How can I add condition in pipeline in R - r

My data was 450K (DNA methylation data). And the results below are from regional analysis. It contains three columns: the chromosome number, start position, and end position:
region <- structure(list(chr = c(2L, 2L, 2L, 3L, 4L, 5L, 5L, 5L, 6L, 6L, 7L, 8L, 10L, 11L, 12L, 15L, 16L, 18L, 18L, 21L, 22L), start = c(95663987L, 80531500L, 154334651L, 24536765L, 187476837L, 16179633L, 2751822L, 63461803L, 133562246L, 29521568L, 49813031L, 24772270L, 128593922L, 30038286L, 6649733L, 65913660L, 51184152L, 6414602L, 5543801L, 22370347L, 24890330L), end = c(95664360L, 80531899L, 154334652L, 24537302L, 187476838L, 16180267L, 2752602L, 63461931L, 133562777L, 29521715L, 49813487L, 24772351L, 128594418L, 30038311L, 6649995L, 65913661L, 51184887L, 6415253L, 5543946L, 22370759L, 24891142L)), class = "data.frame", row.names = c(4L, 12L, 15L, 14L, 20L,8L, 10L, 18L, 1L, 16L, 5L, 6L, 2L, 21L, 9L, 17L, 13L, 7L, 19L, 11L, 3L))
The distribution in my region is:
table(region$chr)
The first chromosome is chr2, chich contains four regions here.
Now I have another probe file, which contains probes with their chromosomes and positions. What I want to do is to extract the probes that are lociated in my target regions. Here is probe file:
probe <- structure(list(chr = c(6L, 12L, 16L, 1L, 13L, 17L, 16L, 13L, 3L, 17L, 20L, 8L, 12L, 17L, 8L, 6L, 15L, 16L, 16L, 16L, 6L, 1L, 7L, 18L, 2L, 8L, 16L, 10L, 11L, 12L, 1L, 15L, 1L, 11L, 13L, 13L, 6L, 6L, 9L, 12L, 1L, 12L, 13L, 13L, 6L, 1L, 2L, 3L, 11L, 22L, 15L, 11L, 19L, 19L, 1L, 6L, 10L, 3L, 4L, 17L, 10L, 8L, 6L, 2L, 8L, 16L, 1L, 2L, 16L, 9L, 6L, 19L, 10L, 4L, 4L, 17L, 11L, 4L, 1L, 1L, 5L, 3L, 12L, 16L, 7L, 11L, 4L, 6L, 19L, 14L, 17L, 1L, 4L, 7L, 11L, 5L, 5L, 2L, 2L, 8L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), pos = c(159064992L, 114367005L, 28835671L, 200003800L, 42692969L, 73780663L, 65236094L, 114057675L, 23713773L, 56326765L, 44142512L, 103668081L, 111806472L, 4437077L, 8871457L, 143771621L, 29993498L, 696801L, 79623625L, 69385761L, 30685686L, 76190435L, 14031049L, 3732002L, 32853151L, 146233339L, 71757240L, 131844944L, 128424176L, 89749142L, 27693242L, 57138252L, 43123399L, 57407842L, 29067224L, 53191387L, 30921630L, 107971593L, 125133314L, 109915400L, 46668882L, 14720858L, 67804654L, 23500367L, 170398571L, 150241781L, 85843232L, 15106710L, 33758223L, 44350860L, 83726483L, 76814245L, 3789435L, 55013663L, 166846008L, 150289488L, 3187835L, 169684620L, 1340602L, 35297146L, 61569177L, 122954569L, 71276472L, 9563665L, 9952926L, 81040735L, 15392793L, 55183957L, 27228679L, 139334396L, 44090748L, 3979938L, 125425262L, 10687769L, 503198L, 55191642L, 19735701L, 184244831L, 10738664L, 17446073L, 140739501L, 49384054L, 56618196L, 71324066L, 27221689L, 8041137L, 149033953L, 169224907L, 3933591L, 76450658L, 46152449L, 93250590L, 1025591L, 37024552L, 1360335L, 156277860L, 157098423L, 85980756L, 2575755L, 142138643L, 80531898L, 80531597L, 80531656L, 95664233L, 95664359L, 95664243L, 80531645L, 80531599L, 80531500L, 80531842L, 95663987L, 80531751L, 154334651L, 80531633L)), row.names = c("cg13598865", "cg02666265", "cg16662787", "cg10513702", "cg10970751", "cg08536977", "cg09084496", "cg08794696", "cg18648917", "cg20272962", "cg03013946", "cg07028608", "cg10361696", "cg06618629", "cg25307778", "cg00888489", "cg21092551", "cg07760369", "cg04317962", "cg08627125", "cg18512512", "cg13901901", "cg13524180", "cg18761756", "cg23633993", "cg07013148", "cg06190759", "cg14070745", "cg11552868", "cg26635451", "cg03201274", "cg25063425", "cg04482817", "cg05082527", "cg24850711", "cg25194273", "cg18964706", "cg01485362", "cg14154487", "cg22511293", "cg01431908", "cg20219035", "cg18855836", "cg06743703", "cg07489447", "cg16269716", "cg12737876", "cg00001245", "cg24871046", "cg07065008", "cg02104456", "cg13466901", "cg17880816", "cg23352067", "cg26870903", "cg12489846", "cg04144333", "cg02399652", "cg24269412", "cg03146993", "cg17307051", "cg20129534", "cg07968224", "cg07814910", "cg02192555", "cg07629951", "cg13322252", "cg18456312", "cg02871891", "cg07874283", "cg26371345", "cg07663404", "cg07036530", "cg17677988", "cg16619777", "cg25182165", "cg20686479", "cg04184793", "cg22513691", "cg17183414", "cg04246144", "cg05383531", "cg25245322", "cg02244933", "cg05516617", "cg11111132", "cg07760722", "cg05357093", "cg08248181", "cg00780666", "cg26932693", "cg14681854", "cg23853026", "cg08044454", "cg22317004", "cg05907764", "cg05482973", "cg03128635", "cg01968492", "cg03460049", "cg00465284", "cg00549910", "cg02856109", "cg03445516", "cg06816651", "cg09409539", "cg09482777", "cg11231249", "cg12078605", "cg21621248", "cg24871414", "cg26355577", "cg26649384", "cg27629977"), class = "data.frame")
Below was what I tried: extracted probes chromosome by chromosome, and region by region. Let's take the chr2 for example.
chr2 %>% probe %>% subset(chr==2) %>% subset(pos >= 95663987 & pos <= 95664360 | pos >= 80531500 & pos <= 80531899 | pos >= 154334651 & pos <= 154334652)
It worked well and showed 14 probes that are located in these four regions. However, my real region file have many more regions whitin each chromosome. It will be time comsuming to put all the "start" and "end" number in the code. So I want to have a easier code to extract the probes, at least chromosome by chromosome.
Below was what I tried:
chr2.df <- probe %>% subset(chr==2) %>% subset(pos >= region$start & pos <= region$end)
It showed no regions...
Can anyone help me with it - how to extract the probes not by using the detail "start" and "end" number in the region file?
Thank you so much.


If your goal is to identify probes that lie in each chromosomal region, then I think that this code will suffice:
library(magrittr)
pdf <- tibble::as_tibble(probe ) %>% dplyr::mutate(probe = rownames(probe))
region %>%
tibble::as_tibble() %>%
dplyr::left_join(pdf, by = "chr") %>%
dplyr::filter(pos < end, pos > start)
I first load the package magrittr, which lets me use the "pipe" function, %>%. I then create a tibble (a data frame) with probe as a (new) column. This reflects my preference to not use rownames with data frames.
I then convert region to a tibble (a type of data frame) before piping it to the left_join function from dplyr package. This function "merges" or "joins" the two data frames by common values of "chr". Since there are repeated values of "chr" in both region and pdf, we get multiple lines with, for example, "chr" value of 2.
Lastly, I use the function filter from dplyr to choose only those rows that have a pos value between start and end.
I hope that this helps.

Related

Panel regression with cross sectional averages

I am estimating a panel regression model, and I need to add the cross sectional average of the dependent variable and regressors to the model.
I am struggling to implement the cross sectional averages in R. Can anyone help me out.
So I have a panel regression code below - using plm package.
I need to add cross sectional average of variable A, B, C and D to the right hand side of the regression
library(plm)
panel_fe <- plm(A ~ B+ C + D, model = "fd", effect="individual", data = PanelS)
So my final regression model would be like this A = B+ C+D + A_bar + B_bar + C_bar + D_bar, where A_bar, B_bar , C_bar and D_bar are the cross sectional averages of A, B,C and D respectively.
My panel datasets is below, PanelS.
structure(list(Country = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 10L, 10L, 10L), .Label = c("CountryA", "CountryB",
"CountryC", "CountryD", "CountryE", "CountryF", "CountryG", "CountryH",
"CountryI", "CountryJ"), class = "factor"), Year = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L,
17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L,
4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L,
19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L,
20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
14L, 15L, 16L, 17L, 18L, 19L, 20L), .Label = c("2000", "2001",
"2002", "2003", "2004", "2005", "2006", "2007", "2008", "2009",
"2010", "2011", "2012", "2013", "2014", "2015", "2016", "2017",
"2018", "2019"), class = "factor"), A = c(0.051539, 0.064525,
0.014292, 0.018774, 0.035449, 0.021988, 0.02396, 0.011415, 0.010358,
-0.029607, -0.020427, -0.012734, 0.006683, 0.007373, -0.039712,
-0.005499, 0.008682, 0.015326, 0.020524, 0.015101, 0.035355,
0.031157, 0.023387, 0.024198, 0.035353, 0.053873, 0.038743, 0.042338,
0.034935, 0.015377, 0.010599, 0.015154, 0.002919, 0.024291, 0.043819,
0.015901, 0.01897, 0.027767, 0.015992, 0.041976, 0.011223, 0.006144,
0.000778, 0.005873, 0.007194, -0.022017, -0.023338, -0.037765,
-0.049356, 0.026135, 0.035633, 0.015691, -0.006196, -0.00025,
0.001181, -0.001472, -0.009324, -0.022664, -0.022623, -0.019586,
-0.012207, -0.004603, -0.013073, -0.010771, -0.009882, -0.014417,
-0.031812, -0.043885, -0.050883, -0.039834, -0.020299, -0.000684,
0.011216, 0.005419, 0.000939, -0.005508, 0.006266, -0.008077,
-0.016137, -0.012681, 0.031612, 0.043729, 0.009314, 0.002734,
-0.012284, 0.002403, 0.016807, 0.019995, 0.033096, 0.024383,
0.010588, 0.019833, 0.031837, 0.03127, 0.029059, 0.020708, 0.019296,
0.017787, 0.032074, 0.027125, 0.005673, 0.003698, -5.3e-05, 0.001794,
-0.011977, -0.008686, -0.031588, -0.039411, -0.073931, -0.076715,
-0.039171, -0.025797, -0.007637, 0.00345, 0.009101, 0.01674,
-0.006968, -0.019178, -0.02438, -0.039663, 0.078313, 0.06707,
0.062822, 0.050771, 0.041274, 0.043921, 0.046429, 0.039418, 0.034671,
0.017356, 0.001054, 0.00414, 0.00226, 0.00275, 0.00085, 0.00495,
0.001276, -0.001446, -0.005771, -0.007513, 0.053734, 0.038679,
0.017375, 0.01438, 0.018403, 0.032943, 0.025539, 0.032463, 0.032267,
0.034009, 0.018229, 0.008958, 0.010079, 0.00749, 0.000604, 0.001948,
0.011782, 0.013253, 0.007898, 0.007546, 0.018052, -0.001123,
-0.012597, -0.042292, -0.058516, -0.022736, -0.03841, -0.050843,
-0.073979, -0.097242, -0.024712, 0.038037, 0.048685, -0.00624,
0.075575, 0.044947, 0.097171, 0.086809, 0.079856, 0.068521, 0.008062,
-0.00911, -0.010527, -4.3e-05, 0.002428, 0.004422, 0.008752,
0.019602, 0.01724, 0.01965, -0.008816, 0.011466, 0.020956, 0.021873,
0.021772, 0.024495, 0.021354, 0.015267, 0.018769, 0.016904),
C = c(0.75345, 0.70657, 0.645051, 0.510055, 0.433786, 0.35728,
0.265817, 0.208721, 0.163261, 0.130248, 0.136607, 0.153873,
0.152275, 0.166592, 0.170559, 0.27089, 0.259813, 0.292847,
0.253142, 0.222618, 0.56764082, 0.523543, 0.485083, 0.49081,
0.461501, 0.44156, 0.374122, 0.315494, 0.27346, 0.333132,
0.401818, 0.425879, 0.460709, 0.448942, 0.440456, 0.442703,
0.397737, 0.372338, 0.359446, 0.340254, 0.064305, 0.05107,
0.047682, 0.056584, 0.055981, 0.051134, 0.047025, 0.046318,
0.037655, 0.045041, 0.071989, 0.066074, 0.061057, 0.097641,
0.101621, 0.105545, 0.09996, 0.099131, 0.091119, 0.082012,
0.120817, 0.120871, 0.138383, 0.13023, 0.141247, 0.146088,
0.119133, 0.100396, 0.084592, 0.185873, 0.368416, 0.479167,
0.4367, 0.421837, 0.400428, 0.416259, 0.37072, 0.40398, 0.390126,
0.371126, 0.079576, 0.074647, 0.076712, 0.074295, 0.074504,
0.079053, 0.080224, 0.082991, 0.082006, 0.15357, 0.161465,
0.201522, 0.190049, 0.219974, 0.236873, 0.227428, 0.219862,
0.200938, 0.223426, 0.209529, 0.217219, 0.224867, 0.258694,
0.248207, 0.221093, 0.189452, 0.159052, 0.124236, 0.119492,
0.123362, 0.217807, 0.296186, 0.339882, 0.371345, 0.376212,
0.391509, 0.378059, 0.373931, 0.351043, 0.347354, 0.440547,
0.424547, 0.409236, 0.401795, 0.427482, 0.426416, 0.399297,
0.381117, 0.339041, 0.325607, 0.415314, 0.469047, 0.482712,
0.536225, 0.562292, 0.598259, 0.636417, 0.631764, 0.612668,
0.596271, 0.605061, 0.503479, 0.518971, 0.498057, 0.492731,
0.484527, 0.486885, 0.43596, 0.388967, 0.374978, 0.407324,
0.381025, 0.371731, 0.375149, 0.402248, 0.449982, 0.437387,
0.422554, 0.407331, 0.389125, 0.989067, 1.049344, 1.070812,
1.048631, 1.014561, 1.028734, 1.073949, 1.036117, 1.03103,
1.094155, 1.267447, 1.474942, 1.752192, 1.619444, 1.784347,
1.802256, 1.770079, 1.807951, 1.792139, 1.862386, 0.601394,
0.590658, 0.579365, 0.597035, 0.633089, 0.649877, 0.673465,
0.667047, 0.639942, 0.655222, 0.729901, 0.823816, 0.79801,
0.811354, 0.787169, 0.756694, 0.72207, 0.692768, 0.651024,
0.617801), B = c(0.147502302, 0.043680673, -0.212478849,
-0.266834333, -0.228099071, -0.199890362, -0.968175801, 1.047500546,
1.273127656, 1.227657506, -0.286068921, -1.356896168, -1.442625298,
-0.291748363, 2.029875219, 1.099611751, -1.112127832, -0.894025857,
0.103213651, 0.286801553, 0.756833023, 0.591945192, 0.525259532,
0.466656359, 0.706692697, -2.361722697, -2.777257989, -4.097114222,
-4.564987155, 2.317853991, 3.44030537, 3.034469093, 5.845290721,
0.403542521, 0.128582254, 0.817094156, -0.886707561, -2.998573025,
-0.491794488, -0.856367773, 0.023343476, -0.209503364, -0.084839186,
-0.146285026, -0.256672799, -0.093852713, 0.145824486, 0.434606031,
0.966980327, 0.67904687, -0.292659443, -0.487763914, -0.084930583,
-0.32722087, -0.442172133, -0.168366978, -0.186469629, 0.046322287,
0.181126569, 0.303486593, 0.171541123, -0.348150815, -0.407466419,
-0.624622679, -0.354132366, -0.15050691, 0.700892294, 0.67692383,
1.014111655, 0.862019536, 0.395600738, -0.256706715, -0.542246369,
-0.539422399, -0.405088653, -0.247954994, -0.497333992, -0.010723655,
0.393516751, 0.169750037, -0.581903347, -0.730163914, 0.351894514,
0.629568917, 0.882078894, 0.760041333, -0.564317727, -0.57799292,
-0.433736512, 0.513350369, 0.55464973, -0.224497194, -0.074326596,
-0.123301819, -0.432013928, -0.25316664, -0.374406673, 0.116449941,
0.308969388, 0.252824183, 2.398228162, -0.033362631, -1.681378615,
-3.655293426, -2.793256764, -3.636310622, 0.149490332, 3.951131246,
7.177449077, 4.831325877, 2.050070679, 1.314471427, -1.687424783,
-3.796189127, -3.329685346, -1.695252718, -3.010416797, -2.414597902,
1.199960369, 4.661041564, 0.531518012, -1.384184059, -0.64216453,
-0.13206166, 0.249287935, -0.153010531, -0.987952985, -1.71711917,
-0.678751076, 0.890062065, 1.663691535, 1.883735194, 2.171029985,
2.383501603, 1.490313839, -0.732542129, -0.291797363, -1.655272704,
-1.613245217, -1.275038743, -0.789256935, -3.589249982, 0.502475039,
1.840081099, 1.141218417, 3.130100399, 3.94751837, 0.97811035,
0.013586974, -3.245960526, -2.068241886, -1.82476664, -1.481654499,
0.37039449, -1.516414277, -1.722381744, 0.683458083, 0.153189319,
3.410781995, 0.067011953, -3.09418792, -4.09753755, -4.682167411,
-1.333607727, 2.505605899, -4.332639317, -2.190945016, 4.048457741,
11.60535564, 13.61047901, 5.145259686, -0.712611552, -3.385649938,
7.214394614, -10.34401695, -1.841542179, -6.437949187, -4.545422837,
-0.012548047, 2.881273043, 3.227611639, 10.96399365, 16.38843255,
14.72001327, -13.84595255, -10.51570643, -13.59695535, -36.70577424,
-12.07070647, 12.51742535, 52.88207865, 9.143152612, -7.818895359,
-15.57456939, -21.31957866, -23.55720863, -5.574415019, 5.783084584,
12.02189272, 22.93207708), D = c(0.77780751, 0.793229898,
0.80623893, 0.821155065, 0.836880111, 0.854312944, 0.873660631,
0.890537317, 0.907536298, 0.912375095, 0.929637942, 0.946439284,
0.965000087, 0.97726773, 0.986870808, 1, 1.019208507, 1.037842597,
1.054711181, 1.072171599, 0.534008473, 0.566583199, 0.58762954,
0.601043497, 0.63362178, 0.673913677, 0.719447102, 0.799187909,
0.864173776, 0.899162389, 0.909465125, 0.96350569, 0.978220642,
0.971679886, 0.976158221, 1, 1.025374896, 1.065804414, 1.108567186,
1.166769344, 0.588726028, 0.64526073, 0.733094431, 0.718268082,
0.746291144, 0.799900392, 0.846050389, 0.894179583, 1.015232882,
0.982856394, 1.012948099, 1.041332642, 1.032947106, 1.013566583,
0.980944689, 1, 1.020576612, 1.061740647, 1.117831183, 1.159906251,
0.750587042, 0.769670674, 0.790024355, 0.801712216, 0.817505148,
0.83991247, 0.856517319, 0.878345181, 0.914006005, 0.920044857,
0.949573071, 0.955207703, 0.978810398, 0.985618398, 0.996205139,
1, 1.004364708, 1.017159213, 1.021013703, 1.02682649, 0.825278825,
0.836048671, 0.847570474, 0.858769029, 0.86834942, 0.871868036,
0.875331803, 0.890827568, 0.898928134, 0.915485416, 0.921392822,
0.931246968, 0.945182975, 0.963702812, 0.981800571, 1, 1.013277522,
1.026999204, 1.044176589, 1.067069774, 0.490666665, 0.523850087,
0.54906662, 0.570457925, 0.597126217, 0.632406036, 0.689467717,
0.775073059, 0.828560075, 0.827109078, 0.842215091, 0.887572897,
0.923280339, 0.960610381, 0.988936452, 1, 1.022699304, 1.054533263,
1.098615084, 1.134067127, 0.757140805, 0.809228408, 0.851488047,
0.884918505, 0.889385715, 0.916751643, 0.948479832, 0.960072842,
0.956196673, 0.911566837, 0.884542463, 0.89644222, 0.917048164,
0.929279352, 0.929337342, 1, 1.010128912, 1.026719845, 1.029923385,
1.062349178, 0.786853444, 0.804351028, 0.831286834, 0.859995963,
0.886334727, 0.906191485, 0.937863282, 0.969963165, 1.012104032,
1.038112793, 1.036283847, 1.046222, 1.043339336, 1.02279939,
1.002888566, 1, 0.994233243, 0.998082845, 0.997049083, 0.998951287,
0.740171055, 0.770579402, 0.802054487, 0.833603662, 0.865965514,
0.90147914, 0.937354271, 0.969378485, 0.99123068, 0.992657113,
0.994179737, 0.993983379, 0.992844694, 0.99680058, 0.994574042,
1, 1.003228988, 1.016266499, 1.028341184, 1.04261954, 0.801617134,
0.817716283, 0.834621959, 0.850140657, 0.863935678, 0.880664424,
0.899645623, 0.9226463, 0.944486016, 0.945115307, 0.95522518,
0.964280334, 0.975483583, 0.983073825, 0.988745617, 1, 1.005225593,
1.010468623, 1.020086873, 1.032605559)), row.names = c("CountryA-2000",
"CountryA-2001", "CountryA-2002", "CountryA-2003", "CountryA-2004",
"CountryA-2005", "CountryA-2006", "CountryA-2007", "CountryA-2008",
"CountryA-2009", "CountryA-2010", "CountryA-2011", "CountryA-2012",
"CountryA-2013", "CountryA-2014", "CountryA-2015", "CountryA-2016",
"CountryA-2017", "CountryA-2018", "CountryA-2019", "CountryB-2000",
"CountryB-2001", "CountryB-2002", "CountryB-2003", "CountryB-2004",
"CountryB-2005", "CountryB-2006", "CountryB-2007", "CountryB-2008",
"CountryB-2009", "CountryB-2010", "CountryB-2011", "CountryB-2012",
"CountryB-2013", "CountryB-2014", "CountryB-2015", "CountryB-2016",
"CountryB-2017", "CountryB-2018", "CountryB-2019", "CountryC-2000",
"CountryC-2001", "CountryC-2002", "CountryC-2003", "CountryC-2004",
"CountryC-2005", "CountryC-2006", "CountryC-2007", "CountryC-2008",
"CountryC-2009", "CountryC-2010", "CountryC-2011", "CountryC-2012",
"CountryC-2013", "CountryC-2014", "CountryC-2015", "CountryC-2016",
"CountryC-2017", "CountryC-2018", "CountryC-2019", "CountryD-2000",
"CountryD-2001", "CountryD-2002", "CountryD-2003", "CountryD-2004",
"CountryD-2005", "CountryD-2006", "CountryD-2007", "CountryD-2008",
"CountryD-2009", "CountryD-2010", "CountryD-2011", "CountryD-2012",
"CountryD-2013", "CountryD-2014", "CountryD-2015", "CountryD-2016",
"CountryD-2017", "CountryD-2018", "CountryD-2019", "CountryE-2000",
"CountryE-2001", "CountryE-2002", "CountryE-2003", "CountryE-2004",
"CountryE-2005", "CountryE-2006", "CountryE-2007", "CountryE-2008",
"CountryE-2009", "CountryE-2010", "CountryE-2011", "CountryE-2012",
"CountryE-2013", "CountryE-2014", "CountryE-2015", "CountryE-2016",
"CountryE-2017", "CountryE-2018", "CountryE-2019", "CountryF-2000",
"CountryF-2001", "CountryF-2002", "CountryF-2003", "CountryF-2004",
"CountryF-2005", "CountryF-2006", "CountryF-2007", "CountryF-2008",
"CountryF-2009", "CountryF-2010", "CountryF-2011", "CountryF-2012",
"CountryF-2013", "CountryF-2014", "CountryF-2015", "CountryF-2016",
"CountryF-2017", "CountryF-2018", "CountryF-2019", "CountryG-2000",
"CountryG-2001", "CountryG-2002", "CountryG-2003", "CountryG-2004",
"CountryG-2005", "CountryG-2006", "CountryG-2007", "CountryG-2008",
"CountryG-2009", "CountryG-2010", "CountryG-2011", "CountryG-2012",
"CountryG-2013", "CountryG-2014", "CountryG-2015", "CountryG-2016",
"CountryG-2017", "CountryG-2018", "CountryG-2019", "CountryH-2000",
"CountryH-2001", "CountryH-2002", "CountryH-2003", "CountryH-2004",
"CountryH-2005", "CountryH-2006", "CountryH-2007", "CountryH-2008",
"CountryH-2009", "CountryH-2010", "CountryH-2011", "CountryH-2012",
"CountryH-2013", "CountryH-2014", "CountryH-2015", "CountryH-2016",
"CountryH-2017", "CountryH-2018", "CountryH-2019", "CountryI-2000",
"CountryI-2001", "CountryI-2002", "CountryI-2003", "CountryI-2004",
"CountryI-2005", "CountryI-2006", "CountryI-2007", "CountryI-2008",
"CountryI-2009", "CountryI-2010", "CountryI-2011", "CountryI-2012",
"CountryI-2013", "CountryI-2014", "CountryI-2015", "CountryI-2016",
"CountryI-2017", "CountryI-2018", "CountryI-2019", "CountryJ-2000",
"CountryJ-2001", "CountryJ-2002", "CountryJ-2003", "CountryJ-2004",
"CountryJ-2005", "CountryJ-2006", "CountryJ-2007", "CountryJ-2008",
"CountryJ-2009", "CountryJ-2010", "CountryJ-2011", "CountryJ-2012",
"CountryJ-2013", "CountryJ-2014", "CountryJ-2015", "CountryJ-2016",
"CountryJ-2017", "CountryJ-2018", "CountryJ-2019"), class = c("pdata.frame",
"data.frame"), index = structure(list(Country = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L), .Label = c("CountryA",
"CountryB", "CountryC", "CountryD", "CountryE", "CountryF", "CountryG",
"CountryH", "CountryI", "CountryJ"), class = "factor"), Year = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L,
17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L,
4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L,
19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L,
20L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
14L, 15L, 16L, 17L, 18L, 19L, 20L), .Label = c("2000", "2001",
"2002", "2003", "2004", "2005", "2006", "2007", "2008", "2009",
"2010", "2011", "2012", "2013", "2014", "2015", "2016", "2017",
"2018", "2019"), class = "factor")), class = c("pindex", "data.frame"
), row.names = c(NA, 200L)))

You can use function Between from package plm to calculate the cross sectional averages and add them to your data:
library(plm)
# PanelS is a pdata.frame (otherwise use pdata.frame(your_data, index))
PanelS$A_bar <- Between(PanelS$A)
PanelS$B_bar <- Between(PanelS$B)
PanelS$C_bar <- Between(PanelS$C)
PanelS$D_bar <- Between(PanelS$D)
mod <- plm(A ~ B + C + D + A_bar + B_bar + C_bar + D_bar, model = "pooling", effect="individual", data = PanelS)
summary(mod)
# Pooling Model
#
# Call:
# plm(formula = A ~ B + C + D + A_bar + B_bar + C_bar + D_bar,
# data = PanelS, effect = "individual", model = "pooling")
#
# Balanced Panel: n = 10, T = 20, N = 200
#
# Residuals:
# Min. 1st Qu. Median 3rd Qu. Max.
# -0.06143690 -0.01311792 0.00070253 0.01186605 0.05107105
#
# Coefficients:
# Estimate Std. Error t-value Pr(>|t|)
# (Intercept) -0.00000000000001042 0.03313743211380626 0.0000 1.000000
# B -0.00076930351859426 0.00020566635571130 -3.7405 0.000242 ***
# C 0.10827039012266901 0.00949296134830719 11.4053 < 0.00000000000000022 ***
# D -0.04222788490989914 0.01136058813979121 -3.7171 0.000264 ***
# A_bar 0.99999999999911215 0.09632471140222754 10.3816 < 0.00000000000000022 ***
# C_bar -0.10827039012256123 0.01033406661607372 -10.4770 < 0.00000000000000022 ***
# D_bar 0.04222788490990802 0.03874710199411169 1.0898 0.277145
# ---
# Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#
# Total Sum of Squares: 0.17549
# Residual Sum of Squares: 0.07128
# R-Squared: 0.59382
# Adj. R-Squared: 0.58119
# F-statistic: 47.0268 on 6 and 193 DF, p-value: < 0.000000000000000222
Note that it seems like you want to estimate a fixed effects model but your estimation has model = "fd" to estimate a first-differenced model. Also note that the cross sectional averages will drop out of the estimation of a fixed effects model.

Undirected network graph calculated by tidygraph shows more degree centrality than should be possible

I have a cleaned data set with 26 nodes. I am placing these 26 nodes in an undirected network graph using tidygraph, where I use the centrality_degree() function to calculate the centrality degree. However, when I graph the resulting network, my highest possible centrality degree is 40, which should not be possible. When I change the graph to directed, this is corrected.
I somewhat confused, as other methods I have used in the past, where I manually calculated the centrality degree, I have never once come across this issue.
Is this regular behaviour, or am I doing something wrong?
Reproducible example:
library(tidygraph)
library(ggraph)
library(tidyverse)
nodes <- structure(list(id = 1:26, label = c("a", "b", "c", "d", "e",
"f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r",
"s", "t", "u", "v", "w", "x", "y", "z")), row.names = c(NA, -26L
), class = "data.frame")
edges <- structure(list(from = c(21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L,
21L, 21L, 21L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 13L, 13L, 13L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 18L,
18L, 18L, 18L, 18L, 18L, 18L, 16L, 16L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 24L,
24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L,
24L, 24L, 24L, 24L, 24L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 14L, 14L, 14L, 14L,
14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 25L, 25L, 25L, 25L, 25L, 25L, 25L, 25L, 25L,
25L, 25L, 25L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L,
22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 15L, 15L, 15L,
15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L,
15L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 20L, 20L, 20L, 20L, 20L, 20L, 20L,
20L, 20L, 20L, 20L, 20L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 17L, 17L, 17L, 17L, 17L),
to = c(1L, 12L, 3L, 16L, 24L, 4L, 10L, 6L, 22L, 2L, 8L, 1L,
12L, 13L, 3L, 18L, 16L, 24L, 5L, 7L, 14L, 4L, 10L, 6L, 9L,
22L, 15L, 2L, 20L, 8L, 21L, 12L, 13L, 3L, 16L, 24L, 5L, 7L,
14L, 4L, 10L, 6L, 22L, 15L, 2L, 8L, 17L, 21L, 1L, 13L, 3L,
16L, 5L, 7L, 14L, 10L, 6L, 9L, 22L, 15L, 2L, 20L, 8L, 17L,
21L, 1L, 3L, 18L, 16L, 5L, 7L, 14L, 4L, 10L, 6L, 25L, 9L,
22L, 15L, 20L, 8L, 17L, 21L, 11L, 1L, 12L, 13L, 18L, 16L,
24L, 5L, 7L, 14L, 4L, 10L, 6L, 25L, 9L, 22L, 15L, 20L, 8L,
17L, 1L, 3L, 10L, 6L, 22L, 20L, 8L, 21L, 11L, 1L, 13L, 3L,
18L, 24L, 7L, 4L, 10L, 6L, 25L, 9L, 22L, 15L, 2L, 20L, 8L,
17L, 21L, 11L, 1L, 12L, 13L, 18L, 16L, 5L, 7L, 14L, 10L,
6L, 25L, 9L, 22L, 15L, 20L, 8L, 17L, 1L, 3L, 18L, 16L, 7L,
14L, 4L, 10L, 6L, 9L, 22L, 15L, 2L, 20L, 8L, 17L, 21L, 11L,
1L, 12L, 13L, 3L, 18L, 16L, 24L, 14L, 4L, 10L, 6L, 25L, 9L,
22L, 15L, 2L, 20L, 8L, 11L, 1L, 3L, 18L, 16L, 7L, 10L, 6L,
9L, 22L, 15L, 2L, 20L, 8L, 17L, 21L, 11L, 1L, 12L, 13L, 3L,
18L, 16L, 24L, 5L, 7L, 14L, 10L, 6L, 25L, 9L, 22L, 15L, 2L,
20L, 8L, 17L, 21L, 11L, 1L, 12L, 13L, 3L, 18L, 16L, 24L,
5L, 7L, 14L, 4L, 6L, 25L, 9L, 22L, 15L, 2L, 20L, 8L, 17L,
21L, 11L, 1L, 12L, 13L, 3L, 18L, 24L, 5L, 7L, 14L, 4L, 10L,
25L, 9L, 22L, 15L, 2L, 20L, 8L, 21L, 1L, 13L, 3L, 18L, 5L,
10L, 6L, 22L, 2L, 20L, 8L, 21L, 1L, 13L, 3L, 18L, 16L, 24L,
4L, 10L, 6L, 22L, 15L, 2L, 20L, 8L, 11L, 1L, 12L, 13L, 3L,
16L, 24L, 5L, 7L, 14L, 4L, 10L, 6L, 25L, 9L, 15L, 2L, 20L,
8L, 17L, 21L, 1L, 12L, 3L, 18L, 16L, 24L, 7L, 10L, 6L, 25L,
9L, 22L, 2L, 20L, 8L, 17L, 21L, 11L, 1L, 12L, 13L, 3L, 18L,
16L, 24L, 5L, 7L, 14L, 4L, 6L, 25L, 9L, 22L, 15L, 20L, 8L,
17L, 21L, 11L, 1L, 3L, 16L, 24L, 7L, 10L, 6L, 22L, 2L, 8L,
21L, 11L, 1L, 12L, 13L, 3L, 18L, 16L, 24L, 14L, 4L, 10L,
6L, 25L, 9L, 22L, 2L, 20L, 7L, 6L, 25L, 22L, 8L), weight = c(3L,
1L, 3L, 2L, 1L, 1L, 5L, 1L, 8L, 2L, 1L, 2L, 3L, 2L, 5L, 1L,
4L, 1L, 4L, 4L, 4L, 1L, 5L, 13L, 3L, 7L, 3L, 2L, 3L, 8L,
1L, 1L, 1L, 15L, 10L, 7L, 2L, 4L, 2L, 5L, 19L, 23L, 6L, 2L,
11L, 7L, 1L, 1L, 2L, 3L, 3L, 5L, 4L, 5L, 4L, 4L, 21L, 2L,
9L, 8L, 1L, 1L, 12L, 1L, 2L, 1L, 3L, 1L, 6L, 6L, 5L, 6L,
1L, 6L, 22L, 2L, 2L, 9L, 8L, 3L, 13L, 1L, 5L, 6L, 4L, 10L,
13L, 3L, 41L, 46L, 11L, 39L, 9L, 55L, 2L, 108L, 2L, 8L, 31L,
30L, 13L, 39L, 2L, 2L, 1L, 3L, 4L, 8L, 5L, 1L, 8L, 1L, 6L,
1L, 8L, 2L, 3L, 23L, 2L, 12L, 96L, 1L, 3L, 21L, 1L, 6L, 12L,
38L, 4L, 5L, 4L, 4L, 8L, 8L, 3L, 29L, 3L, 11L, 3L, 3L, 63L,
2L, 5L, 18L, 19L, 4L, 25L, 1L, 2L, 3L, 1L, 7L, 6L, 7L, 1L,
3L, 17L, 1L, 3L, 6L, 1L, 4L, 11L, 1L, 5L, 1L, 5L, 1L, 1L,
15L, 4L, 7L, 3L, 1L, 4L, 12L, 8L, 1L, 9L, 32L, 3L, 7L, 5L,
35L, 1L, 1L, 3L, 1L, 6L, 4L, 4L, 12L, 2L, 5L, 4L, 2L, 2L,
9L, 1L, 2L, 3L, 4L, 9L, 13L, 2L, 1L, 25L, 25L, 10L, 14L,
10L, 4L, 59L, 4L, 5L, 21L, 19L, 1L, 8L, 27L, 3L, 5L, 8L,
8L, 11L, 12L, 111L, 5L, 50L, 45L, 15L, 32L, 10L, 49L, 109L,
1L, 8L, 28L, 39L, 53L, 13L, 48L, 5L, 13L, 2L, 20L, 3L, 3L,
27L, 10L, 8L, 1L, 58L, 1L, 7L, 32L, 13L, 21L, 110L, 1L, 17L,
27L, 124L, 1L, 1L, 1L, 2L, 3L, 1L, 1L, 2L, 7L, 1L, 1L, 1L,
2L, 2L, 1L, 5L, 2L, 2L, 2L, 1L, 3L, 3L, 14L, 2L, 2L, 4L,
1L, 3L, 14L, 5L, 8L, 44L, 16L, 14L, 4L, 12L, 4L, 19L, 41L,
47L, 2L, 1L, 11L, 24L, 2L, 18L, 1L, 7L, 5L, 1L, 7L, 3L, 27L,
3L, 15L, 7L, 54L, 1L, 4L, 17L, 5L, 6L, 27L, 1L, 1L, 2L, 3L,
4L, 10L, 56L, 3L, 25L, 25L, 7L, 16L, 5L, 29L, 59L, 3L, 3L,
20L, 17L, 5L, 31L, 3L, 6L, 1L, 4L, 7L, 1L, 3L, 1L, 6L, 5L,
13L, 1L, 2L, 9L, 1L, 15L, 2L, 1L, 16L, 4L, 4L, 3L, 1L, 6L,
17L, 10L, 1L, 13L, 63L, 11L, 12L, 1L, 5L, 1L, 2L, 3L)), row.names = c(NA,
-383L), class = c("tbl_df", "tbl", "data.frame"))
routes_tidy <- tbl_graph(nodes=nodes, edges=edges, directed=FALSE) %>% mutate(neighbors = centrality_degree())
# Filtering out 3 nodes out of the graph as they have no connections and zoom the figure way out
ggraph(routes_tidy, layout="graphopt") +
geom_node_point(aes(size=neighbors, filter=(label!="z" & label!="s" & label!="w"))) +
geom_edge_link(aes(width=weight, alpha=weight)) +
scale_edge_width(range=c(0.2, 2)) +
geom_node_text(aes(label=label, fontface="bold", size=neighbors, filter=(label!="z" & label!="s" & label!="w")), repel=TRUE) +
labs(edge_width="N") +
theme_graph()

I'm new to the whole tidygraph thing, stumbled over this question, got confused, and figured it'd be a nice way to get to know stuff. So, I don't know if it's a bug or a feature, but the behaviour is triggered because you have doubled edges:
# Given your edges
edges %>%
filter((from == 1 & to == 2) | from == 2 & to == 1)
# A tibble: 2 x 3
from to weight
<int> <int> <int>
1 1 2 11
2 2 1 3
And those count as 2 connections in the calculation of the degree centrality. One way to remove those double edges is to convert the network to a simple network:
routes_simple <-
routes_tidy %>%
morph(to_simple) %>%
crystallise() %>%
pull(graph) %>%
getElement(1) %>%
activate(nodes) %>%
mutate(neighbors = centrality_degree())
Now the maximum degree is 22 (and the heighest possible, presumably, 25).

R: stacked geom_area plot displays blank polygons

I need some help regarding transforming a geom_bar into a geom_area plot. This is my df:
dput(df)
df <- structure(list(new_day = c(-25L, 3L, 7L, -7L, 3L, 7L, -7L, 0L,
-25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L, -7L,
0L, -25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L, -7L, 0L, 3L, 7L, -7L,
0L, -25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L,
-25L, 3L, 7L, -7L, 0L, 3L, -7L, 0L, -25L, 7L, 3L, 7L, -7L, 0L,
-25L, 3L, 7L, -7L, 0L, -25L, 3L, 7L, 3L, 7L, -7L, 0L, -25L, 3L,
7L, -7L, 0L, 7L, -25L, 3L, 7L, -7L, 0L, 3L, 7L, -25L, -25L, -25L,
-25L, -25L, -25L, -25L), order = structure(c(8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 11L, 11L, 11L, 11L, 11L, 13L, 13L, 13L, 13L,
13L, 10L, 10L, 10L, 10L, 10L, 7L, 7L, 7L, 7L, 7L, 2L, 2L, 2L,
2L, 2L, 7L, 7L, 7L, 7L, 9L, 9L, 9L, 9L, 9L, 1L, 1L, 1L, 1L, 1L,
9L, 9L, 9L, 2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 13L, 13L, 14L, 14L,
14L, 14L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 13L, 13L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 2L, 2L, 2L, 2L, 2L, 6L, 6L, 1L, 7L, 5L, 2L,
12L, 2L, 2L), .Label = c("Alteromonadales", "Betaproteobacteriales",
"Caulobacterales", "Chitinophagales", "Flavobacteriales", "Parvibaculales",
"Pseudomonadales", "Rhizobiales", "Rhodobacterales", "Rhodospirillales",
"Sneathiellales", "Sphingobacteriales", "Sphingomonadales", "Thalassobaculales"
), class = "factor"), family = structure(c(13L, 13L, 13L, 13L,
12L, 12L, 12L, 12L, 15L, 15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L,
16L, 7L, 7L, 7L, 7L, 7L, 11L, 11L, 11L, 11L, 11L, 1L, 1L, 1L,
1L, 1L, 11L, 11L, 11L, 11L, 14L, 14L, 14L, 14L, 14L, 4L, 4L,
4L, 4L, 4L, 14L, 14L, 14L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 16L,
16L, 17L, 17L, 17L, 17L, 8L, 8L, 8L, 8L, 8L, 5L, 5L, 5L, 16L,
16L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 11L, 8L, 8L, 8L, 8L,
8L, 10L, 10L, 6L, 11L, 3L, 1L, 9L, 1L, 1L), .Label = c("Burkholderiaceae",
"Chitinophagaceae", "Flavobacteriaceae", "Gallaecimonadaceae",
"Hyphomonadaceae", "Idiomarinaceae", "Magnetospiraceae", "Methylophilaceae",
"NS11-12_marine_group", "Parvibaculaceae", "Pseudomonadaceae",
"Rhizobiaceae", "Rhizobiales_unclassified", "Rhodobacteraceae",
"Sneathiellaceae", "Sphingomonadaceae", "Thalassobaculaceae"), class = "factor"),
genus = structure(c(16L, 16L, 16L, 16L, 7L, 7L, 7L, 7L, 3L,
3L, 3L, 3L, 3L, 19L, 19L, 19L, 19L, 19L, 24L, 24L, 24L, 24L,
24L, 14L, 14L, 14L, 14L, 14L, 17L, 17L, 17L, 17L, 17L, 14L,
14L, 14L, 14L, 15L, 15L, 15L, 15L, 15L, 5L, 5L, 5L, 5L, 5L,
10L, 10L, 10L, 2L, 2L, 2L, 2L, 2L, 22L, 22L, 22L, 20L, 20L,
23L, 23L, 23L, 23L, 11L, 11L, 11L, 11L, 11L, 8L, 8L, 8L,
21L, 21L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 11L, 11L,
11L, 11L, 11L, 13L, 13L, 9L, 14L, 4L, 6L, 12L, 1L, 18L), .Label = c("Burkholderiaceae_unclassified",
"Cupriavidus", "Ferrovibrio", "Flavobacteriaceae_unclassified",
"Gallaecimonas", "GKS98_freshwater_group", "Hoeflea", "Hyphomonas",
"Idiomarina", "Marivivens", "Methylotenera", "NS11-12_marine_group_ge",
"Parvibaculum", "Pseudomonas", "Pseudorhodobacter", "Rhizobiales_unclassified",
"Rhodoferax", "RS62_marine_group", "Sphingomonadaceae_unclassified",
"Sphingopyxis", "Sphingorhabdus", "Terrimonas", "Thalassobaculum",
"uncultured"), class = "factor"), Abundance = c(0.758296593899054,
0.728046713738242, 0.421798852637834, 0.185971692147469,
7.36584152568739, 11.0004160226707, 1.93134577450352, 19.7144376530921,
46.2350237547082, 25.8715062086956, 22.1549641486618, 34.4112477828867,
20.4937613394223, 3.73518219692229, 15.9295990367068, 13.8490383262387,
13.3481723220855, 20.3866145291388, 0.165618346100574, 8.86991024549668,
8.5330814375361, 6.86819004205197, 5.72129192186814, 1.04512973253723,
3.77880217461655, 6.47871112880127, 1.12084852451492, 0.903754246093232,
19.0854333497858, 15.7152146349298, 12.3768753373503, 15.8790763239117,
10.2875187327705, 2.82159106304821, 4.22393981370602, 8.82452898193968,
4.8507226701533, 6.19619716749583, 8.28477594908417, 8.05201189383953,
9.7404731686272, 9.84535225459449, 1.7940554465653, 2.62276259756813,
2.74008811315788, 0.543937440677315, 0.55325167765205, 0.910457573040239,
0.451385497886567, 0.655661306732001, 6.59400178917785, 1.92570846362683,
2.62192443054515, 2.10049053655497, 2.13139299576524, 0.20799245164738,
0.324291631088576, 0.369492771993701, 1.52162438803598, 0.151864202275619,
0.420953084533189, 0.391517677365401, 0.29116200940885, 0.232440441774702,
4.21428798609281, 0.859779996836882, 1.33107018783728, 1.013155122065,
0.447286602320585, 0.165001492967355, 0.285983094976304,
0.377758692391269, 0.21556919104275, 0.314057858254493, 0.354649793637887,
0.338799824269294, 0.218027624939685, 0.914324162324944,
1.22932824654674, 0.731649603629864, 0.566393265064962, 0.247942012186621,
1.73171328618728, 0.636597714441988, 0.505393049999761, 0.491318560043637,
0.990988961717433, 0.195417142399681, 0.210412739808352,
0.476107780140271, 0.936663899397428, 0.251540964619117,
0.963667386912928, 0.504905545701818, 0.296220086916766,
0.240809811677774)), class = "data.frame", row.names = c(52L,
68L, 72L, 93L, 165L, 169L, 190L, 194L, 246L, 262L, 266L, 287L,
291L, 343L, 359L, 363L, 384L, 388L, 440L, 456L, 460L, 481L, 485L,
634L, 650L, 654L, 675L, 679L, 731L, 747L, 751L, 772L, 776L, 844L,
848L, 869L, 873L, 925L, 941L, 945L, 966L, 970L, 1022L, 1038L,
1042L, 1063L, 1067L, 1216L, 1232L, 1236L, 1313L, 1329L, 1333L,
1354L, 1358L, 1426L, 1451L, 1455L, 1507L, 1527L, 1717L, 1721L,
1742L, 1746L, 2186L, 2202L, 2206L, 2227L, 2231L, 2380L, 2396L,
2400L, 3075L, 3079L, 3294L, 3298L, 3350L, 3366L, 3370L, 3391L,
3395L, 3467L, 4223L, 4239L, 4243L, 4264L, 4268L, 4433L, 4437L,
4708L, 4805L, 4902L, 5193L, 5969L, 7909L, 8006L))
and this is the structure:
> str(df)
'data.frame': 96 obs. of 5 variables:
$ new_day : int -25 3 7 -7 3 7 -7 0 -25 3 ...
$ order : Factor w/ 14 levels "Alteromonadales",..: 8 8 8 8 8 8 8 8 11 11 ...
$ family : Factor w/ 17 levels "Burkholderiaceae",..: 13 13 13 13 12 12 12 12 15 15 ...
$ genus : Factor w/ 24 levels "Burkholderiaceae_unclassified",..: 16 16 16 16 7 7 7 7 3 3 ...
$ Abundance: num 0.758 0.728 0.422 0.186 7.366 ...
my data is about relative abundances of species over time, I removed rare species so it doesn't add up to 100 % anymore,
but that is fine, it is about 98 % per date. However, I get these weird free polygons and triangles which I recognize from incorrect grouping etc., but the group parameter did not change anything here. I also tried several position and stat arguments, which did not help. Maybe it is about the order of factors or something?
What I'm looking for is a stacked plot of the abundances of cumulated orders without empty spaces in between etc. Create proportional geom_area plot directly in ggplot2
# area plot combining species on order level
ggplot(df, aes(x = new_day, y = Abundance, fill = order)) +
geom_area(stat = "identity") +
geom_vline(aes(xintercept = 0), linetype = "dashed", size = 1.2)
I get fewer weird shapes when going to a more detailed hierarchical level (genus instead of order)
# area plot on genus level
ggplot(df, aes(x = new_day, y = Abundance, fill = genus)) +
geom_area(stat = "identity", position = "stack") +
geom_vline(aes(xintercept = 0), linetype = "dashed", size = 1.2)
but these are still more blank areas than there should be by the sum of abundances for a given time
# total abundance per day
sum(subset(df, new_day == -25)$Abundance)
[1] 98.03997
Any suggestions on how to fix this?

The problem is that you sometimes have several abundance values for one new_day, even with more detailed hierarchical levels.
This is what creates discontinuities in the area plot. You need to have only one unique value for each new_day. In my example below, I just take the first abundance value after grouping by new_day and order, but it is probably not relevant for what you want to show. (You may want to take the mean or attributes these values to other new_day points in between, whatever you need).
The remaining little gaps are caused by the missing abundance values, since as you said, it does not add up to 100%. This is not a big deal, but you can probably fix it by replacing the missing values by 0.
EDIT : Now doing the sum of abundance values as you mentioned, and removing the small remaining gaps by replacing missing values by 0.
library(tidyverse)
df %>%
# Sum abundance values, to only keep one per point
group_by(new_day, order) %>%
summarise(abundance=sum(Abundance)) %>%
ungroup() %>%
# Replace missing values by 0
spread(key=order, value=abundance) %>%
gather(key=order, value=abundance, -new_day) %>%
replace_na(list(abundance=0)) -> data
ggplot(data, aes(x = new_day, y = abundance, fill=order)) +
geom_area(stat = "identity") +
geom_vline(aes(xintercept = 0), linetype = "dashed", size = 1.2)

Use ifelse() to Identify inconsistent responses in data

I have a long format dataframe of responses to a repeated question about puberty status vb_ asked approximately yearly at ages 9, 10, 11, 13, 14, 15, 16, and 17.
Each year participants were asked to rate their development from 1 to 5, with 1 being least developed and 5 being most developed.
I would like to use R's ifelse() to identify inconsistent responses i.e. those that report a stage at one year that is lower than any of the previous years.
Here is some fake example data for 20 people:
vb <- structure(list(id = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 11L, 11L,
11L, 11L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 13L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L,
15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L, 16L,
16L, 16L, 16L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 17L, 18L, 18L,
18L, 18L, 18L, 18L, 18L, 18L, 19L, 19L, 19L, 19L, 19L, 19L, 19L,
19L, 20L, 20L, 20L, 20L, 20L, 20L, 20L, 20L), age = c(9L, 10L,
11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L,
17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L,
14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L,
10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L,
16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L,
13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L,
9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L,
15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L,
11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L,
17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L,
14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L,
10L, 11L, 13L, 14L, 15L, 16L, 17L, 9L, 10L, 11L, 13L, 14L, 15L,
16L, 17L), vb_ = c(1L, 1L, 1L, 3L, 4L, 4L, 4L, 5L, 2L, 2L, 3L,
4L, 5L, 5L, 5L, 5L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 2L, 1L, 3L,
4L, 4L, 5L, 5L, 5L, 2L, 2L, 1L, 3L, 4L, 3L, 4L, 4L, 1L, 1L, 1L,
3L, 4L, 4L, 5L, 5L, 1L, 1L, 2L, 4L, 4L, 4L, 5L, 5L, 2L, 2L, 2L,
4L, 5L, 4L, 4L, 5L, 2L, 2L, 1L, 4L, 5L, 5L, 5L, 5L, 1L, 2L, 3L,
4L, 5L, 5L, 4L, 5L, 1L, 1L, 1L, 4L, 4L, 5L, 5L, 5L, 1L, 1L, 1L,
1L, 4L, 4L, 4L, 4L, 1L, 1L, 3L, 4L, 4L, 4L, 5L, 5L, 1L, 1L, 1L,
4L, 4L, 5L, 5L, 5L, 2L, 2L, 2L, 2L, 4L, 4L, 5L, 5L, 2L, 3L, 3L,
4L, 4L, 5L, 5L, 5L, 1L, 1L, 2L, 2L, 4L, 5L, 5L, 5L, 1L, 1L, 1L,
3L, 3L, 4L, 5L, 5L, 1L, 1L, 1L, 2L, 4L, 4L, 4L, 4L, 1L, 1L, 1L,
2L, 4L, 4L, 4L, 4L)), class = "data.frame", row.names = c(NA,
-160L), .Names = c("id", "age", "vb_"))

If you insist on a ifelse approach you can do:
vb <- vb[order(vb$id, vb$age), ]
vb$inconsistent <- ifelse(vb$id == lag(vb$id),
ifelse(vb$vb_ < lag(vb$vb_), "inconsistent", ""),
"")
vb$inconsistent[1] <- ""
id age vb_ inconsistent
1 1 9 1
2 1 10 1
3 1 11 1
4 1 13 3
5 1 14 4
6 1 15 4
7 1 16 4
8 1 17 5
9 2 9 2
10 2 10 2
11 2 11 3
12 2 13 4
13 2 14 5
14 2 15 5
15 2 16 5
16 2 17 5
17 3 9 2
18 3 10 3
19 3 11 3
20 3 13 3
21 3 14 4
22 3 15 4
23 3 16 4
24 3 17 5
25 4 9 2
26 4 10 1 inconsistent
27 4 11 3
...
Or one approach with dplyr is:
library(dplyr)
vb %>%
group_by(id) %>%
arrange(id, age) %>%
mutate(vb_diff = vb_ - lag(vb_)) %>%
filter(vb_diff < 0)
# A tibble: 6 x 4
# Groups: id [5]
id age vb_ vb_diff
<int> <int> <int> <int>
1 4 10 1 -1
2 5 11 1 -1
3 5 15 3 -1
4 8 15 4 -1
5 9 11 1 -1
6 10 16 4 -1

Here you go.
vb <- vb[order(vb$id, vb$age),]
vb$decreasingdevelopment <- c(0, diff(vb$vb_))<0 #difference between this score and previous <0
vb$sameperson <- c(0, diff(vb$id))==0 #is this the same participant than previous
vb$inconsistency <- vb$decreasingdevelopment&vb$sameperson #ifelse(vb$devdiff&vb$sameperson, T, F)
which(vb$inconsistency)
#[1] 26 35 38 62 67 79
Note that the use of ifelse() is possible but not necessary.
PS: for completeness of the answer, you should always use the following :
vb$inconsistency_robust <- apply(vb, 1, function(x) length(which(vb$vb_>x["vb_"]&vb$age<x["age"]&vb$id==x["id"]))>0)
#x["decreasingdevelopment"]&x["sameperson"])
all.equal(which(vb$inconsistency_robust), which(vb$inconsistency))
#> which(vb$inconsistency_robust)
#[1] 26 35 38 62 63 67 79
#> which(vb$inconsistency)
#[1] 26 35 38 62 67 79
Note how the robust method spots all the occurences of inconsistencies while my more naive ifelse() method here only compares line to line.

R: Error when using knncat to do classification on categorical variable

I have a data set with 4 columns, 2 of which are numeric, 1 is categorical and 1 is the label. The label has 13 levels (A to M). I tried to use knncat package in R to do classification, but every time I ran the code, I got the following error message:
Error in `[<-.data.frame`(`*tmp*`, factor.vars, value = c("M", "J", "K", :
replacement has 45500 rows, data has 1
The following is the code I used:
data <- read.csv('mosaic_data2.csv', header = T)
num <- dim(data)[1]
library(sampling)
set.seed(1234)
train_index <- sample(seq(1,num,1), floor(num * 0.7), replace = F)
test_index <- setdiff(seq(1,num,1), train_index)
train_data <- data[train_index,]
test_data <- data[test_index,]
library(knncat)
model <- knncat(train_data, classcol = 2)
Could anyone please take a look at the code and advise how I could eliminate this bug? Thank you very much!
The output of dput(head(data,100)) is as follows:
structure(list(latitude = c(52.7326028, 52.74287543, 52.82107841,
52.82025363, 52.81980596, 52.81721897, 52.81274172, 52.81274172,
52.8089586, 52.81424219, 52.8089586, 52.74007929, 52.77394023,
52.73659034, 52.73672518, 52.73764626, 52.73753744, 52.73659034,
52.73815233, 52.73679388, 52.73890319, 52.71697237, 52.63730282,
52.62720385, 52.63730282, 52.63543017, 52.63768035, 52.63510366,
52.6346578, 52.6346578, 52.6346578, 52.63447454, 52.63576418,
52.63447454, 52.6346578, 52.63447454, 52.69820719, 52.69603926,
52.68246919, 52.54600173, 52.54210198, 52.60628983, 52.61003275,
52.60278236, 52.60239604, 52.60348688, 52.60239604, 52.60382146,
52.60315644, 52.86047938, 52.86576353, 52.86954228, 52.81039471,
52.82094872, 52.82395073, 52.82444705, 52.88098384, 52.88469208,
52.88469208, 52.84979201, 52.84720159, 52.84831759, 52.82435938,
52.82319493, 52.82168337, 52.8230402, 52.8230402, 52.82513486,
52.82472379, 52.82756385, 52.82475438, 52.82434902, 52.82166611,
52.823712, 52.82401481, 52.82483489, 52.82103704, 52.82060763,
52.8208682, 52.82211317, 52.81868547, 52.8198332, 52.82023595,
52.81989134, 52.8196971, 52.82051066, 52.82463338, 52.82539131,
52.82580625, 52.82509199, 52.83759415, 52.83946254, 52.83946254,
52.83891871, 52.83821538, 52.84757879, 52.84663773, 52.8449371,
52.84592185, 52.84331619), longitude = c(-6.892397941, -6.915346343,
-6.922554014, -6.924997835, -6.926099967, -6.883340697, -6.897757597,
-6.897757597, -6.895500952, -6.883129556, -6.895500952, -6.703781864,
-6.680851783, -6.771845364, -6.773301282, -6.772958488, -6.77484647,
-6.771845364, -6.773422218, -6.772164896, -6.770622695, -6.784187251,
-6.901922588, -6.905109015, -6.901922588, -6.976679508, -6.973114498,
-6.974753462, -6.947990431, -6.947990431, -6.947990431, -6.976921427,
-6.958295227, -6.976921427, -6.947990431, -6.976921427, -6.902010609,
-6.915233457, -6.871160885, -6.832461149, -6.862126342, -6.943925285,
-6.93813643, -6.925128034, -6.932247524, -6.93461305, -6.932247524,
-6.934657053, -6.929283954, -6.845259603, -6.861188287, -6.866476268,
-6.940851164, -6.939203401, -6.930506188, -6.933317462, -6.929441954,
-6.922589037, -6.922589037, -6.926037258, -6.929423169, -6.917829279,
-6.938211918, -6.940658091, -6.940651748, -6.940107883, -6.940107883,
-6.938704642, -6.939084526, -6.933331264, -6.937496468, -6.937678962,
-6.940276221, -6.94018054, -6.939876475, -6.938983181, -6.934235666,
-6.93387209, -6.933134226, -6.934193569, -6.934383596, -6.933832641,
-6.937454656, -6.933818238, -6.93443811, -6.936913947, -6.920030341,
-6.920400963, -6.92215006, -6.910771124, -6.901500591, -6.899018998,
-6.899018998, -6.903007684, -6.90119821, -6.91063672, -6.909935672,
-6.90240965, -6.900066763, -6.901411136), mosaic_group = structure(c(10L,
10L, 8L, 8L, 8L, 7L, 7L, 7L, 7L, 7L, 7L, 10L, 10L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 12L, 12L, 12L, 10L, 10L, 10L, 13L, 13L, 13L, 13L,
9L, 6L, 6L, 6L, 6L, 6L, 10L, 8L, 8L, 9L, 9L, 9L, 9L, 7L, 7L,
7L, 9L, 9L, 9L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 8L, 8L, 8L, 8L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 8L,
6L, 6L, 6L, 6L, 6L, 8L, 8L, 10L, 10L, 10L), .Label = c("A", "B",
"C", "D", "E", "F", "G", "H", "I", "J", "K", "L", "M"), class = "factor"),
small_code = c(1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,
4L, 5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 8L, 8L, 8L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 11L,
11L, 12L, 12L, 13L, 14L, 14L, 14L, 14L, 14L, 15L, 16L, 16L,
17L, 17L, 18L, 18L, 19L, 19L, 19L, 20L, 20L, 20L, 21L, 21L,
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L,
22L, 22L, 22L, 22L, 23L, 23L, 23L, 23L, 23L, 23L, 24L, 24L,
24L, 25L, 26L, 26L, 26L, 26L, 26L, 27L, 27L, 28L, 28L, 28L
)), .Names = c("latitude", "longitude", "mosaic_group", "small_code"
), row.names = c(NA, 100L), class = "data.frame")

The function knncat::knncat accepts the argument classcol which is defined as:
Column with classification in it. Default: 1.
You have a data set with structure:
latitude longitude mosaic_group small_code
1 52.73260 -6.892398 J 1
2 52.74288 -6.915346 J 1
3 52.82108 -6.922554 H 2
4 52.82025 -6.924998 H 2
5 52.81981 -6.926100 H 2
6 52.81722 -6.883341 G 3
Therefore your argument should be classcol = 3 (or 4) I am assuming, but we can see that it certainly shouldn't be classcol = 2.

Resources