Feature/issue 102 allow specify nt features and nt distances with partial name rather than a vector

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: bmm
 Title: Easy and Accesible Bayesian Measurement Models using 'brms'
-Version: 0.3.4.9000
+Version: 0.3.5.9000
 Authors@R: c(
     person("Vencislav", "Popov", , "[email protected]", role = c("aut", "cre", "cph")),
     person("Gidon", "Frischkorn", , "[email protected]", role = c("aut", "cph")))

NAMESPACE

@@ -12,6 +12,8 @@ S3method(check_data,vwm)
 S3method(check_formula,bmmmodel)
 S3method(check_formula,default)
 S3method(check_formula,nontargets)
+S3method(check_model,bmmmodel)
+S3method(check_model,default)
 S3method(configure_model,IMMabc)
 S3method(configure_model,IMMbsc)
 S3method(configure_model,IMMfull)
@@ -25,6 +27,7 @@ S3method(postprocess_brm,bmmmodel)
 S3method(postprocess_brm,default)
 S3method(postprocess_brm,sdmSimple)
 S3method(postprocess_brm,vwm)
+S3method(print,message)
 S3method(rhs_vars,bmmformula)
 S3method(rhs_vars,formula)
 S3method(update,bmmfit)

NEWS.md

@@ -7,6 +7,7 @@
 * add postprocessing methods for sdmSimple to allow for pp_check(), conditional_effects and bridgesampling usage with the model (#30)
 * add informed default priors for all models. You can always use the `get_model_prior()` function to see the default priors for a model
 * add a new function `set_default_prior` for developers, which allows them to more easily set default priors on new models regardless of the user-specified formula
+* you can now specify variables for models via regular expressions rather than character vectors [#102]
 
 ### Bug fixes
 * fix a bug in the mixture3p and IMM models which caused an error when intercept was not supressed and set size was used as predictor

R/bmm_model_IMM.R

@@ -2,7 +2,7 @@
 # MODELS                                                                 ####
 #############################################################################!
 
-.model_IMMabc <- function(resp_err, nt_features, setsize, ...) {
+.model_IMMabc <- function(resp_err, nt_features, setsize, regex = FALSE, ...) {
   out <- list(
     resp_vars = nlist(resp_err),
     other_vars = nlist(nt_features, setsize),
@@ -29,11 +29,13 @@
       )),
     void_mu = FALSE
   )
+  attr(out, "regex") <- regex
+  attr(out, "regex_vars") <- c('nt_features') # variables that can be specified via regular expression
   class(out) <- c("bmmmodel", "vwm","nontargets","IMMabc")
   out
 }
 
-.model_IMMbsc <- function(resp_err, nt_features, nt_distances, setsize, ...) {
+.model_IMMbsc <- function(resp_err, nt_features, nt_distances, setsize, regex = FALSE, ...) {
   out <- list(
     resp_vars = nlist(resp_err),
     other_vars = nlist(nt_features, nt_distances, setsize),
@@ -60,11 +62,14 @@
       )),
     void_mu = FALSE
   )
+  attr(out, "regex") <- regex
+  # variables that can be specified via regular expression
+  attr(out, "regex_vars") <- c('nt_features', 'nt_distances')
   class(out) <- c("bmmmodel","vwm","nontargets","IMMspatial","IMMbsc")
   out
 }
 
-.model_IMMfull <- function(resp_err,  nt_features, nt_distances, setsize, ...) {
+.model_IMMfull <- function(resp_err,  nt_features, nt_distances, setsize, regex = FALSE, ...) {
   out <- list(
     resp_vars = nlist(resp_err),
     other_vars = nlist(nt_features, nt_distances, setsize),
@@ -92,6 +97,9 @@
       )),
     void_mu = FALSE
   )
+  attr(out, "regex") <- regex
+  # variables that can be specified via regular expression
+  attr(out, "regex_vars") <- c('nt_features', 'nt_distances')
   class(out) <- c("bmmmodel","vwm","nontargets","IMMspatial","IMMfull")
   out
 }
@@ -114,20 +122,71 @@
 #'
 #'   - b = "Background activation (internally fixed to 0)"
 #'
-#' @param resp_err The name of the variable in the provided dataset containing the
-#'   response error. The response Error should code the response relative to the to-be-recalled
-#'   target in radians. You can transform the response error in degrees to radian using the `deg2rad` function.
-#' @param nt_features A character vector with the names of the non-target variables.
-#'   The non_target variables should be in radians and be centered relative to the
-#'   target.
-#' @param nt_distances A vector of names of the columns containing the distances of
-#'   non-target items to the target item. Only necessary for the `IMMbsc` and `IMMfull` models
+#' @param resp_err The name of the variable in the provided dataset containing
+#'   the response error. The response Error should code the response relative to
+#'   the to-be-recalled target in radians. You can transform the response error
+#'   in degrees to radian using the `deg2rad` function.
+#' @param nt_features A character vector with the names of the non-target
+#'   variables. The non_target variables should be in radians and be centered
+#'   relative to the target. Alternatively, if regex=TRUE, a regular
+#'   expression can be used to match the non-target feature columns in the
+#'   dataset.
+#' @param nt_distances A vector of names of the columns containing the distances
+#'   of non-target items to the target item. Alternatively, if regex=TRUE, a regular
+#'   expression can be used to match the non-target distances columns in the
+#'   dataset. Only necessary for the `IMMbsc` and `IMMfull` models.
 #' @param setsize Name of the column containing the set size variable (if
 #'   setsize varies) or a numeric value for the setsize, if the setsize is
 #'   fixed.
+#' @param regex Logical. If TRUE, the `nt_features` and `nt_distances` arguments
+#'   are interpreted as a regular expression to match the non-target feature
+#'   columns in the dataset.
 #' @param ... used internally for testing, ignore it
 #' @return An object of class `bmmmodel`
 #' @keywords bmmmodel
+#' @examples
+#' \dontrun{
+#' # load data
+#' data <- OberauerLin_2017
+#'
+#' # define formula
+#' ff <- bmmformula(
+#'   kappa ~ 0 + set_size,
+#'   c ~ 0 + set_size,
+#'   a ~ 0 + set_size,
+#'   s ~ 0 + set_size
+#' )
+#'
+#' # specify the full IMM model with explicit column names for non-target features and distances
+#' model1 <- IMMfull(resp_err = "dev_rad",
+#'                   nt_features = paste0('col_nt',1:7),
+#'                   nt_distances = paste0('dist_nt',1:7),
+#'                   setsize = 'set_size')
+#'
+#' # fit the model
+#' fit <- fit_model(formula = ff,
+#'                  data = data,
+#'                  model = model1,
+#'                  parallel = T,
+#'                  iter = 500,
+#'                  backend = 'cmdstanr')
+#'
+#' # alternatively specify the IMM model with a regular expression to match non-target features
+#' # this is equivalent to the previous call, but more concise
+#' model2 <- IMMfull(resp_err = "dev_rad",
+#'                   nt_features = 'col_nt',
+#'                   nt_distances = 'dist_nt',
+#'                   setsize = 'set_size',
+#'                   regex = TRUE)
+#'
+#' # fit the model
+#' fit <- fit_model(formula = ff,
+#'                  data = data,
+#'                  model = model2,
+#'                  parallel=T,
+#'                  iter = 500,
+#'                  backend='cmdstanr')
+#'}
 #' @export
 IMMfull <- .model_IMMfull
 

R/bmm_model_mixture3p.R

@@ -2,7 +2,7 @@
 # MODELS                                                                 ####
 #############################################################################!
 
-.model_mixture3p <- function(resp_err, nt_features, setsize, ...) {
+.model_mixture3p <- function(resp_err, nt_features, setsize, regex = FALSE, ...) {
   out <- list(
     resp_vars = nlist(resp_err),
     other_vars = nlist(nt_features, setsize),
@@ -30,6 +30,8 @@
       )),
     void_mu = FALSE
   )
+  attr(out, "regex") <- regex
+  attr(out, "regex_vars") <- c('nt_features') # variables that can be specified via regular expression
   class(out) = c("bmmmodel", "vwm", "nontargets", "mixture3p")
   out
 }
@@ -43,11 +45,15 @@
 #'   the to-be-recalled target in radians. You can transform the response error
 #'   in degrees to radians using the `deg2rad` function.
 #' @param nt_features A character vector with the names of the non-target
-#'   feature values. The non_target feature values should be in radians and centered
-#'   relative to the target.
+#'   feature values. The non_target feature values should be in radians and
+#'   centered relative to the target. Alternatively, if regex=TRUE, a regular
+#'   expression can be used to match the non-target feature columns in the
+#'   dataset.
 #' @param setsize Name of the column containing the set size variable (if
 #'   setsize varies) or a numeric value for the setsize, if the setsize is
 #'   fixed.
+#' @param regex Logical. If TRUE, the `nt_features` argument is interpreted as
+#'  a regular expression to match the non-target feature columns in the dataset.
 #' @param ... used internally for testing, ignore it
 #' @return An object of class `bmmmodel`
 #' @keywords bmmmodel
@@ -69,13 +75,25 @@
 #'   thetant ~ 1
 #' )
 #'
-#' # specify the 3-parameter model
-#' model <- mixture3p(resp_err = "y", nt_features = paste0('nt',1:3,'_loc'), setsize = 4)
+#' # specify the 3-parameter model with explicit column names for non-target features
+#' model1 <- mixture3p(resp_err = "y", nt_features = paste0('nt',1:3,'_loc'), setsize = 4)
 #'
 #' # fit the model
 #' fit <- fit_model(formula = ff,
 #'                  data = dat,
-#'                  model = model,
+#'                  model = model1,
+#'                  parallel=T,
+#'                  iter = 500,
+#'                  backend='cmdstanr')
+#'
+#' # alternatively specify the 3-parameter model with a regular expression to match non-target features
+#' # this is equivalent to the previous call, but more concise
+#' model2 <- mixture3p(resp_err = "y", nt_features = "nt.*_loc", setsize = 4, regex = TRUE)
+#'
+#' # fit the model
+#' fit <- fit_model(formula = ff,
+#'                  data = dat,
+#'                  model = model2,
 #'                  parallel=T,
 #'                  iter = 500,
 #'                  backend='cmdstanr')

R/fit_model.R

@@ -89,7 +89,7 @@ fit_model <- function(formula, data, model, parallel = FALSE, chains = 4,
   opts <- configure_options(nlist(parallel, chains, sort_data, silent))
 
   # check model, formula and data, and transform data if necessary
-  model <- check_model(model)
+  model <- check_model(model, data)
   data <- check_data(model, data, formula)
   formula <- check_formula(model, data, formula)
 

R/helpers-data.R

@@ -276,7 +276,7 @@ rad2deg <- function(rad){
 get_standata <- function(formula, data, model, prior=NULL, ...) {
 
   # check model, formula and data, and transform data if necessary
-  model <- check_model(model)
+  model <- check_model(model, data)
   data <- check_data(model, data, formula)
   formula <- check_formula(model, data, formula)