sjevelazco/flexsdm

Error in data_ens[[2]] : subscript out of bounds

dannyvelezv opened this issue · 9 comments

dannyvelezv commented

HI,

Any ideas why I am getting this error when trying to apply esm_max()? How can I solve it?

Code:
esm_max_t1 <- esm_max(
data = ex_spxy2,
response = "pr_ab",
predictors= c("PC1", "PC2"),
partition = ".part",
thr = NULL,
background = ex_bg2,
clamp = TRUE,
classes = "lq",
pred_type = "cloglog",
regmult = 2.5
)

Presences, background points and predictors attached,

Thanks
background.txt
Presencias.txt
somevar.zip

KonstiDE commented

How did you solve it? I have the same error, #338

karolceron commented

Did you solve it? Same error here, only for esm_max

sjevelazco commented

Hi all
Sorry, I forgot to work on this bug. I will work on this and let you know when it is fixed. Thanks

sjevelazco commented

Please,
Can one of you send a dataset to help me reproduce this error? A txt with presences (or presences/absences), .partition, and environmental data, and another .txt with background points with same columns. I can´t reproduce the error with the dataset provided by @dannyvelezv . Thanks

KonstiDE commented

Solved in #338, did this not work here? It was just an indexing problem that you could solve through just using more predictors

sjevelazco commented
sjevelazco commented

The problem is you are using the esm_ family function with two predictors. It makes no sense because it is the same as constructing a single model with fit_ or tune_ family function. I added an error message to all esm_ functions. So, use tune or fit functions. Thank yo so much for reporting this error.
Best

KonstiDE commented

@sjevelazco, just have a look into this small project: https://github.com/KonstiDE/FlexSDM
Whilst running, just remove two of the predictor variables you dont like in the esm function family in flexsdm.R, Line 172 and following

sjevelazco commented