minor edits to R scripts for CANADA and NZ

merge.data.CANADA.R

@@ -17,15 +17,7 @@ species.clean <- read.csv("./data/raw/DataCanada/FIA_REF_SPECIES.csv",stringsAsF
 ######################################
 ## MASSAGE TRAIT DATA
 ############################
-# ## Compute maximum height per species plus sd from observed height to add variables to the traits data base
-# ## Because we have two heights, then take the max of the two heights and then bootstrap 
-# q <- log10(apply(data.canada[,c("ht1","ht2")],1,max,na.rm=T)); q[!is.finite(q)] <- NA
-# res.quant.boot <- t(sapply(levels(factor(data.canada[["Species"]])),FUN=f.quantile.boot,R=1000,x=q,fac=(data.canada[["Species"]])))
-# #max.heights <- read.csv("/media/fhui/Lexar/Career & Work/GKunstler_competition/data/raw/DataCanada/MaximumHeigth.csv", header = T)
-# # 
-# # ## create data base
-# data.max.height <- data.frame(code=rownames(res.quant.boot),Max.height.mean=res.quant.boot[,1],Max.height.sd=res.quant.boot[,2],Max.height.nobs=res.quant.boot[,3])
-# rm(res.quant.boot)
+## HEIGHT DATA FOR TREE MISSING
 
 ##########################################
 ## FORMAT INDIVIDUAL TREE DATA
@@ -39,7 +31,7 @@ data.canada$D <- data.canada[["InitDBH"]]; data.canada$D[data.canada$D == 0] <-
 data.canada$dead <- as.numeric(data.canada$FinalDBH == -999) ## dummy variable for dead tree 0 alive 1 dead
 data.canada$sp <- as.character(data.canada[["Species"]]) ## species code
 data.canada$plot <- (data.canada[["PLOT_ID"]]) ## plot code
-data.canada$htot <- rep(NA,length(data.canada[["Species"]]))## height of tree in m - MISSING
+data.canada$htot <- rep(NA,length(data.canada[["Species"]])) ## height of tree in m - MISSING
 data.canada$tree.id <- data.canada$PLOTTREE ## tree unique id
 data.canada$sp.name <- NA; 
 for(i in 1:length(unique(data.canada$sp))) { 
@@ -47,7 +39,9 @@ for(i in 1:length(unique(data.canada$sp))) {
 	data.canada$sp.name[which(data.canada$sp == unique(data.canada$sp)[i])] <- species.clean$COMMON_NAME[which(v == unique(data.canada$sp)[i])] }
 
 
-############################
+######################
+## ECOREGION
+###################
 ## merge greco to have no ecoregion with low number of observation
 greco <- read.csv(file = "./data/raw/DataCanada/EcoregionCodes.csv", header = T, sep = "\t") 
 
@@ -62,7 +56,9 @@ table(data.canada$Ecocode)
 # ## PA1219 looks to be similar to PA1209; merge them together
 # data.canada$eco_codemerged <- combine_factor(data.canada$eco_code, c(1:8,6,9))
 
-#######################
+######################
+## PERCENT DEAD
+###################
 ## variable percent dead/cannot do with since dead variable is missing
 ## compute numer of dead per plot to remove plot with disturbance
 perc.dead <- tapply(data.canada[["dead"]],INDEX=data.canada[["plot"]],FUN=function.perc.dead)

merge.data.NZ.R

@@ -33,7 +33,11 @@ data.nz$plot <- data.nz$plid
 data.nz$htot <- rep(NA,length(data.nz[["sp"]])) ## I ASSUME THE "height.m" IN data.trait IS A MAX HEIGHT, WHICH IS NOT WHAT WE WANT HERE?
 data.nz$tree.id <- data.nz[["tag"]]; data.nz$tree.id <- gsub("__", "_",data.nz$tree.id); data.nz$tree.id <- gsub("_", ".",data.nz$tree.id) ## tree unique id
 
-#### change coordinates system of Easting Northing to be in lat long WGS84 - DON'T KNOW THE EPSG CODE HERE
+##########################################
+## CHANGE COORDINATE SYSTEM
+#############
+## DON'T KNOW THE EPSG CODE HERE
+#### change coordinates system of Easting Northing to be in lat long WGS84
 data.nz <- merge(data.plot[,c(1,3,4)], data.nz, by = "plid")
 library(sp); 
 #library(dismo); library(rgdal); 
@@ -52,11 +56,15 @@ data.nz$Lon <- coordinates(data.sp2)[,"Easting"]; data.nz$Lat <- coordinates(dat
 ## points(data.sp2,cex=0.2,col="red")
 rm(data.sp,data.sp2)
 
-############################
-## DON'T KNOW WHICH VARIABLE TO USE FOR ECOREGION =(
+######################
+## ECOREGION
+###################
+## DON'T KNOW WHICH VARIABLE TO USE FOR ECOREGION
 greco <- greco[,c("tree.id","BIOME","eco_code")]
 
-#######################
+######################
+## PERCENT DEAD
+###################
 ## variable percent dead - MISSING
 data.nz$perc.dead <- NA