#!/usr/bin/env Rscript

##### FORMAT TRAIT FOR Sweden
source("R/find.trait/trait.fun.R")

### read species names
data.tree <- read.csv("output/formatted/Sweden/tree.csv", stringsAsFactors = FALSE)
species.clean <- data.frame(sp=data.tree[!duplicated(data.tree[["sp"]]),"sp"],
                             Latin_name=data.tree[!duplicated(data.tree[["sp"]]),"sp.name"],
                             Latin_name_syn=data.tree[!duplicated(data.tree[["sp"]]),"sp.name"],
                             stringsAsFactors =FALSE)
## delete the sp code with no species
species.clean <- subset(species.clean,subset=!is.na(species.clean$Latin_name))

## select column to keep

## read in data
data.TRY.std <- readRDS("output/formatted/TRY/data.TRY.std.rds")
## read France max height
max.height <- read.csv(file="output/formatted/France/max.height.csv", stringsAsFactors = FALSE)
## load latin name France
data.tree <- read.csv("output/formatted/France/tree.csv", stringsAsFactors = FALSE)
species.clean2 <- data.frame(sp=data.tree[!duplicated(data.tree[["sp"]]),"sp"],
                             Latin_name=data.tree[!duplicated(data.tree[["sp"]]),"sp.name"],
                             Latin_name_syn=data.tree[!duplicated(data.tree[["sp"]]),"sp.name"],
                             stringsAsFactors =FALSE)
## delete the sp code with no species
#species.clean2 <- subset(species.clean2,subset=!is.na(species.clean2$Latin_name)) ## add latin name
max.height <- merge(subset(max.height,select=c("sp","Max.height.mean","Max.height.sd","Max.height.nobs")),species.clean2,by="sp") 
## extract traits and height
data.traits <- fun.extract.format.sp.traits.TRY(sp=species.clean[["sp"]],sp.syno.table=species.clean,
                                                data=data.TRY.std)
#data.traits <- merge(data.traits,subset(max.height,select=c("Latin_name","Max.height.mean","Max.height.sd")),by="Latin_name",all.x=TRUE,all.y=FALSE)
data.traits <- merge(data.traits,subset(max.height,select=c("Latin_name","Max.height.mean","Max.height.sd")),
                     by="Latin_name",all.x=TRUE,all.y=FALSE)
data.traits$Max.height.genus <- FALSE
# genus mean for height
height.genus.DF <- do.call("rbind",lapply(data.traits$Latin_name,fun.compute.mean.genus,max.height,
                                          "Max.height.mean"))
data.traits[is.na(data.traits[["Max.height.mean"]]),
            c("Max.height.mean","Max.height.sd","Max.height.genus")] <- height.genus.DF[is.na(data.traits[["Max.height.mean"]]),]

#### Assume sp.30 Betula spp is mainly sp.31 Betula pendula and sp.32 Betula pubsecens and take the mean of that
data.traits$Leaf.N.mean[data.traits$sp=="sp.30"] <- mean(data.traits$Leaf.N.mean[data.traits$sp %in%
                            c("sp.31","sp.32")])
data.traits$Seed.mass.mean[data.traits$sp=="sp.30"] <- mean(data.traits$Seed.mass.mean[data.traits$sp %in%
                               c("sp.31","sp.32")])
data.traits$SLA.mean[data.traits$sp=="sp.30"] <- mean(data.traits$SLA.mean[data.traits$sp %in%
                         c("sp.31","sp.32")])
data.traits$Wood.density.mean[data.traits$sp=="sp.30"] <- mean(data.traits$Wood.density.mean[data.traits$sp
                                  %in% c("sp.31","sp.32")])
data.traits$Max.height.mean[data.traits$sp=="sp.30"] <- mean(data.traits$Max.height.mean[data.traits$sp
                                %in% c("sp.31","sp.32")])

data.traits$Leaf.N.genus[data.traits$sp=="sp.30"] <- FALSE
data.traits$Seed.mass.genus[data.traits$sp=="sp.30"] <- FALSE
data.traits$SLA.genus[data.traits$sp=="sp.30"] <- FALSE
data.traits$Wood.density.genus[data.traits$sp=="sp.30"] <- FALSE
data.traits$Max.height.genus[data.traits$sp=="sp.30"] <- FALSE

## do the same for quercus robur and quercus petraea

data.quercus <-(data.frame(sp=c("sp.500","sp.501"),
                           Latin_name=c("Quercus robur","Quercus petraea"),
                           Latin_name_syn=c("Quercus robur","Quercus petraea")))
data.quercus <- fun.extract.format.sp.traits.TRY(sp=data.quercus[["sp"]],
                                                 sp.syno.table=data.quercus,
                                                 data=data.TRY.std)

data.traits$Leaf.N.mean[data.traits$sp=="sp.51"] <- mean(data.quercus$Leaf.N.mean)
data.traits$Seed.mass.mean[data.traits$sp=="sp.51"] <- mean(data.quercus$Seed.mass.mean)
data.traits$SLA.mean[data.traits$sp=="sp.51"] <- mean(data.quercus$SLA.mean)
data.traits$Wood.density.mean[data.traits$sp=="sp.51"] <- mean(data.quercus$Wood.density.mean)
data.traits$Max.height.mean[data.traits$sp=="sp.51"] <- mean(max.height$Max.height.mean[max.height$Latin_name
                                %in% c("Quercus robur","Quercus petraea")])

data.traits$Leaf.N.genus[data.traits$sp=="sp.51"] <- FALSE
data.traits$Seed.mass.genus[data.traits$sp=="sp.51"] <- FALSE
data.traits$SLA.genus[data.traits$sp=="sp.51"] <- FALSE
data.traits$Wood.density.genus[data.traits$sp=="sp.51"] <- FALSE
data.traits$Max.height.genus[data.traits$sp=="sp.51"] <- FALSE

### TODO ADD GENUS MEAN FOR HEIGHT IF SPECIES IS MISSING
write.csv(data.traits,file="output/formatted/Sweden/traits.csv",row.names = FALSE)