r - 并行parLapply设置

我正在尝试并行使用来自openNLP/NLP包的部分语音标记。我需要在任何操作系统上都能使用的代码，因此选择并行使用parLapply函数(但对其他独立于操作系统的选项开放)。过去，我在tagPOS中从openNLP包中运行了parLapply函数，没有任何问题。但是，openNLP软件包最近进行了一些更改，从而消除了tagPOS并添加了一些更灵活的选项。 Kurt非常友好，可以帮助我从新程序包的工具中重新创建tagPOS函数。我可以使用lapply版本，但不能使用并行版本。它一直说节点需要更多的变量传递给它们，直到最终要求openNLP提供非导出的功能。这似乎很奇怪，它会不断要求传递越来越多的变量，这告诉我我设置的parLapply不正确。如何设置tagPOS以并行，独立于操作系统的方式进行操作？

library(openNLP)
library(NLP)
library(parallel)

## POS tagger
tagPOS <-  function(x, pos_tag_annotator, ...) {
    s <- as.String(x)
    ## Need sentence and word token annotations.
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, pos_tag_annotator, a2)

    ## Determine the distribution of POS tags for word tokens.
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, `[[`, "POS"))

    ## Extract token/POS pairs (all of them): easy.
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
} ## End of tagPOS function

## Set up a parallel run
text.var <- c("I like it.", "This is outstanding soup!",
    "I really must get the recipe.")
ntv <- length(text.var)
PTA <- Maxent_POS_Tag_Annotator()

cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterExport(cl=cl, varlist=c("text.var", "ntv",
    "tagPOS", "PTA", "as.String", "Maxent_Word_Token_Annotator"),
    envir = environment())
m <- parLapply(cl, seq_len(ntv), function(i) {
        x <- tagPOS(text.var[i], PTA)
        return(x)
    }
)
stopCluster(cl)

## Error in checkForRemoteErrors(val) :
##   3 nodes produced errors; first error: could not find function
##   "Maxent_Simple_Word_Tokenizer"

openNLP::Maxent_Simple_Word_Tokenizer

## >openNLP::Maxent_Simple_Word_Tokenizer
## Error: 'Maxent_Simple_Word_Tokenizer' is not an exported
##     object from 'namespace:openNLP'

## It's a non exported function
openNLP:::Maxent_Simple_Word_Tokenizer


## Demo that it works with lapply
lapply(seq_len(ntv), function(i) {
    tagPOS(text.var[i], PTA)
})

lapply(text.var, function(x) {
    tagPOS(x, PTA)
})

## >     lapply(seq_len(ntv), function(i) {
## +         tagPOS(text.var[i], PTA)
## +     })
## [[1]]
## [[1]]$POStagged
## [1] "I/PRP like/IN it/PRP ./."
##
## [[1]]$POStags
## [1] "PRP" "IN"  "PRP" "."
##
## [[1]]$word.count
## [1] 3
##
##
## [[2]]
## [[2]]$POStagged
## [1] "THis/DT is/VBZ outstanding/JJ soup/NN !/."
##
## [[2]]$POStags
## [1] "DT"  "VBZ" "JJ"  "NN"  "."
##
## [[2]]$word.count
## [1] 4
##
##
## [[3]]
## [[3]]$POStagged
## [1] "I/PRP really/RB must/MD get/VB the/DT recip/NN ./."
##
## [[3]]$POStags
## [1] "PRP" "RB"  "MD"  "VB"  "DT"  "NN"  "."
##
## [[3]]$word.count
## [1] 6

编辑:根据史蒂夫的建议

请注意，openNLP是全新的。我从CRAN的tar.gz安装了2.1版。即使存在此功能，我也会收到以下错误消息。

library(openNLP); library(NLP); library(parallel)

tagPOS <-  function(text.var, pos_tag_annotator, ...) {
    s <- as.String(text.var)

    ## Set up the POS annotator if missing (for parallel)
    if (missing(pos_tag_annotator)) {
        PTA <- Maxent_POS_Tag_Annotator()
    }

    ## Need sentence and word token annotations.
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, PTA, a2)

    ## Determine the distribution of POS tags for word tokens.
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, "[[", "POS"))

    ## Extract token/POS pairs (all of them): easy.
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
}

text.var <- c("I like it.", "This is outstanding soup!",
    "I really must get the recipe.")

cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterEvalQ(cl, {library(openNLP); library(NLP)})
m <- parLapply(cl, text.var, tagPOS)

## > m <- parLapply(cl, text.var, tagPOS)
## Error in checkForRemoteErrors(val) :
##   3 nodes produced errors; first error: could not find function "Maxent_POS_Tag_Annotator"

stopCluster(cl)


> packageDescription('openNLP')
Package: openNLP
Encoding: UTF-8
Version: 0.2-1
Title: Apache OpenNLP Tools Interface
Authors@R: person("Kurt", "Hornik", role = c("aut", "cre"), email =
          "[email protected]")
Description: An interface to the Apache OpenNLP tools (version 1.5.3).  The Apache OpenNLP
          library is a machine learning based toolkit for the processing of natural language
          text written in Java.  It supports the most common NLP tasks, such as tokenization,
          sentence segmentation, part-of-speech tagging, named entity extraction, chunking,
          parsing, and coreference resolution.  See http://opennlp.apache.org/ for more
          information.
Imports: NLP (>= 0.1-0), openNLPdata (>= 1.5.3-1), rJava (>= 0.6-3)
SystemRequirements: Java (>= 5.0)
License: GPL-3
Packaged: 2013-08-20 13:23:54 UTC; hornik
Author: Kurt Hornik [aut, cre]
Maintainer: Kurt Hornik <[email protected]>
NeedsCompilation: no
Repository: CRAN
Date/Publication: 2013-08-20 15:41:22
Built: R 3.0.1; ; 2013-08-20 13:48:47 UTC; windows

最佳答案

由于要从集群工作程序上的NLP调用函数，因此应在调用parLapply之前将其加载到每个工作程序上。您可以从worker函数中做到这一点，但是在创建集群对象之后，我倾向于立即使用clusterCall或clusterEvalQ:

clusterEvalQ(cl, {library(openNLP); library(NLP)})

由于as.String和Maxent_Word_Token_Annotator位于这些软件包中，因此不应导出它们。

请注意，在我的计算机上运行示例时，我注意到PTA对象在导出到辅助计算机后不起作用。大概在那个对象中有一些不能安全地序列化和反序列化的东西。在使用clusterEvalQ在工作人员上创建该对象之后，该示例成功运行。使用openNLP 0.2-1:

library(parallel)
tagPOS <-  function(x, ...) {
    s <- as.String(x)
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, PTA, a2)
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, `[[`, "POS"))
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
}
text.var <- c("I like it.", "This is outstanding soup!",
    "I really must get the recipe.")
cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterEvalQ(cl, {
    library(openNLP)
    library(NLP)
    PTA <- Maxent_POS_Tag_Annotator()
})
m <- parLapply(cl, text.var, tagPOS)
print(m)
stopCluster(cl)

如果clusterEvalQ因找不到Maxent_POS_Tag_Annotator而失败，则可能是在工作程序上加载了错误版本的openNLP。您可以通过使用sessionInfo执行clusterEvalQ来确定要使用的软件包版本:

library(parallel)
cl <- makeCluster(2)
clusterEvalQ(cl, {library(openNLP); library(NLP)})
clusterEvalQ(cl, sessionInfo())

这将返回在每个集群工作程序上执行sessionInfo()的结果。这是我正在使用且对我有用的某些软件包的版本信息:

other attached packages:
[1] NLP_0.1-0     openNLP_0.2-1

loaded via a namespace (and not attached):
[1] openNLPdata_1.5.3-1 rJava_0.9-4

关于r - 并行parLapply设置，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/18357788/