R 用行值生成列

我假设在这个问题上已经有了一些答案。但是我找不到它

我有以下数据：

library(tidyverse)
glimpse(samp)
Observations: 5
Variables: 2
$ business_id <chr> "--6MefnULPED_I942VcFNA", "--9e1ONYQuAa-CB_Rrw7Tw", "--...
$ Ambience    <chr> "romantic': False, 'intimate': False, 'classy': False, ...

但我得到了这个错误：

Error: Duplicate identifiers for rows (2, 3, 4, 5, 6, 7, 8), (10, 11, 12, 13, 14, 15, 16, 17), (19, 20, 21, 22, 23, 24, 25, 26), (28, 29, 30, 31, 32, 33, 34, 35), (37, 38, 39, 40, 41, 42, 43) Call `rlang::last_error()` to see a backtrace

这是一个dput：

structure(list(business_id = c("--6MefnULPED_I942VcFNA", "--9e1ONYQuAa-CB_Rrw7Tw", 
"--cjBEbXMI2obtaRHNSFrA", "--cZ6Hhc9F7VkKXxHMVZSQ", "--DaPTJW3-tB1vP-PfdTEg"
), Ambience = c("romantic': False, 'intimate': False, 'classy': False, 'hipster': False, 'touristy': False, 'trendy': False, 'upscale': False, 'casual': True}", 
"romantic': False, 'intimate': False, 'classy': True, 'hipster': False, 'divey': False, 'touristy': False, 'trendy': False, 'upscale': True, 'casual': False}", 
"romantic': False, 'intimate': False, 'classy': False, 'hipster': False, 'divey': False, 'touristy': False, 'trendy': False, 'upscale': False, 'casual': False}", 
"romantic': False, 'intimate': False, 'classy': False, 'hipster': False, 'divey': False, 'touristy': False, 'trendy': False, 'upscale': False, 'casual': True}", 
"romantic': False, 'intimate': False, 'classy': False, 'hipster': False, 'touristy': False, 'trendy': False, 'upscale': False, 'casual': True}"
)), row.names = c(NA, -5L), class = c("tbl_df", "tbl", "data.frame"
))

---

稍微整理一下你的数据似乎就可以了。具体来说，删除'and}。也许还有一种方法可以用jsonlite解析，但我没有调查：

library(tidyverse)

samp %>%
  mutate(Ambience = strsplit(str_remove_all(Ambience, '[\'|}]'), ",")) %>%
  unnest() %>%
  mutate_at(vars(Ambience), str_trim) %>%
  separate(Ambience, into = c("key", "value")) %>%
  spread(key, value)

# A tibble: 5 x 10
  business_id            casual classy divey hipster intimate romantic touristy trendy upscale
  <chr>                  <chr>  <chr>  <chr> <chr>   <chr>    <chr>    <chr>    <chr>  <chr>  
1 --6MefnULPED_I942VcFNA True   False  NA    False   False    False    False    False  False  
2 --9e1ONYQuAa-CB_Rrw7Tw False  True   False False   False    False    False    False  True   
3 --cjBEbXMI2obtaRHNSFrA False  False  False False   False    False    False    False  False  
4 --cZ6Hhc9F7VkKXxHMVZSQ True   False  False False   False    False    False    False  False  
5 --DaPTJW3-tB1vP-PfdTEg True   False  NA    False   False    False    False    False  False  

如果要假定NA为FALSE，则始终可以使用fill=FALSE参数进行扩展

library(tidyverse)

samp %>%
  mutate(Ambience = strsplit(str_remove_all(Ambience, '[\'|}]'), ",")) %>%
  unnest() %>%
  mutate_at(vars(Ambience), str_trim) %>%
  separate(Ambience, into = c("key", "value")) %>%
  spread(key, value)

# A tibble: 5 x 10
  business_id            casual classy divey hipster intimate romantic touristy trendy upscale
  <chr>                  <chr>  <chr>  <chr> <chr>   <chr>    <chr>    <chr>    <chr>  <chr>  
1 --6MefnULPED_I942VcFNA True   False  NA    False   False    False    False    False  False  
2 --9e1ONYQuAa-CB_Rrw7Tw False  True   False False   False    False    False    False  True   
3 --cjBEbXMI2obtaRHNSFrA False  False  False False   False    False    False    False  False  
4 --cZ6Hhc9F7VkKXxHMVZSQ True   False  False False   False    False    False    False  False  
5 --DaPTJW3-tB1vP-PfdTEg True   False  NA    False   False    False    False    False  False