在 R 中展平嵌套的 JSON

Question

大家好：我已经在堆栈溢出和互联网的其余部分搜索了这个问题的答案，但我找不到的答案似乎对我有用。

我有数千行 json 数据，其中包含来自相机陷阱研究的图像信息。我在解压数据时遇到了很多麻烦。我使用jsonlite::fromJSON 无济于事。来自 tidyjson 的 as.tbl_json 相同。

我的目标是编写一些代码，为我提供一个数据框，其中包含以 json 格式存储的每个变量的列。你能帮忙吗？

这是我正在使用的数据向量，尽管我实际上将数据作为单个列放在更大的 .csv 文件中。第一行是列名。

annotations<-c(annotations,
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""DEERWHITETAILED"",""answers"":{""HOWMANY"":""1"",""YOUNGPRESENT"":""NO"",""ANTLERSPRESENT"":""NO"",""WHATBEHAVIORSDOYOUSEE"":[""ALERT""],""ESTIMATEOFSNOWDEPTHSEETUTORIAL"":""NOSNOWBAREGROUND"",""ISITACTIVELYRAININGORSNOWINGINTHEPICTURE"":""NO""},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""FISHER"",""answers"":{""HOWMANY"":""1"",""YOUNGPRESENT"":""NO"",""WHATBEHAVIORSDOYOUSEE"":[""WALKINGRUNNING"",""ALERT""],""ESTIMATEOFSNOWDEPTHSEETUTORIAL"":""1020CM"",""ISITACTIVELYRAININGORSNOWINGINTHEPICTURE"":""NO""},""filters"":{}}]}]"
"[{""task"":""T0"",""value"":[{""choice"":""NOTHINGHERE"",""answers"":{},""filters"":{}}]}]")

如果我运行 dput(annotations)，会得到以下结果：

structure(list(annotations = c("[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"DEERWHITETAILED\",\"answers\":{\"HOWMANY\":\"1\",\"YOUNGPRESENT\":\"NO\",\"ANTLERSPRESENT\":\"NO\",\"WHATBEHAVIORSDOYOUSEE\":[\"ALERT\"],\"ESTIMATEOFSNOWDEPTHSEETUTORIAL\":\"NOSNOWBAREGROUND\",\"ISITACTIVELYRAININGORSNOWINGINTHEPICTURE\":\"NO\"},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"FISHER\",\"answers\":{\"HOWMANY\":\"1\",\"YOUNGPRESENT\":\"NO\",\"WHATBEHAVIORSDOYOUSEE\":[\"WALKINGRUNNING\",\"ALERT\"],\"ESTIMATEOFSNOWDEPTHSEETUTORIAL\":\"1020CM\",\"ISITACTIVELYRAININGORSNOWINGINTHEPICTURE\":\"NO\"},\"filters\":{}}]}]", 
"[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]"
)), class = "data.frame", row.names = c(NA, -10L))

Answer 1

我并不完全清楚您正在寻找什么输出格式。有很多不同的方法可以做到这一点。此外，数据结构中的数组（每个数组中只有一个对象）有点复杂，因为它们可以包含更多对象。

无论如何，感谢spread_all()，tidyjson 不需要太多代码。您还可以使用spread_values() 或enter_object(answers) 仅传播特定值以传播答案等。希望对您有所帮助！

library(tidyjson)
#> 
#> Attaching package: 'tidyjson'
#> The following object is masked from 'package:stats':
#> 
#>     filter
library(tibble)

annotations <- structure(list(annotations = c("[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"DEERWHITETAILED\",\"answers\":{\"HOWMANY\":\"1\",\"YOUNGPRESENT\":\"NO\",\"ANTLERSPRESENT\":\"NO\",\"WHATBEHAVIORSDOYOUSEE\":[\"ALERT\"],\"ESTIMATEOFSNOWDEPTHSEETUTORIAL\":\"NOSNOWBAREGROUND\",\"ISITACTIVELYRAININGORSNOWINGINTHEPICTURE\":\"NO\"},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"FISHER\",\"answers\":{\"HOWMANY\":\"1\",\"YOUNGPRESENT\":\"NO\",\"WHATBEHAVIORSDOYOUSEE\":[\"WALKINGRUNNING\",\"ALERT\"],\"ESTIMATEOFSNOWDEPTHSEETUTORIAL\":\"1020CM\",\"ISITACTIVELYRAININGORSNOWINGINTHEPICTURE\":\"NO\"},\"filters\":{}}]}]", 
                                              "[{\"task\":\"T0\",\"value\":[{\"choice\":\"NOTHINGHERE\",\"answers\":{},\"filters\":{}}]}]"
)), class = "data.frame", row.names = c(NA, -10L))

ant <- tibble(raw = annotations$annotations)

as.tbl_json(ant, json.column = "raw") %>%
  gather_array("object_id") %>% 
  spread_all() %>%
  enter_object("value") %>%
  gather_array("value_id") %>%
  spread_all() %>%
  as_tibble()
#> # A tibble: 10 x 9
#>    object_id task  value_id choice answers.HOWMANY answers.YOUNGPR…
#>        <int> <chr>    <int> <chr>  <chr>           <chr>           
#>  1         1 T0           1 NOTHI… <NA>            <NA>            
#>  2         1 T0           1 NOTHI… <NA>            <NA>            
#>  3         1 T0           1 DEERW… 1               NO              
#>  4         1 T0           1 NOTHI… <NA>            <NA>            
#>  5         1 T0           1 NOTHI… <NA>            <NA>            
#>  6         1 T0           1 NOTHI… <NA>            <NA>            
#>  7         1 T0           1 NOTHI… <NA>            <NA>            
#>  8         1 T0           1 NOTHI… <NA>            <NA>            
#>  9         1 T0           1 FISHER 1               NO              
#> 10         1 T0           1 NOTHI… <NA>            <NA>            
#> # … with 3 more variables: answers.ANTLERSPRESENT <chr>,
#> #   answers.ESTIMATEOFSNOWDEPTHSEETUTORIAL <chr>,
#> #   answers.ISITACTIVELYRAININGORSNOWINGINTHEPICTURE <chr>

^{由reprex package (v0.3.0) 于 2020 年 3 月 14 日创建}