add new filter functions

DESCRIPTION

@@ -40,6 +40,7 @@ Imports:
     rlang,
     tidyr,
     utils,
+    lubridate,
     vroom
 Suggests: 
     here,

NAMESPACE

@@ -4,6 +4,10 @@ export(compute_abundances)
 export(compute_concentration_bins_CPR_n)
 export(compute_concentrations)
 export(compute_frequencies)
+export(filter_by_coordinates)
+export(filter_by_month)
+export(filter_by_species)
+export(filter_by_year)
 export(get_cpr_north_data)
 export(get_cpr_south_data)
 export(get_forcis_db)
@@ -12,9 +16,11 @@ export(get_pump_data)
 export(get_required_columns)
 export(get_sediment_trap_data)
 export(get_species_names)
+export(reshape_forcis)
 export(select_columns)
 export(select_taxonomy)
 import(dplyr)
+import(lubridate)
 import(rlang)
 import(tidyr)
 import(vroom)

R/filter.R

@@ -0,0 +1,130 @@
+
+#' Reshape and simplify forcis data
+#'
+#' @param data forcis data
+#'
+#' @return A `data.frame`
+#' @export
+#'
+#' 
+reshape_forcis <- function(data){
+
+  if (get_data_type(data) %in% c("CPR North")) {
+    stop(paste0("This function is not designed to work with 'CPR North' data"), call. = FALSE) 
+  }
+
+  taxa_cols <- get_species_names(data) 
+  metadat_cols <- get_required_columns()
+  dat_reshaped <- dat_reshaped %>% 
+    select(all_of(taxa_cols),metadat_cols) %>% 
+    pivot_longer(all_of(taxa_cols), 
+                 names_to  = 'taxa', 
+                 values_to = 'counts')
+  return(dat_reshaped)
+}
+
+
+
+#' Filter forcis data by year of sampling
+#'
+#' @param data forcis data in long format
+#' @param years numeric vector of selected years
+#'
+#' @return A `data.frame`.
+#' @export
+#'
+#' @import lubridate
+#' 
+filter_by_year <- function(data,years){
+  year_vector <- as.numeric(years)
+  filtered_dat <- data %>% 
+    filter(! is.na(.data$profile_date_time)) %>% 
+    mutate(new_profile_date_time = dmy(.data$profile_date_time)) %>% 
+             mutate(year=year(.data$new_profile_date_time)) %>% 
+             filter(.data$year %in% year_vector) %>% 
+             select(-c(.data$year,.data$new_profile_date_time))
+
+           return(filtered_dat)
+
+}
+
+
+#' Filter forcis data by month of sampling
+#'
+#' @param data forcis data in long format
+#' @param months  numeric vector of selected months
+#'
+#' @return A `data.frame`.
+#' @export
+#'
+#' @import lubridate
+filter_by_month <- function(data,months){
+
+  month_vector <- as.numeric(months)
+
+  filtered_dat <- data %>% 
+    filter(! is.na(.data$profile_date_time)) %>% 
+    mutate(new_profile_date_time =dmy(.data$profile_date_time)) %>% 
+    mutate(month=month(.data$new_profile_date_time)) %>% 
+    filter(.data$month %in% month_vector)%>% 
+    select(-c(.data$month,.data$new_profile_date_time))
+
+  return(filtered_dat)
+
+}
+
+
+#' Filter forcis data by coordinate square 
+#'
+#' @param data forcis data in long format
+#' @param coord_square a numeric vector containing in this order minimum latitute,
+#' minimum longitude, maximum latitude, maximum longitude
+#'
+#' @return A `data.frame`.
+#' @export
+#'
+#' @examples
+filter_by_coordinates <- function(data, coord_square){
+
+  min_lat <- coord_square[1] 
+  min_long <- coord_square[2] 
+  max_lat <- coord_square[3]
+  max_long <- coord_square[3]
+
+  filtered_dat <- data %>% 
+    filter(! is.na(.data$site_lat_start_decimal)) %>% 
+    filter(! is.na (.data$site_lon_start_decimal)) %>%   
+    filter(.data$site_lat_start_decimal>= min_lat &
+             .data$site_lat_start_decimal <=max_lat &
+             .data$site_lon_start_decimal>= min_long &
+             .data$site_lon_start_decimal <=max_long)
+
+  return(filtered_dat)
+}
+
+#' Filter forcis data by species 
+#'
+#' @param data forcis data in long format, except for CPR North data
+#' @param species a character vector listing species of interest
+#'
+#' @return A `data.frame`
+#' @export
+#'
+#' @examples
+filter_by_species <- function (data,species ){
+  my_species <- as.character(species)
+
+  filtered_dat <- data %>% 
+    filter(.data$taxa %in% my_species)
+  # filter(! is.na(counts))
+
+  return(filtered_dat)
+}
+
+
+
+
+
+
+
+