4

让我从Tidytext 简介@CRAN中的以下完整工作代码开始 

library(janeaustenr)
library(dplyr)
library(stringr)

original_books <- austen_books() %>%
  group_by(book) %>%
  mutate(linenumber = row_number(),
         chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
                                                 ignore_case = TRUE)))) %>%
  ungroup()

original_books

library(tidytext)
tidy_books <- original_books %>%
  unnest_tokens(word, text)

tidy_books

data("stop_words")
cleaned_books <- tidy_books %>%
  anti_join(stop_words)

到目前为止一切都很好。我有六本简·奥斯汀的小说，去掉了标准的垃圾词。

unique(cleaned_books$book)

这让我明白了：《理智与情感》、《傲慢与偏见》、《曼斯菲尔德公园》、《艾玛》、《诺桑格修道院》、《说服》。

所以如果我想做一个所有六个的标准TF词云，没问题。就像这样（添加颜色）：

library(wordcloud)
library(RColorBrewer)
dark2 <- brewer.pal(8, "Dark2")

cleaned_books %>%
  count(word) %>%
  with(wordcloud(word, n, color = dark2, max.words = 100))

工作精美。但是，我该如何对所有六本小说进行commonality.cloud ()以及对相同内容的 compare.cloud() 呢？

我需要的所有数据都在clean_books中——但我不知道如何重塑它。感谢您的帮助！

知道了。谢谢。

如果其他人有类似的问题，将离开。

上面的代码 &

set1 <- brewer.pal(8, "Set1") ## a second color just for other cloud type

library(reshape2)

# title size and scale optional, obviously
cleaned_books %>%
   group_by(book) %>%
   count(word) %>%
   acast(word ~ book, value.var = "n", fill = 0) %>%
   comparison.cloud(color = dark2, title.size = 1,  scale = c(3,  0.3), random.order = FALSE, max.words = 100)


cleaned_books %>%
   group_by(book) %>%
   count(word) %>%
   acast(word ~ book, value.var = "n", fill = 0) %>%
   commonality.cloud(color = set1, title.size = 1, scale = c(3,  0.3), random.order = FALSE,  max.words = 100)

效果很好。

4

1 回答 1

2

知道了。谢谢。运行上面的代码。然后

set1 <- brewer.pal(8, "Set1") ## a second color just for other cloud type
library(reshape2)

颜色是可选的。reshape2 必不可少。然后按书分组，然后去。

cleaned_books %>%
   group_by(book) %>%
   count(word) %>%
   acast(word ~ book, value.var = "n", fill = 0) %>%
   comparison.cloud(color = dark2, title.size = 1, scale = c(3,  0.3), random.order = FALSE,  max.words = 100)

cleaned_books %>%
   group_by(book) %>%
   count(word) %>%
   acast(word ~ book, value.var = "n", fill = 0) %>%
   commonality.cloud(color = set1, title.size = 1, scale = c(3,  0.3), random.order = FALSE,  max.words = 100)

都好！

于 2017-11-14T11:10:57.063 回答