我正在尝试提取 JSON 数据，它是 CSV 文件中的一列。到目前为止，我已经以正确的格式提取了列，但只有在变量类型为 factor 时，格式才正确。但是我无法使用jsonlite包将因子转换为 json 文件。
[1] {"id":509746197991998767,"visibility":{"percentage":100,"time":149797,"visible1":true,"visible2":false,"visible3":false,"activetab":true},"interaction":{"mouseovercount":1,"mouseovertime":1426,"videoplaytime":0,"engagementtime":0,"expandtime":0,"exposuretime":35192}}
另一种方法是stringsAsFactors = F在导入时使用，但我正在努力使格式正确，其中每个条目如下所示：
[1] "{\"id\":509746197991998767,\"visibility\":{\"percentage\":100,\"time\":149797,\"visible1\":true,\"visible2\":false,\"visible3\":false,\"activetab\":true},\"interaction\":{\"mouseovercount\":1,\"mouseovertime\":1426,\"videoplaytime\":0,\"engagementtime\":0,\"expandtime\":0,\"exposuretime\":35192}}"
我在这里遗漏了一些明显的东西吗？我只是想提取JSON位于 CSV 文件中的文件。
这是 CSV 文件的一个小例子：
"","CookieID","UnloadVars"
"1",-8857188784608690176,"{""id"":509746197991998767,""visibility"":{""percentage"":100,""time"":149797,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":1,""mouseovertime"":1426,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":35192}}"
"2",-1695626857458244096,"{""id"":2917654329769114342,""visibility"":{""percentage"":46,""time"":0,""visible1"":false,""visible2"":false,""visible3"":false,""activetab"":true}}"
"3",437299165071669184,"{""id"":2252707957388071809,""visibility"":{""percentage"":99,""time"":10168,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":0,""mouseovertime"":0,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":542},""clicks"":[{""x"":105,""y"":449}]}"
"4",292660729552227520,""
"5",7036383942916227072,"{""id"":2299674593327687292,""visibility"":{""percentage"":76,""time"":1145,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":0,""mouseovertime"":0,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":74},""clicks"":[{""x"":197,""y"":135},{""x"":197,""y"":135}]}"
问候，
弗雷德里克。
df <- readr::read_csv('"","CookieID","UnloadVars"
"1",-8857188784608690176,"{""id"":509746197991998767,""visibility"":{""percentage"":100,""time"":149797,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":1,""mouseovertime"":1426,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":35192}}"
"2",-1695626857458244096,"{""id"":2917654329769114342,""visibility"":{""percentage"":46,""time"":0,""visible1"":false,""visible2"":false,""visible3"":false,""activetab"":true}}"
"3",437299165071669184,"{""id"":2252707957388071809,""visibility"":{""percentage"":99,""time"":10168,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":0,""mouseovertime"":0,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":542},""clicks"":[{""x"":105,""y"":449}]}"
"4",292660729552227520,""
"5",7036383942916227072,"{""id"":2299674593327687292,""visibility"":{""percentage"":76,""time"":1145,""visible1"":true,""visible2"":false,""visible3"":false,""activetab"":true},""interaction"":{""mouseovercount"":0,""mouseovertime"":0,""videoplaytime"":0,""engagementtime"":0,""expandtime"":0,""exposuretime"":74},""clicks"":[{""x"":197,""y"":135},{""x"":197,""y"":135}]}"',
col_types = "-cc")
使用jsonlite::fromJSON在每个单独的值，则tidyr::unnest
library(dplyr)
f <- function(.x)
if (is.na(.x) || .x == "") data.frame()[1, ] else
as.data.frame(jsonlite::fromJSON(.x))
df %>%
tidyr::unnest(UnloadVars = lapply(UnloadVars, f)) %>%
mutate_at(vars(ends_with("id")), as.character)
# A tibble: 6 x 16
# CookieID id visibility.percentage visibility.time visibility.visible1 visibility.visible2 visibility.visible3 visibility.activetab interaction.mouseovercount interaction.mouseovertime interaction.videoplaytime interaction.engagementtime interaction.expandtime interaction.exposuretime clicks.x clicks.y
# <chr> <chr> <int> <int> <lgl> <lgl> <lgl> <lgl> <int> <int> <int> <int> <int> <int> <int> <int>
# 1 -8857188784608690176 509746197991998784 100 149797 TRUE FALSE FALSE TRUE 1 1426 0 0 0 35192 NA NA
# 2 -1695626857458244096 2917654329769114112 46 0 FALSE FALSE FALSE TRUE NA NA NA NA NA NA NA NA
# 3 437299165071669184 2252707957388071936 99 10168 TRUE FALSE FALSE TRUE 0 0 0 0 0 542 105 449
# 4 292660729552227520 <NA> NA NA NA NA NA NA NA NA NA NA NA NA NA NA
# 5 7036383942916227072 2299674593327687168 76 1145 TRUE FALSE FALSE TRUE 0 0 0 0 0 74 197 135
# 6 7036383942916227072 2299674593327687168 76 1145 TRUE FALSE FALSE TRUE 0 0 0 0 0 74 197 135
本文收集自互联网，转载请注明来源。
如有侵权，请联系[email protected] 删除。
我来说两句