added enterodata_since1995 and associated documentation

R/enterodata_since1995.R

@@ -0,0 +1,25 @@
+#' Enterococcus data from 53 key Enterococcus stations since 1995
+#'
+#' Note, the data frame was created and named with 1995-2023 as the date range in the Water Quality Portal call, but the first actual date is 2 Aug 2000.
+#'
+#' @format A data frame with 6207 rows and 12 columns:
+#' \describe{
+#'  \item{date}{data, sample date}
+#'  \item{station}{character, sample station, as named in the Water Quality Portal}
+#'  \item{ecocci}{numeric, sample's Enterococcus concentration}
+#'  \item{ecocci_censored}{logical, whether sample concentration was censored (below detection limit)}
+#'  \item{Latitude}{numeric, latitude in decimal degrees}
+#'  \item{Longitude}{numeric, longitude in decimal degrees}
+#'  \item{ecocci_units}{character, units of measurement of Enterococcus}
+#'  \item{time}{character, time sample was obtained, in 24hr format}
+#'  \item{time_zone}{character, time zone of sample time}
+#'  \item{MDL}{numeric, minimum detection limit of laboratory for Enterococcus}
+#'  \item{yr}{numeric year of sample date}
+#'  \item{mo}{numeric month of sample date}
+#' }
+#' @details
+#' A sample dataset containing Enterococcus from 53 stations in the TBEP watershed from 2000-2023. Generated by \code{data-raw/enterodata_since1995-raw.R} (view on github: \url{https://github.com/tbep-tech/tbeptools/blob/master/data-raw/enterodata_since1995-raw.R})
+#' @source Water Quality Portal, \url{https://waterqualitydata.us}
+#'
+
+"enterodata_since1995"

data-raw/enterodata_since1995-raw.R

@@ -0,0 +1,22 @@
+# all data from key Enterococcus stations, 1995-2023
+# although apparently data collection only started in 2000 at the earliest of these stations
+
+stations <- unique(catch_precip$station)
+entero_names <- c('Enterococci',
+                  'Enterococcus')
+startDate <- as.Date('1995-01-01')
+endDate <- as.Date('2023-12-31')
+
+args <- list(
+  siteid = stations,
+  characteristicName = entero_names,
+  startDateLo = format(startDate, '%m-%d-%Y'),
+  startDateHi = format(endDate, '%m-%d-%Y')
+)
+# date format has to be mm-dd-yyyy
+
+enterodata_since1995 <- read_importentero(args = args) %>%
+  dplyr::select(-qualifier,
+                -LabComments)
+
+save(enterodata_since1995, file = 'data/enterodata_since1995.RData', compress = 'xz')