1

我正在使用 tidytext。当我命令 unnest_tokens 时。R返回错误

请提供列名

我该如何解决这个错误？

library(tidytext)
library(tm)
library(dplyr)
library(stats)
library(base)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
  #Build a corpus: a collection of statements
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
f <-Corpus(DirSource("C:/Users/Boon/Desktop/Dissertation/F"))
doc_dir <- "C:/Users/Boon/Desktop/Dis/F/f.csv"
doc <- read.csv(file_loc, header = TRUE)
docs<- Corpus(DataframeSource(doc))
dtm <- DocumentTermMatrix(docs)
text_df<-data_frame(line=1:115,docs=docs)

#This is the output from the code above,which is fine!: 
# text_df
# A tibble: 115 x 2
#line          docs
#<int> <S3: VCorpus>
# 1      1 <S3: VCorpus>
#2      2 <S3: VCorpus>
#3      3 <S3: VCorpus>
#4      4 <S3: VCorpus>
#5      5 <S3: VCorpus>
#6      6 <S3: VCorpus>
#7      7 <S3: VCorpus>
#8      8 <S3: VCorpus>
#9      9 <S3: VCorpus>
#10    10 <S3: VCorpus>
# ... with 105 more rows

unnest_tokens(word, docs)

# Error: Please supply column name
4

1 回答 1

2

如果要将文本数据转换为整洁的格式，则无需先将其转换为语料库或文档术语矩阵或任何东西。这是使用整洁的文本数据格式背后的主要思想之一；你不使用那些其他格式，除非你需要建模。

您只需将原始文本放入数据框中，然后用于unnest_tokens()整理它。（我在这里对您的 CSV 的外观做出一些假设；下次 发布可重现的示例会更有帮助。）

library(dplyr)

docs <- data_frame(line = 1:4,
                   document = c("This is an excellent document.",
                                "Wow, what a great set of words!",
                                "Once upon a time...",
                                "Happy birthday!"))

docs
#> # A tibble: 4 x 2
#>    line                        document
#>   <int>                           <chr>
#> 1     1  This is an excellent document.
#> 2     2 Wow, what a great set of words!
#> 3     3             Once upon a time...
#> 4     4                 Happy birthday!

library(tidytext)

docs %>%
    unnest_tokens(word, document)
#> # A tibble: 18 x 2
#>     line      word
#>    <int>     <chr>
#>  1     1      this
#>  2     1        is
#>  3     1        an
#>  4     1 excellent
#>  5     1  document
#>  6     2       wow
#>  7     2      what
#>  8     2         a
#>  9     2     great
#> 10     2       set
#> 11     2        of
#> 12     2     words
#> 13     3      once
#> 14     3      upon
#> 15     3         a
#> 16     3      time
#> 17     4     happy
#> 18     4  birthday
于 2017-07-21T18:47:49.273 回答