如何基于R中的多列聚合数据帧？
我有以下df（如何基于R中的多列聚合数据帧？,r,R,我有以下df（dput（）在问题的末尾）： 我想要的是创建一个新的df，在这里我可以看到哪个人从（类型==“出发”）哪个区域（ID1）到（type==“到达”）哪个区域（ID1）以及在哪个出发点bin） 从上面示例的最后4行可以看出，同一人员可能有多个到达和离开。因此，重要的是将两个最接近的单元组合在一起（因此最小的增量bin） 因此，新的df应该如下所示： person departure arrival bin 514677 347 379 36900 514
dput（）人从（类型==“出发”
）哪个区域（ID1
）到（type==“到达”
）哪个区域（ID1
）以及在哪个出发点bin
）
从上面示例的最后4行可以看出，同一人员可能有多个到达
和离开
。因此，重要的是将两个最接近的单元组合在一起（因此最小的增量bin
）
因此，新的df应该如下所示：
person departure arrival bin
514677 347 379 36900
514679 374 374 42300
514681 42 233 25200
514681 233 42 45000
...
library(dplyr)
data %>%
group_by(person) %>%
summarize(departure = ID1[type == "departure"][1],
arrival = ID1[type == "arrival"][1],
bin = bin[type == "departure"][1])
如您所见，此人514681
在42和233之间来回移动
我想你可以说我想根据人
来聚合数据。
我不太清楚如何才能做到这一点，如果能得到一些帮助，我将非常高兴
structure(list(link = c("793482", "66154", "858880", "858880",
"992830", "992830", "858880", "858880", "514143", "87723", "481929",
"481929", "87723", "87723", "964586", "87723", "1013453", "pt_8591034",
"973606", "pt_8591034", "481929", "481929", "87723", "87723",
"399738", "399738", "87723", "738635", "481929", "738635", "481929",
"738635", "301867", "89053", "92917", "92917", "981899", "981899",
"89053", "92917", "89053", "89053", "699715", "699715", "89053",
"452176", "738635", "452176", "738635", "641738", "712438", "699715",
"215822", "621953", "634264", "362138", "634264", "634264", "763815",
"763815", "631191", "631191", "763815", "763815", "634264", "634264",
"10826", "10826", "634264", "999977", "1046826", "1046826", "634264",
"999977", "848815", "848815", "999977", "999977", "848815", "848815",
"999977", "261239", "993653", "287772", "763815", "763815", "287772",
"494898", "824071", "594222", "494898", "494898", "452642", "452642",
"494898", "494898", "452642", "494898", "787840", "442285"),
person = c(514677L, 514677L, 514679L, 514679L, 514680L, 514680L,
514680L, 514680L, 514680L, 514681L, 514681L, 514681L, 514681L,
514682L, 514682L, 514683L, 514683L, 514684L, 514684L, 514684L,
514684L, 514684L, 514684L, 514685L, 514685L, 514685L, 514685L,
514688L, 514688L, 514688L, 514688L, 514690L, 514690L, 514707L,
514707L, 514707L, 514707L, 514707L, 514707L, 514708L, 514708L,
514709L, 514709L, 514709L, 514709L, 514710L, 514710L, 514710L,
514710L, 514711L, 514711L, 514733L, 514733L, 514757L, 514757L,
514757L, 514757L, 514759L, 514759L, 514759L, 514759L, 514759L,
514759L, 514759L, 514759L, 514760L, 514760L, 514760L, 514760L,
514774L, 514774L, 514774L, 514774L, 514774L, 514774L, 514774L,
514774L, 514774L, 514774L, 514774L, 514774L, 514782L, 514782L,
514786L, 514786L, 514786L, 514786L, 514802L, 514802L, 514802L,
514802L, 514803L, 514803L, 514803L, 514803L, 514803L, 514803L,
514804L, 514804L, 514805L), type = c("departure", "arrival",
"departure", "arrival", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"arrival", "departure", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"arrival", "departure", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure", "arrival", "departure",
"arrival", "departure", "arrival", "departure", "arrival",
"departure", "arrival", "departure"), ID1 = c(347L, 379L,
374L, 374L, 140L, 140L, 374L, 374L, 401L, 42L, 233L, 233L,
42L, 42L, 496L, 42L, 235L, 172L, 231L, 172L, 233L, 233L,
42L, 42L, 267L, 267L, 42L, 58L, 233L, 58L, 233L, 58L, 292L,
96L, 264L, 264L, 26L, 26L, 96L, 264L, 96L, 96L, 266L, 266L,
96L, 57L, 58L, 57L, 58L, 123L, 55L, 266L, 77L, 412L, 407L,
410L, 407L, 407L, 297L, 297L, 169L, 169L, 297L, 297L, 407L,
407L, 566L, 566L, 407L, 403L, 380L, 380L, 407L, 403L, 436L,
436L, 403L, 403L, 436L, 436L, 403L, 545L, 324L, 448L, 297L,
297L, 448L, 209L, 152L, 205L, 209L, 209L, 204L, 204L, 209L,
209L, 204L, 209L, 383L, 181L), bin = c(36900, 36900, 42300,
46800, 31500, 32400, 34200, 61200, 72000, 25200, 27900, 45000,
45900, 27900, 31500, 30600, 33300, 56700, 56700, 60300, 61200,
63900, 65700, 28800, 32400, 75600, 77400, 24300, 26100, 45900,
47700, 51300, 53100, 27900, 31500, 36900, 38700, 41400, 42300,
62100, 63900, 15300, 16200, 45900, 47700, 35100, 35100, 67500,
67500, 63900, 65700, 45900, 46800, 63000, 64800, 90000, 90900,
27000, 28800, 45000, 46800, 63000, 67500, 68400, 72000, 48600,
50400, 53100, 55800, 37800, 38700, 40500, 41400, 47700, 48600,
51300, 52200, 62100, 63000, 63900, 64800, 22500, 24300, 19800,
20700, 54000, 57600, 21600, 22500, 55800, 56700, 36900, 38700,
51300, 52200, 62100, 63900, 30600, 34200, 33300)), row.names = c(1311752L,
1020897L, 1376554L, 1374956L, 1567933L, 1568804L, 1378922L, 1378604L,
796332L, 1396610L, 726547L, 723875L, 1396595L, 1398179L, 1513826L,
1396821L, 27568L, 1607272L, 1542798L, 1606758L, 721147L, 720198L,
1397549L, 1398033L, 621908L, 626763L, 1397225L, 1184210L, 729418L,
1185149L, 728038L, 1183207L, 465692L, 1426554L, 1460666L, 1457289L,
1551709L, 1550925L, 1429217L, 1461183L, 1427235L, 1428930L, 1117203L,
1119814L, 1431191L, 683362L, 1183236L, 684338L, 1184602L, 990483L,
1142535L, 1125893L, 288323L, 947577L, 966966L, 544664L, 969372L,
964351L, 1230180L, 1231933L, 960341L, 960438L, 1238195L, 1241438L,
965853L, 964667L, 105034L, 106179L, 966724L, 1586724L, 72120L,
76232L, 969048L, 1587092L, 1360314L, 1361152L, 1585499L, 1586919L,
1361549L, 1359631L, 1587109L, 378600L, 1573640L, 428095L, 1236840L,
1235995L, 430374L, 757402L, 1331227L, 916001L, 760182L, 757620L,
686066L, 685765L, 759010L, 760140L, 687455L, 758617L, 1287055L,
676520L), class = "data.frame")
使用dplyr
，可能是这样的：
person departure arrival bin
514677 347 379 36900
514679 374 374 42300
514681 42 233 25200
514681 233 42 45000
...
library(dplyr)
data %>%
group_by(person) %>%
summarize(departure = ID1[type == "departure"][1],
arrival = ID1[type == "arrival"][1],
bin = bin[type == "departure"][1])
这里是一个试图满足附加逻辑的改进版本。既然问题不太清楚，我很肯定它还不是100%好
data %>%
arrange(person, bin) %>%
group_by(person) %>%
mutate(pair = rep(row_number(), each = 2, length.out = n())) %>%
group_by(person, pair) %>%
summarize(departure = ID1[type == "departure"][1],
arrival = ID1[type == "arrival"][1],
bin = bin[type == "departure"][1])
在base R中，我们可以分割数据，只保留超过1行的person/bin组合（表示有到达和离开），然后提取数据
splitdata <- split(df,with(df,paste0(person,bin)))
splitdata <- splitdata[sapply(splitdata,nrow)>1]
do.call(rbind,
lapply(splitdata, function(x)
data.frame(
person = x[1,2],
departure = x$ID1[x$type == "departure"],
arrival = x$ID1[x$type == "arrival"],
bin = x[1,5])))
514679人的到达和离开箱子不一样。那么，你只是想显示出发行李箱？非常感谢，这似乎部分起到了作用。恐怕我的描述太模糊了（我会修改这个问题）。一个人
可能有多个到达
和离开
。因此，必须以您呈现的方式考虑和组合最接近的内容。是否可以调整代码以实现此目的？您是否可以添加这样一个案例以获得预期的结果？有可能同一个人多次出现在输出中吗？我编辑了所需的输出：）感谢您查看itHmm，仍然没有很好定义的查询。例如，514680人有五行。他的产出会是什么样子？同一行李厢内是否可能有多个离港航班？（也许“链接”会有帮助）。如果行数不均匀，我希望是NA。可能在同一个箱子内有多个发车（每个箱子包含900秒，链接为ID1）。如果每个箱子和每个人都有一个以上的出发点，我会在下一步删除它们，因为很难区分出发点和目的地。非常感谢！不幸的是，我收到了一个错误：`` data.frame中的错误（person=x[1,2]，deposition=x$ID1[x$type==“deposition”]），参数表示行数不同：1,0``您知道这里可能存在什么问题吗？