r - 使用 R 中的汇总查找汇总度量、非 NA 值和特定值进行分组

Question

我有这个示例数据集 (df)

structure(list(from = c("(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452", "(122) 212-3452", 
"(122) 212-3452", "(122) 212-3452", "(122) 212-3452"), to = c("(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542", "(700) 890-6542", "(700) 890-6542", "(700) 890-6542", 
"(700) 890-6542"), extension = c("9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls", "9205 - Raw IRS Calls", "9205 - Raw IRS Calls", 
"9205 - Raw IRS Calls"), forwarded_to = c(NA, "(323) 457-2039", 
"(310) 598-1753", "(818) 900-0706", "(818) 539-7811", "(213) 344-4965", 
"(213) 458-7662", "(818) 208-3012", "(818) 293-0175", "(818) 284-4238", 
"(818) 206-9506", "(310) 299-7340", "(310) 405-0875", "(213) 260-9113", 
"(213) 805-5208", "(818) 887-3058", "(424) 271-2141", "(213) 218-6579", 
"(818) 638-9466", "(213) 784-7164", "(323) 457-2038", "(213) 805-6959", 
"(228) 285-7898", "(213) 341-1055", "(213) 568-0979", "(213) 344-4905", 
"(818) 459-3811", NA, "(323) 457-2039", "(310) 598-1753", "(818) 900-0706", 
"(818) 539-7811", "(213) 344-4965", "(213) 458-7662", "(818) 208-3012", 
"(818) 293-0175", "(818) 284-4238", "(818) 206-9506", "(310) 299-7340", 
"(310) 405-0875", "(213) 260-9113", "(213) 805-5208", "(818) 887-3058", 
"(424) 271-2141", "(213) 218-6579", "(818) 638-9466", "(213) 784-7164", 
"(323) 457-2038", "(213) 805-6959", "(228) 285-7898", "(213) 341-1055", 
"(213) 568-0979", "(213) 344-4905", "(818) 459-3811"), date = c("Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", "Mon 12/31/2018", 
"Mon 12/31/2018"), time = structure(c(55440, 55440, 55440, 55440, 
55440, 55440, 55440, 55440, 55440, 55440, 55440, 55440, 55440, 
55440, 55440, 55440, 55440, 55440, 55440, 55440, 55500, 55500, 
55500, 55500, 55500, 55500, 55500, 55320, 55320, 55320, 55320, 
55320, 55320, 55320, 55320, 55320, 55320, 55320, 55320, 55320, 
55320, 55320, 55320, 55320, 55320, 55320, 55320, 55380, 55380, 
55380, 55380, 55380, 55380, 55380), class = c("hms", "difftime"
), units = "secs"), action = c("Phone Call", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "Phone Call", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", "FindMe", 
"FindMe", "FindMe", "FindMe"), action_result = c("Accepted", 
"No Answer", "No Answer", "No Answer", "No Answer", "No Answer", 
"No Answer", "No Answer", "No Answer", "IP Phone Offline", "No Answer", 
"No Answer", "No Answer", "No Answer", "No Answer", "No Answer", 
"No Answer", "No Answer", "No Answer", "No Answer", "Stopped", 
"Stopped", "IP Phone Offline", "Stopped", "Stopped", "Call connected", 
"Stopped", "Accepted", "No Answer", "No Answer", "No Answer", 
"No Answer", "No Answer", "No Answer", "No Answer", "No Answer", 
"IP Phone Offline", "No Answer", "No Answer", "No Answer", "No Answer", 
"No Answer", "No Answer", "No Answer", "No Answer", "No Answer", 
"No Answer", "Stopped", "Stopped", "IP Phone Offline", "Call connected", 
"Stopped", "Stopped", "Stopped"), result_description = c("The call connected to and was accepted by this number.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"This DigitalLine was either not plugged in or did not have an internet connection.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
NA, NA, "This DigitalLine was either not plugged in or did not have an internet connection.", 
NA, NA, "The call connected to and was accepted by this number.", 
NA, "The call connected to and was accepted by this number.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"This DigitalLine was either not plugged in or did not have an internet connection.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
"The phone number you dialed was not answered.", "The phone number you dialed was not answered.", 
NA, NA, "This DigitalLine was either not plugged in or did not have an internet connection.", 
"The call connected to and was accepted by this number.", NA, 
NA, NA), duration = structure(c(297, 52, 52, 51, 51, 51, 51, 
51, 51, 0, 51, 51, 51, 51, 51, 51, 51, 51, 51, 51, 9, 9, 0, 9, 
9, 236, 9, 71, 52, 52, 52, 51, 51, 51, 51, 51, 0, 51, 51, 51, 
51, 51, 51, 51, 51, 51, 51, 7, 7, 0, 13, 7, 7, 7), class = c("hms", 
"difftime"), units = "secs"), ID = c(19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L), CallConnected = c(FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE), who_answered = c("NA", 
"NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", 
"NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", 
"NA", "NA", "(213) 344-4905", "NA", "NA", "NA", "NA", "NA", "NA", 
"NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", 
"NA", "NA", "NA", "NA", "NA", "NA", "NA", "(213) 341-1055", "NA", 
"NA", "NA")), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-54L))

这显示调用电话和接听电话的电话号码的通话数据。 完整数据集有更多的数字对，但为了简洁起见，我只发布了一对

我想查找每对号码中 CallConnected 中 TRUE 的号码，即 who_answered 中的第一个电话号码，以及与调用已连接对应的持续时间值。我想过使用 group_by 和 summarise 但我想不出办法。

所需的输出如下所示:

from          | to           | CallConnected | WhoAnswered  | Duration
----------------------------------------------------------------------
(122) 212-3452|(700) 890-6542| 2             |(213) 344-4905| 00:03:56

Answer 1

使用dplyr，我们可以通过取TRUE值的sum来计算CallConnected的数量，找到第一个值非“NA”who_answered 列和 duration 中的第一个 TRUE 值。

library(dplyr)

df %>%
  group_by(from, to) %>%
  summarise(count_call = sum(CallConnected), 
            who_answered = who_answered[which.max(who_answered != "NA")],
            Duration = duration[which.max(CallConnected)])


#  from           to             count_call who_answered   Duration
#  <chr>          <chr>               <int> <chr>          <time>  
#1 (122) 212-3452 (700) 890-6542          2 (213) 344-4905 03'56"