Question

以下字符串中的json根据http://jsonlint.com/是正确的json但是tidyjson对象：

library(dplyr)
library(tidyjson)

json <- '
    [{"country":"us","city":"Portland","topics":[{"urlkey":"videogame","name":"Video Games","id":4471},{"urlkey":"board-games","name":"Board Games","id":19585},{"urlkey":"computer-programming","name":"Computer programming","id":48471},{"urlkey":"opensource","name":"Open Source","id":563}],"joined":1416349237000,"link":"http://www.meetup.com/members/156440062","bio":"Analytics engineer.  Primarily work in the Hadoop space.","lon":-122.65,"other_services":{},"name":"Aaron Wirick","visited":1443078098000,"self":{"common":{}},"id":156440062,"state":"OR","lat":45.56,"status":"active"}]
    '
    json %>% as.tbl_json %>% gather_keys

我明白了：

Error in gather_keys(.) : 1 records are values not objects

Answer 1

正如其中一条评论所述，gather_keys正在寻找具有数组的对象。你应该在这里使用的是gather_array。

此外，另一个答案使用更强力的方法来解析tidyjson包创建的JSON属性。如果需要，tidyjson提供了在更清洁的管道中处理这个问题的方法：

library(dplyr)
library(tidyjson)

json <- '
[{"country":"us","city":"Portland"
,"topics":[
 {"urlkey":"videogame","name":"Video Games","id":4471}
 ,{"urlkey":"board-games","name":"Board Games","id":19585}
 ,{"urlkey":"computer-programming","name":"Computer programming","id":48471}
 ,{"urlkey":"opensource","name":"Open Source","id":563}
]
,"joined":1416349237000
,"link":"http://www.meetup.com/members/156440062"
,"bio":"Analytics engineer.  Primarily work in the Hadoop space."
,"lon":-122.65,"other_services":{}
,"name":"Aaron Wirick","visited":1443078098000
,"self":{"common":{}}
,"id":156440062,"state":"OR","lat":45.56,"status":"active"
}]
'

mydf <- json %>% as.tbl_json %>% gather_array %>% 
spread_values(
 country=jstring('country')
 , city=jstring('city')
 , joined=jnumber('joined')
 , bio=jstring('bio')
) %>% 
enter_object('topics') %>% 
gather_array %>%
spread_values(urlkey=jstring('urlkey'))

如果阵列中有多个这样的对象，这个管道真的很棒。希望有用，即使事后很长时间！

Answer 2

由as.tbl_json生成的对象对我的思维方式有点奇怪，其中一个项目的名称为document.id，值为1.其属性中有一个名为{{ 1}}：

JSON

看看你可以看到，为了获得嵌入式列表对象的名称，你需要这样做：

json <- '
     [{"country":"us","city":"Portland","topics":[{"urlkey":"videogame","name":"Video Games","id":4471},{"urlkey":"board-games","name":"Board Games","id":19585},{"urlkey":"computer-programming","name":"Computer programming","id":48471},{"urlkey":"opensource","name":"Open Source","id":563}],"joined":1416349237000,"link":"http://www.meetup.com/members/156440062","bio":"Analytics engineer.  Primarily work in the Hadoop space.","lon":-122.65,"other_services":{},"name":"Aaron Wirick","visited":1443078098000,"self":{"common":{}},"id":156440062,"state":"OR","lat":45.56,"status":"active"}]
     '
    obj <-  json %>% as.tbl_json

> dput(obj)
structure(list(document.id = 1L), .Names = "document.id", row.names = 1L, class = c("tbl_json", 
"tbl", "data.frame"), JSON = list(list(structure(list(country = "us", 
    city = "Portland", topics = list(structure(list(urlkey = "videogame", 
        name = "Video Games", id = 4471L), .Names = c("urlkey", 
    "name", "id")), structure(list(urlkey = "board-games", name = "Board Games", 
        id = 19585L), .Names = c("urlkey", "name", "id")), structure(list(
        urlkey = "computer-programming", name = "Computer programming", 
        id = 48471L), .Names = c("urlkey", "name", "id")), structure(list(
        urlkey = "opensource", name = "Open Source", id = 563L), .Names = c("urlkey", 
    "name", "id"))), joined = 1416349237000, link = "http://www.meetup.com/members/156440062", 
    bio = "Analytics engineer.  Primarily work in the Hadoop space.", 
    lon = -122.65, other_services = structure(list(), .Names = character(0)), 
    name = "Aaron Wirick", visited = 1443078098000, self = structure(list(
        common = structure(list(), .Names = character(0))), .Names = "common"), 
    id = 156440062L, state = "OR", lat = 45.56, status = "active"), .Names = c("country", 
"city", "topics", "joined", "link", "bio", "lon", "other_services", 
"name", "visited", "self", "id", "state", "lat", "status")))))

希望我能得到更多帮助，但至少你了解错误的来源。（我也希望在该软件包的帮助页面上有更多示例。）

什么＆＃39;记录是值而不是对象＆＃39;在tidyjson

2 个答案: