基于RHadoop的linear-least-squares算法

library(rmr2)

## @knitr LLS-data
X = matrix(rnorm(2000), ncol = 10)
X.index = to.dfs(cbind(1:nrow(X), X))
y = as.matrix(rnorm(200))
## @knitr LLS-sum
Sum = 
  function(., YY) 
    keyval(1, list(Reduce('+', YY)))
## @knitr LLS-XtX
XtX = 
  values(
    from.dfs(
      mapreduce(
        input = X.index,
        map = 
          function(., Xi) {
            Xi = Xi[,-1]
            keyval(1, list(t(Xi) %*% Xi))},
        reduce = Sum,
        combine = TRUE)))[[1]]
## @knitr LLS-Xty
Xty = 
  values(
    from.dfs(
      mapreduce(
        input = X.index,
        map = function(., Xi) {
          yi = y[Xi[,1],]
          Xi = Xi[,-1]
          keyval(1, list(t(Xi) %*% yi))},
        reduce = Sum,
        combine = TRUE)))[[1]]
## @knitr LLS-solve
solve(XtX, Xty)
## @knitr end