USEPA · cristinamullin · Feb 4, 2023 · Feb 3, 2023 · Feb 3, 2023 · Feb 3, 2023
diff --git a/.gitignore b/.gitignore
@@ -13,56 +13,9 @@ TADA.Rproj
 # Session Data files
 .RData
 
-# tempdata folder files for TADABigdataRetrieval
-AL_raw_data.rds
-AR_raw_data.rds
-AZ_raw_data.rds
-CA_raw_data.rds
-CO_raw_data.rds
-CT_raw_data.rds
-DC_raw_data.rds
-DE_raw_data.rds
-FL_raw_data.rds
-GA_raw_data.rds
-ID_raw_data.rds
-IA_raw_data.rds
-IL_raw_data.rds
-IN_raw_data.rds
-KS_raw_data.rds
-KY_raw_data.rds
-LA_raw_data.rds
-ME_raw_data.rds
-MD_raw_data.rds
-MA_raw_data.rds
-MI_raw_data.rds
-MN_raw_data.rds
-MS_raw_data.rds
-MO_raw_data.rds
-MT_raw_data.rds
-NE_raw_data.rds
-NV_raw_data.rds
-NH_raw_data.rds
-NJ_raw_data.rds
-NM_raw_data.rds
-NY_raw_data.rds
-NC_raw_data.rds
-ND_raw_data.rds
-OH_raw_data.rds
-OK_raw_data.rds
-OR_raw_data.rds
-PA_raw_data.rds
-RI_raw_data.rds
-SC_raw_data.rds
-SD_raw_data.rds
-TN_raw_data.rds
-TX_raw_data.rds
-UT_raw_data.rds
-VT_raw_data.rds
-VA_raw_data.rds
-WA_raw_data.rds
-WV_raw_data.rds
-WI_raw_data.rds
-WY_raw_data.rds
 .Rdata
 .httr-oauth
 .DS_Store
+
+#
+_snaps
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -17,6 +17,12 @@ Authors@R:
            role = "aut"),
     person(given = "Laura",
            family = "Shumway",
+           role = "aut"),
+    person(given = "Elise",
+           family = "Hinman",
+           role = "aut"), 
+    person(given = "Kathleen",
+           family = "Healy",
            role = "aut")
     )
 Description: Assists data partners in performing automated assessments with
@@ -30,23 +36,23 @@ RoxygenNote: 7.2.3
 Imports:
     plyr, 
     data.table, 
-    dataRetrieval,
     dplyr,
-    ggplot2,
     grDevices,
     magrittr,
     stringr,
     utils, 
     RColorBrewer,
     stats, 
-    gganimate,
     lubridate,
-    maps
+    maps, 
+    dataRetrieval, 
+    ggplot2, 
+    gganimate, 
+    gifski
 Depends: 
     R (>= 3.5.0)
 Suggests: 
     readr,
-    gifski,
     rlang,
     remotes, 
     tidyverse,
@@ -62,6 +68,6 @@ Suggests:
 VignetteBuilder: knitr, rmarkdown
 Language: en-US
 Config/testthat/edition: 3
-Config/testthat/load-all: list(export_all = FALSE, helpers = FALSE
+Config/testthat/load-all: list(export_all = FALSE, helpers = FALSE)
 URL: https://usepa.github.io/TADA/, https://github.com/USEPA/TADA
 LazyData: true
diff --git a/NAMESPACE b/NAMESPACE
@@ -6,7 +6,6 @@ export(AggregatedContinuousData)
 export(BelowNationalWQXLowerThreshold)
 export(ConvertDepthUnits)
 export(ConvertResultUnits)
-export(CreateAnimatedMap)
 export(FilterFieldReview)
 export(FilterFields)
 export(FilterParFieldReview)

diff --git a/R/DataDiscoveryRetrieval.R b/R/DataDiscoveryRetrieval.R
@@ -28,6 +28,10 @@
 #' to the "ResultMeasureValue" and "DetectionLimitMeasureValue" columns; 
 #' and to provide information about the result values that is needed to address
 #' censored data later on (i.e., nondetections)
+#' 
+#' Users can reference the \href{https://www.epa.gov/waterdata/storage-and-retrieval-and-water-quality-exchange-domain-services-and-downloads}{WQX domain tables}
+#' to find allowable vales for queries, e.g., reference the WQX domain table to find countycode and statecode: https://cdx.epa.gov/wqx/download/DomainValues/County_CSV.zip
+#' Alternatively, you can use the WQP services to find areas where data is available in the US: https://www.waterqualitydata.us/Codes/countycode
 #'  
 #' See ?MeasureValueSpecialCharacters and ?autoclean documentation for more information.
 #' 
@@ -37,7 +41,7 @@
 #' @param siteid Unique monitoring station identifier
 #' @param siteType Type of waterbody
 #' @param characteristicName Name of parameter
-#' @param ActivityMediaName Sampling substrate such as water, air, or sediment
+#' @param sampleMedia Sampling substrate such as water, air, or sediment
 #' @param ProjectIdentifier A string of letters and/or numbers (some additional characters also possible) used to signify a project with data in the Water Quality Portal
 #' @param OrganizationIdentifier A string of letters and/or numbers (some additional characters also possible) used to signify an organization with data in the Water Quality Portal
 #' @param endDate End Date in the format YYYY-MM-DD
@@ -52,14 +56,32 @@
 #' tada1 <- TADAdataRetrieval(statecode = "WI",
 #'                            countycode = "Dane",
 #'                            characteristicName = "Phosphorus")
+#' 
+#' tada2 <- TADAdataRetrieval(ProjectIdentifier = "Anchorage Bacteria 20-21")
+#' 
+#' tada3 <- TADAdataRetrieval(statecode = "UT", 
+#'                            characteristicName = c("Ammonia", "Nitrate", "Nitrogen"), 
+#'                            startDate = "10-01-2020")
+#' 
+#' tada4 <- TADAdataRetrieval(statecode = "SC", countycode  = "Abbeville")
+#' 
+#' # countycode queries require a statecode
+#' tada5 <- TADAdataRetrieval(countycode = "US:02:020")
+#' 
+#' tada6 <- TADABigdataRetrieval(startDate = "2019-01-01", 
+#'                               endDate = "2021-12-31", 
+#'                               characteristicName = "Temperature, water",
+#'                               statecode = c("AK","AL"))
+#' 
 #' }
+#' 
 TADAdataRetrieval <- function(statecode = "null",
                               startDate = "null",
                               countycode = "null", 
                               siteid = "null",
                               siteType = "null",
                               characteristicName = "null",
-                              ActivityMediaName = "null",
+                              sampleMedia = "null",
                               ProjectIdentifier = "null",
                               OrganizationIdentifier = "null",
                               endDate = "null",
@@ -104,10 +126,10 @@ TADAdataRetrieval <- function(statecode = "null",
     WQPquery <- c(WQPquery, characteristicName = characteristicName)
   }
 
-  if (length(ActivityMediaName)>1) {
-    WQPquery <- c(WQPquery, ActivityMediaName = list(ActivityMediaName)) 
-  } else if (ActivityMediaName != "null") {
-    WQPquery <- c(WQPquery, ActivityMediaName = ActivityMediaName)
+  if (length(sampleMedia)>1) {
+    WQPquery <- c(WQPquery, sampleMedia = list(sampleMedia)) 
+  } else if (sampleMedia != "null") {
+    WQPquery <- c(WQPquery, sampleMedia = sampleMedia)
   }
 
   if (length(ProjectIdentifier)>1) {
@@ -151,6 +173,7 @@ TADAdataRetrieval <- function(statecode = "null",
                           Sites = sites.DR,
                           Narrow = narrow.DR,
                           Projects = projects.DR)
+
   # run autoclean function
   if(applyautoclean==TRUE){
 
@@ -270,7 +293,7 @@ TADAReadWQPWebServices <- function(webservice) {
 #' @param startDate Start Date YYYY-MM-DD format, for example, "1995-01-01"
 #' @param endDate end date in YYYY-MM-DD format, for example, "2020-12-31"
 #' @param statecode Character/character vector. State/territory abbreviations from FIPS codes consist of two letters 
-#' @param huc An 8-digit numeric code denoting a hydrologic unit. Example: "04030202"
+#' @param huc A numeric code denoting a hydrologic unit. Example: "04030202". Different size hucs can be entered.
 #' @param characteristicName Name of water quality parameter
 #' @param siteType Name of water body type (e.g., "Stream", "Lake, Reservoir, Impoundment")
 #' @param sampleMedia Defaults to "Water". Refer to WQP domain tables for other options.
@@ -506,7 +529,7 @@ JoinWQPProfiles <- function(FullPhysChem = "null",
     if(nrow(Sites.df)>0){
       join1 <- FullPhysChem.df %>%
         # join stations to results
-        dplyr::left_join(Sites.df, by = "MonitoringLocationIdentifier") %>%
+        dplyr::left_join(Sites.df, by = "MonitoringLocationIdentifier", multiple = "all") %>%
         # remove ".x" suffix from column names
         dplyr::rename_at(dplyr::vars(dplyr::ends_with(".x")), ~ stringr::str_replace(., "\\..$", "")) %>%
         # remove columns with ".y" suffix
@@ -545,8 +568,8 @@ JoinWQPProfiles <- function(FullPhysChem = "null",
         ),
         by = c(
           "OrganizationIdentifier", "OrganizationFormalName",
-          "ProjectIdentifier","ProjectName"
-        )
+          "ProjectIdentifier","ProjectName"),
+        multiple = "all"
         )
     }else{join3 = join2}
 

diff --git a/R/ResultFlagsIndependent.R b/R/ResultFlagsIndependent.R
@@ -983,6 +983,7 @@ QAPPDocAvailable <- function(.data, clean = FALSE) {
 #' 
 #' # Remove data with imprecise coordinates or coordinates outside the USA from the dataframe:
 #' InvalidCoord_removed <- InvalidCoordinates(Nutrients_Utah, clean_outsideUSA = "remove", clean_imprecise = TRUE)
+#' 
 
 InvalidCoordinates <- function(.data, 
                                clean_outsideUSA = c("no", "remove", "change sign"), 
@@ -996,7 +997,7 @@ InvalidCoordinates <- function(.data,
   checkType(clean_imprecise, "logical")
   # check .data has required columns
   checkColumns(.data, c("LatitudeMeasure", "LongitudeMeasure"))
-  #check lat and long are "numeric"
+  # check lat and long are "numeric"
   if (class(.data$LongitudeMeasure) != "numeric") {
     warning("LongitudeMeasure field must be numeric")
   }
@@ -1017,7 +1018,7 @@ InvalidCoordinates <- function(.data,
       LongitudeMeasure > 0 & LongitudeMeasure < 145 ~ "LONG_OutsideUSA",
       grepl("999", LatitudeMeasure) ~ "Imprecise_Latincludes999",
       grepl("999", LongitudeMeasure) ~ "Imprecise_Longincludes999",
-      #for below, lat and long fields must be numeric
+      # for below, lat and long fields must be numeric
       # this checks if there are at least 3 significant figures to the 
       # right of the decimal point
       sapply(.data$LatitudeMeasure, decimalplaces) < 3 
@@ -1043,7 +1044,7 @@ InvalidCoordinates <- function(.data,
 
   # if clean_outsideUSA is "change sign", change the sign of lat/long coordinates outside of USA
   if (clean_outsideUSA == "change sign") {
-    print("Note: This is a temporary solution. Data owner should fix the raw data to address invalid coordinates through WQX. For assistance, email the WQX helpdesk ([email protected]).")
+    print("When clean_outsideUSA == change sign, the sign for any lat/long coordinates flagged as outside of USA are switched. This is a temporary solution. Data owners should fix the raw data to address invalid coordinates through WQX. For assistance fixing data errors you see in the WQP, email the WQX helpdesk ([email protected]).")
     .data <- .data %>% 
       dplyr::mutate(
         LatitudeMeasure = dplyr::case_when(
@@ -1055,7 +1056,7 @@ InvalidCoordinates <- function(.data,
       )
   }
 
-  #return only flagged data if errorsonly = true
+  # return only flagged data if errorsonly = true
   if ((errorsonly == TRUE)) {
     .data <- dplyr::filter(.data, is.na(TADA.InvalidCoordinates) != TRUE)
   }

diff --git a/R/Visualizations.R b/R/Visualizations.R
@@ -1,71 +1,3 @@
-#' @title Generate Animated Map
-#' 
-#' @description
-#' Animated map code adapted from USGS blog: https://waterdata.usgs.gov/blog/large_sample_pull/
-#'
-#' @param .data TADA dataframe
-#'
-#' @return Animated map
-#'
-#' @export
-#' 
-
-CreateAnimatedMap <- function(.data) { 
-
-  # code adapted from USGS blog: https://waterdata.usgs.gov/blog/large_sample_pull/
-
-  # pull the year from the date
-  .data$year <- base::format(as.Date(.data$ActivityStartDate, format="%Y-%m-%d"),"%Y")
-
-  # create new data frame of summarized result data by year
-  n_bysite <- 
-    .data %>% 
-    dplyr::group_by(MonitoringLocationIdentifier, LatitudeMeasure, LongitudeMeasure, year) %>% 
-    dplyr::summarize(mean = mean(.data$ResultMeasureValue, na.rm = TRUE), 
-              median = stats::median(.data$ResultMeasureValue, na.rm = TRUE))
-
-  # create a new character column with total nitrogen acceptable range designations
-  n_bysite <- 
-    n_bysite %>% dplyr::mutate(TN_mean=
-                               dplyr::case_when(mean<2 ~ "<2 mg/l", 
-                               mean>=2 & mean<=6 ~ "2-6 mg/l", 
-                               mean>6 ~ ">6 mg/l")) 
-
-  # convert latitude, longitude, and year data to numeric form
-  n_bysite$LatitudeMeasure <- as.numeric(n_bysite$LatitudeMeasure)
-  n_bysite$LongitudeMeasure <- as.numeric(n_bysite$LongitudeMeasure)
-  n_bysite$year <- as.numeric(n_bysite$year)
-
-  # first, create the base map data frame
-  all_state <- "usa"
-
-  usa <- map_data("state", interior=TRUE)
-  base_map <- ggplot2::ggplot(data = usa, mapping = aes(x = long, 
-                                               y = lat, 
-                                               group = group)) +
-    ggplot2::geom_polygon(color = "black", fill = "white") +
-    ggplot2::coord_quickmap() +
-    ggplot2::theme_void() 
-
-  # second, plot the base map and add data to it
-  map_with_data <- base_map +
-    ggplot2::geom_point(data = n_bysite, aes(x = LongitudeMeasure, 
-                                    y = LatitudeMeasure, 
-                                    color = TN_mean, 
-                                    group = year, 
-                                    frame = year)) +
-    gganimate::transition_time(year) +
-    ggplot2::ggtitle('Year: {frame_time}', # add year to the title
-            subtitle = 'Frame {frame} of {nframes}') +
-    ggplot2::scale_colour_manual(values = c("blue", "red", "green")) 
-  num_years <- max(n_bysite$year)-min(n_bysite$year) + 1 
-
-  # lastly, run the animation
-  gganimate::animate(map_with_data, nframes = num_years, fps = 1)
-
-  }
-
-
 #' @title Generate Map
 #'
 #' @description 

diff --git a/docs/404.html b/docs/404.html
diff --git a/docs/LICENSE.html b/docs/LICENSE.html
diff --git a/docs/articles/CONTRIBUTING.html b/docs/articles/CONTRIBUTING.html
diff --git a/docs/articles/WQPDataHarmonization_files/figure-html/unnamed-chunk-10-1.png b/docs/articles/WQPDataHarmonization_files/figure-html/unnamed-chunk-10-1.png
diff --git a/docs/articles/index.html b/docs/articles/index.html