如何使用R解析DataFrame列中的JSON
我怎么从这里来如何使用R解析DataFrame列中的JSON,json,r,Json,R,我怎么从这里来 | ID | JSON Request | ============================================================================== | 1 | {"user":"xyz1","weightmap": {"P1":0,"P2":100}, "domains":["a1","b1"]} | -----
| ID | JSON Request |
==============================================================================
| 1 | {"user":"xyz1","weightmap": {"P1":0,"P2":100}, "domains":["a1","b1"]} |
------------------------------------------------------------------------------
| 2 | {"user":"xyz2","weightmap": {"P1":100,"P2":0}, "domains":["a2","b2"]} |
------------------------------------------------------------------------------
此处(要求在第2列中创建一个JSON表):
以下是生成data.frame的代码:
raw_df <-
data.frame(
id = 1:2,
json =
c(
'{"user": "xyz2", "weightmap": {"P1":100,"P2":0}, "domains": ["a2","b2"]}',
'{"user": "xyz1", "weightmap": {"P1":0,"P2":100}, "domains": ["a1","b1"]}'
),
stringsAsFactors = FALSE
)
raw_df我会选择jsonlite包,并结合使用mapply、一个转换函数和数据。表的rbindlist
# data
raw_df <- data.frame(id = 1:2, json = c('{"user": "xyz2", "weightmap": {"P1":100,"P2":0}, "domains": ["a2","b2"]}', '{"user": "xyz1", "weightmap": {"P1":0,"P2":100}, "domains": ["a1","b1"]}'), stringsAsFactors = FALSE)
# libraries
library(jsonlite)
library(data.table)
# 1) First, make a transformation function that works for a single entry
f <- function(json, id){
# transform json to list
tmp <- jsonlite::fromJSON(json)
# transform list to data.frame
tmp <- as.data.frame(tmp)
# add id
tmp$id <- id
# return
return(tmp)
}
# 2) apply it via mapply
json_dfs <-
mapply(f, raw_df$json, raw_df$id, SIMPLIFY = FALSE)
# 3) combine the fragments via rbindlist
clean_df <-
data.table::rbindlist(json_dfs)
# 4) et-voila
clean_df
## user weightmap.P1 weightmap.P2 domains id
## 1: xyz2 100 0 a2 1
## 2: xyz2 100 0 b2 1
## 3: xyz1 0 100 a1 2
## 4: xyz1 0 100 b1 2
#数据
raw_df无法使展平参数按我的预期工作,因此需要取消列表,然后在使用do.call进行rbinding之前“重新列表”:
library(jsonlite)
do.call( rbind,
lapply(raw_df$json,
function(j) as.list(unlist(fromJSON(j, flatten=TRUE)))
) )
user weightmap.P1 weightmap.P2 domains1 domains2
[1,] "xyz2" "100" "0" "a2" "b2"
[2,] "xyz1" "0" "100" "a1" "b1"
诚然,这将需要进一步处理,因为它强制所有的行为字符。如果您愿意使用长格式(对于域,在本例中为),这里有一个tidyverse解决方案(也使用jsonlite):
library(jsonlite)
图书馆(dplyr)
图书馆(purrr)
图书馆(tidyr)
d%
mutate(json=map(json,~fromJSON(.)%%>%as.data.frame())%%>%
unnest(json)
#>id用户weightmap.P1 weightmap.P2域
#>1 1 xyz1 0 100 a1
#>2 1 xyz1 0 100 b1
#>3 2 xyz2 100 0 a2
#>4 2 xyz2 100 0 b2
mutate…
正在将嵌套数据帧的字符串转换为列
unest…
正在将这些数据帧取消到多列中
使用tidyjson
install.packages(“tidyjson”)
库(tidyjson)
json_作为_df%spread_all
#保留列
json\u as\u df%as.tbl\u json(json.column=“json”)%%>%spread\u all
查看Jsonlite软件包。它将Json读入一个嵌套列表中,然后您可以轻松地将其改写为data.frames.+1,以尽可能多地使用基本R-尽管data.table::rbindlist的性能比do.call(rbind,
好几个级别,而不是as.data.frame
,现在应该使用as__-tible
。
library(jsonlite)
do.call( rbind,
lapply(raw_df$json,
function(j) as.list(unlist(fromJSON(j, flatten=TRUE)))
) )
user weightmap.P1 weightmap.P2 domains1 domains2
[1,] "xyz2" "100" "0" "a2" "b2"
[2,] "xyz1" "0" "100" "a1" "b1"
library(jsonlite)
library(dplyr)
library(purrr)
library(tidyr)
d <- data.frame(
id = c(1, 2),
json = c(
'{"user":"xyz1","weightmap": {"P1":0,"P2":100}, "domains":["a1","b1"]}',
'{"user":"xyz2","weightmap": {"P1":100,"P2":0}, "domains":["a2","b2"]}'
),
stringsAsFactors = FALSE
)
d %>%
mutate(json = map(json, ~ fromJSON(.) %>% as.data.frame())) %>%
unnest(json)
#> id user weightmap.P1 weightmap.P2 domains
#> 1 1 xyz1 0 100 a1
#> 2 1 xyz1 0 100 b1
#> 3 2 xyz2 100 0 a2
#> 4 2 xyz2 100 0 b2
library(jsonlite)
json = c(
'{"user":"xyz1","weightmap": {"P1":0,"P2":100}, "domains":["a1","b1"]}',
'{"user":"xyz2","weightmap": {"P1":100,"P2":0}, "domains":["a2","b2"]}'
)
json <- lapply( paste0("[", json ,"]"),
function(x) jsonlite::fromJSON(x))
df <- data.frame(matrix(unlist(json), nrow=2, ncol=5, byrow=T))
df <- df %>% unite(Domains, X4, X5, sep = ", ")
colnames(df) <- c("user", "P1", "P2", "domains")
head(df)
user P1 P2 domains
1 xyz1 0 100 a1, b1
2 xyz2 100 0 a2, b2
install.packages("tidyjson")
library(tidyjson)
json_as_df <- raw_df$json %>% spread_all
# retain columns
json_as_df <- raw_df %>% as.tbl_json(json.column = "json") %>% spread_all