53

我有一个包含超过 1500 个 json 对象的文件,我想在 R 中使用这些对象。我已经能够将数据作为列表导入,但是在将其强制转换为有用的结构时遇到了麻烦。我想创建一个数据框,其中包含每个 json 对象的行和每个键:值对的列。

我用这个小的假数据集重现了我的情况:

[{"name":"Doe, John","group":"Red","age (y)":24,"height (cm)":182,"wieght (kg)":74.8,"score":null},
{"name":"Doe, Jane","group":"Green","age (y)":30,"height (cm)":170,"wieght (kg)":70.1,"score":500},
{"name":"Smith, Joan","group":"Yellow","age (y)":41,"height (cm)":169,"wieght (kg)":60,"score":null},
{"name":"Brown, Sam","group":"Green","age (y)":22,"height (cm)":183,"wieght (kg)":75,"score":865},
{"name":"Jones, Larry","group":"Green","age (y)":31,"height (cm)":178,"wieght (kg)":83.9,"score":221},
{"name":"Murray, Seth","group":"Red","age (y)":35,"height (cm)":172,"wieght (kg)":76.2,"score":413},
{"name":"Doe, Jane","group":"Yellow","age (y)":22,"height (cm)":164,"wieght (kg)":68,"score":902}]

数据的一些特点:

  • 这些对象都包含相同数量的键:值对,尽管其中一些值为空
  • 每个对象有两个非数字列(名称和组)
  • name是唯一标识符,有10个左右的组
  • 许多名称和组整体包含空格、逗号和其他标点符号。

基于这个问题:R list(structure(list())) to data frame,我尝试了以下方法:

json_file <- "test.json"
json_data <- fromJSON(json_file)
asFrame <- do.call("rbind.fill", lapply(json_data, as.data.frame))

使用我的真实数据和这个假数据,最后一行给了我这个错误:

Error in data.frame(name = "Doe, John", group = "Red", `age (y)` = 24,  : 
  arguments imply differing number of rows: 1, 0
4

6 回答 6

56

您只需要用 NA 替换您的 NULL:

require(RJSONIO)    

json_file <-  '[{"name":"Doe, John","group":"Red","age (y)":24,"height (cm)":182,"wieght (kg)":74.8,"score":null},
    {"name":"Doe, Jane","group":"Green","age (y)":30,"height (cm)":170,"wieght (kg)":70.1,"score":500},
    {"name":"Smith, Joan","group":"Yellow","age (y)":41,"height (cm)":169,"wieght (kg)":60,"score":null},
    {"name":"Brown, Sam","group":"Green","age (y)":22,"height (cm)":183,"wieght (kg)":75,"score":865},
    {"name":"Jones, Larry","group":"Green","age (y)":31,"height (cm)":178,"wieght (kg)":83.9,"score":221},
    {"name":"Murray, Seth","group":"Red","age (y)":35,"height (cm)":172,"wieght (kg)":76.2,"score":413},
    {"name":"Doe, Jane","group":"Yellow","age (y)":22,"height (cm)":164,"wieght (kg)":68,"score":902}]'


json_file <- fromJSON(json_file)

json_file <- lapply(json_file, function(x) {
  x[sapply(x, is.null)] <- NA
  unlist(x)
})

一旦每个元素都有一个非空值,就可以调用rbind而不会出现错误:

do.call("rbind", json_file)
     name           group    age (y) height (cm) wieght (kg) score
[1,] "Doe, John"    "Red"    "24"    "182"       "74.8"      NA   
[2,] "Doe, Jane"    "Green"  "30"    "170"       "70.1"      "500"
[3,] "Smith, Joan"  "Yellow" "41"    "169"       "60"        NA   
[4,] "Brown, Sam"   "Green"  "22"    "183"       "75"        "865"
[5,] "Jones, Larry" "Green"  "31"    "178"       "83.9"      "221"
[6,] "Murray, Seth" "Red"    "35"    "172"       "76.2"      "413"
[7,] "Doe, Jane"    "Yellow" "22"    "164"       "68"        "902"
于 2013-06-05T19:26:10.023 回答
36

如果您使用library(jsonlite)library(jsonify)

这两个都处理null值并将它们转换为NA,并且它们保留数据类型。

数据

json_file <-  '[{"name":"Doe, John","group":"Red","age (y)":24,"height (cm)":182,"wieght (kg)":74.8,"score":null},
{"name":"Doe, Jane","group":"Green","age (y)":30,"height (cm)":170,"wieght (kg)":70.1,"score":500},
{"name":"Smith, Joan","group":"Yellow","age (y)":41,"height (cm)":169,"wieght (kg)":60,"score":null},
{"name":"Brown, Sam","group":"Green","age (y)":22,"height (cm)":183,"wieght (kg)":75,"score":865},
{"name":"Jones, Larry","group":"Green","age (y)":31,"height (cm)":178,"wieght (kg)":83.9,"score":221},
{"name":"Murray, Seth","group":"Red","age (y)":35,"height (cm)":172,"wieght (kg)":76.2,"score":413},
{"name":"Doe, Jane","group":"Yellow","age (y)":22,"height (cm)":164,"wieght (kg)":68,"score":902}]'

jsonlite

library(jsonlite)
jsonlite::fromJSON( json_file )
#           name  group age (y) height (cm) wieght (kg) score
# 1    Doe, John    Red      24         182        74.8    NA
# 2    Doe, Jane  Green      30         170        70.1   500
# 3  Smith, Joan Yellow      41         169        60.0    NA
# 4   Brown, Sam  Green      22         183        75.0   865
# 5 Jones, Larry  Green      31         178        83.9   221
# 6 Murray, Seth    Red      35         172        76.2   413
# 7    Doe, Jane Yellow      22         164        68.0   902

str( jsonlite::fromJSON( json_file ) )
# 'data.frame': 7 obs. of  6 variables:
# $ name       : chr  "Doe, John" "Doe, Jane" "Smith, Joan" "Brown, Sam" ...
# $ group      : chr  "Red" "Green" "Yellow" "Green" ...
# $ age (y)    : int  24 30 41 22 31 35 22
# $ height (cm): int  182 170 169 183 178 172 164
# $ wieght (kg): num  74.8 70.1 60 75 83.9 76.2 68
# $ score      : int  NA 500 NA 865 221 413 902

json化

library(jsonify)
jsonify::from_json( json_file )
#           name  group age (y) height (cm) wieght (kg) score
# 1    Doe, John    Red      24         182        74.8    NA
# 2    Doe, Jane  Green      30         170        70.1   500
# 3  Smith, Joan Yellow      41         169        60.0    NA
# 4   Brown, Sam  Green      22         183        75.0   865
# 5 Jones, Larry  Green      31         178        83.9   221
# 6 Murray, Seth    Red      35         172        76.2   413
# 7    Doe, Jane Yellow      22         164        68.0   90


str( jsonify::from_json( json_file ) )
# 'data.frame': 7 obs. of  6 variables:
# $ name       : chr  "Doe, John" "Doe, Jane" "Smith, Joan" "Brown, Sam" ...
# $ group      : chr  "Red" "Green" "Yellow" "Green" ...
# $ age (y)    : int  24 30 41 22 31 35 22
# $ height (cm): int  182 170 169 183 178 172 164
# $ wieght (kg): num  74.8 70.1 60 75 83.9 76.2 68
# $ score      : int  NA 500 NA 865 221 413 902
于 2016-06-10T04:10:06.830 回答
2

要删除空值,请使用参数 nullValue

json_data <- fromJSON(json_file, nullValue = NA)
asFrame <- do.call("rbind.fill", lapply(json_data, as.data.frame))

这样你的输出中就不会有任何不必要的引号

于 2015-05-19T09:25:26.670 回答
1
library(rjson)
Lines <- readLines("yelp_academic_dataset_business.json") 
business <- as.data.frame(t(sapply(Lines, fromJSON)))

您可以尝试将 JSON 数据加载到 R 中

于 2016-11-02T19:04:01.860 回答
0

将包从更改rjsonjsonlite为我修复。

所以代替这个:

fromAPIPlantsPages <- rjson::fromJSON(content(apiGetPlants,type="text",encoding = "UTF-8"))

dfPlantenAPI <- as.data.frame(fromAPIPlantsPages)

我把它改成这样:

fromAPIPlantsPages <- jsonlite::fromJSON(content(apiGetPlants,type="text",encoding = "UTF-8"))

dfPlantenAPI <- as.data.frame(fromAPIPlantsPages)
于 2021-12-25T10:38:31.640 回答
0
dplyr::bind_rows(fromJSON(file_name))
于 2016-06-10T03:12:24.107 回答