rhadoop linear regression 问题

Posted 2020-10-03 lxjshuju

library(rhdfs)

library(rmr2)

hdfs.init()

hdfs.delete("/user/output/lm.output")

map <- function(k,lines) {

lines<-unlist(strsplit(lines,‘#‘))

k<-lines[1]

x<-unlist(strsplit(lines[2],‘,‘))

y<-unlist(strsplit(lines[3],‘,‘))

x<-as.numeric(x)

y<-as.numeric(y)

lm <- lm(y ~ x)

return( keyval(k, lm$coefficients[[2]]) )

}

reduce <- function(key, lmres) {

  # keyval(key, lmres)

  return lmres

}

wordcount <- function (input, output=NULL) {

  mapreduce(input=input, output=output, input.format="text",output.format = "text", map=map, reduce=reduce)

}

hdfs.root <- ‘/user‘

hdfs.data <- file.path(hdfs.root, ‘input/lm.input‘)

hdfs.out <- file.path(hdfs.root, ‘output/lm.output‘)

out <- wordcount(hdfs.data, hdfs.out)

输入文件为：/user/input/lm.input

1#1,2,3,4#2,4,6,8

2#1,2,3,4#3,6,9,12

3#1,2,3,4#4,8,12,16

4#1,2,3,4#1.5,3,4.5,6

可是输出却仅仅有2个结果：

1       2

4       1.5