gbsm.res: Results on generalised B-spline modelling (presented in Lagat...

In vitaliskim/msco: Multi-Species Co-Occurrence Analyses

Results on generalised B-spline modelling (presented in Lagat et al., 2021b)

Description

This function allows the replication of the results on generalised B-spline modelling, presented in Lagat et al. (2021b). Executing gbsm.res() therefore gives these outputs that are saved as .RDS files in msco. If the codes that produced these (saved) outcomes are desired, the codes below are made available.

Usage

gbsm.res()

Value

Returns all the results presented in Lagat et al. (2021b). To replicate

• Figs. 1, 3, 4, 5, and Tables 1 and S1, execute the following code:

   my.path <- system.file("extdata/gsmdat", package = "msco")
   setwd(my.path)
   s.data <- get(load("s.data.csv")) ##Species-by-site matrix
   t.data <- get(load("t.data.csv")) ##Species-by-trait matrix
   p.d.mat <- get(load("p.d.mat.csv")) ##Species-by-species phylogenetic distance matrix
   RNGkind(sample.kind = "Rejection")
   set.seed(1)
   gb.res <- msco::gbsm_m.orders(s.data,
               t.data,
               p.d.mat,
               metric = "Simpson_eqn",
               gbsm.model,
               orders = c(2:5, 8, 10, 15),
               d.f = 4,
               degree = 3,
               n = 1000,
               k = 5,
               p = 0.8,
               type = "k-fold",
               scat.plots = TRUE,
               response.curves = TRUE,
               j.occs.distrbn = TRUE,
               mp.plots = TRUE,
               max.vif = 10,
               max.vif2 = 3,
               start.range=c(-0.1,0)
             )
  
   gb.res$contbn_table$`order 3`  ## Table 1
   gb.res$model.validation.table  ## Table S1
   gb.res$Original.VIFs$`order 3`
   gb.res$Intermediate.VIFs$`order 3` ## Resulting covariate VIFs after removing
                                         ## covariates with VIF > max.vif
   gb.res$Final.VIFs$`order 3` ## Resulting covariate VIFs after removing
                                          ## covariates with VIF > max.vif2
  
  
  

• Figs. S1, 2, and S2, execute the following codes:

  • Fig. S1:

    remotes::install_github("jinyizju/V.PhyloMaker", force = TRUE)
    library(V.PhyloMaker)
    my.path <- system.file("extdata/gsmdat", package = "msco")
    setwd(my.path)
    s.data <- get(load("s.data.csv")) ##Species-by-site matrix
    taxa <- get(load("taxa.levels.csv")) ##Species taxa
    my.phylo.plot <- msco::s.phylo(s.data,
                              p.d.mat = NULL,
                              database = "ncbi",
                              obs.taxa = FALSE,
                              taxa.levels = taxa,
                              Obs.data = FALSE,
                              phy.d.mat = FALSE,
                              phylo.plot = TRUE)
  
  

  • Fig. 2:

    my.path <- system.file("extdata/gsmdat", package = "msco")
    setwd(my.path)
    s.data <- get(load("s.data.csv")) ##Species-by-site matrix
    t.data <- get(load("t.data.csv")) ##Species-by-trait matrix
    p.d.mat <- get(load("p.d.mat.csv")) ##Species-by-species phylogenetic distance matrix
    RNGkind(sample.kind = "Rejection")
    set.seed(1)
    my.gbsm <- msco::gbsm(s.data,
                      t.data,
                      p.d.mat,
                      metric = "Simpson_eqn",
                      gbsm.model,
                      d.f = 4,
                      order.jo = 3,
                      degree = 3,
                      n = 1000,
                      b.plots = TRUE,
                      scat.plot = FALSE,
                      response.curves = FALSE,
                      leg = 1,
                      max.vif = 10,
                      max.vif2 = 3,
                      start.range=c(-0.1,0)
                    )
  
  

  • Fig. 6:

    my.path <- system.file("extdata/gsmdat", package = "msco")
    setwd(my.path)
    s.data <- get(load("s.data.csv")) ##Species-by-site matrix
    t.data <- get(load("t.data.csv")) ##Species-by-trait matrix
    p.d.mat <- get(load("p.d.mat.csv")) ##Species-by-species phylogenetic distance matrix
    RNGkind(sample.kind = "Rejection")
    set.seed(1)
    pe <- msco::pred.error.bands(s.data,
                        t.data,
                        p.d.mat,
                        metric = "Simpson_eqn",
                        gbsm.model,
                        d.f = 4,
                        simm = 10,
                        orders = c(2:5, 8, 10, 15),
                        degree = 3,
                        n = 1000,
                        start.range = c(-0.2, 0)
                      )
  

Caveat: The above codes can collectively take approximately 7 minutes to execute (with prediction uncertainty plot taking 6 minutes alone). It took 7.3895 minutes to run (and output results) on a 64 bit system with 8 GB RAM and 3.60 GHz CPU.

Note

The function gbsm.res is not for general use. We included it in this package to help the readers of Lagat et al. (2021b) paper, who may want to get a deeper understanding of how the results presented in this paper were arrived at. It also allows deeper scrutiny of Lagat et al. (2021b)'s findings.

References

Lagat, V. K., Latombe, G. and Hui, C. (2021b). Dissecting the effects of random encounter versus functional trait mismatching on multi-species co-occurrence and interference with generalised B-spline modelling. DOI: ⁠<To be added>⁠.

Examples

## Not run: 

gbs.res <- msco::gbsm.res()
gbs.res$contbn_table$`order 3`
gbs.res$model.validation.table
gbs.res$Original.VIFs$`order 3`
gbs.res$Intermediate.VIFs$`order 3`
gbs.res$Final.VIFs$`order 3`


## End(Not run)

vitaliskim/msco documentation built on Sept. 29, 2023, 9:22 p.m.