#To spatially rarefaction of data distance and splitting data into training and testing#
#Additional information and a step by step guide for installing and loading packages, and using that function of this package can be found in its GitHub repository (https://github.com/marlonecobos/ellipsenm)#

library(ellipsenm)

# Thinning (spatially rarefaction of data distance = 5 km)

ppoints<-"stephadiscus_todos.csv"
occ_t <- thin_data(ppoints, longitude = "longitude", latitude = "latitude", 
                   thin_distance = 5)


# Splitting data into training and testing
## a list with all, train, and test records will be returned
occ_calibration <- ellipsenm::split_data(occ_t, method = "random", 
                                         longitude = "longitude", latitude = "latitude", 
                                         train_proportion = 0.70)


#To obtaina ENMs models#
#Cobos ME, Peterson AT, Barve N, Osorio-Olvera L. 2019. kuenm: an R package for detailed development of ecological niche models using Maxent.PeerJ 7:e6281 https://doi.org/10.7717/peerj.6281#
#Additional information and a step by step guide for installing and loading packages, and using the main functions of this package can be found in its GitHub repository (https://github.com/marlonecobos/kuenm)#


library(kuenm)
# Variables with information to be used as arguments. Change "YOUR/DIRECTORY" by your actual directory.

#Calibration of models#
occ_joint <- "stephadiscus_joint.csv"
occ_tra <- "stephadiscus_train.csv"
M_var_dir <- "M_variables"
batch_cal <- "Candidate_models"
out_dir <- "Candidate_Models"
reg_mult <- c(0.1,0.5,1,2)
f_clas <- c("all") # alternativamente "all"
args <- NULL # e.g., "maximumbackground=20000" for increasing the number of pixels in the bacground or
             # note that some arguments are fixed in the function and should not be changed
maxent_path <- "YOUR/DIRECTORY/" # path de maxent
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)


#Evaluation and selection of best models#
occ_test <- "stephadiscus_test.csv"
out_eval <- "Calibration_results"
threshold <- 5
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)

#Final model creation#
batch_fin <- "Final_models"
mod_dir <- "Final_Models"
rep_n <- 5
rep_type <- "Bootstrap"
jackknife <- FALSE
out_format <- "logistic"
project <- TRUE
G_var_dir <- "G_variables"
ext_type <- "no_ext" # para extrapolacion "all"
write_mess <- FALSE
write_clamp <- FALSE
wait1 <- FALSE
run1 <- TRUE
args <- NULL 

kuenm_mod(occ.joint = occ_joint, M.var.dir = M_var_dir, out.eval = out_eval, batch = batch_fin, rep.n = rep_n,
          rep.type = rep_type, jackknife = jackknife, out.dir = mod_dir, out.format = out_format, project = project,
          G.var.dir =G_var_dir, ext.type = ext_type, write.mess = write_mess, write.clamp = write_clamp, 
          maxent.path = maxent_path, args = args, wait = wait1, run = run1)

#Extrapolation risk analysis#

sets_var <- "set_01" # a vector of various sets can be used
out_mop <- "MOP_results"
percent <- 10
paral <- FALSE # make this true to perform MOP calculations in parallel, recommended
               # only if a powerfull computer is used (see function's help)
# Two of the variables used here as arguments were already created for previous functions


#To identify extrapolation risk areas#
kuenm_mmop(G.var.dir = G_var_dir, M.var.dir = M_var_dir, sets.var = sets_var, out.mop = out_mop,
           percent = percent, parallel = paral)


#To obtain binary presence-absence maps# 
#Additional information and a step by step guide for installing and loading packages, and using that function of this package can be found in its GitHub repository (https://github.com/narayanibarve/ENMGadgets)#

library (ENMGadgets)

ModelThreshold(InSuitFile="Stephadiscus_avg.asc", OccurrenceFile="stephadiscus_train.csv", PercentThreshold=0.01, OutSuitFile="stephadiscus_bin_001.asc")