dataOrganize: R6 class to assist in reformatting the data to be used in dataSDM.

Description

Internal functions used to temporarily store data and other information before adding to dataSDM.

Arguments

Methods

Public methods

`dataOrganize$makeData()`

Function to form the data into sf objects, as well as extract other information about the model required.

Usage

dataOrganize$makeData(
  datapoints,
  datanames,
  coords,
  proj,
  marktrialname,
  paresp,
  countsresp,
  trialname,
  speciesname,
  marks,
  pointcovnames,
  markfamily,
  temporalvar,
  offsetname
)

Arguments

datapoints: A list of datasets as either sf, data.frame or SpatialPoints objects.
datanames: A vector of the names of the datasets.
coords: Names of the coordinates used in the model.
proj: The projection reference system used in the model.
marktrialname: Name of the trial variable used by the binomial marks.
paresp: Name of the response variable used by the presence absence datasets.
countsresp: Name of the response variable used by the counts data.
trialname: Name of the trial variable used by the presence absence datasets.
speciesname: Name of the species name variable.
marks: Name of the marks considered in the model.
pointcovnames: Name of the point covariates used in the model.
markfamily: A vector describing the distribution of the marks.
temporalvar: The name of the temporal variable.
offsetname: The name of the offset

`dataOrganize$makeSpecies()`

Function used to separate the datasets by species.

Usage

dataOrganize$makeSpecies(speciesname, repl = FALSE)

Arguments

speciesname: The name of the species variable.
repl: Are species effects replicate. Defaults to FALSE.

`dataOrganize$makeMultinom()`

Function to make multinomial marks, if any are included in the model.

Usage

dataOrganize$makeMultinom(multinomVars, return, oldVars, repl = FALSE)

Arguments

multinomVars: Name of the multinomial marks.
return: What to return: species or marks.
oldVars: If any multinomial marks were included in a previous iteration, what where their names.
repl: Species replicate model included. Defaults to FALSE.

`dataOrganize$makeFormulas()`

Function used to create formulas for the processes.

Usage

dataOrganize$makeFormulas(
  spatcovs,
  spatcovclass,
  speciesname,
  paresp,
  countresp,
  marks,
  marksspatial,
  speciesintercept,
  speciesenvironment,
  spatial,
  intercept,
  temporalname,
  speciesindependent,
  markintercept,
  pointcovs,
  speciesspatial,
  biasformula,
  covariateformula
)

Arguments

spatcovs: Names of the spatial covariates used in the model.
spatcovclass: Class of the spatial covariates.
speciesname: Name of the species variable.
paresp: Name of the presence absence response variable.
countresp: Name of the count data response variable.
marks: Name of the marks used in the model.
marksspatial: Logical: should spatial fields be included for the marks.
speciesintercept: Logical: should specific species intercept terms be created for the species.
speciesenvironment: Logical: should species specific environmental terms be created.
spatial: Logical: are spatial effects run in the model.
intercept: Logical: are intercepts run in the model.
temporalname: Name of the temporal variable used in the model.
speciesindependent: Logical: make independent species effects.
markintercept: Logical: are intercepts run for the marks in the model.
pointcovs: Name of the point covariates.
speciesspatial: Logical: should the species have spatial fields.
biasformula: Terms to include for PO data.
covariateformula: Terms to include for the covariate formula.

`dataOrganize$makeComponents()`

Function used to make components for the model.

Usage

dataOrganize$makeComponents(
  spatial,
  intercepts,
  datanames,
  marks,
  speciesname,
  multinomnames,
  pointcovariates,
  covariatenames,
  covariateclass,
  marksspatial,
  marksintercept,
  temporalname,
  speciesspatial,
  speciesenvironment,
  speciesintercept,
  numtime,
  temporalmodel,
  offsetname,
  copymodel,
  speciesindependent,
  biasformula,
  covariateformula,
  marksCopy
)

Arguments

spatial: Logical: are spatial effects run in the model.
intercepts: Logical: are intercepts run in the model.
datanames: Names of the datasets used in the model.
marks: Names of the marks used in the model.
speciesname: Name of the species variable.
multinomnames: Names of the multinomial marks.
pointcovariates: Names of the point covariates.
covariatenames: Names of the spatially varying covariates.
covariateclass: The classes of the spatially varying covariates.
marksspatial: Logical: should spatial fields be included for the marks.
marksintercept: Logical: should intercepts be included for the marks.
temporalname: Name of the temporal variable used in the model.
speciesspatial: Logical: Should the species be run with spatial fields.
speciesenvironment: Logical: Should the species have their own environmental effects.
numtime: Number of time increments included in the model.
offsetname: Name of the offset column in the datasets.
copymodel: List of the hyper parameters for the copy model.
speciesindependent: Logical: should species effects be made independent.
biasformula: Terms to include for PO data.
covariateformula: Terms to include for the covariate formula.
marksCopy: Names of where each mark occurs in the dataset.
speciesintercept:: Logical: should intercept terms be created for each species.

`dataOrganize$makeLhoods()`

Function to make the datasets into likelihoods.

Usage

dataOrganize$makeLhoods(
  mesh,
  ips,
  paresp,
  ntrialsvar,
  markstrialsvar,
  speciesname
)

Arguments

mesh: An fm_mesh_2d object.
ips: Integration points used.
paresp: The response variable name for the presence absence datasets.
ntrialsvar: The trials variable name for the presence absence datasets.
markstrialsvar: The trial variable name for the binomial marks.
speciesname: The name of the species variable used.

`dataOrganize$clone()`

The objects of this class are cloneable with this method.

Usage

dataOrganize$clone(deep = FALSE)

Arguments

deep: Whether to make a deep clone.