Question

我正在使用R构建mapreduce程序，该程序使用遗传算法从数据集中的一组要素中提取相关要素。我需要将许多文件作为输入添加到我的mapreduce作业中。我的代码是我的mapreduce程序，但它只适用于一个输入文件（data.csv）。

library(caret)
library(dplyr)
library(rmr2)
Sys.setenv(HADOOP_CMD="/home/rania/hadoop-2.7.3/bin/hadoop")
Sys.getenv("HADOOP_CMD")
Sys.setenv(HADOOP_STREAMING="/home/rania/hadoop-streaming-2.7.3.jar")
library(rhdfs)
hdfs.init()
rmr.options(backend = "hadoop")
hdfs.mkdir("/user/rania/genetic")
hdfs.mkdir("/user/rania/genetic/data")

我将文件放在hdfs

中的一个文件夹中

hadoop fs -copyFromLocal /home/rania/Downloads/matrices/*.csv /user/rania/genetic/data/

这是地图功能

mon.map <- function(.,data){ 
data <- read.csv("/home/rania/Downloads/dataset.csv", header = T, sep = ";")
y <- c(1,0,1,0,1,1,1,1,0,0,1,0,1)

ga_ctrl <- gafsControl(functions = rfGA, # Assess fitness with RF
                       method = "cv")   # 10 fold cross validation
set.seed(10)
lev <- c("1","0")
rf_ga3 <- gafs(x = data, y = y,
                           iters = 10, # 100 generations of algorithm
                           popSize = 4, # population size for each generation
                           levels = lev,
                           gafsControl = ga_ctrl)
keyval(rf_ga3$ga$final, data[names(data) %in% rf_ga3$ga$final]  ) 
 }

这是减少功能

mon.reduce <- function(k,v){
keyval(k,v) }

现在我应用mapreduce作业

hdfs.root = 'genetic' 
hdfs.data = file.path(hdfs.root, 'data')
hdfs.out = file.path(hdfs.root, 'out')
csv.format <- make.output.format("csv")
genetic = function (input, output) {mapreduce(input=input, output=output, input.format="csv",output.format=csv.format, map=mon.map,reduce=mon.reduce)}
out = genetic(hdfs.data, hdfs.out)

然后我们从hdfs打印结果

results <- from.dfs(out, format="csv")
print(results)

OR

hdfs.cat("/genetic/out/part-00000")

我尝试更改地图功能，使其适用于许多文件，但失败了

mon.map <- function(.,data){ 
data <- list.files(path="/home/rania/Downloads/matrices/", full.names=TRUE, pattern="\\.csv") %>% lapply(read.csv, header=TRUE, sep=",") 
y <- c(1,0,1,0,1,1,1,1,0,0,1,0,1)
for (i in 1:4){
ga_ctrl <- gafsControl(functions = rfGA, # Assess fitness with RF
                       method = "cv")   # 10 fold cross validation
set.seed(10)
lev <- c("1","0")
rf_ga3 <- gafs(x = data[[i]], y = y,
                           iters = 10, # 100 generations of algorithm
                           popSize = 4, # population size for each generation
                           levels = lev,
                           gafsControl = ga_ctrl)
               }
keyval(rf_ga3$ga$final, do.call(cbind, Map(`[`, data, c(rf_ga3$ga$final)))  )  
 }

我可以在之前的地图功能中更改哪些内容以使其适用于许多输入文件？谢谢

Rhadoop mapreduce用于多个输入文件

0 个答案: