Question

我有一个包含超过1500个json对象的文件，我想在R中使用。我已经能够将数据作为列表导入，但是很难将其强制转换为有用的结构。我想创建一个数据框，其中包含每个json对象的行和每个key：value对的列。

我用这个小的假数据集重新创建了我的情况：

[{"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}]

数据的一些功能：

对象都包含相同数量的键：值对一些值为null
每个对象（名称和组）
name是唯一标识符，有10个左右的组
许多名称和群组包含空格，逗号和其他标点符号。

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

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些假数据，最后一行给出了这个错误：

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

Answer 1

你只需要用NAs替换你的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)
})

每个元素都有一个非空值后，您可以调用rbind而不会收到错误：

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"

Answer 2

如果您使用library(jsonlite)和函数fromJSON，这非常简单。它还处理null值并将其转换为NA。

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}]'

library(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(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

Answer 3

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))

这样输出中就不会有任何不必要的引号

Answer 4

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

Answer 5

dplyr::bind_rows(fromJSON(file_name))

将导入的json数据导入数据框

5 个答案: