Question

我想要完成的是将列拆分为同一个表中的多个列。

我的数据：

eventCategory   eventAction  eVentLabel
HomePage        Click        {"Name":"Ariel","number":"aaa"}
HomePage        Click        {"Name":"Dan","number":"bbb"}
HomePage        Click        {"Name":"Daf","number":"ccc"}

我需要什么：

eventCategory   eventAction eVentLabel                      Name    number
HomePage        Click       {"Name":"Ariel","number":"aaa"} Ariel   aaa
HomePage        Click       {"Name":"Dan","number":"bbb"}   Dan     bbb
HomePage        Click       {"Name":"Daf","number":"ccc"}   Daf     ccc

Answer 1

Another tidyverse answer; this time employing jsonlite::fromJSON and purrr. This solution transparently handles additional columns embedded in the JSON and fills missing values appropriately.

library(tidyverse)
library(jsonlite)

data.raw <- 'eventCategory  eventAction eVentLabel
HomePage    Click   {"Name":"Ariel","number":"aaa"}
HomePage    Click   {"Name":"Dan","number":"bbb"}
HomePage    Click   {"Name":"Daf","number":"ccc"}'

data = read_tsv(data.raw)

data %>%
    mutate(new_cols = map(eVentLabel, fromJSON),
           new_cols = map(new_cols, as_data_frame)) %>%
    unnest(new_cols)

#> # A tibble: 3 x 5
#>   eventCategory eventAction                      eVentLabel  Name number
#>           <chr>       <chr>                           <chr> <chr>  <chr>
#> 1      HomePage       Click {"Name":"Ariel","number":"aaa"} Ariel    aaa
#> 2      HomePage       Click   {"Name":"Dan","number":"bbb"}   Dan    bbb
#> 3      HomePage       Click   {"Name":"Daf","number":"ccc"}   Daf    ccc

Please note that unnest will drop all rows that have null values in the data. Consider this example:

data.raw <- 'eventCategory  eventAction eVentLabel
HomePage    Click   {"Name":"Ariel","number":"aaa"}
HomePage    Click   {"Name":"Dan","number":"bbb"}
HomePage    Click   {"Name":"Daf","number":"ccc"}
HomePage    Click   {}
HomePage    Click   {"Account": "010001"}'

data = read_tsv(data.raw)

data %>%
    mutate(new_cols = map(eVentLabel, fromJSON),
           new_cols = map(new_cols, as_data_frame)) %>%
    unnest(new_cols)

#> # A tibble: 4 x 6
#>   eventCategory eventAction                      eVentLabel  Name number   Account
#>           <chr>       <chr>                           <chr> <chr>  <chr>     <chr>
#> 1      HomePage       Click {"Name":"Ariel","number":"aaa"} Ariel    aaa      <NA>
#> 2      HomePage       Click   {"Name":"Dan","number":"bbb"}   Dan    bbb      <NA>
#> 3      HomePage       Click   {"Name":"Daf","number":"ccc"}   Daf    ccc      <NA>
#> 4      HomePage       Click           {"Account": "010001"}  <NA>   <NA>      010001

Note that we drop the row that has empty JSON ({}) in the original data. We also add a column for the new variable Account, and fill in NA values appropriately.

Finally, trying to run if there are blank lines on the JSON (e.g. ("" or NA)) rows will fail; you need to remove those before passing into fromJSON with a filter statement. By example:

data %>%
    filter(nchar(eVentLabel) > 0, !is.na(eVentLabel)) %>%
    ...

Answer 2

一种选择是将字符串分割为:以提取元素

v1 <- lapply(strsplit(gsub('[{"},]', ':', df1$eVentLabel), ":"), 
        function(x) {x1 <- trimws(x[nzchar(x)])
             setNames(x1[c(FALSE, TRUE)], x1[c(TRUE, FALSE)]) })[[1]]
df1[names(v1)] <- v1
df1
#  eventCategory eventAction                      eVentLabel  Name number
#1      HomePage       Click {"Name":"Ariel","number":"aaa"} Ariel    aaa

对于新数据集

res <- do.call(rbind, lapply(strsplit(gsub('[{"},]', ':', df2$eVentLabel), ":"),
              function(x) {x1 <- trimws(x[nzchar(x)])
              setNames(x1[c(FALSE, TRUE)], x1[c(TRUE, FALSE)]) }))
df2[names(res)] <- res
df2
#  eventCategory eventAction                      eVentLabel  Name number
#1      HomePage       Click {"Name":"Ariel","number":"aaa"} Ariel    aaa
#2      HomePage       Click   {"Name":"Dan","number":"bbb"}   Dan    bbb
#3      HomePage       Click   {"Name":"Daf","number":"ccc"}   Daf    ccc

数据

df1 <- structure(list(eventCategory = "HomePage", eventAction = "Click", 
eVentLabel = "{\"Name\":\"Ariel\",\"number\":\"aaa\"}"), 
.Names = c("eventCategory", 
"eventAction", "eVentLabel"), class = "data.frame", row.names = c(NA, 
-1L))

df2 <- structure(list(eventCategory = c("HomePage", "HomePage", "HomePage"
 ), eventAction = c("Click", "Click", "Click"), 
  eVentLabel = c("{\"Name\":\"Ariel\",\"number\":\"aaa\"}", 
 "{\"Name\":\"Dan\",\"number\":\"bbb\"}", "{\"Name\":\"Daf\",\"number\":\"ccc\"}"
 ), Name = c("Ariel", "Dan", "Daf"), number = c("aaa", "bbb", 
 "ccc")), .Names = c("eventCategory", "eventAction", "eVentLabel", 
 "Name", "number"), class = "data.frame", row.names = c(NA, -3L
 ))

Answer 3

tidyverse方法

library(tidyverse)
library(stringr) 

    df <- structure(list(eventCategory = c("HomePage", "HomePage", "HomePage"
), eventAction = c("Click", "Click", "Click"), eventLabel = c("{\"Name\":\"Ariel\",\"number\":\"aaa\"}", 
"{\"Name\":\"Dan\",\"number\":\"bbb\"}", "{\"Name\":\"Daf\",\"number\":\"ccc\"}"
)), .Names = c("eventCategory", "eventAction", "eventLabel"), row.names = c(NA, 
-3L), class = "data.frame")

  eventCategory eventAction                      eventLabel
1      HomePage       Click {"Name":"Ariel","number":"aaa"}
2      HomePage       Click   {"Name":"Dan","number":"bbb"}
3      HomePage       Click   {"Name":"Daf","number":"ccc"}

vars <- c("name", "number")

df %>% 
  separate(eventLabel, into = c("name", "number"), sep = ",") %>% 
  map_at(vars, ~str_split(., ":")) %>% 
  as_data_frame() %>% 
  unnest() %>% 
  map_at(vars, ~str_replace_all(., "[[:punct:]]", "")) %>% 
  as_data_frame() %>% 
  filter(name != "Name")

  eventCategory eventAction  name number
          <chr>       <chr> <chr>  <chr>
1      HomePage       Click Ariel    aaa
2      HomePage       Click   Dan    bbb
3      HomePage       Click   Daf    ccc

将数据框字符串列拆分为同一个表中的多个不同列

3 个答案:

数据