#http://stackoverflow.com/questions/6449588/r-memory-management-advice-caret-model-matrices-data-frames
library(caret)
library(Matrix)
library(doMC)
registerDoMC(2)

response = 'class'

repr = 'dummy'
do.impute = F

xmode = function(xs) names(which.max(table(xs)))

read.orng = function(path) {
  # read header
  hdr = strsplit(readLines(path, n=1), '\t')
  pairs = sapply(hdr, function(field) strsplit(field, '#'))
  names = sapply(pairs, function(pair) pair[2])
  classes = sapply(pairs, function(pair)
    if (grepl('C', pair[1])) 'numeric' else 'factor')

  # read data
  dfbase = read.table(path, header=T, sep='\t', quote='', col.names=names, na.strings='?', colClasses=classes, comment.char='')

  # switch response, remove meta columns
  df = dfbase[sapply(pairs, function(pair) !grepl('m', pair[1]) && pair[2] != 'class' || pair[2] == response)]

  df
}

train.and.test = function(x, y, trains, method) {
  m = train(x[trains,], y[trains,], method=method)
  ps = extractPrediction(list(m), testX=x[!trains,], testY=y[!trains,])
  perf = postResample(ps$pred, ps$obs)
  list(m=m, ps=ps, perf=perf)
}

# From 
sparse.cor = function(x){
  memory.limit(size=10000)
  n 200 levels')
badfactors = sapply(mergef, function(x)
  is.factor(x) && (nlevels(x)  200))
mergef = mergef[, -which(badfactors)]

print('remove near-zero variance predictors')
mergef = mergef[, -nearZeroVar(mergef)]

print('create model matrix, making everything numeric')
if (repr == 'dummy') {
  dummies = dummyVars(as.formula(paste(response, '~ .')), mergef)
  mergem = predict(dummies, newdata=mergef)
} else {
  mat = if (repr == 'sparse') model.matrix else sparse.model.matrix
  mergem = mat(as.formula(paste(response, '~ .')), data=mergef)
  # remove intercept column
  mergem = mergem[, -1]
}

print('remove high-correlation predictors')
merge.cor = (if (repr == 'sparse') sparse.cor else cor)(mergem)
mergem = mergem[, -findCorrelation(merge.cor, cutoff=.75)]

print('try a couple of different methods')
do.method = function(method) {
  train.and.test(mergem, mergef[response], mergef$istrain, method)
}
res.gbm = do.method('gbm')
res.glmnet = do.method('glmnet')
res.rf = do.method('parRF')