() does produce values for pval_pROC, AICc, delta_AICc and W_AICc

[jmburgos]

Hi Marlon,

I am having trouble with a model that was previously working. This time, kuenm_cal_swd() does not produce values for pval_pROC, AICc, delta_AICc and W_AICc. After creating my datasets withprepare_swd() I calibrate my models like this:

kuenm_cal_swd(occ.joint = "Boars_SWD_joint.csv",
              occ.tra = "Boars_SWD_train.csv",
              occ.test = "Boars_SWD_test.csv",
              back.dir = "M_variables",
              batch = "Candidate_models",
              out.dir.models = "Candidate_models",
              reg.mult = c(0.1, 0.25, 0.5, 0.75, 1, 2.5, 5),
              f.clas = "basic",
              max.memory = 1000,
              maxent.path = ".",
              selection = "OR_AICc",
              threshold = 5,
              rand.percent = 50,
              out.dir.eval = "Candidate_models_eval",
              kept = TRUE)

After running the models, I get the following:

A total of 35 candidate models will be created

Starting evaluation process
Evaluation using partial ROC, omission rates, and AICc
  |======================================================================| 100%None of the significant candidate models met the omission rate criterion,
models with the lowest omission rate and lowest AICc will be presented

Writing calibration results
Error in plot.window(...) : need finite 'xlim' values
In addition: There were 43 warnings (use warnings() to see them)
> warnings()
Warning messages:
1: In aicc(oc, mod, par_num) :
  AICc not valid: too many parameters, or likelihood = Inf... returning NA.
2: `mutate_()` was deprecated in dplyr 0.7.0.
Please use `mutate()` instead.
See vignette('programming') for more help
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.
3: In aicc(oc, mod, par_num) :
  AICc not valid: too many parameters, or likelihood = Inf... returning NA.
4: In aicc(oc, mod, par_num) :
  AICc not valid: too many parameters, or likelihood = Inf... returning NA.
5: In aicc(oc, mod, par_num) :......

Do you have an idea of what could be the problem? I cannot figure it out.
Many thanks,

Julian

[dannyvelezv]

Hi Julian,

I'm having a similar issue, did you find a solution?

Thanks!

[lyyjat]

Igual con las nuevas SSP me esta ocurriendo el mismo error a que se debe?????

[lyyjat]

olvide comentar que solo me funciona utilizando PCA, si utilizo variables crudas, sale el error que menciona jmburgos???

[AllexanderN]

Hello, Julian. Have you solved your problem. I have exactly the same.

[lyyjat]

Creo que si logre solucionarlo, hay varias cosas que debes checar, el primero, checa si tienes correcto el orden de tus ocurrencias de tu archivo de excel, es decir primero es el nombre de la sp, luego longitude y luego latitude, si te funciona adelante y si no es que tus capas están mal, es decir, tienes que checar si todas las capas tienen el mismo extent, si difiere en un solo número tienes que poner el mismo extent a todas, también tienes que checar el NoData por lo general maxent reconoce el -9999, luego las capas traen por default caracteres distintos en el NoData entonces tienes que checar y corregir...espero te funcione y puedas solucionarlo...saludos cordiales. Hay otra cosa que mencionan en los comentarios que es cambiar desde maxent pero no lo he probado. Espero haber sido de ayuda AllexanderN...

…

________________________________ De: AllexanderN ***@***.***> Enviado: martes, 27 de septiembre de 2022 03:57 p. m. Para: marlonecobos/kuenm ***@***.***> CC: lyyjat ***@***.***>; Comment ***@***.***> Asunto: Re: [marlonecobos/kuenm] kuenm_cal_swd() does produce values for pval_pROC, AICc, delta_AICc and W_AICc (#29) Hello, Julian. Have you solved your problem. I have exactly the same. — Reply to this email directly, view it on GitHub<#29 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AZEUCPZ7TXTPS6B5BTDZW6TWAMKNPANCNFSM5BDIBFFA>. You are receiving this because you commented.Message ID: ***@***.***>