From 9f7ae44b5e9661d67e89f8e5dba6b842d4f1032f Mon Sep 17 00:00:00 2001 From: fawda123 Date: Sun, 27 Oct 2024 12:16:12 -0400 Subject: [PATCH] rework read_formphyto for correct taxa grouping --- DESCRIPTION | 2 +- R/read_formphyto.R | 14 +++++++------- man/read_formphyto.Rd | 4 ++-- vignettes/intro.Rmd | 2 +- 4 files changed, 11 insertions(+), 11 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 565540378..2fc759f98 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: tbeptools Title: Data and Indicators for the Tampa Bay Estuary Program Version: 3.0.0.9000 -Date: 2024-10-25 +Date: 2024-10-27 Authors@R: c( person(given = "Marcus", family = "Beck", diff --git a/R/read_formphyto.R b/R/read_formphyto.R index 2e611a06e..6373cb1a7 100644 --- a/R/read_formphyto.R +++ b/R/read_formphyto.R @@ -9,7 +9,7 @@ #' #' @importFrom dplyr %>% #' -#' @details Only seven taxonomic groups are summarized. Pyrodinium bahamense, Karenia brevis, Tripos hircus, Pseudo-nitzschia sp., and Pseudo-nitzschia pungens are retained at the species level. Bacillariophyta and Cyanobacteria are retained at the phylum level. All other taxa are grouped into an "other" category. +#' @details Only seven taxonomic groups are summarized. Pyrodinium bahamense, Karenia brevis, Tripos hircus, Pseudo-nitzschia sp., and Pseudo-nitzschia pungens are retained at the species level. Diatoms are summarized at the class level using Bacillariophyceae, Coscinodiscophyceae, and Mediophyceae and Cyanobacteria are summarized at the phylum level using Cyanobacteriota. All other taxa are grouped into an "other" category. #' #' @seealso \code{\link{read_importphyto}} #' @@ -19,7 +19,7 @@ #' xlsx <- '~/Desktop/phyto_data.xlsx' #' #' # load and assign to object -#' phytodata <- read_importphyto(xlsx) +#' phytodata <- read_importphyto(xlsx, download_latest = TRUE) #' } read_formphyto <- function(datin){ @@ -29,7 +29,7 @@ read_formphyto <- function(datin){ # format out <- datin %>% - dplyr::select(epchc_station = StationNumber, Date = SampleTime, phylum = PHYLUM, name = NAME, count = COUNT, units = Units) %>% + dplyr::select(epchc_station = StationNumber, Date = SampleTime, phylum = PHYLUM, class = CLASS, name = NAME, count = COUNT, units = Units) %>% dplyr::filter(epchc_station %in% !!stations) %>% dplyr::mutate( count = as.numeric(count), @@ -37,14 +37,14 @@ read_formphyto <- function(datin){ # qrt = quarter(Date, with_year = TRUE), name = dplyr::case_when( name %in% c('Pyrodinium bahamense', 'Karenia brevis', 'Tripos hircus', 'Pseudo-nitzschia sp.', 'Pseudo-nitzschia pungens') ~ name, - phylum %in% c('Bacillariophyta', 'Cyanobacteria') ~ phylum, - !is.na(phylum) ~ 'other', - T ~ NA_character_ + class %in% c('Bacillariophyceae', 'Coscinodiscophyceae', 'Mediophyceae') ~ 'Diatoms', + phylum %in% 'Cyanobacteriota' ~ 'Cyanobacteria', + T ~ 'other' ) ) %>% dplyr::filter(!is.na(name)) %>% dplyr::group_by(epchc_station, Date, name, units) %>% - dplyr::summarise(count = sum(count, na.rm = T)) %>% + dplyr::summarise(count = median(count, na.rm = T)) %>% dplyr::ungroup() %>% dplyr::mutate( yrqrt = lubridate::floor_date(Date, unit = 'quarter'), diff --git a/man/read_formphyto.Rd b/man/read_formphyto.Rd index 9b8c73a2b..521eeb71d 100644 --- a/man/read_formphyto.Rd +++ b/man/read_formphyto.Rd @@ -16,7 +16,7 @@ A formatted \code{data.frame} with phytoplankton count data Format phytoplankton data } \details{ -Only seven taxonomic groups are summarized. Pyrodinium bahamense, Karenia brevis, Tripos hircus, Pseudo-nitzschia sp., and Pseudo-nitzschia pungens are retained at the species level. Bacillariophyta and Cyanobacteria are retained at the phylum level. All other taxa are grouped into an "other" category. +Only seven taxonomic groups are summarized. Pyrodinium bahamense, Karenia brevis, Tripos hircus, Pseudo-nitzschia sp., and Pseudo-nitzschia pungens are retained at the species level. Diatoms are summarized at the class level using Bacillariophyceae, Coscinodiscophyceae, and Mediophyceae and Cyanobacteria are summarized at the phylum level using Cyanobacteriota. All other taxa are grouped into an "other" category. } \examples{ \dontrun{ @@ -24,7 +24,7 @@ Only seven taxonomic groups are summarized. Pyrodinium bahamense, Karenia brevis xlsx <- '~/Desktop/phyto_data.xlsx' # load and assign to object -phytodata <- read_importphyto(xlsx) +phytodata <- read_importphyto(xlsx, download_latest = TRUE) } } \seealso{ diff --git a/vignettes/intro.Rmd b/vignettes/intro.Rmd index a2bbf1d45..cb63329f6 100644 --- a/vignettes/intro.Rmd +++ b/vignettes/intro.Rmd @@ -122,7 +122,7 @@ After the phytoplankton data are successfully imported, you can view them from t phytodata ``` -These data are highly summarized from the raw data file available online. Cell counts (as number of cells per 0.1mL) for selected taxa are summed for each station by quarters (i.e., Jan/Feb/Mar, Apr/May/Jun, etc.). The quarter is indicated in the `yrqrt` column specified by the starting date of each quarter (e.g., `1975-07-01` is the quarter Jul/Aug/Sep for 1975). These data are primarily used to support analyses in the water quality dashboard: +These data are highly summarized from the raw data file available online. Cell counts (as number of cells per 0.1mL) for selected taxa are shown by date and quarter (i.e., Jan/Feb/Mar, Apr/May/Jun, etc.) for each station. The quarter is indicated in the `yrqrt` column specified by the starting date of each quarter (e.g., `1975-07-01` is the quarter Jul/Aug/Sep for 1975). These data are primarily used to support analyses in the water quality dashboard: ### Retrieving additional water quality data