Update QA

R/QA.R

@@ -1,7 +1,6 @@
-QA = function(known, isoscape, bySite = TRUE, 
-              valiStation = 1, valiTime = 50, by = 2, 
-              prior = NULL, mask = NULL, setSeed = TRUE, 
-              name = NULL){
+QA = function(known, isoscape, bySite = TRUE, valiStation = 1, 
+              valiTime = 50, recal = TRUE, by = 2, prior = NULL, 
+              mask = NULL, setSeed = TRUE, name = NULL){
 
   #space to handle messages and warnings
   mstack = wstack = character(0)
@@ -123,6 +122,21 @@ QA = function(known, isoscape, bySite = TRUE,
     stop("invalid object provided for known")
   }
 
+  #check recal
+  if(class(recal) != "logical"){
+    stop("recal must be logical")
+  }
+  if(!recal){
+    valiTime = nrow(known)
+    valiStation = 1
+    bySite = FALSE
+  }
+
+  #check valiTime
+  if(valiTime < 2){
+    stop("valiTime must be an integer greater than 1")
+  }
+
   #check valiStation
   if(bySite){
     if(valiStation > (length(unique(known$Site_ID)) - 3)){
@@ -136,11 +150,6 @@ QA = function(known, isoscape, bySite = TRUE,
     }
   }
 
-  #check valiTime
-  if(valiTime < 2){
-    stop("valiTime must be an integer greater than 1")
-  }
-
   #check by
   if(!(as.integer(by) == by) || by < 1 || by > 25){
     stop("by must be an integer between 1 and 25")
@@ -157,7 +166,6 @@ QA = function(known, isoscape, bySite = TRUE,
   if(!is.logical(setSeed)){
     stop("setSeed must be logical")
   }
-
   if(setSeed){
     set.seed(100)
   }
@@ -169,11 +177,15 @@ QA = function(known, isoscape, bySite = TRUE,
     rowLength = nrow(known)
     ids = seq_len(rowLength)
   }
-  val_stations = sort(sample(ids, valiStation, replace = FALSE))
-  for (i in seq_len(valiTime)[-1]){
-    val_stations = rbind(val_stations, 
-                          sort(sample(ids, valiStation, 
-                                      replace = FALSE)))
+  if(recal){
+    val_stations = sort(sample(ids, valiStation, replace = FALSE))
+    for (i in seq_len(valiTime)[-1]){
+      val_stations = rbind(val_stations, 
+                           sort(sample(ids, valiStation, 
+                                       replace = FALSE)))
+    }
+  } else{
+    val_stations = matrix(ids, nrow = rowLength)
   }
 
   xx = seq(1, 101, by)
@@ -197,28 +209,32 @@ QA = function(known, isoscape, bySite = TRUE,
       m = known[-val_stations[i,],]
     }
 
-    if(ni > 1){
-      rescales = list()
-      for(j in 1:ni){
-        m_sub = m
-        m_sub@data = m_sub@data[,(j * 2 - 1):(j * 2)]
-        class(m_sub) = "QAData"
-        rescales[[j]] = withCallingHandlers(
+    if(recal){
+      if(ni > 1){
+        rescales = list()
+        for(j in 1:ni){
+          m_sub = m
+          m_sub@data = m_sub@data[,(j * 2 - 1):(j * 2)]
+          class(m_sub) = "QAData"
+          rescales[[j]] = withCallingHandlers(
+            message = addm,
+            warning = addw,
+            calRaster(m_sub, isoscape[[j]], mask, genplot = FALSE, 
+                      verboseLM = FALSE)[[1]]
+          )
+        }
+        rescale = isoStack(rescales)
+      } else{
+        class(m) = "QAData"
+        rescale = withCallingHandlers(
           message = addm,
           warning = addw,
-          calRaster(m_sub, isoscape[[j]], mask, genplot = FALSE, 
-                    verboseLM = FALSE)[[1]]
+          calRaster(m, isoscape, mask, genplot = FALSE, 
+                    verboseLM = FALSE)
         )
-      }
-      rescale = isoStack(rescales)
+      } 
     } else{
-      class(m) = "QAData"
-      rescale = withCallingHandlers(
-        message = addm,
-        warning = addw,
-        calRaster(m, isoscape, mask, genplot = FALSE, 
-                            verboseLM = FALSE)
-      )
+      rescale = isoscape
     }
 
     pd = withCallingHandlers(

Rmarkdown/assignR.Rmd

@@ -1,8 +1,7 @@
 ---
-title: "assignR Examples"
+title: "assignR Examples - Dev Release"
 author: "Gabe Bowen, Chao Ma"
-params:
-  date:
+date: "`r format(Sys.Date(), '%B %d, %Y')`"
 output: 
   html_document:
     toc: true
@@ -320,7 +319,9 @@ qtlRaster(Ll_up, threshold = 0.1)
 *****
 # Quality Analysis
 
-How good are the geographic assignments? What area or probability threshold should be used? Is it better to use isoscape *A* or *B* for my analysis? These questions can be answered through split-sample validation using `QA`.
+How good are the geographic assignments? What area or probability threshold should be used? Is it better to use isoscape *A* or *B* for my analysis? The `QA` function is designed to help answer these questions. 
+
+`QA` uses known-origin data to test the quality of isotope-based assignments and returns a set of metrics from this test. The default method conducts a split-sample test, iteratively splitting the dataset and using part to calibrate the isoscape(s) and the rest to evaluate assignment quality. The option `recal = FALSE` allows `QA` to be run without the `calRaster` calibration step. This provides a less complete assessment of methodological error but allows evaluation of assignments to tissue isoscapes made outside of the `QA` function, for example those calibrated using a different known-origin dataset or made through spatial modeling of tissue data, directly. 
 
 We will run quality assessment on the Loggerhead shrike known-origin dataset and precipitation isoscape. These analyses take some time to run, depending on the number of stations and iterations used. 
 

Rmarkdown/renderVignette.R

@@ -1,5 +1,4 @@
 rmarkdown::render(
   "Rmarkdown/assignR.Rmd",
-  params = list(date = format(Sys.Date(), "%B %d, %Y")),
   output_file = "../docs/index.html"
 )

man/QA.rd

@@ -7,12 +7,13 @@ Quality assessment of geographic assignments
 }
 
 \description{
-How well does a given isoscape and known origin data set constrain the geographic origin of samples? Uses iterative re-sampling of the known origin data set to evaluate sample assignments and reports a suite of quality metrics.
+How well does a given isoscape and/or known origin data set constrain the geographic origin of samples? Uses iterative re-sampling of known origin data to evaluate sample assignments and reports a suite of quality metrics.
 }
 
 \usage{
 QA(known, isoscape, bySite = TRUE, valiStation = 1, valiTime = 50, 
-  by = 2, prior = NULL, mask = NULL, setSeed = TRUE, name = NULL)
+  recal = TRUE, by = 2, prior = NULL, mask = NULL, setSeed = TRUE, 
+  name = NULL)
 }
 
 \arguments{
@@ -24,8 +25,9 @@ subOrigData, list of subOrigData, or SpatialPointsDataFrame. Known-origin tissue
   \item{bySite}{logical. Resample known by site (TRUE) or by sample (FALSE)?}
   \item{valiStation}{numeric. How many sites or samples from known are withheld for validation? Must be two or more smaller than the length of \code{known}.
 }
-  \item{valiTime}{numeric. How many times do you want to randomly draw validation samples and run the validation? Must be an integer equal to or greater than one. 
+  \item{valiTime}{numeric. How many times do you want to randomly draw validation samples and run the validation? Must be an integer greater than one.
 }
+  \item{recal}{logical. Recalibrate the isoscape(s) using the known-origin data? If FALSE, \code{isoscape} should be a calibrated product appropriate to the samples, and a single iteration is run for each sample in \code{known}; parameters \code{bySite}, \code{valiStation}, and \code{valiTime} are ignored.}
   \item{by}{integer. Threshold increment to use in evaluating assignment performance. Must be between 1 and 25.}
   \item{prior}{raster. Optional raster layer with prior probabilities, which has the same projection, resolution and extent as \code{isoscape}.
 }