R/filtering_out.R

Defines functions filtering_out_data

Documented in filtering_out_data

#' @title Filtering out
#'
#' @description Filertting out based on numner of nunique occurences
#'
#' @param data A `data.frame` or similar.
#' @param threshold an integer
#'
#' @return
#'   * `data_filtered` `data.frame` same as data filtered out according to threshold
#'   * `validation_rules` a set of validation rules defined with [validate::validator()].
#'
#'
#' @export
#'
#' @name filtering_out
#'
#' @importFrom dplyr group_by count filter
filtering_out_data <- function(data, threshold) {
  
  if (!is.na(threshold)) {
    
    species_to_keep <- 
      data %>% 
      dplyr::group_by(.__taxa) %>% 
      dplyr::count() %>% 
      dplyr::filter(n < threshold)
    
    data_filtered <- data %>% 
      dplyr::filter(.__taxa %in% species_to_keep$.__taxa)
    
  } else {
    
    data_filtered <- data 
    
  }
  
  return(data_filtered)
}
gdauby/conrappli documentation built on Jan. 21, 2025, 12:51 p.m.