Merge branch 'master' of github.com:noaa-nwfsc/FishSET into policy_ad…

…ditions

R/create_distance_matrix.R

@@ -52,6 +52,7 @@ create_dist_matrix <-
     warning("CRS is not specfied, distance matrix will be created using WGS 84 (4326).",
             call. = FALSE)
   }
+
   # occasion ----
 
   ## Centroid ----
@@ -62,20 +63,17 @@ create_dist_matrix <-
 
     fromXY <- dataset[zone_ind, o_var]
 
-      if (occasion == "zonal centroid") cent_tab <- zone_cent
-      else if (occasion == "fishing centroid") cent_tab <- fish_cent 
+    if (occasion == "zonal centroid") cent_tab <- zone_cent
+    else if (occasion == "fishing centroid") cent_tab <- fish_cent 
 
-    if (o_var == zoneID | !any(fromXY[[o_var]] %in% port$Port_Name)) {
-      # o_var == zoneID = single haul
-      # otherwise, multi-haul w/ prev area variable
+    if (o_var == zoneID){ # o_var == zoneID = single haul
       # join centroid lon-lat by zoneID
       join_by <- stats::setNames("ZoneID", o_var)
       fromXY <- dplyr::left_join(fromXY, cent_tab, by = join_by)
 
     } else { # Previous Area (multi-haul)
       # include port table previous area if o_var contains port names (this happens 
       # when creating a previous area/starting loc variable and the port is not within a zone)
-
       area_tab <- 
         do.call(rbind, 
                 lapply(list(port, cent_tab), function(x) {
@@ -125,6 +123,7 @@ create_dist_matrix <-
     fromXY <- dataset[zone_ind, occasion_var]
   }
 
+
   # alt_var ----
 
   ## centroid ----

R/create_startingloc.R

@@ -1,8 +1,9 @@
 #' Create starting location variable
 #'
 #' Creates a variable containing the zone/area location of a vessel when choice of 
-#' where to fish next was made. This variable is required for the full information 
-#' model with Dahl's correction (\code{\link{logit_correction}}).
+#' where to fish next was made. This variable is required for data with multiple sets
+#' or hauls in a single trip and for the full information model with 
+#' Dahl's correction (\code{\link{logit_correction}}).
 #'
 #' @param dat  Primary data containing information on hauls or trips.
 #'   Table in FishSET database contains the string 'MainDataTable'.
@@ -12,6 +13,9 @@
 #' @param port Port data. Contains columns: Port_Name, Port_Long, Port_Lat. 
 #'   Table is generated using the \code{\link{load_port}} and saved in the FishSET 
 #'   database as the project and port table, for example 'pollockPortTable'.
+#' @param port_name Character string indicating the column in port table that contains the port name
+#' @param port_lon Character string indication the column in port table that contains port longitude
+#' @param port_lat Character string indication the column in port table that contains port latitude
 #' @param trip_id Variable in \code{dat} that identifies unique trips.
 #' @param haul_order Variable in \code{dat} containing information on the order 
 #'   that hauls occur within a trip. Can be time, coded variable, etc.
@@ -45,23 +49,24 @@
 #' )
 #' }
 #
-create_startingloc <-
-  function(dat,
-           project = NULL,
-           spat,
-           port,
-           trip_id,
-           haul_order,
-           starting_port,
-           zoneID,
-           spatID, 
-           name = "startingloc") {
+create_startingloc <- function(dat,
+                               project = NULL,
+                               spat,
+                               port,
+                               port_name,
+                               port_lon,
+                               port_lat,
+                               trip_id,
+                               haul_order,
+                               starting_port,
+                               zoneID,
+                               spatID, 
+                               name = "startingloc") {
 
   # TODO: consider removing assignment_column() functionality
   # TODO: Change this to required? project is required for nearly every other function
   # why not here?
   if (is.null(project)) {
-
     project <- sub("\\MainDataTable", "", dat)
   }
 
@@ -78,29 +83,29 @@ create_startingloc <-
   # Call in spatial data
   spat_out <- data_pull(spat, project)
   spatdat <- spat_out$dataset
-  spat <- parse_data_name(dat, "spat", project)
+  spat <- parse_data_name(spat, "spat", project)
 
+  # Make sure columns are present in primary data table
   column_check(dataset, cols = c(trip_id, haul_order, starting_port, zoneID))
 
-  column_check(spatdat, cols = c(zoneID))
+  # Make sure columns are present in spat table
+  column_check(spatdat, cols = c(spatID))
 
- # name <- ifelse(is_empty(name), "startingloc", name)
+  # Make sure new column name is unique and doesn't already exist
   name <- name_check(dataset, name, repair = TRUE)
 
   port.table <- assignment_column(
     dat = port.table, project = project, spat = spatdat, hull.polygon = FALSE, 
-    lon.dat = "Port_Long", lat.dat = "Port_Lat", cat = spatID, closest.pt = TRUE, 
+    lon.dat = port_lon, lat.dat = port_lat, cat = spatID, closest.pt = TRUE, 
     log.fun = FALSE, bufferval = 100 # need to consider how this affects things
   )
 
   # Create starting loc variable
   # TODO: trip_id is currently required; can't be NULL. Resolve.
   if (is.null(trip_id)) {
-
     dataset <- dataset[order(dataset[[haul_order]]), ]
 
   } else {
-
     dataset <- dataset[order(dataset[[trip_id]], dataset[[haul_order]]), ]
   }
 
@@ -109,24 +114,23 @@ create_startingloc <-
 
   # Make starting of trips set to zone of starting port
   if (!is.null(trip_id)) {
-
-    rownumbers <- match(trimws(dataset[tapply(seq_along(dataset[[trip_id]]), dataset[[trip_id]], min), starting_port]), port.table$Port_Name)
+    rownumbers <- match(
+      trimws(dataset[tapply(seq_along(dataset[[trip_id]]), dataset[[trip_id]], min), starting_port][[1]]), 
+      port.table[port_name])
 
     if (any(is.na(rownumbers))) { 
-
       warning('NAs produced. At least one disembarked port was not found in the port table.')
     }
 
     newvar[tapply(seq_along(dataset[[trip_id]]), dataset[[trip_id]], min)] <- port.table[rownumbers, 'ZoneID']
 
   } else {
-
     rownumbers <- match(trimws(dataset[1, starting_port]), port.table$Port_Name)
     newvar[1] <- port.table[rownumbers, zoneID]
   }
 
-  g <- cbind(dataset, newvar)
-  colnames(g)[dim(g)[2]] = name
+  g <- cbind(dataset, as.character(newvar))
+  colnames(g)[dim(g)[2]] <- name
 
   create_startingloc_function <- list()
   create_startingloc_function$functionID <- "create_startingloc"

R/data.R

@@ -7,21 +7,12 @@
 #' \describe{
 #'   \item{TRIPID}{Randomly assigned trip ID number.}
 #'   \item{DATE_TRIP}{Date of landing.}
-#'   \item{scallop_fishing_year}{Scallop fishing year.}
-#'   \item{OPERNUM}{Randomly assigned captains Identification number.}
 #'   \item{PERMIT.y}{Randomly assigned six-digit vessel fishing permit number.}
 #'   \item{TRIP_LENGTH}{Days calculated from the elapsed time between the 
 #'   date-time sailed and date-time landed; this is a measure of days absent.}
-#'   \item{DEALER_RPT_ID}{}
 #'   \item{GEARCODE}{Fishing gear used on the trip.}
-#'   \item{dbsource}{Primary data source for observation.}
-#'   \item{geoid}{10 digit county subdivision from US Census.}
-#'   \item{namelsad}{Port of landing.}
 #'   \item{port_lat}{Latitude of the geoid.}
 #'   \item{port_lon}{longitude of the geoid.}
-#'   \item{previous_namelsad}{Previous port of landing.}
-#'   \item{previous_state_fips}{Previous 2 digit state fips code.}
-#'   \item{previous_geoid}{Previous geoid.}
 #'   \item{previous_port_lat}{Previous latitude of geoid.}
 #'   \item{previous_port_lon}{Previous longitude of geoid.}
 #'   \item{Plan Code}{Portion of the VMS declaration code that identifies the 
@@ -38,8 +29,6 @@
 #'   99th percentile value, respectively.}
 #'   \item{DDLAT}{The latitude reported on a VTR (Vessel Trip Reports).}
 #'   \item{DDLON}{The longitude reported on a VTR (Vessel Trip Reports).}
-#'   \item{MN30SQID}{Unique identifier assigned to a thirty minute square.}
-#'   \item{MN10SQID}{Unique identifier assigned to a ten minute square.}
 #'   \item{NAME}{Name of wind lease which is found within a given ten minute square.}
 #'   \item{ZoneID}{FishSET's version of a ten minute square.}
 #'   \item{POUNDS}{Live pounds.}
@@ -100,49 +89,4 @@
 #'   \item{NAME}{Name of wind lease.}
 #' }
 #' 
-"windLease"
-
-
-#' Alaskan Ports
-#' 
-#' A dataframe of Alaskan ports.
-#' 
-#' @format `alaskaPorts`
-#' A dataframe with three columns and 88 rows:
-#' \describe{
-#'   \item{PORT}{Name of port.}
-#'   \item{LONGITUDE}{LONGITUDE of port.}
-#'   \item{LATITUDE}{LATITUDE of port.}
-#' }
-#' 
-"alaskaPorts"
-
-
-#' Alaskan NMFS Areas
-#' 
-#' A spatial dataset of Alaskan NMFS areas.
-#' 
-#' @format `alaskaNMFSAreas`
-#' A simple features multipolygon dataframe with 10 features and two fields:
-#' \describe{
-#'   \item{NMFS_AREA}{NMFS area number.}
-#'   \item{geometry}{Coordinates for NMFS area.}
-#' }
-#' 
-"alaskaNMFSAreas"
-
-
-#' Pollock Data
-#'
-#' @description
-#' Bering Sea pollock data from 2011
-#'
-#' @format `PollockData` 
-#' A dataframe with 36 columns and 839 rows:
-#' \describe{
-#' }
-#'
-#' @usage data(PollockData)
-#'
-"PollockData"
-
+"windLease"

R/map_viewer.R

@@ -44,13 +44,12 @@ map_viewer <- function(dat, project, spat, avd, avm, num_vars, temp_vars, id_var
   #'            avd = 'ZoneID', avm = 'TEN_ID', num_vars = 'LANDED_thousands', 
   #'            temp_vars = 'DATE_TRIP', lon_start = 'previous_port_lon', 
   #'            lat_start = 'previous_port_lat', lon_end = 'DDLON', 
-  #'            lat_end = 'DDLAT', id_vars = 'previous_namelsad')
+  #'            lat_end = 'DDLAT')
   #'    
   #' # Plot observed fishing locations        
   #' map_viewer(scallopMainDataTable, 'scallop', "scallopTMSSpatTable", 
   #'            avd = 'ZoneID', avm = 'TEN_ID', num_vars = 'LANDED_thousands', 
-  #'            temp_vars = 'DATE_TRIP', lon_start = 'DDLON', lat_start = 'DDLAT', 
-  #'            id_vars = 'previous_namelsad')
+  #'            temp_vars = 'DATE_TRIP', lon_start = 'DDLON', lat_start = 'DDLAT')
   #' 
   #' #Plot haul path
   #' map_viewer(pollockMainDataTable, 'pollock', spat=spatdat, avd='NMFS_AREA',

R/view_grid_dat.R

@@ -20,10 +20,6 @@ view_grid_dat <- function(grid, project, lon, lat, value, split_by = NULL,
   #' @export
   #' @import ggplot2
   #' @importFrom rlang sym
-  #' @examples 
-  #' \dontrun{
-  #' view_grid_dat('SST', "pollock", "lon", "lat", value = "analysed_sst")
-  #' }
   #'
 
   out <- data_pull(grid, project)