在 R 中读取 JSON 文件时出现问题

Question

我有一个 JSON 文件（从 mongoDB 导出），我想将它加载到 R 中。该文档大小约为 890 MB，包含 12 个字段的大约 63,000 行。这些字段是数字、字符和日期。我想最终得到一个 63000 x 12 的数据框。

lines <-  readLines("fb2013.json")

结果：jFile 包含 char 类中的所有 63,000 个元素，并且所有字段都集中在一个字段中。

每个文件看起来像这样：

"{ \"_id\" : \"10151271769737669\", \"cmets_count\" : 36, \"created_at\" : { \"$date\" : 1357941938000 }, \"icon\" : \" http://blahblah.gif\", \"likes_count\" : 450, \"link\" : \"http://www.blahblahblah.php\", \"message\" : \"我希望我能弄清楚这个！\", \"page_category\" : \"Computers\", \"page_id\" : \"30968999999\", \"page_name\" : \"NothingButTrouble\", \"type\" : \ "照片\", \"updated_at\" : { \"$date\" : 1358210153000 } }"

使用 rjson，

jFile <- fromJSON(paste(readLines("fb2013.json"), collapse=""))

只有第一行被读入 jFile 但有 12 个字段。

使用 RJSONIO：

jFile <- fromJSON(lines)

结果如下：

Warning messages:
1: In if (is.na(encoding)) return(0L) :
  the condition has length > 1 and only the first element will be used

同样，只有第一行被读入 jFile，共有 12 个字段。

rjson 和 RJSONIO 的输出如下所示：

$`_id`
[1] "1018535"

$comments_count
[1] 0

$created_at
       $date 
1.357027e+12 

$icon
[1] "http://blah.gif"

$likes_count
[1] 20

$link
[1] "http://www.chachacha"

$message
[1] "I'd love to figure this out."

$page_category
[1] "Internet/software"

$page_id
[1] "3924395872345878534"

$page_name
[1] "Not Entirely Hopeless"

$type
[1] "photo"

$updated_at
       $date 
1.357027e+12 

Answer 1

试试

library(rjson)
path <- "WHERE/YOUR/JSON/IS/SAVED"
c <- file(path, "r")
l <- readLines(c, -1L)
json <- lapply(X=l, fromJSON)

Answer 2

既然你想要一个 data.frame，试试这个：

# three copies of your sample...
line.1<- "{ \"_id\" : \"10151271769737669\", \"comments_count\" : 36, \"created_at\" : { \"$date\" : 1357941938000 }, \"icon\" : \"http://blahblah.gif\", \"likes_count\" : 450, \"link\" : \"http://www.blahblahblah.php\", \"message\" : \"I wish I could figure this out!\", \"page_category\" : \"Computers\", \"page_id\" : \"30968999999\", \"page_name\" : \"NothingButTrouble\", \"type\" : \"photo\", \"updated_at\" : { \"$date\" : 1358210153000 } }" 
line.2<- "{ \"_id\" : \"10151271769737669\", \"comments_count\" : 36, \"created_at\" : { \"$date\" : 1357941938000 }, \"icon\" : \"http://blahblah.gif\", \"likes_count\" : 450, \"link\" : \"http://www.blahblahblah.php\", \"message\" : \"I wish I could figure this out!\", \"page_category\" : \"Computers\", \"page_id\" : \"30968999999\", \"page_name\" : \"NothingButTrouble\", \"type\" : \"photo\", \"updated_at\" : { \"$date\" : 1358210153000 } }" 
line.3<- "{ \"_id\" : \"10151271769737669\", \"comments_count\" : 36, \"created_at\" : { \"$date\" : 1357941938000 }, \"icon\" : \"http://blahblah.gif\", \"likes_count\" : 450, \"link\" : \"http://www.blahblahblah.php\", \"message\" : \"I wish I could figure this out!\", \"page_category\" : \"Computers\", \"page_id\" : \"30968999999\", \"page_name\" : \"NothingButTrouble\", \"type\" : \"photo\", \"updated_at\" : { \"$date\" : 1358210153000 } }" 
x <- paste(line.1, line.2, line.3, sep="\n")
lines <-  readLines(textConnection(x))
library(rjson)

# this is the important bit
df <- data.frame(do.call(rbind,lapply(lines,fromJSON)))
ncol(df)
# [1] 12

# finally, there's some cleaning up to do...
df$created_at
# [[1]]
# [[1]]$`$date`
# [1] 1.357942e+12
# ...
df$created_at <- as.POSIXlt(unname(unlist(df$created_at)/1000),origin="1970-01-01")
df$created_at
# [1] "2013-01-11 17:05:38 EST" "2013-01-11 17:05:38 EST" "2013-01-11 17:05:38 EST"

df$updated_at <- as.POSIXlt(unname(unlist(df$updated_at)/1000),origin="1970-01-01")

请注意，此转换假定日期存储为自纪元以来的毫秒数。