各位大神,以下是代码,求帮忙啊!看看哪里出错了。。。。
Sys.setenv("HADOOP_CMD"="/usr/bin/hadoop")
Sys.setenv("HADOOP_STREAMING"="/usr/hdp/2.2.0.0-2041/hadoop-mapreduce/hadoop-streaming-2.6.0.2.2.0.0-2041.jar")
##
## packages
##
require(rmr2)
## hadoop specific definitions
rmr.options(backend.parameters = list(
hadoop = list(D = "mapreduce.map.memory.mb=1024")
))
small.ints <- to.dfs(1:100)
myMapper <- function(k,v){
S=sum(v)
L=length(v)
return (keyval(key=c("S","L"), c=c(S,L)))
}
myReducer <- function(k, vv) {
return(keyval(key = k, val = sum(vv)))
}
newOut <- mapreduce(
input = small.ints,
map = myMapper,
reduce = myReducer)
localNewOut <- from.dfs(newOut)