Include updated stream points dataset. Remove RSA date filter. Use mo…

…st recent dumpsite impact assessment

R/dumpsites.R

@@ -2,10 +2,6 @@
 #'
 #' @param df_point Point data from Rapid Stream Assessment (RSA) dataset.
 #' @param df_reach Reach data from Rapid Stream Assessment (RSA) dataset.
-#' @param start_date Beginning of timeframe being evaluated (ex. first day of
-#'     five-year assessment period).
-#' @param end_date End of timeframe being evaluated (ex. last day of
-#'     five-year assessment period).
 #' @param reach_prefix_from_table Field name prefix sourced from RSA reach
 #'     attribute table. Should be consistent with the name of the stream reach
 #'     attribute table from the RSA geodatabase.
@@ -24,21 +20,18 @@
 #'
 #' @examples assess_dumpsites(df_point_example,
 #'                            df_reach_example,
-#'                            "2020-01-01",
-#'                            "2024-12-31",
 #'                            "StreamReachAttributes",
 #'                            "StreamReaches",
 #'                            "StreamPointAttributes",
 #'                            "StreamPoints_Intersect" )
 
-assess_dumpsites <- function(df_point, df_reach, start_date, end_date, reach_prefix_from_table, reach_prefix_from_layer, point_prefix_from_table, point_prefix_from_layer){
+assess_dumpsites <- function(df_point, df_reach, reach_prefix_from_table, reach_prefix_from_layer, point_prefix_from_table, point_prefix_from_layer){
 
   df_length <- df_reach %>%
     dplyr::select(location_name = dplyr::all_of(paste0(reach_prefix_from_layer, ".subshed")),
                   reach_length = dplyr::all_of(paste0(reach_prefix_from_layer, ".Shape_Length")),
                   id = dplyr::all_of(paste0(reach_prefix_from_table, ".featureGlobalID_key")),
                   date = dplyr::all_of(paste0(reach_prefix_from_table, ".assessment_time"))) %>%
-    dplyr::filter(date >= start_date & date <= end_date) %>%
     dplyr::group_by(id) %>%
     dplyr::slice_max(date, n=1, with_ties = FALSE) %>% # Remove duplicate reaches. Keep most recent reach assessment. If same date/time and ID, maintain only one record
     dplyr::ungroup() %>%
@@ -53,7 +46,7 @@ assess_dumpsites <- function(df_point, df_reach, start_date, end_date, reach_pre
                   date = dplyr::all_of(paste0(point_prefix_from_table, ".assessment_time")),
                   d_impact = dplyr::all_of(paste0(point_prefix_from_table, ".d_impact")),
                   ) %>%
-    dplyr::filter(date >= start_date & date <= end_date) %>%
+    tidyr::drop_na(d_impact) %>% # remove NA records in d_impact field. Likely assessments of existing points that did not change. Need to reference original record.
     dplyr::group_by(id) %>%
     dplyr::slice_max(date, n=1, with_ties = FALSE) %>% # Remove duplicate point. Keep most recent point assessment. If same date/time and ID, maintain only one record
     dplyr::ungroup() %>%

R/trash.R

@@ -1,10 +1,6 @@
 #' Calculate trash scores.
 #'
 #' @param df_reach Reach data from Rapid Stream Assessment (RSA) dataset.
-#' @param start_date Beginning of timeframe being evaluated (ex. first day of
-#'     five-year assessment period).
-#' @param end_date End of timeframe being evaluated (ex. last day of
-#'     five-year assessment period).
 #' @param reach_prefix_from_table Field name prefix sourced from RSA reach
 #'     attribute table. Should be consistent with the name of the stream reach
 #'     attribute table from the RSA geodatabase.
@@ -15,11 +11,12 @@
 #' @return List of 2 dataframes: summary and score.
 #' @export
 #'
-#' @examples assess_trash(df_reach_example, "2020-01-01", "2024-12-31",
-#'     "StreamReachAttributes", "StreamReaches")
+#' @examples assess_trash(df_reach_example,
+#'                        "StreamReachAttributes",
+#'                        "StreamReaches")
 
 
-assess_trash <- function(df_reach, start_date, end_date, reach_prefix_from_table, reach_prefix_from_layer) {
+assess_trash <- function(df_reach, reach_prefix_from_table, reach_prefix_from_layer) {
 
   df_summary <- df_reach %>%
     dplyr::select(location_name = dplyr::all_of(paste0(reach_prefix_from_layer, ".subshed")),

R/wq_nutrients.R

@@ -1,9 +1,13 @@
 #' Calculate water quality scores for nutrients
 #'
-#' @param df DOEE Ambient Water Quality Data that has been processed and formatted
-#' @param parameter_name String to indicate target parameter: "Nitrogen", "Phosphorus, Total (as P)"
-#' @param piedmont_criteria Nutrient criteria recommendation for Piedmont Ecoregion 64 in mg/L
-#' @param coastal_plain_criteria Nutrient criteria recommendation for Coastal Plain Ecoregion 65 in mg/L
+#' @param df DOEE Ambient Water Quality Data that has been processed and
+#'    formatted
+#' @param parameter_name String to indicate target parameter: "Nitrogen",
+#'    "Phosphorus, Total (as P)"
+#' @param piedmont_criteria Nutrient criteria recommendation for Piedmont
+#'    Ecoregion 64 in mg/L
+#' @param coastal_plain_criteria Nutrient criteria recommendation for Coastal
+#'    Plain Ecoregion 65 in mg/L
 #'
 #' @return List of three dataframes: results, summary, score
 #' @export

output/all_scores.csv

@@ -1,26 +1,26 @@
-"","sci_subshed","Trash","Dumpsites","Effective Impervious Area","Temperature, water","pH","Dissolved oxygen (DO)","Escherichia coli","Turbidity","Conductivity","Nitrogen","Phosphorus, Total (as P)","Connectivity","Fish","Habitat","Macroinvertebrates"
-"1","Battery Kemble Creek",8.43478260869565,10,6,10,10,10,7.17122657287291,10,1.32946707229891,1.1722461961956,10,10,3,4,7
-"2","Broad Branch",8.88235294117647,8,2,10,9.49484604605374,10,3.96201632162848,10,1.39551171022171,2.53189561427939,10,10,2,4,6
-"3","Dumbarton Oaks",10,10,4,10,10,10,8.54782802837774,10,1.70833294620897,1.32807710704536,2.8679579947462,10,3,5,7
-"4","Fenwick Branch",7.42857142857143,10,3,9.49476657878656,10,10,6.8791964501452,10,1.75285115573104,2.32427732195356,10,10,2,3,6
-"5","Fort Davis Tributary",8.33333333333333,2,2,10,10,10,4.56378937695466,3.40381314529514,1.28521704525446,0.950005376536892,1.78543632558786,1,1,5,5
-"6","Fort Dupont Tributary",7.64285714285714,7,8,10,10,8.19644566724721,4.39637929649141,3.667361623274,2.99612324159937,0.749069894299005,10,1,3,4,6
-"7","Fort Stanton Tributary",6.47058823529412,4,1,9.49458887028815,10,10,3.49306972579195,8.24161710963122,2.14961627380251,0.950005376536892,10,1,1,3,7
-"8","Foundry Branch",8.83333333333333,10,2,10,10,10,5.43588122762784,4.44089503244838,2.9615349603606,2.05698424129608,10,1,1,4,NA
-"9","Hickey Run",8.03846153846154,10,9,9.32570696570447,10,9.31006357105735,1.71733915151806,7.52739827502453,1.92353016456839,0.749069894299005,2.7927191991411,10,6,2,4
-"10","Klingle Valley Run",6.25,10,2,10,10,10,6.5392010054142,10,2.16336911176854,1.52948677601239,10,10,2,3,6
-"11","Luzon Branch",5.2,10,1,10,10,10,2.74149789121648,5.16856938057974,1.68139016788936,2.13654818496565,2.91985046082419,10,2,3,6
-"12","Normanstone Creek",7.21428571428571,10,1,10,8.9888961180284,10,4.46891175504634,10,1.49230558316491,2.58568816872641,10,10,3,3,6
-"13","Oxon Run",5.85714285714286,8,1,9.49482509665549,10,10,4.08034192298863,7.26446748330366,2.73668115439965,0.677223449104501,0.963293817107756,10,4,4,4
-"14","Pinehurst Branch",8.66666666666667,10,6,10,9.45561327204199,10,6.86529198320573,10,1.64381726305677,2.53189561427939,10,10,2,4,5
-"15","Piney Branch",8,10,1,10,10,10,6.24485935433058,10,1.37920467622303,2.43350524767764,10,10,3,2,4
-"16","Pope Branch",8,10,3,10,10,10,6.70307871860358,4.63848137391428,2.04750999680075,0.950005376536892,10,1,4,7,8
-"17","Portal Branch",7,10,3,10,8.98692894850945,10,4.24400479220216,6.90674993457207,1.02448007263146,2.74453544775747,10,10,1,3,6
-"18","Reservation 630",9.21052631578947,10,3,9.49484222518253,10,10,4.89875662885154,6.54810880322023,1.95694969141548,2.32427732195356,10,10,4,7,7
-"19","Rock Creek",8.23913043478261,7,1,9.03991429859265,9.63931584712039,10,4.75298766520739,8.85351874858907,3.01758638876789,2.35646823207748,10,10,5,4,5
-"20","Soapstone Creek",8.71428571428571,10,1,10,8.98764540312439,10,6.80566463860387,10,1.91408087817814,2.53189561427939,2.88434296861746,10,2,3,6
-"21","Texas Avenue Tributary",7,10,3,10,10,10,3.54658539291944,7.3375495518317,1.74050116850977,0.837784090876652,10,1,1,4,3
-"22","Watts Branch",3.55,6,1,9.32024027311975,9.03799489304956,9.94283156569335,3.52383649640539,8.10990235278729,2.71307679688268,0.80598894736693,4.92721388547487,10,4,3,6
-"23","Dalecarlia Tributary",NA,10,4,9.49281310022025,9.49429215204554,10,2.26543812278347,7.88130147148155,1.57723215112077,1.64140564675688,1.50035060003774,1,2,3,6
-"24","Fort Chaplin Tributary",NA,10,2,10,10,9.44055926057385,3.66863632512962,8.77121712686461,2.01955422326341,1.09628813677057,10,1,1,4,3
-"25","Nash Run",NA,10,3,8.97058038494947,9.49162145959481,10,2.85130675778872,8.98648127446675,3.13741218623777,1.09628813677057,10,10,6,5,4
+"","sci_subshed","Dumpsites","Effective Impervious Area","Temperature, water","pH","Dissolved oxygen (DO)","Escherichia coli","Turbidity","Conductivity","Nitrogen","Phosphorus, Total (as P)","Connectivity","Fish","Habitat","Macroinvertebrates"
+"1","Broad Branch",7,2,10,9.49484604605374,10,3.96201632162848,10,1.39551171022171,2.53189561427939,10,10,2,4,6
+"2","Fort Davis Tributary",1,2,10,10,10,4.56378937695466,3.40381314529514,1.28521704525446,0.950005376536892,1.78543632558786,1,1,5,5
+"3","Fort Dupont Tributary",2,8,10,10,8.19644566724721,4.39637929649141,3.667361623274,2.99612324159937,0.749069894299005,10,1,3,4,6
+"4","Fort Stanton Tributary",4,1,9.49458887028815,10,10,3.49306972579195,8.24161710963122,2.14961627380251,0.950005376536892,10,1,1,3,7
+"5","Normanstone Creek",4,1,10,8.9888961180284,10,4.46891175504634,10,1.49230558316491,2.58568816872641,10,10,3,3,6
+"6","Oxon Run",8,1,9.49482509665549,10,10,4.08034192298863,7.26446748330366,2.73668115439965,0.677223449104501,0.963293817107756,10,4,4,4
+"7","Pinehurst Branch",7,6,10,9.45561327204199,10,6.86529198320573,10,1.64381726305677,2.53189561427939,10,10,2,4,5
+"8","Rock Creek",7,1,9.03991429859265,9.63931584712039,10,4.75298766520739,8.85351874858907,3.01758638876789,2.35646823207748,10,10,5,4,5
+"9","Watts Branch",5,1,9.32024027311975,9.03799489304956,9.94283156569335,3.52383649640539,8.10990235278729,2.71307679688268,0.80598894736693,4.92721388547487,10,4,3,6
+"10","Battery Kemble Creek",10,6,10,10,10,7.17122657287291,10,1.32946707229891,1.1722461961956,10,10,3,4,7
+"11","Dalecarlia Tributary",10,4,9.49281310022025,9.49429215204554,10,2.26543812278347,7.88130147148155,1.57723215112077,1.64140564675688,1.50035060003774,1,2,3,6
+"12","Dumbarton Oaks",10,4,10,10,10,8.54782802837774,10,1.70833294620897,1.32807710704536,2.8679579947462,10,3,5,7
+"13","Foundry Branch",10,2,10,10,10,5.43588122762784,4.44089503244838,2.9615349603606,2.05698424129608,10,1,1,4,NA
+"14","Fort Chaplin Tributary",10,2,10,10,9.44055926057385,3.66863632512962,8.77121712686461,2.01955422326341,1.09628813677057,10,1,1,4,3
+"15","Fenwick Branch",10,3,9.49476657878656,10,10,6.8791964501452,10,1.75285115573104,2.32427732195356,10,10,2,3,6
+"16","Hickey Run",10,9,9.32570696570447,10,9.31006357105735,1.71733915151806,7.52739827502453,1.92353016456839,0.749069894299005,2.7927191991411,10,6,2,4
+"17","Klingle Valley Run",10,2,10,10,10,6.5392010054142,10,2.16336911176854,1.52948677601239,10,10,2,3,6
+"18","Luzon Branch",10,1,10,10,10,2.74149789121648,5.16856938057974,1.68139016788936,2.13654818496565,2.91985046082419,10,2,3,6
+"19","Reservation 630",10,3,9.49484222518253,10,10,4.89875662885154,6.54810880322023,1.95694969141548,2.32427732195356,10,10,4,7,7
+"20","Nash Run",10,3,8.97058038494947,9.49162145959481,10,2.85130675778872,8.98648127446675,3.13741218623777,1.09628813677057,10,10,6,5,4
+"21","Pope Branch",10,3,10,10,10,6.70307871860358,4.63848137391428,2.04750999680075,0.950005376536892,10,1,4,6,8
+"22","Portal Branch",10,3,10,8.98692894850945,10,4.24400479220216,6.90674993457207,1.02448007263146,2.74453544775747,10,10,1,3,6
+"23","Piney Branch",10,1,10,10,10,6.24485935433058,10,1.37920467622303,2.43350524767764,10,10,3,2,4
+"24","Soapstone Creek",10,1,10,8.98764540312439,10,6.80566463860387,10,1.91408087817814,2.53189561427939,2.88434296861746,10,2,3,6
+"25","Texas Avenue Tributary",10,3,10,10,10,3.54658539291944,7.3375495518317,1.74050116850977,0.837784090876652,10,1,1,5,3

vignettes/pre-processing.Rmd

@@ -20,7 +20,7 @@ knitr::opts_chunk$set(
 
 -   The R functions assess_trash() and assess_dumpsites() require dataframe inputs of processed RSA reach data and RSA point data (dumpsites only)
 
--   The watershed layer included in RSA database was not used due to issue found. For example, layer "Watersheds_Notes_RSA2021" has missing area in Rock Creek. Instead used: [DC Subwatersheds  Open Data Layer](https://opendata.dc.gov/datasets/dc-subwatersheds/explore?location=38.890772%2C-77.021832%2C12.98&showTable=true).
+-   The watershed layer included in RSA database was not used due to issue found. For example, layer "Watersheds_Notes_RSA2021" has missing area in Rock Creek. Instead used: [DC Subwatersheds Open Data Layer](https://opendata.dc.gov/datasets/dc-subwatersheds/explore?location=38.890772%2C-77.021832%2C12.98&showTable=true).
 
 <br>
 
@@ -34,26 +34,29 @@ knitr::opts_chunk$set(
 
     -   This step is needed so that the GlobalID information will be included in the intersected table
 
-2.  Intersect [DC Subwatersheds  Open Data Layer](https://opendata.dc.gov/datasets/dc-subwatersheds/explore?location=38.890772%2C-77.021832%2C12.98&showTable=true) with StreamPoints layer
+2.  Intersect [DC Subwatersheds Open Data Layer](https://opendata.dc.gov/datasets/dc-subwatersheds/explore?location=38.890772%2C-77.021832%2C12.98&showTable=true) with StreamPoints layer
 
-3.  Run the 'Add Attribute Index' tool:
+3.  Run the 'Add Attribute Index' tool on the Intersected layer so that ID field is indexed:
 
     -   Field to Index: GlobalID_copy
 
     -   Index Name: GlobalID_index
 
 4.  Join StreamPoints attributes table to StreamPoints feature layer. See settings in screenshot below:
 
+    -   If 'One to Many" Join Operation not an option, make sure attribute table and feature layer are in the same geodatabase
+
     ![](figures/rsa_join.png){width="326"}
 
-5.  Export joined StreamPoints table to Excel
+5.  Export joined StreamPoints by using 'Table to Excel' geoprocessing tool
 
     -   Save file to R package data folder
+
     -   Update file name input variable in workflow.R file
 
 6.  In the input variables section of workflow.R, update the field name prefix variables (if needed)
 
-7.  Repeat steps 1, 3,4, 5 and 6 using StreamReaches feature layer and attribute table
+7.  Repeat steps 1, 3, 4, 5 and 6 using StreamReaches feature layer and attribute table
 
     -   Skip Step 2 since subshed information is already included as a field in the StreamReaches feature layer
 

workflow.R

@@ -18,18 +18,13 @@ df_point <- readxl::read_excel("data/StreamPoints_20241105_INT.xlsx")
 start_date <- "2015-07-01"
 end_date <- "2020-06-30"
 
-# Date ranges used for filtering RSA data (for trees and dumpsites)
-rsa_start_date <- "2020-01-01"
-rsa_end_date <- "2024-12-31"
-
-
 # Field name prefixes for RSA dataset
 # Prefixes change depending on layer and table names pulled from geodatabase
 reach_prefix_from_table <- "StreamReachAttributes"  # Should match name of stream reach attribute table from RSA .gdb
 reach_prefix_from_layer <- "StreamReaches"          # Should match name of stream reach polyline layer from RSA .gdb
 
 point_prefix_from_table <- "StreamPointAttributes"  # Should match name of stream point attribute table from RSA .gdb
-point_prefix_from_layer <- "StreamPoints_Intersect" # Should match name of intersected stream point layer from RSA .gdb
+point_prefix_from_layer <- "StreamPoints_Nov2024_Intersect" # Should match name of intersected stream point layer from RSA .gdb
 
 
 
@@ -112,18 +107,19 @@ macro <- macroinvertebrate_summary %>% dplyr::select(sci_subshed,
 
 
 # Assess RSA Data
-trash <- assess_trash(df_reach, rsa_start_date, rsa_end_date, reach_prefix_from_table, reach_prefix_from_layer)
+# trash <- assess_trash(df_reach, reach_prefix_from_table, reach_prefix_from_layer)
 dumpsite <- assess_dumpsites(df_point, df_reach,
-                             rsa_start_date, rsa_end_date,
                              reach_prefix_from_table, reach_prefix_from_layer,
                              point_prefix_from_table, point_prefix_from_layer)
 
 # EIA
 eia <- assess_eia()
 
 # Compile scores
-all_scores <- trash[["score"]] %>%
-  dplyr::full_join(dumpsite[["score"]]) %>%
+all_scores <-
+  # trash[["score"]] %>%
+  # dplyr::full_join(dumpsite[["score"]]) %>%
+  dumpsite[["score"]] %>%
   dplyr::full_join(eia[["score"]]) %>%
   dplyr::full_join(temp[["score"]]) %>%
   dplyr::full_join(ph[["score"]]) %>%