bm_ModelingOptions: Configure the modeling options for each selected model
In biomod2: Ensemble Platform for Species Distribution Modeling
View source: R/bm_ModelingOptions.R
bm_ModelingOptions R Documentation
Configure the modeling options for each selected model
Description
Parameterize and/or tune biomod2's single models options.
Usage
bm_ModelingOptions(
data.type,
models = c("ANN", "CTA", "FDA", "GAM", "GBM", "GLM", "MARS", "MAXENT", "MAXNET", "RF",
"SRE", "XGBOOST"),
strategy,
user.val = NULL,
user.base = "bigboss",
bm.format = NULL,
calib.lines = NULL
)
Arguments
data.type
a character corresponding to the data type to be used, must be either
binary, binary.PA, abundance, compositional
models
a vector containing model names to be computed, must be among
ANN, CTA, FDA, GAM, GBM, GLM, MARS,
MAXENT, MAXNET, RF, SRE, XGBOOST
strategy
a character corresponding to the method to select models' parameters
values, must be either default, bigboss, user.defined, tuned
user.val
(optional, default NULL)
A list containing parameters values for some (all) models
user.base
(optional, default bigboss)
A character,
default or bigboss used when strategy = 'user.defined'.
It sets the bases of parameters to be modified by user defined values.
bm.format
(optional, default NULL)
A BIOMOD.formated.data or BIOMOD.formated.data.PA object returned
by the BIOMOD_FormatingData function
calib.lines
(optional, default NULL)
A data.frame object returned by get_calib_lines or
bm_CrossValidation functions
Details
This function creates a BIOMOD.models.options object containing parameter values
for each single model that can be run within biomod2 through
BIOMOD_Modeling function.
12 models are currently available, and are listed within the ModelsTable dataset.
Different strategies are available to set those parameters, through the strategy
argument :
- default
all parameters names and values are directly retrieve from functions to be
called through formalArgs and formals functions respectively
- bigboss
default parameter values are updated with values predefined by biomod2
team
- user.defined
default parameter values are updated with values provided by the user
- tuned
default parameter values are updated by calling bm_Tuning
function
Value
A BIOMOD.models.options of object that can be used to build species
distribution model(s) with the BIOMOD_Modeling function.
Note
MAXENT being the only external model (not called through a R package),
default parameters, and their values, are the following :
-
path_to_maxent.jar = getwd() : a character corresponding to path to
maxent.jar file
-
memory_allocated = 512 : an integer corresponding to the amount of
memory (in Mo) reserved for java to run MAXENT, must be either 64,
128, 256, 512, 1024... or NULL to use default java
memory limitation parameter
-
initial_heap_size = NULL : a character corresponding to initial heap
space (shared memory space) allocated to java (argument -Xms when calling
java), must be either 1024K, 4096M, 10G ... or NULL to
use default java parameter. Used in BIOMOD_Projection but not in
BIOMOD_Modeling.
-
max_heap_size = NULL : a character corresponding to maximum heap
space (shared memory space) allocated to java (argument -Xmx when calling
java), must be either 1024K, 4096M, 10G ... or NULL to
use default java parameter, and must be larger than initial_heap_size. Used
in BIOMOD_Projection but not in BIOMOD_Modeling.
-
background_data_dir = 'default' : a character corresponding to path
to folder where explanatory variables are stored as ASCII files (raster format).
If specified, MAXENT will generate its own background data from rasters of
explanatory variables ('default' value). Otherwise biomod2 pseudo-absences
will be used (see BIOMOD_FormatingData).
-
visible = FALSE : a logical value defining whether MAXENT
user interface is to be used or not
-
linear = TRUE : a logical value defining whether linear features are
to be used or not
-
quadratic = TRUE : a logical value defining whether quadratic features are
to be used or not
-
product = TRUE : a logical value defining whether product features are
to be used or not
-
threshold = TRUE : a logical value defining whether threshold features are
to be used or not
-
hinge = TRUE : a logical value defining whether hinge features are
to be used or not
-
l2lqthreshold = 10 : an integer corresponding to the number of
samples at which quadratic features start being used
-
lq2lqptthreshold = 80 : an integer corresponding to the number of
samples at which product and threshold features start being used
-
hingethreshold = 15 : an integer corresponding to the number of
samples at which hinge features start being used
-
beta_lqp = -1.0 : a numeric corresponding to the regularization
parameter to be applied to all linear, quadratic and product features (negative value
enables automatic setting)
-
beta_threshold = -1.0 : a numeric corresponding to the regularization
parameter to be applied to all threshold features (negative value enables automatic
setting)
-
beta_hinge = -1.0 : a numeric corresponding to the regularization
parameter to be applied to all hinge features (negative value enables automatic
setting)
-
beta_categorical = -1.0 : a numeric corresponding to the regularization
parameter to be applied to all categorical features (negative value enables automatic
setting)
-
betamultiplier = 1 : a numeric corresponding to the number by which
multiply all automatic regularization parameters (higher number gives a more
spread-out distribution)
-
defaultprevalence = 0.5 : a numeric corresponding to the default
prevalence of the modelled species (probability of presence at ordinary occurrence
points)
Author(s)
Damien Georges, Wilfried Thuiller, Maya Gueguen
See Also
ModelsTable, BIOMOD.models.options,
bm_Tuning, BIOMOD_Modeling
Other Secundary functions:
bm_BinaryTransformation(),
bm_CrossValidation(),
bm_FindOptimStat(),
bm_MakeFormula(),
bm_PlotEvalBoxplot(),
bm_PlotEvalMean(),
bm_PlotRangeSize(),
bm_PlotResponseCurves(),
bm_PlotVarImpBoxplot(),
bm_PseudoAbsences(),
bm_RunModelsLoop(),
bm_SRE(),
bm_SampleBinaryVector(),
bm_SampleFactorLevels(),
bm_Tuning(),
bm_VariablesImportance()
Examples
library(terra)
# Load species occurrences (6 species available)
data(DataSpecies)
head(DataSpecies)
# Select the name of the studied species
myRespName <- 'GuloGulo'
# Get corresponding presence/absence data
myResp <- as.numeric(DataSpecies[, myRespName])
# Get corresponding XY coordinates
myRespXY <- DataSpecies[, c('X_WGS84', 'Y_WGS84')]
# Load environmental variables extracted from BIOCLIM (bio_3, bio_4, bio_7, bio_11 & bio_12)
data(bioclim_current)
myExpl <- terra::rast(bioclim_current)
# ---------------------------------------------------------------#
# Format Data with true absences
myBiomodData <- BIOMOD_FormatingData(resp.var = myResp,
expl.var = myExpl,
resp.xy = myRespXY,
resp.name = myRespName)
# k-fold selection
cv.k <- bm_CrossValidation(bm.format = myBiomodData,
strategy = 'kfold',
nb.rep = 2,
k = 3)
# ---------------------------------------------------------------#
allModels <- c('ANN', 'CTA', 'FDA', 'GAM', 'GBM', 'GLM'
, 'MARS', 'MAXENT', 'MAXNET', 'RF', 'SRE', 'XGBOOST')
# default parameters
opt.d <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'default')
# providing formated data
opt.df <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'default',
bm.format = myBiomodData,
calib.lines = cv.k)
opt.d
opt.d@models
opt.d@options$ANN.binary.nnet.nnet
names(opt.d@options$ANN.binary.nnet.nnet@args.values)
opt.df@options$ANN.binary.nnet.nnet
names(opt.df@options$ANN.binary.nnet.nnet@args.values)
# ---------------------------------------------------------------#
# bigboss parameters
opt.b <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'bigboss')
# user defined parameters
user.SRE <- list('_allData_allRun' = list(quant = 0.01))
user.XGBOOST <- list('_allData_allRun' = list(nrounds = 10))
user.val <- list(SRE.binary.biomod2.bm_SRE = user.SRE
, XGBOOST.binary.xgboost.xgboost = user.XGBOOST)
opt.u <- bm_ModelingOptions(data.type = 'binary',
models = c('SRE', 'XGBOOST'),
strategy = 'user.defined',
user.val = user.val)
opt.b
opt.u
## Not run:
# tuned parameters with formated data
opt.t <- bm_ModelingOptions(data.type = 'binary',
models = c('SRE', 'XGBOOST'),
strategy = 'tuned',
bm.format = myBiomodData)
opt.t
## End(Not run)
biomod2 documentation built on June 22, 2024, 10:56 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
View source: R/bm_ModelingOptions.R
| bm_ModelingOptions | R Documentation |
Configure the modeling options for each selected model
Description
Parameterize and/or tune biomod2's single models options.
Usage
bm_ModelingOptions(
data.type,
models = c("ANN", "CTA", "FDA", "GAM", "GBM", "GLM", "MARS", "MAXENT", "MAXNET", "RF",
"SRE", "XGBOOST"),
strategy,
user.val = NULL,
user.base = "bigboss",
bm.format = NULL,
calib.lines = NULL
)
Arguments
data.type |
a |
models |
a |
strategy |
a |
user.val |
(optional, default |
user.base |
(optional, default |
bm.format |
(optional, default |
calib.lines |
(optional, default |
Details
This function creates a BIOMOD.models.options object containing parameter values
for each single model that can be run within biomod2 through
BIOMOD_Modeling function.
12 models are currently available, and are listed within the ModelsTable dataset.
Different strategies are available to set those parameters, through the strategy
argument :
- default
all parameters names and values are directly retrieve from functions to be called through
formalArgsandformalsfunctions respectively- bigboss
default parameter values are updated with values predefined by biomod2 team
- user.defined
default parameter values are updated with values provided by the user
- tuned
default parameter values are updated by calling
bm_Tuningfunction
Value
A BIOMOD.models.options of object that can be used to build species
distribution model(s) with the BIOMOD_Modeling function.
Note
MAXENT being the only external model (not called through a R package),
default parameters, and their values, are the following :
-
path_to_maxent.jar = getwd(): acharactercorresponding to path tomaxent.jarfile -
memory_allocated = 512: anintegercorresponding to the amount of memory (in Mo) reserved forjavato runMAXENT, must be either64,128,256,512,1024... orNULLto use defaultjavamemory limitation parameter -
initial_heap_size = NULL: acharactercorresponding to initial heap space (shared memory space) allocated tojava(argument-Xmswhen callingjava), must be either1024K,4096M,10G... orNULLto use defaultjavaparameter. Used inBIOMOD_Projectionbut not inBIOMOD_Modeling. -
max_heap_size = NULL: acharactercorresponding to maximum heap space (shared memory space) allocated tojava(argument-Xmxwhen callingjava), must be either1024K,4096M,10G... orNULLto use defaultjavaparameter, and must be larger thaninitial_heap_size. Used inBIOMOD_Projectionbut not inBIOMOD_Modeling. -
background_data_dir = 'default': acharactercorresponding to path to folder where explanatory variables are stored asASCIIfiles (raster format). If specified,MAXENTwill generate its own background data from rasters of explanatory variables ('default'value). Otherwise biomod2 pseudo-absences will be used (seeBIOMOD_FormatingData). -
visible = FALSE: alogicalvalue defining whetherMAXENTuser interface is to be used or not -
linear = TRUE: alogicalvalue defining whether linear features are to be used or not -
quadratic = TRUE: alogicalvalue defining whether quadratic features are to be used or not -
product = TRUE: alogicalvalue defining whether product features are to be used or not -
threshold = TRUE: alogicalvalue defining whether threshold features are to be used or not -
hinge = TRUE: alogicalvalue defining whether hinge features are to be used or not -
l2lqthreshold = 10: anintegercorresponding to the number of samples at which quadratic features start being used -
lq2lqptthreshold = 80: anintegercorresponding to the number of samples at which product and threshold features start being used -
hingethreshold = 15: anintegercorresponding to the number of samples at which hinge features start being used -
beta_lqp = -1.0: anumericcorresponding to the regularization parameter to be applied to all linear, quadratic and product features (negative value enables automatic setting) -
beta_threshold = -1.0: anumericcorresponding to the regularization parameter to be applied to all threshold features (negative value enables automatic setting) -
beta_hinge = -1.0: anumericcorresponding to the regularization parameter to be applied to all hinge features (negative value enables automatic setting) -
beta_categorical = -1.0: anumericcorresponding to the regularization parameter to be applied to all categorical features (negative value enables automatic setting) -
betamultiplier = 1: anumericcorresponding to the number by which multiply all automatic regularization parameters (higher number gives a more spread-out distribution) -
defaultprevalence = 0.5: anumericcorresponding to the default prevalence of the modelled species (probability of presence at ordinary occurrence points)
Author(s)
Damien Georges, Wilfried Thuiller, Maya Gueguen
See Also
ModelsTable, BIOMOD.models.options,
bm_Tuning, BIOMOD_Modeling
Other Secundary functions:
bm_BinaryTransformation(),
bm_CrossValidation(),
bm_FindOptimStat(),
bm_MakeFormula(),
bm_PlotEvalBoxplot(),
bm_PlotEvalMean(),
bm_PlotRangeSize(),
bm_PlotResponseCurves(),
bm_PlotVarImpBoxplot(),
bm_PseudoAbsences(),
bm_RunModelsLoop(),
bm_SRE(),
bm_SampleBinaryVector(),
bm_SampleFactorLevels(),
bm_Tuning(),
bm_VariablesImportance()
Examples
library(terra)
# Load species occurrences (6 species available)
data(DataSpecies)
head(DataSpecies)
# Select the name of the studied species
myRespName <- 'GuloGulo'
# Get corresponding presence/absence data
myResp <- as.numeric(DataSpecies[, myRespName])
# Get corresponding XY coordinates
myRespXY <- DataSpecies[, c('X_WGS84', 'Y_WGS84')]
# Load environmental variables extracted from BIOCLIM (bio_3, bio_4, bio_7, bio_11 & bio_12)
data(bioclim_current)
myExpl <- terra::rast(bioclim_current)
# ---------------------------------------------------------------#
# Format Data with true absences
myBiomodData <- BIOMOD_FormatingData(resp.var = myResp,
expl.var = myExpl,
resp.xy = myRespXY,
resp.name = myRespName)
# k-fold selection
cv.k <- bm_CrossValidation(bm.format = myBiomodData,
strategy = 'kfold',
nb.rep = 2,
k = 3)
# ---------------------------------------------------------------#
allModels <- c('ANN', 'CTA', 'FDA', 'GAM', 'GBM', 'GLM'
, 'MARS', 'MAXENT', 'MAXNET', 'RF', 'SRE', 'XGBOOST')
# default parameters
opt.d <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'default')
# providing formated data
opt.df <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'default',
bm.format = myBiomodData,
calib.lines = cv.k)
opt.d
opt.d@models
opt.d@options$ANN.binary.nnet.nnet
names(opt.d@options$ANN.binary.nnet.nnet@args.values)
opt.df@options$ANN.binary.nnet.nnet
names(opt.df@options$ANN.binary.nnet.nnet@args.values)
# ---------------------------------------------------------------#
# bigboss parameters
opt.b <- bm_ModelingOptions(data.type = 'binary',
models = allModels,
strategy = 'bigboss')
# user defined parameters
user.SRE <- list('_allData_allRun' = list(quant = 0.01))
user.XGBOOST <- list('_allData_allRun' = list(nrounds = 10))
user.val <- list(SRE.binary.biomod2.bm_SRE = user.SRE
, XGBOOST.binary.xgboost.xgboost = user.XGBOOST)
opt.u <- bm_ModelingOptions(data.type = 'binary',
models = c('SRE', 'XGBOOST'),
strategy = 'user.defined',
user.val = user.val)
opt.b
opt.u
## Not run:
# tuned parameters with formated data
opt.t <- bm_ModelingOptions(data.type = 'binary',
models = c('SRE', 'XGBOOST'),
strategy = 'tuned',
bm.format = myBiomodData)
opt.t
## End(Not run)
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.