library(readr)
library(ggplot2)
library(tidyr)
library(purrr)
library(reshape2)
library(Tplyr)
library(stringr)
library(rlang)
library(tidystats)
library(dplyr)
library(lazyeval)
library(corrplot)


GGMMYY<-"..." #to be changed according to MPs group/ file name




myPath <- "..." #your path for saving folders 
#change with your output_data path
batch<-"batch1"

```{r verify reference}
tempR = as.vector(list.files(paste0(myPath,GGMMYY), pattern ="areaREF.csv")) #data from ImageJ, "..." your data folder
#tempR <- tempR[str_detect(tempR, batch)] 
namesR<- paste0(myPath,GGMMYY,"/",tempR)

myfilesR = lapply(namesR, read.csv)
DF_RL<-lapply(myfilesR, "[", c(2,3))
DF_R<-bind_rows(DF_RL, .id = "picture_number")
SMZR<- melt(DF_R,"picture_number")%>%group_by(variable)
SMZR<-summarise(SMZR,mean = mean(value),max=max(value),min=min(value), D = (max(value)-min(value)))
SMZR<-cbind(SMZR[,1],(round(SMZR[,2:5],digits=3)))
write.csv(SMZR,paste0(myPath,GGMMYY,"/",GGMMYY,batch,"Reference.csv")) #depends on your saving folder
rm(SMZR,DF_RL,DF_R,namesR,tempR,myfilesR)
```

```{r load files of results from ImageJ and prepare file list}

temp = list.files(paste0(myPath,GGMMYY), pattern = "part.csv") 
names<- paste0(paste0(myPath,GGMMYY,"/",temp))
#prepare files giving an individual ID to each particle
myfiles = lapply(names, read.csv)
for (i in 1:length(myfiles)){
 myfiles[[i]]$ID_list_row=paste0("p_",i,"_",seq.int(1:nrow(myfiles[[i]])))
}
# Remove column by name in each element of the list
ToRemove<-c("Angle", "FeretX", "FeretY","FeretAngle","MinFeret", "BX","BY","Width","Height")
myfiles = map(myfiles, ~ (.x %>% select(-all_of(ToRemove))))
rm(ToRemove,i)

for (i in 1:length(myfiles)){
myfiles[[i]] <-myfiles[[i]][,c(11,4,5,2,3,6,7,8,9,10)]
}
rm(i,names,temp)
```

```{r filter list} 
#from records with area = 0
myfiles_f<-list()
df_f<-data.frame()
for (i in 1:length(myfiles)){
df_f<-myfiles[[i]]
 df_f<-df_f[df_f$Area <= 0.5,] #to remove background noise, keeping possible fragmented particles. Use 0.5 for S25,P25. For all others use 0.05
 if(nrow(df_f)>0){
  myfiles_f[[i]] <- myfiles[[i]][ ! myfiles[[i]]$ID_list_row %in% df_f$ID_list_row, ]
  }else{
  myfiles_f[[i]]<-myfiles[[i]]
  } 
  }
rm(df_f)
rm(i)

```



```{r from wide to long data}
DF_long_f<-fun_long(myfiles_f,names_pl ="PARAM",values_pl="measurement",from_pl = "Major",to_pl = "Solidity")

```

```{r models}
#NB change the Tanoiri function if studying primary or secondary MPs
DFL_mod<- list()
for (i in 1:length(myfiles_f)){
  myfiles_f[[i]]$ID_list_row=paste0("p_",i,"_",seq.int(1:nrow(myfiles_f[[i]])))
}
RT<-list()
for (i in 1:length(myfiles_f)){
RT[[i]]<-median(myfiles_f[[i]]$Minor/myfiles_f[[i]]$Major)
DFL_mod[[i]]<-round(as.data.frame(cbind(fun_medina(myfiles_f[[i]]$Area),fun_simon(myfiles_f[[i]]$Major, myfiles_f[[i]]$Minor,RT[[i]]), fun_cozar(myfiles_f[[i]]$Major),fun_isobe(myfiles_f[[i]]$Major), fun_Tanoiri_2(myfiles_f[[i]]$Major,myfiles_f[[i]]$Minor),        fun_Barchiesi(myfiles_f[[i]]$Major,myfiles_f[[i]]$Minor,RT[[i]],myfiles_f[[i]]$Perim.))),digits = 3)

a=myfiles_f[[i]]$ID_list_row
DFL_mod[[i]]$ID_list_row<-a   
DFL_mod[[i]]$ID<-paste0("p_",i) 
DFL_mod[[i]]<-DFL_mod[[i]][,c(8,7,1,2,3,4,5,6)]

colnames(DFL_mod[[i]])<-c("ID","ID_list_row","Medina_V","Simon_V","Cozar_V","Isobe_V","Tanoiri_V","Mod_new")
}

```

```{r, verify total}
SUM_mod<-list()
LabData <- read_csv(paste0("...",GGMMYY,"batch1LAB_DATA.txt")) # "..." depends on your input data folder (where the volume data is stored)
SUM_mod<-list()
for (i in 1:length(DFL_mod)){
SUM_mod[[i]]<-round(colSums(DFL_mod[[i]][,c(3:8)])/1000, digits = 3)#units of measurements from cmc to mmc
SUM_mod[[i]]<-as.data.frame(SUM_mod[[i]])
}
SUM_modT <- do.call("cbind",SUM_mod)
SUM_modT$Rmean <- round(rowMeans(SUM_modT), digits= 3)

D_mod_data_rel <-round((as.vector(SUM_modT$Rmean)/as.numeric(LabData[4,2])),digits=2)
SUM_modT<-cbind(SUM_modT,D_mod_data_rel)
colnames(SUM_modT)<-c("ID_1","ID_2","ID_3","Rmean")
write.csv(SUM_modT,paste0(myPath,GGMMYY,"/",GGMMYY,"_Comparison_model_data_mod.csv")) #"..." your output folder
rm(i,D_mod_data_rel)
#rm(LabData)

```

```{r, RSS}

opt_m<-list()
LDM<-as.numeric(LabData[4,2])

for(i in 1:3){
opt_m[[i]]<-OPTI_m(0.02,myfiles_f[[i]]$Major,myfiles_f[[i]]$Minor,LDM)
}
opt_m<-as.data.frame(do.call(cbind,opt_m))
row.names(opt_m)<-c("OPT_PAR_m","RSS_m")
colnames(opt_m)<-c("B1","B2","B3")

opt_M<-list()

for(i in 1:3){
opt_M[[i]]<-OPTI_M(0.002,myfiles_f[[i]]$Major,myfiles_f[[i]]$Minor,LDM)
}
opt_M<-as.data.frame(do.call(cbind,opt_M))
row.names(opt_M)<-c("OPT_PAR_M","RSS_M")
colnames(opt_M)<-c("B1","B2","B3")

opt_C<-list()

for(i in 1:3){
opt_C[[i]]<-OPTI_COZAR(0.1,myfiles_f[[i]]$Major,LDM)
}
opt_C<-as.data.frame(do.call(cbind,opt_C))
row.names(opt_C)<-c("OPT_PAR_C","RSS_C")
colnames(opt_C)<-c("B1","B2","B3")


opt_I<-list()

for(i in 1:3){
opt_I[[i]]<-OPTI_ISOBE(0.4,myfiles_f[[i]]$Major,LDM)
}
opt_I<-as.data.frame(do.call(cbind,opt_I))
row.names(opt_I)<-c("OPT_PAR_I","RSS_I")
colnames(opt_I)<-c("B1","B2","B3")

#opt_B<-list()
#for(i in 1:3){
#opt_B[[i]]<-OPTI_B(0.4,myfiles_f[[i]]$Major,myfiles_f[[i]]$Minor,myfiles_f[[i]]$Perim.,LDM)
#}
#opt_B<-as.data.frame(do.call(cbind,opt_B))
#row.names(opt_B)<-c("OPT_PAR_B","RSS_B")
#colnames(opt_B)<-c("B1","B2","B3")


OPT_tot<-rbind(opt_B,opt_m,opt_M,opt_C,opt_I)
write.csv(OPT_tot,paste0(".../RSS_models_assessment/OPT_results/",GGMMYY,"OPT_ToT.csv"))#change according to your folders/path

```