#MODIFIED ON: 03/23/2015            

source /nobackupp6/aguzman4/climateLayers/sharedModules/etc/environ.sh 

MODULEPATH=$MODULEPATH:/nex/modules/files

module load pythonkits/gdal_1.10.0_python_2.7.3_nex

out_prefix<-"run10_1500x4500_global_analyses_03232015" #PARAM5

#### Table 1: Average accuracy metrics per tile and predictions

###Table 2: daily validation/testing accuracy metrics for all tiles

###Table 3: monthly fit/training accuracy information for all tiles

#################

###Table 4: daily fit/training accuracy information with predictions for all tiles

## daily fit info:

tb_diagnostic_s_list <- mclapply(list_raster_obj_files,FUN=function(x){try(x<-load_obj(x));try(x[["tb_diagnostic_s"]])},mc.preschedule=FALSE,mc.cores = num_cores)                           

names(tb_diagnostic_s_list) <- list_names_tile_id

tb_diagnostic_s_tmp <- remove_from_list_fun(tb_diagnostic_s_list)$list

#df_tile_processed$tb_diag <- remove_from_list_fun(tb_diagnostic_v_list)$valid

tb_diagnostic_s_NA <- do.call(rbind.fill,tb_diagnostic_s_tmp) #create a df for NA tiles with all accuracy metrics

tile_id_tmp <- lapply(1:length(tb_diagnostic_s_tmp),

                     FUN=function(i,x,y){rep(y[i],nrow(x[[i]]))},x=tb_diagnostic_s_tmp,y=names(tb_diagnostic_s_tmp))

tb_diagnostic_s_NA$tile_id <- unlist(tile_id_tmp) #adding identifier for tile

tb_diagnostic_s_NA <- merge(tb_diagnostic_s_NA,df_tile_processed[,1:2],by="tile_id")

write.table((tb_diagnostic_s_NA),

            file=file.path(out_dir,paste("tb_diagnostic_s_NA","_",out_prefix,".txt",sep="")),sep=",")

##### Table 5: Add later on: daily info

### with also data_s and data_v saved!!!

#Insert here...compute input and predicted ranges to spot potential errors?

##### SPDF of Monhtly Station info

##### SPDF of Daily Station info

######################################################

####### PART 3: EXAMINE STATIONS AND MODEL FITTING ###

### Stations and model fitting ###

#summarize location and number of training and testing used by tiles

names(robj1$clim_method_mod_obj[[1]]$data_month) # monthly data for January

#names(robj1$validation_mod_month_obj[[1]]$data_s) # daily for January with predictions

#note that there is no holdout in the current run at the monthly time scale:

robj1$clim_method_mod_obj[[1]]$data_month_v #zero rows for testing stations at monthly timescale

#load data_month for specific tiles

data_month <- extract_from_list_obj(robj1$clim_method_mod_obj,"data_month")

names(data_month) #this contains LST means (mm_1, mm_2 etc.) as well as TMax and other info

use_day=TRUE

use_month=TRUE

#list_raster_obj_files <- c("/data/project/layers/commons/NEX_data/output_run3_global_analyses_06192014/output10Deg/reg1//30.0_-100.0/raster_prediction_obj_gam_CAI_dailyTmax30.0_-100.0.RData",

#                    "/data/project/layers/commons/NEX_data/output_run3_global_analyses_06192014/output10Deg/reg1//30.0_-105.0/raster_prediction_obj_gam_CAI_dailyTmax30.0_-105.0.RData")

list_names_tile_id <- df_tile_processed$tile_id

list_raster_obj_files[list_names_tile_id]

#list_names_tile_id <- c("tile_1","tile_2")

list_param_training_testing_info <- list(list_raster_obj_files[list_names_tile_id],use_month,use_day,list_names_tile_id)

names(list_param_training_testing_info) <- c("list_raster_obj_files","use_month","use_day","list_names_tile_id")

list_param <- list_param_training_testing_info

#debug(extract_daily_training_testing_info)

#pred_data_info <- extract_daily_training_testing_info(1,list_param=list_param_training_testing_info)

pred_data_info <- mclapply(1:length(list_raster_obj_files[list_names_tile_id]),FUN=extract_daily_training_testing_info,list_param=list_param_training_testing_info,mc.preschedule=FALSE,mc.cores = num_cores)

#pred_data_info <- mclapply(1:length(list_raster_obj_files[list_names_tile_id][1:6]),FUN=extract_daily_training_testing_info,list_param=list_param_training_testing_info,mc.preschedule=FALSE,mc.cores = 6)

#pred_data_info <- lapply(1:length(list_raster_obj_files),FUN=extract_daily_training_testing_info,list_param=list_param_training_testing_info)

#pred_data_info <- lapply(1:length(list_raster_obj_files[1]),FUN=extract_daily_training_testing_info,list_param=list_param_training_testing_info)

pred_data_info_tmp <- remove_from_list_fun(pred_data_info)$list #remove data not predicted

##Add tile nanmes?? it is alreaready there

#names(pred_data_info)<-list_names_tile_id

pred_data_month_info <- do.call(rbind,lapply(pred_data_info_tmp,function(x){x$pred_data_month_info}))

pred_data_day_info <- do.call(rbind,lapply(pred_data_info_tmp,function(x){x$pred_data_day_info}))

#putput inforamtion in csv !!

write.table(pred_data_month_info,

            file=file.path(out_dir,paste("pred_data_month_info_",out_prefix,".txt",sep="")),sep=",")

write.table(pred_data_day_info,

            file=file.path(out_dir,paste("pred_data_day_info_",out_prefix,".txt",sep="")),sep=",")