library(rpart)

target.lrn <- read.table("../lrn/num/472.dat",header=T,colClasses="numeric")
target.val <- read.table("../val/num/472.dat",header=T,colClasses="numeric")
target.tst <- read.table("../tst/num/472.dat",header=T,colClasses="numeric")

 
y.lrn <- target.lrn[,1]
y.val <- target.val[,1]
y.tst <- target.tst[,1]
y     <- c(y.lrn,y.val,y.tst)

n.lrn <- length(y.lrn)
n.val <- length(y.val)
n.tst <- length(y.tst)
n     <- length(y)

rm(target.lrn,target.val,target.tst)

wts <- mat.or.vec(n,1) ; for (i in 1:n.lrn) wts[i]=1
idx.lrn <- 1:n.lrn
idx.val <- (n.lrn+1):(n.lrn+n.val)
idx.tst <- (n.lrn+n.val+1):n

mod <- read.table("../cty_mod.txt",
         header=F,colClasses="character",col.names=c("file","feature","type"))

n.mod <- length(mod$file)

first.time <- TRUE

for (i in 1:n.mod) {

  fn.lrn <- paste("../lrn/",mod$type[i],"/",mod$file[i],".dat",sep="")
  fn.val <- paste("../val/",mod$type[i],"/",mod$file[i],".dat",sep="")
  fn.tst <- paste("../tst/",mod$type[i],"/",mod$file[i],".dat",sep="")
  print(mod$feature[i])

  if (mod$type[i]=="chr") {

    f.lrn <- read.table(fn.lrn,
               header=T,colClasses="character",blank.lines.skip=F)
    f.val <- read.table(fn.val,
               header=T,colClasses="character",blank.lines.skip=F)
    f.tst <- read.table(fn.tst,
               header=T,colClasses="character",blank.lines.skip=F)

    f <- c(f.lrn[,1],f.val[,1],f.tst[,1])

    if (mod$feature[i]=="STATE") {
      f[f=="AS"|f=="DC"|f=="DE"|f=="MA"|f=="ME"|f=="NH"] <- "S1"
      f[f=="OH"|f=="RI"|f=="VI"|f=="WV"]                 <- "S1"
      f[f=="AA"|f=="AE"|f=="AP"|f=="CT"|f=="GU"|f=="MD"] <- "S2"
      f[f=="NJ"|f=="NY"|f=="PA"|f=="PA"|f=="VA"|f=="VT"] <- "S2"
      f[f=="WY"]                                         <- "S2"  
      f[f=="AK"|f=="UT"|f=="MS"]                         <- "S3"
      f[f=="NE"|f=="ND"]                                 <- "S4"
      f[f=="SD"|f=="SC"]                                 <- "S5"
    } 
    
    f <- as.factor(f)

    n.lev <- nlevels(f)
    f.name <- levels(f) 
    if(n.lev==2) f.name <- c(mod$feature[i],mod$feature[i])
    print(paste("  nlevels = ",n.lev))

    f <- model.matrix(y ~ f - 1)      # Note: Intercept removed.
    f <- f[,2:n.lev]                  # Note: First dummy deleted.
    f.name <- f.name[2:n.lev]         # Note: First name deleted.

  } else {
    
    f.lrn<-read.table(fn.lrn,
             header=T,colClasses="numeric",blank.lines.skip=F)
    f.val<-read.table(fn.val,
             header=T,colClasses="numeric",blank.lines.skip=F)
    f.tst<-read.table(fn.tst,
             header=T,colClasses="numeric",blank.lines.skip=F)

    f <- c(f.lrn[,1],f.val[,1],f.tst[,1])

    f[is.na(f)] <- 0

    f.name <- mod$feature[i]

  }

  if (first.time) {
    X <- f
    X.names <- f.name
    first.time <- FALSE
  } else {
    X <- cbind(prev.X,f)
    X.names <- c(prev.X.names,f.name)
  }

  prev.X <- X
  prev.X.names <- X.names

}

rm(prev.X,prev.X.names)
rm(f.lrn,f.val,f)

dimnames(X) <- list(NULL,X.names)

print(X.names)

X.lrn <- X[idx.lrn,]
X.val <- X[idx.val,]
X.tst <- X[idx.tst,]


print(length(y.lrn[(X.lrn[,1]>=69) & (X.lrn[,2]>=0.5)]))
print(  mean(y.lrn[(X.lrn[,1]>=69) & (X.lrn[,2]>=0.5)]))

print(length(y.val[(X.val[,1]>=69) & (X.val[,2]>=0.5)]))
print(  mean(y.val[(X.val[,1]>=69) & (X.val[,2]>=0.5)]))

print(length(y.tst[(X.tst[,1]>=69) & (X.tst[,2]>=0.5)]))
print(  mean(y.tst[(X.tst[,1]>=69) & (X.tst[,2]>=0.5)]))

print(length(y.lrn[(X.lrn[,1]>=69) & (X.lrn[,2]>=0.5) & (X.lrn[,39]>=9612)]))
print(  mean(y.lrn[(X.lrn[,1]>=69) & (X.lrn[,2]>=0.5) & (X.lrn[,39]>=9612)]))

print(length(y.val[(X.val[,1]>=69) & (X.val[,2]>=0.5) & (X.val[,39]>=9612)]))
print(  mean(y.val[(X.val[,1]>=69) & (X.val[,2]>=0.5) & (X.val[,39]>=9612)]))

print(length(y.tst[(X.tst[,1]>=69) & (X.tst[,2]>=0.5) & (X.tst[,39]>=9612)]))
print(  mean(y.tst[(X.tst[,1]>=69) & (X.tst[,2]>=0.5) & (X.tst[,39]>=9612)]))

print(length(y.lrn[(X.lrn[,1]< 20) & (X.lrn[,2]< 0.5)]))
print(  mean(y.lrn[(X.lrn[,1]< 20) & (X.lrn[,2]< 0.5)]))

print(length(y.lrn[(X.lrn[,1]>=20) & (X.lrn[,2]< 0.5)]))
print(  mean(y.lrn[(X.lrn[,1]>=20) & (X.lrn[,2]< 0.5)]))

print(length(y.lrn[(X.lrn[,1]< 20) & (X.lrn[,2]>=0.5)]))
print(  mean(y.lrn[(X.lrn[,1]< 20) & (X.lrn[,2]>=0.5)]))

print(length(y.lrn[(X.lrn[,1]>=20) & (X.lrn[,2]>=0.5)]))
print(  mean(y.lrn[(X.lrn[,1]>=20) & (X.lrn[,2]>=0.5)]))