#DATE: 02/26/2013                                                                                 

### Parameters and argument

infile2<-"list_365_dates_04212012.txt"

infile_monthly<-"monthly_covariates_ghcn_data_TMAXy2010_2010_VE_02082013.shp"

infile_daily<-"daily_covariates_ghcn_data_TMAXy2010_2010_VE_02082013.shp"

infile_locs<-"stations_venezuela_region_y2010_2010_VE_02082013.shp"

infile3<-"covariates__venezuela_region__VE_01292013.tif" #this is an output from covariate script

#CRS_interp<-"+proj=lcc +lat_1=43 +lat_2=45.5 +lat_0=41.75 +lon_0=-120.5 +x_0=400000 +y_0=0 +ellps=GRS80 +units=m +no_defs";

#infile_monthly<-"monthly_covariates_ghcn_data_TMAXy2010_2010_VE_02082013.shp" #outile4 from database_covar script

#infile_daily<-"daily_covariates_ghcn_data_TMAXy2010_2010_VE_02082013.shp"  #outfile3 from database_covar script

#infile_locs<-"stations_venezuela_region_y2010_2010_VE_02082013.shp" #outfile2? from database covar script

if (var=="TMAX"){

  y_var_name<-"dailyTmax"                                       

}

if (var=="TMIN"){

  y_var_name<-"dailyTmin"                                       

}

prop_min<-0.3          #if prop_min=prop_max and step=0 then predicitons are done for the number of dates...

prop_max<-0.3

source(file.path(script_path,"GAM_fusion_function_multisampling_02262013.R"))

log_fname<-paste("R_log_t",out_prefix, ".log",sep="")

############### Reading the daily station data and other data #################

ghcn<-readOGR(dsn=in_path,layer=sub(".shp","",infile_daily))

stat_loc<-readOGR(dsn=in_path,layer=sub(".shp","",infile_locs))

dates <-readLines(file.path(in_path,infile2)) #dates to be predicted

rnames <-c("x","y","lon","lat","N","E","N_w","E_w","elev","slope","aspect","CANHEIGHT","DISTOC")

lc_names<-c("LC1","LC2","LC3","LC4","LC5","LC6","LC7","LC8","LC9","LC10","LC11","LC12")

lst_names<-c("mm_01","mm_02","mm_03","mm_04","mm_05","mm_06","mm_07","mm_08","mm_09","mm_10","mm_11","mm_12",

                    "nobs_01","nobs_02","nobs_03","nobs_04","nobs_05","nobs_06","nobs_07","nobs_08",

                    "nobs_09","nobs_10","nobs_11","nobs_12")                  

covar_names<-c(rnames,lc_names,lst_names)                

s_raster<-brick(infile3)                   #read in the data brck

data3<-readOGR(dsn=in_path,layer=sub(".shp","",infile_monthly))

#Cleaning/sceerniging functions for daily stations, monthly stations and covariates?? do this at the preparation stage!!!

##

##### Create sampling: select training and testing sites ###

#Make this a a function!!!!

if (seed_number>0) {

  set.seed(seed_number)                        #Using a seed number allow results based on random number to be compared...

}

nel<-length(dates)

dates_list<-vector("list",nel) #list of one row data.frame

prop_range<-(seq(from=prop_min,to=prop_max,by=step))*100     #range of proportion to run

sn<-length(dates)*nb_sample*length(prop_range)               #Number of samples to run

for(i in 1:length(dates)){

  d_tmp<-rep(dates[i],nb_sample*length(prop_range)) #repeating same date

  s_nb<-rep(1:nb_sample,length(prop_range))         #number of random sample per proportion

  prop_tmp<-sort(rep(prop_range, nb_sample))

  tab_run_tmp<-cbind(d_tmp,s_nb,prop_tmp)

  dates_list[[i]]<-tab_run_tmp

}

sampling_dat<-as.data.frame(do.call(rbind,dates_list))

names(sampling_dat)<-c("date","run_samp","prop")

for(i in 2:3){            # start of the for loop #1

  sampling_dat[,i]<-as.numeric(as.character(sampling_dat[,i]))  

}

sampling_dat$date<- as.character(sampling_dat[,1])

#ghcn.subsets <-lapply(dates, function(d) subset(ghcn, date==d)) #this creates a list of 10 or 365 subsets dataset based on dates

ghcn.subsets <-lapply(as.character(sampling_dat$date), function(d) subset(ghcn, date==d)) #this creates a list of 10 or 365 subsets dataset based on dates

#Make this a function??

## adding choice of constant sample 

if (seed_number>0) {

  set.seed(seed_number)                        #Using a seed number allow results based on random number to be compared...

}

sampling<-vector("list",length(ghcn.subsets))

sampling_station_id<-vector("list",length(ghcn.subsets))

for(i in 1:length(ghcn.subsets)){

  n<-nrow(ghcn.subsets[[i]])

  prop<-(sampling_dat$prop[i])/100

  ns<-n-round(n*prop)   #Create a sample from the data frame with 70% of the rows

  nv<-n-ns              #create a sample for validation with prop of the rows

  ind.training <- sample(nrow(ghcn.subsets[[i]]), size=ns, replace=FALSE) #This selects the index position for 70% of the rows taken randomly

  ind.testing <- setdiff(1:nrow(ghcn.subsets[[i]]), ind.training)

  #Find the corresponding 

  data_sampled<-ghcn.subsets[[i]][ind.training,] #selected the randomly sampled stations

  station_id.training<-data_sampled$station     #selected id for the randomly sampled stations (115)

  #Save the information

  sampling[[i]]<-ind.training

  sampling_station_id[[i]]<- station_id.training

}

## Use same samples across the year...

if (constant==1){

  sampled<-sampling[[1]]

  data_sampled<-ghcn.subsets[[1]][sampled,] #selected the randomly sampled stations

  station_sampled<-data_sampled$station     #selected id for the randomly sampled stations (115)

  list_const_sampling<-vector("list",sn)

  list_const_sampling_station_id<-vector("list",sn)

  for(i in 1:sn){

    station_id.training<-intersect(station_sampled,ghcn.subsets[[i]]$station)

    ind.training<-match(station_id.training,ghcn.subsets[[i]]$station)

    list_const_sampling[[i]]<-ind.training

    list_const_sampling_station_id[[i]]<-station_id.training

  }

  sampling<-list_const_sampling 

  sampling_station_id<-list_const_sampling_station_id

}

#return()

########### PREDICT FOR MONTHLY SCALE  #############

#gamclim_fus_mod<-mclapply(1:12, runClim_KGFusion,mc.preschedule=FALSE,mc.cores = 4) #This is the end bracket from mclapply(...) statement

rast_clim_yearlist<-list_tmp

gam_fus_mod<-mclapply(1:length(ghcn.subsets), runGAMFusion,mc.preschedule=FALSE,mc.cores = 9) #This is the end bracket from mclapply(...) statement