在R中，我有两个数据框。第一个叫做d，看起来像这样：
d <- structure(list(id = c(384923059L, 384923060L, 384923061L, 386269528L
), decimalLatitude = c(46.08, 48.73333, 46.35, 58.16), decimalLongitude = c(-55.40333,
-52.96667, -52.73333, -61.088), datecollected = structure(c(2L,
3L, 2L, 1L), .Label = c("2015-08-20 12:00:00+02", "2015-11-19 12:00:00+01",
"2015-11-27 12:00:00+01"), class = "factor"), institutioncode = c("ARC",
"ARC", "ARC", "DFOCENARC"), individualcount = c(NA_real_, NA_real_,
NA_real_, NA_real_), depth = c(93, 95, 166, 216), resname = structure(c(1L,
1L, 1L, 2L), .Label = c("Atlantic Reference Centre Museum of Canadian Atlantic Organisms - Invertebrates and Fishes Data",
"DFO Central and Arctic Multi-species Stock Assessment Surveys"
), class = "factor"), originalscientificname = structure(c(1L,
1L, 1L, 1L), .Label = "Mallotus villosus", class = "factor"),
collectioncode = structure(c(1L, 1L, 1L, 2L), .Label = c("ARC",
"DFOSurvey_Modified Standard (14\") Campelen"), class = "factor"),
year = c(2015, 2015, 2015, 2015), month = c(11, 11, 11, 8
), day = c(19, 27, 19, 20)), row.names = c(7216L, 7217L,
7218L, 11980L), class = "data.frame")
str（d）揭示
'data.frame': 50 obs. of 6 variables:
$ layer_name: num 0.506 1.556 2.668 3.856 5.14 ...
$ raw_min : num 0 1.03 2.11 3.26 4.5 ...
$ raw_max : num 1.03 2.11 3.26 4.5 5.84 ...
$ bin_min : int 0 1 2 3 5 6 7 9 11 13 ...
$ bin_max : int 0 1 2 4 5 6 8 10 12 15 ...
$ layer_no : int 1 2 3 4 5 6 7 8 9 10 ...
第二个数据帧称为c
c <- structure(list(layer_name = c(0.505760014, 1.55585527, 2.66768169,
3.85627985, 5.14036131, 6.5430336, 8.09251881, 9.82275009, 11.7736797,
13.9910383, 16.525322, 19.4298019, 22.757616, 26.5583, 30.8745613,
35.7402039, 41.1800232, 47.211895, 53.8506355, 61.1128387, 69.0216827,
77.6111603, 86.9294281, 97.0413132, 108.030281, 120, 133.075821,
147.40625, 163.164459, 180.549927, 199.789963, 221.141174, 244.890625,
271.356384, 300.887512, 333.862823, 370.688477, 411.793854, 457.62561,
508.639893, 565.292297, 628.026001, 697.258667, 773.368286, 856.678955,
947.447876, 1045.85425, 1151.99121, 1265.86145, 1387.37695),
raw_min = c(0, 1.030807642, 2.11176848, 3.26198077, 4.49832058,
5.841697455, 7.317776205, 8.95763445, 10.7982149, 12.882359,
15.25818015, 17.97756195, 21.09370895, 24.657958, 28.71643065,
33.3073826, 38.46011355, 44.1959591, 50.53126525, 57.4817371,
65.0672607, 73.3164215, 82.2702942, 91.98537065, 102.5357971,
114.0151405, 126.5379105, 140.2410355, 155.2853545, 171.857193,
190.169945, 210.4655685, 233.0158995, 258.1235045, 286.121948,
317.3751675, 352.27565, 391.2411655, 434.709732, 483.1327515,
536.966095, 596.659149, 662.642334, 735.3134765, 815.0236205,
902.0634155, 996.651063, 1098.92273, 1208.92633, 1326.6192
), raw_max = c(1.030807642, 2.11176848, 3.26198077, 4.49832058,
5.841697455, 7.317776205, 8.95763445, 10.7982149, 12.882359,
15.25818015, 17.97756195, 21.09370895, 24.657958, 28.71643065,
33.3073826, 38.46011355, 44.1959591, 50.53126525, 57.4817371,
65.0672607, 73.3164215, 82.2702942, 91.98537065, 102.5357971,
114.0151405, 126.5379105, 140.2410355, 155.2853545, 171.857193,
190.169945, 210.4655685, 233.0158995, 258.1235045, 286.121948,
317.3751675, 352.27565, 391.2411655, 434.709732, 483.1327515,
536.966095, 596.659149, 662.642334, 735.3134765, 815.0236205,
902.0634155, 996.651063, 1098.92273, 1208.92633, 1326.6192,
1387), bin_min = c(0L, 1L, 2L, 3L, 5L, 6L, 7L, 9L, 11L, 13L,
16L, 18L, 21L, 25L, 29L, 33L, 39L, 44L, 51L, 58L, 65L, 73L,
82L, 92L, 103L, 114L, 127L, 140L, 155L, 172L, 190L, 211L,
233L, 258L, 286L, 317L, 352L, 391L, 435L, 483L, 537L, 597L,
663L, 735L, 815L, 902L, 997L, 1099L, 1209L, 1327L), bin_max = c(0L,
1L, 2L, 4L, 5L, 6L, 8L, 10L, 12L, 15L, 17L, 20L, 24L, 28L,
32L, 38L, 43L, 50L, 57L, 64L, 72L, 81L, 91L, 102L, 113L,
126L, 139L, 154L, 171L, 189L, 210L, 232L, 257L, 285L, 316L,
351L, 390L, 434L, 482L, 536L, 596L, 662L, 734L, 814L, 901L,
996L, 1098L, 1208L, 1326L, 1387L), layer_no = 1:50), class = "data.frame", row.names = c(NA,
-50L))
str（c）揭示
'data.frame': 15 obs. of 13 variables:
$ id : int 384923059 384923060 384923061 386269528 386270555 386270577 386270682 386272010 386272026 386272096 ...
$ decimalLatitude : num 46.1 48.7 46.4 58.2 61.6 ...
$ decimalLongitude : num -55.4 -53 -52.7 -61.1 -69.7 ...
$ datecollected : Factor w/ 13219 levels "","1854-07-02 12:00:00+00:17:30",..: 13218 13219 13218 13208 13209 13209 13210 13211 13212 13212 ...
$ institutioncode : chr "ARC" "ARC" "ARC" "DFOCENARC" ...
$ individualcount : num NA NA NA NA NA NA NA NA NA NA ...
$ depth : num 93 95 166 216 289 227 149 223 440 451 ...
$ resname : Factor w/ 39 levels "Arctic Marine Fish Museum Specimens",..: 3 3 3 14 14 14 14 14 14 14 ...
$ originalscientificname: Factor w/ 2 levels "Mallotus catervarius",..: 2 2 2 2 2 2 2 2 2 2 ...
$ collectioncode : Factor w/ 98 levels "","12.190","14.102",..: 35 35 35 59 58 58 58 58 58 58 ...
$ year : num 2015 2015 2015 2015 2015 ...
$ month : num 11 11 11 8 8 8 8 9 9 9 ...
$ day : num 19 27 19 20 28 28 29 9 10 10 ...
我想对d中的每一行，找到d$depth在>= c$binmin & < c$binmax的位置，然后将c$layer_name中的相应值添加到d$depth_layer。其中d$depth == NA，d$depthlayer也将== NA
在上面的示例数据帧中，结果数据帧d如下所示：
id depth depth_layer
1 1 1.55585527
2 5 5.14036131
3 NA NA
4 6 6.5430336
5 3 3.85627985
我尝试创建一个for循环
for (i in 1:nrow(d)){
if (d$depth[i] >= c$bin_min & d$depth[i] <= c$bin_max) {
d$depth_layer[i] <- c$layer_name
} else {
d$depth_layer[i] <- NA
}
}
但是它给出了以下错误：
�>=� not meaningful for factors�<=� not meaningful for factorsthe condition has length > 1 and only the first element will be usedError in if (d$depth[i] >= c$bin_min & d$depth[i] <= : missing value where TRUE/FALSE needed
我不确定如何修复循环。感谢您的帮助。
附加
正如@forestfanjoe在评论中指出的那样，我的变量之一（d$depth）是一个因素。将其更改为数字（as.numeric之后，@ forestfanjoe和@TinglTanglBob解决方案都可以使用。
答案 0 :(得分：2)
这对您有用吗？
d <- data.frame("id" = c(1:5), "depth" = c(1, 5, NA, 6, 3))
c <- data.frame(matrix(data = c(
0, 0, 1, 0.505760014,
1, 1, 2, 1.55585527,
2, 2, 3, 2.66768169,
3, 4, 4, 3.85627985,
5, 5, 5, 5.14036131,
6, 6, 6, 6.5430336,
7, 8, 7, 8.09251881), ncol = 4, byrow = T))
names(c) <- c("bin_min", "bin_max", "layer_no", "layer_name")
check_depth <- function(d_temp)
{
print(d_temp)
if(is.na(d_temp)) return(NA) # if d_temp is na just return NA
layer_name_temp <- c$layer_name[which(c$bin_min <= d_temp & c$bin_max >= d_temp)]
if(length(layer_name_temp) > 1) layer_name_temp <- layer_name_temp[1] # in case there are more hits, the first one is taken
return(layer_name_temp)
}
d$depth_layer <- sapply(d$depth, check_depth)
d
d的输出
> d
id depth depth_layer
1 1 1 1.555855
2 2 5 5.140361
3 3 NA NA
4 4 6 6.543034
5 5 3 3.856280
答案 1 :(得分：1)
类似于TinglTanglBob的解决方案：
d <- read.table(
text =
"
id depth
1 1
2 5
3 NA
4 6
5 3
", header = T)
c <- read.table(
text = "
bin_min bin_max layer_no layer_name
0 0 1 0.505760014
1 1 2 1.55585527
2 2 3 2.66768169
3 4 4 3.85627985
5 5 5 5.14036131
6 6 6 6.5430336
7 8 7 8.09251881
", header = T)
如果您需要将其作为for循环：
for (i in 1:nrow(d)){
if(!is.na(d$depth[i])) {
rw <- which(d$depth[i] >= c$bin_min & d$depth[i] <= c$bin_max)
d$depth_layer[i] <- c$layer_name[rw]
} else {
d$depth_layer[i] <- NA
}
}
您也可以尝试vapply：
d$depth_layer <- vapply(d$depth,
function(x) {
if(is.na(x)) return(NA)
rw <- which(x >= c$bin_min & x <= c$bin_max)
c$layer_name[rw]
}, 0)