library(raster)                              # Hijmans et al. package for raster processing

### Parameters and argument

infile2<-"list_10_dates_04212012.txt"                     #List of 10 dates for the regression

#infile2<-"list_365_dates_04212012.txt"

infile3<-"LST_dates_var_names.txt"                        #LST dates name

prop<-0.3                                                                           #Proportion of testing retained for validation   

seed_number<- 100                                                                   #Seed number for random sampling

setwd(path)

############ START OF THE SCRIPT ##################

# cor_LST_LC3<-matrix(1,10,1)      #correlation LST-LC3

# cor_LST_tmax<-matrix(1,10,1)     #correlation LST-tmax

ghcn_all<-ghcn

ghcn_test2<-subset(ghcn_test,ghcn_test$ELEV_SRTM>0)

ghcn<-ghcn_test2

#coords<- ghcn[,c('x_OR83M','y_OR83M')]

  #added by Benoit 

  #d<-ghcn.subsets[[i]]

  d<-data_s

  names(d)[1]<-c("id")

  dmoday=merge(modst,d,by="id")  #LOOSING DATA HERE!!! from 162 t0 146

  names(dmoday)[4]<-c("lat")

  names(dmoday)[5]<-c("lon")

  ###

  #dmoday contains the daily tmax values with TMax being the monthly station tmax mean

  # windows()

  #### Added by Benoit on 06/19

  data_s<-dmoday #put the 

  data_s$daily_delta<-daily_delta

  #Model and response variable can be changed without affecting the script

  mod1<- gam(y_var~ s(lat) + s (lon) + s (ELEV_SRTM), data=data_s)

    ##validation: using the testing data

    #This was modified on 06192012

    y_mod<- predict(mod, newdata=data_v, se.fit = TRUE) #Using the coeff to predict new values.

    RMSE_mod <- sqrt(sum(res_mod^2)/nv)                 #RMSE FOR REGRESSION STEP 1: GAM     

    MAE_mod<- sum(abs(res_mod))/nv                     #MAE, Mean abs. Error FOR REGRESSION STEP 1: GAM