Using the dataset "dat" (found below), I'm seeking a way to condense down the data.frame such that each "site" (i.e., "CID_1"..."CID_13") has a maximum of 7 rows of post-processed data, where the first 6 have the highest "countPercentage" and the 7th row is the sum of "countPercentage" from all other rows within that "site", and it is assigned the name "Other". So, for the first two sites in the provided data.frame, CID_1 & CID_10, they would reduce to: CID_1 Cyanobacteria 37.48 CID_1 Proteobacteria 29.24 CID_1 Bacteroidetes 15.83 CID_1 Verrucomicrobia 6.38 CID_1 Firmicutes 2.30 CID_1 Acidobacteria 2.08 CID_1 Other 6.68 CID_10 Proteobacteria 35.37 CID_10 Bacteroidetes 25.19 CID_10 Cyanobacteria 23.29 CID_10 Verrucomicrobia 6.97 CID_10 Acidobacteria 1.99 CID_10 Actinobacteria 1.64 CID_10 Other 5.55 dat <- read.table(header=TRUE, sep=",", text="site,tax_name,count,countTotal,countPercentage CID_1,Cyanobacteria,46295,123509,37.483098398 CID_1,Proteobacteria,36120,123509,29.244832360 CID_1,Bacteroidetes,19546,123509,15.825567368 CID_1,Verrucomicrobia,7886,123509,6.384959801 CID_1,Firmicutes,2843,123509,2.301856545 CID_1,Acidobacteria,2563,123509,2.075152418 CID_1,Actinobacteria,2069,123509,1.675181566 CID_1,Planctomycetes,1481,123509,1.199102899 CID_1,Chloroflexi,1181,123509,0.956205621 CID_1,Gemmatimonadetes,956,123509,0.774032662 CID_1,Spirochaetes,688,123509,0.557044426 CID_1,Lentisphaerae,526,123509,0.425879895 CID_1,Ignavibacteriae,324,123509,0.262329061 CID_1,Chlorobi,238,123509,0.192698508 CID_1,Nitrospirae,230,123509,0.186221247 CID_1,Nitrospinae,169,123509,0.136832134 CID_1,Elusimicrobia,131,123509,0.106065145 CID_1,Tenericutes,114,123509,0.092300966 CID_1,Fibrobacteres,72,123509,0.058295347 CID_1,Thermotogae,21,123509,0.017002810 CID_1,Fusobacteria,21,123509,0.017002810 CID_1,Armatimonadetes,15,123509,0.012144864 CID_1,Synergistetes,10,123509,0.008096576 CID_1,Deinococcus-Thermus,6,123509,0.004857946 CID_1,Deferribacteres,2,123509,0.001619315 CID_1,Caldiserica,2,123509,0.001619315 CID_10,Proteobacteria,16043,45362,35.366606411 CID_10,Bacteroidetes,11426,45362,25.188483753 CID_10,Cyanobacteria,10567,45362,23.294828270 CID_10,Verrucomicrobia,3162,45362,6.970592126 CID_10,Acidobacteria,902,45362,1.988448481 CID_10,Actinobacteria,746,45362,1.644548300 CID_10,Firmicutes,718,45362,1.582822627 CID_10,Gemmatimonadetes,358,45362,0.789206825 CID_10,Planctomycetes,357,45362,0.787002337 CID_10,Chloroflexi,265,45362,0.584189410 CID_10,Spirochaetes,235,45362,0.518054759 CID_10,Ignavibacteriae,177,45362,0.390194436 CID_10,Lentisphaerae,108,45362,0.238084741 CID_10,Nitrospinae,75,45362,0.165336625 CID_10,Nitrospirae,58,45362,0.127860324 CID_10,Chlorobi,44,45362,0.096997487 CID_10,Elusimicrobia,28,45362,0.061725673 CID_10,Fibrobacteres,26,45362,0.057316697 CID_10,Armatimonadetes,15,45362,0.033067325 CID_10,Deinococcus-Thermus,13,45362,0.028658348 CID_10,Tenericutes,10,45362,0.022044883 CID_10,Synergistetes,9,45362,0.019840395 CID_10,Fusobacteria,9,45362,0.019840395 CID_10,Deferribacteres,6,45362,0.013226930 CID_10,Thermotogae,3,45362,0.006613465 CID_10,Caldiserica,2,45362,0.004408977 CID_11,Proteobacteria,10019,31387,31.920858954 CID_11,Cyanobacteria,8811,31387,28.072131774 CID_11,Bacteroidetes,7930,31387,25.265237200 CID_11,Verrucomicrobia,1750,31387,5.575556759 CID_11,Firmicutes,806,31387,2.567942142 CID_11,Acidobacteria,548,31387,1.745945774 CID_11,Actinobacteria,434,31387,1.382738076 CID_11,Chloroflexi,203,31387,0.646764584 CID_11,Planctomycetes,197,31387,0.627648389 CID_11,Gemmatimonadetes,192,31387,0.611718227 CID_11,Ignavibacteriae,87,31387,0.277184822 CID_11,Spirochaetes,80,31387,0.254882595 CID_11,Tenericutes,71,31387,0.226208303 CID_11,Fusobacteria,67,31387,0.213464173 CID_11,Lentisphaerae,54,31387,0.172045751 CID_11,Chlorobi,40,31387,0.127441297 CID_11,Nitrospinae,33,31387,0.105139070 CID_11,Armatimonadetes,22,31387,0.070092714 CID_11,Fibrobacteres,15,31387,0.047790487 CID_11,Nitrospirae,13,31387,0.041418422 CID_11,Elusimicrobia,13,31387,0.041418422 CID_11,Deinococcus-Thermus,2,31387,0.006372065 CID_12,Cyanobacteria,241,644,37.422360248 CID_12,Bacteroidetes,210,644,32.608695652 CID_12,Proteobacteria,118,644,18.322981366 CID_12,Verrucomicrobia,38,644,5.900621118 CID_12,Acidobacteria,11,644,1.708074534 CID_12,Ignavibacteriae,6,644,0.931677019 CID_12,Lentisphaerae,5,644,0.776397516 CID_12,Firmicutes,5,644,0.776397516 CID_12,Planctomycetes,3,644,0.465838509 CID_12,Fusobacteria,3,644,0.465838509 CID_12,Tenericutes,2,644,0.310559006 CID_12,Actinobacteria,2,644,0.310559006 CID_13,Cyanobacteria,8581,25530,33.611437524 CID_13,Bacteroidetes,6878,25530,26.940853897 CID_13,Proteobacteria,5341,25530,20.920485703 CID_13,Verrucomicrobia,1244,25530,4.872698786 CID_13,Firmicutes,1148,25530,4.496670584 CID_13,Acidobacteria,548,25530,2.146494320 CID_13,Spirochaetes,477,25530,1.868390129 CID_13,Ignavibacteriae,298,25530,1.167254211 CID_13,Actinobacteria,227,25530,0.889150020 CID_13,Planctomycetes,184,25530,0.720720721 CID_13,Chloroflexi,181,25530,0.708969839 CID_13,Gemmatimonadetes,121,25530,0.473952213 CID_13,Lentisphaerae,93,25530,0.364277321 CID_13,Tenericutes,61,25530,0.238934587 CID_13,Fibrobacteres,47,25530,0.184097141 CID_13,Nitrospinae,28,25530,0.109674892 CID_13,Nitrospirae,26,25530,0.101840971 CID_13,Chlorobi,18,25530,0.070505288 CID_13,Elusimicrobia,13,25530,0.050920486 CID_13,Synergistetes,8,25530,0.031335684 CID_13,Fusobacteria,4,25530,0.015667842 CID_13,Deinococcus-Thermus,2,25530,0.007833921 CID_13,Thermotogae,2,25530,0.007833921 CID_2,Cyanobacteria,43812,94826,46.202518297 CID_2,Proteobacteria,22180,94826,23.390209436 CID_2,Bacteroidetes,16993,94826,17.920190665 CID_2,Verrucomicrobia,4779,94826,5.039757029 CID_2,Acidobacteria,1728,94826,1.822285027 CID_2,Firmicutes,1385,94826,1.460569886 CID_2,Planctomycetes,815,94826,0.859468922 CID_2,Actinobacteria,677,94826,0.713939215 CID_2,Gemmatimonadetes,625,94826,0.659101934 CID_2,Chloroflexi,416,94826,0.438698247 CID_2,Spirochaetes,415,94826,0.437643684 CID_2,Lentisphaerae,221,94826,0.233058444 CID_2,Ignavibacteriae,180,94826,0.189821357 CID_2,Fibrobacteres,155,94826,0.163457280 CID_2,Chlorobi,112,94826,0.118111067 CID_2,Elusimicrobia,111,94826,0.117056503 CID_2,Tenericutes,75,94826,0.079092232 CID_2,Nitrospinae,40,94826,0.042182524 CID_2,Nitrospirae,31,94826,0.032691456 CID_2,Deinococcus-Thermus,17,94826,0.017927573 CID_2,Armatimonadetes,17,94826,0.017927573 CID_2,Synergistetes,16,94826,0.016873010 CID_2,Fusobacteria,15,94826,0.015818446 CID_2,Deferribacteres,7,94826,0.007381942 CID_2,Caldiserica,2,94826,0.002109126 CID_2,Thermotogae,2,94826,0.002109126 CID_3,Cyanobacteria,18888,46181,40.899937204 CID_3,Proteobacteria,12532,46181,27.136701241 CID_3,Bacteroidetes,9070,46181,19.640111734 CID_3,Verrucomicrobia,2291,46181,4.960914662 CID_3,Acidobacteria,689,46181,1.491955566 CID_3,Firmicutes,631,46181,1.366362790 CID_3,Actinobacteria,470,46181,1.017734566 CID_3,Spirochaetes,366,46181,0.792533726 CID_3,Planctomycetes,326,46181,0.705918018 CID_3,Chloroflexi,282,46181,0.610640740 CID_3,Gemmatimonadetes,194,46181,0.420086183 CID_3,Fibrobacteres,116,46181,0.251185552 CID_3,Ignavibacteriae,109,46181,0.236027804 CID_3,Nitrospinae,46,46181,0.099608064 CID_3,Nitrospirae,44,46181,0.095277279 CID_3,Tenericutes,40,46181,0.086615708 CID_3,Lentisphaerae,38,46181,0.082284922 CID_3,Chlorobi,16,46181,0.034646283 CID_3,Elusimicrobia,14,46181,0.030315498 CID_3,Fusobacteria,10,46181,0.021653927 CID_3,Armatimonadetes,7,46181,0.015157749 CID_3,Synergistetes,2,46181,0.004330785 CID_4,Proteobacteria,433,1005,43.084577114 CID_4,Bacteroidetes,301,1005,29.950248756 CID_4,Actinobacteria,111,1005,11.044776119 CID_4,Cyanobacteria,44,1005,4.378109453 CID_4,Acidobacteria,28,1005,2.786069652 CID_4,Chloroflexi,24,1005,2.388059701 CID_4,Nitrospirae,21,1005,2.089552239 CID_4,Verrucomicrobia,12,1005,1.194029851 CID_4,Gemmatimonadetes,12,1005,1.194029851 CID_4,Firmicutes,7,1005,0.696517413 CID_4,Spirochaetes,5,1005,0.497512438 CID_4,Ignavibacteriae,5,1005,0.497512438 CID_4,Elusimicrobia,2,1005,0.199004975 CID_5,Proteobacteria,5002,11914,41.984220245 CID_5,Bacteroidetes,1512,11914,12.690951821 CID_5,Verrucomicrobia,1361,11914,11.423535337 CID_5,Acidobacteria,1207,11914,10.130938392 CID_5,Cyanobacteria,721,11914,6.051703878 CID_5,Planctomycetes,635,11914,5.329864026 CID_5,Actinobacteria,398,11914,3.340607688 CID_5,Nitrospirae,314,11914,2.635554809 CID_5,Chloroflexi,313,11914,2.627161323 CID_5,Firmicutes,195,11914,1.636729898 CID_5,Gemmatimonadetes,129,11914,1.082759778 CID_5,Chlorobi,31,11914,0.260198086 CID_5,Armatimonadetes,22,11914,0.184656706 CID_5,Ignavibacteriae,21,11914,0.176263220 CID_5,Fusobacteria,14,11914,0.117508813 CID_5,Deinococcus-Thermus,10,11914,0.083934867 CID_5,Lentisphaerae,9,11914,0.075541380 CID_5,Elusimicrobia,7,11914,0.058754407 CID_5,Nitrospinae,7,11914,0.058754407 CID_5,Synergistetes,4,11914,0.033573947 CID_5,Spirochaetes,2,11914,0.016786973 CID_6,Cyanobacteria,6462,17852,36.197624916 CID_6,Proteobacteria,5036,17852,28.209724401 CID_6,Bacteroidetes,3906,17852,21.879901412 CID_6,Verrucomicrobia,1016,17852,5.691239077 CID_6,Acidobacteria,317,17852,1.775711405 CID_6,Actinobacteria,286,17852,1.602061394 CID_6,Firmicutes,234,17852,1.310777504 CID_6,Planctomycetes,134,17852,0.750616177 CID_6,Gemmatimonadetes,112,17852,0.627380686 CID_6,Spirochaetes,97,17852,0.543356487 CID_6,Chloroflexi,77,17852,0.431324221 CID_6,Lentisphaerae,56,17852,0.313690343 CID_6,Ignavibacteriae,35,17852,0.196056464 CID_6,Nitrospirae,23,17852,0.128837105 CID_6,Nitrospinae,19,17852,0.106430652 CID_6,Tenericutes,12,17852,0.067219359 CID_6,Chlorobi,8,17852,0.044812906 CID_6,Armatimonadetes,7,17852,0.039211293 CID_6,Fibrobacteres,7,17852,0.039211293 CID_6,Elusimicrobia,4,17852,0.022406453 CID_6,Fusobacteria,2,17852,0.011203227 CID_6,Deferribacteres,2,17852,0.011203227 CID_7,Cyanobacteria,11046,30425,36.305669680 CID_7,Proteobacteria,8418,30425,27.668036154 CID_7,Bacteroidetes,6197,30425,20.368118324 CID_7,Verrucomicrobia,1745,30425,5.735414955 CID_7,Firmicutes,732,30425,2.405916187 CID_7,Acidobacteria,582,30425,1.912900575 CID_7,Actinobacteria,365,30425,1.199671323 CID_7,Fusobacteria,344,30425,1.130649137 CID_7,Planctomycetes,253,30425,0.831552999 CID_7,Chloroflexi,221,30425,0.726376335 CID_7,Gemmatimonadetes,131,30425,0.430566968 CID_7,Spirochaetes,127,30425,0.417419885 CID_7,Lentisphaerae,88,30425,0.289235826 CID_7,Ignavibacteriae,69,30425,0.226787182 CID_7,Nitrospinae,37,30425,0.121610518 CID_7,Nitrospirae,21,30425,0.069022186 CID_7,Chlorobi,17,30425,0.055875103 CID_7,Elusimicrobia,15,30425,0.049301561 CID_7,Fibrobacteres,9,30425,0.029580937 CID_7,Armatimonadetes,4,30425,0.013147083 CID_7,Deferribacteres,4,30425,0.013147083 CID_8,Cyanobacteria,14446,43589,33.141388883 CID_8,Proteobacteria,13270,43589,30.443460506 CID_8,Bacteroidetes,8834,43589,20.266581018 CID_8,Verrucomicrobia,2529,43589,5.801922503 CID_8,Firmicutes,1176,43589,2.697928376 CID_8,Acidobacteria,780,43589,1.789442290 CID_8,Actinobacteria,542,43589,1.243432976 CID_8,Spirochaetes,406,43589,0.931427654 CID_8,Planctomycetes,295,43589,0.676776251 CID_8,Chloroflexi,277,43589,0.635481429 CID_8,Ignavibacteriae,243,43589,0.557480098 CID_8,Lentisphaerae,230,43589,0.527656060 CID_8,Gemmatimonadetes,162,43589,0.371653399 CID_8,Fusobacteria,106,43589,0.243180619 CID_8,Tenericutes,57,43589,0.130766937 CID_8,Nitrospirae,51,43589,0.117001996 CID_8,Chlorobi,50,43589,0.114707839 CID_8,Nitrospinae,36,43589,0.082589644 CID_8,Fibrobacteres,34,43589,0.078001331 CID_8,Elusimicrobia,29,43589,0.066530547 CID_8,Armatimonadetes,19,43589,0.043588979 CID_8,Aquificae,8,43589,0.018353254 CID_8,Deferribacteres,7,43589,0.016059097 CID_8,Dictyoglomi,2,43589,0.004588314 CID_9,Proteobacteria,26463,77120,34.314056017 CID_9,Cyanobacteria,20329,77120,26.360217842 CID_9,Bacteroidetes,15956,77120,20.689834025 CID_9,Verrucomicrobia,3323,77120,4.308869295 CID_9,Firmicutes,2726,77120,3.534751037 CID_9,Spirochaetes,1644,77120,2.131742739 CID_9,Acidobacteria,1634,77120,2.118775934 CID_9,Actinobacteria,1200,77120,1.556016598 CID_9,Chloroflexi,1128,77120,1.462655602 CID_9,Planctomycetes,872,77120,1.130705394 CID_9,Ignavibacteriae,578,77120,0.749481328 CID_9,Lentisphaerae,264,77120,0.342323651 CID_9,Gemmatimonadetes,263,77120,0.341026971 CID_9,Fibrobacteres,170,77120,0.220435685 CID_9,Nitrospirae,148,77120,0.191908714 CID_9,Nitrospinae,136,77120,0.176348548 CID_9,Chlorobi,74,77120,0.095954357 CID_9,Tenericutes,71,77120,0.092064315 CID_9,Elusimicrobia,46,77120,0.059647303 CID_9,Armatimonadetes,27,77120,0.035010373 CID_9,Fusobacteria,25,77120,0.032417012 CID_9,Aquificae,13,77120,0.016856846 CID_9,Synergistetes,12,77120,0.015560166 CID_9,Deferribacteres,8,77120,0.010373444 CID_9,Thermotogae,7,77120,0.009076763 CID_9,Chrysiogenetes,3,77120,0.003890041 ") [[alternative HTML version deleted]]
> datBySite <- split(dat, dat$site)> output <- lapply(datBySite, function(x){ + x$idx <- seq_len(nrow(x)) + x$grp <- ifelse(x$idx < 7, x$idx, 7) + rval <- tapply(x$countPercentage, x$grp, sum) + x$grp <- x$count <- x$countTotal <- NULL + x <- x[seq_len(7), ] + x$tax_name <- as.character(x$tax_name) + x$tax_name[7] <- "Others" + x$new <- rval + return(x) + }) > > head(do.call(rbind, output), 14) site tax_name countPercentage idx new CID_1.1 CID_1 Cyanobacteria 37.483098 1 37.483098 CID_1.2 CID_1 Proteobacteria 29.244832 2 29.244832 CID_1.3 CID_1 Bacteroidetes 15.825567 3 15.825567 CID_1.4 CID_1 Verrucomicrobia 6.384960 4 6.384960 CID_1.5 CID_1 Firmicutes 2.301857 5 2.301857 CID_1.6 CID_1 Acidobacteria 2.075152 6 2.075152 CID_1.7 CID_1 Others 1.675182 7 6.684533 CID_10.27 CID_10 Proteobacteria 35.366606 1 35.366606 CID_10.28 CID_10 Bacteroidetes 25.188484 2 25.188484 CID_10.29 CID_10 Cyanobacteria 23.294828 3 23.294828 CID_10.30 CID_10 Verrucomicrobia 6.970592 4 6.970592 CID_10.31 CID_10 Acidobacteria 1.988448 5 1.988448 CID_10.32 CID_10 Actinobacteria 1.644548 6 1.644548 CID_10.33 CID_10 Others 1.582823 7 5.546493 > I hope this helps. Chel Hee Lee On 12/07/2014 08:21 AM, Morway, Eric wrote:> Using the dataset "dat" (found below), I'm seeking a way to condense down > the data.frame such that each "site" (i.e., "CID_1"..."CID_13") has a > maximum of 7 rows of post-processed data, where the first 6 have the > highest "countPercentage" and the 7th row is the sum of "countPercentage" > from all other rows within that "site", and it is assigned the name > "Other". So, for the first two sites in the provided data.frame, CID_1 & > CID_10, they would reduce to: > > CID_1 Cyanobacteria 37.48 > CID_1 Proteobacteria 29.24 > CID_1 Bacteroidetes 15.83 > CID_1 Verrucomicrobia 6.38 > CID_1 Firmicutes 2.30 > CID_1 Acidobacteria 2.08 > CID_1 Other 6.68 > CID_10 Proteobacteria 35.37 > CID_10 Bacteroidetes 25.19 > CID_10 Cyanobacteria 23.29 > CID_10 Verrucomicrobia 6.97 > CID_10 Acidobacteria 1.99 > CID_10 Actinobacteria 1.64 > CID_10 Other 5.55 > > > dat <- read.table(header=TRUE, sep=",", > text="site,tax_name,count,countTotal,countPercentage > CID_1,Cyanobacteria,46295,123509,37.483098398 > CID_1,Proteobacteria,36120,123509,29.244832360 > CID_1,Bacteroidetes,19546,123509,15.825567368 > CID_1,Verrucomicrobia,7886,123509,6.384959801 > CID_1,Firmicutes,2843,123509,2.301856545 > CID_1,Acidobacteria,2563,123509,2.075152418 > CID_1,Actinobacteria,2069,123509,1.675181566 > CID_1,Planctomycetes,1481,123509,1.199102899 > CID_1,Chloroflexi,1181,123509,0.956205621 > CID_1,Gemmatimonadetes,956,123509,0.774032662 > CID_1,Spirochaetes,688,123509,0.557044426 > CID_1,Lentisphaerae,526,123509,0.425879895 > CID_1,Ignavibacteriae,324,123509,0.262329061 > CID_1,Chlorobi,238,123509,0.192698508 > CID_1,Nitrospirae,230,123509,0.186221247 > CID_1,Nitrospinae,169,123509,0.136832134 > CID_1,Elusimicrobia,131,123509,0.106065145 > CID_1,Tenericutes,114,123509,0.092300966 > CID_1,Fibrobacteres,72,123509,0.058295347 > CID_1,Thermotogae,21,123509,0.017002810 > CID_1,Fusobacteria,21,123509,0.017002810 > CID_1,Armatimonadetes,15,123509,0.012144864 > CID_1,Synergistetes,10,123509,0.008096576 > CID_1,Deinococcus-Thermus,6,123509,0.004857946 > CID_1,Deferribacteres,2,123509,0.001619315 > CID_1,Caldiserica,2,123509,0.001619315 > CID_10,Proteobacteria,16043,45362,35.366606411 > CID_10,Bacteroidetes,11426,45362,25.188483753 > CID_10,Cyanobacteria,10567,45362,23.294828270 > CID_10,Verrucomicrobia,3162,45362,6.970592126 > CID_10,Acidobacteria,902,45362,1.988448481 > CID_10,Actinobacteria,746,45362,1.644548300 > CID_10,Firmicutes,718,45362,1.582822627 > CID_10,Gemmatimonadetes,358,45362,0.789206825 > CID_10,Planctomycetes,357,45362,0.787002337 > CID_10,Chloroflexi,265,45362,0.584189410 > CID_10,Spirochaetes,235,45362,0.518054759 > CID_10,Ignavibacteriae,177,45362,0.390194436 > CID_10,Lentisphaerae,108,45362,0.238084741 > CID_10,Nitrospinae,75,45362,0.165336625 > CID_10,Nitrospirae,58,45362,0.127860324 > CID_10,Chlorobi,44,45362,0.096997487 > CID_10,Elusimicrobia,28,45362,0.061725673 > CID_10,Fibrobacteres,26,45362,0.057316697 > CID_10,Armatimonadetes,15,45362,0.033067325 > CID_10,Deinococcus-Thermus,13,45362,0.028658348 > CID_10,Tenericutes,10,45362,0.022044883 > CID_10,Synergistetes,9,45362,0.019840395 > CID_10,Fusobacteria,9,45362,0.019840395 > CID_10,Deferribacteres,6,45362,0.013226930 > CID_10,Thermotogae,3,45362,0.006613465 > CID_10,Caldiserica,2,45362,0.004408977 > CID_11,Proteobacteria,10019,31387,31.920858954 > CID_11,Cyanobacteria,8811,31387,28.072131774 > CID_11,Bacteroidetes,7930,31387,25.265237200 > CID_11,Verrucomicrobia,1750,31387,5.575556759 > CID_11,Firmicutes,806,31387,2.567942142 > CID_11,Acidobacteria,548,31387,1.745945774 > CID_11,Actinobacteria,434,31387,1.382738076 > CID_11,Chloroflexi,203,31387,0.646764584 > CID_11,Planctomycetes,197,31387,0.627648389 > CID_11,Gemmatimonadetes,192,31387,0.611718227 > CID_11,Ignavibacteriae,87,31387,0.277184822 > CID_11,Spirochaetes,80,31387,0.254882595 > CID_11,Tenericutes,71,31387,0.226208303 > CID_11,Fusobacteria,67,31387,0.213464173 > CID_11,Lentisphaerae,54,31387,0.172045751 > CID_11,Chlorobi,40,31387,0.127441297 > CID_11,Nitrospinae,33,31387,0.105139070 > CID_11,Armatimonadetes,22,31387,0.070092714 > CID_11,Fibrobacteres,15,31387,0.047790487 > CID_11,Nitrospirae,13,31387,0.041418422 > CID_11,Elusimicrobia,13,31387,0.041418422 > CID_11,Deinococcus-Thermus,2,31387,0.006372065 > CID_12,Cyanobacteria,241,644,37.422360248 > CID_12,Bacteroidetes,210,644,32.608695652 > CID_12,Proteobacteria,118,644,18.322981366 > CID_12,Verrucomicrobia,38,644,5.900621118 > CID_12,Acidobacteria,11,644,1.708074534 > CID_12,Ignavibacteriae,6,644,0.931677019 > CID_12,Lentisphaerae,5,644,0.776397516 > CID_12,Firmicutes,5,644,0.776397516 > CID_12,Planctomycetes,3,644,0.465838509 > CID_12,Fusobacteria,3,644,0.465838509 > CID_12,Tenericutes,2,644,0.310559006 > CID_12,Actinobacteria,2,644,0.310559006 > CID_13,Cyanobacteria,8581,25530,33.611437524 > CID_13,Bacteroidetes,6878,25530,26.940853897 > CID_13,Proteobacteria,5341,25530,20.920485703 > CID_13,Verrucomicrobia,1244,25530,4.872698786 > CID_13,Firmicutes,1148,25530,4.496670584 > CID_13,Acidobacteria,548,25530,2.146494320 > CID_13,Spirochaetes,477,25530,1.868390129 > CID_13,Ignavibacteriae,298,25530,1.167254211 > CID_13,Actinobacteria,227,25530,0.889150020 > CID_13,Planctomycetes,184,25530,0.720720721 > CID_13,Chloroflexi,181,25530,0.708969839 > CID_13,Gemmatimonadetes,121,25530,0.473952213 > CID_13,Lentisphaerae,93,25530,0.364277321 > CID_13,Tenericutes,61,25530,0.238934587 > CID_13,Fibrobacteres,47,25530,0.184097141 > CID_13,Nitrospinae,28,25530,0.109674892 > CID_13,Nitrospirae,26,25530,0.101840971 > CID_13,Chlorobi,18,25530,0.070505288 > CID_13,Elusimicrobia,13,25530,0.050920486 > CID_13,Synergistetes,8,25530,0.031335684 > CID_13,Fusobacteria,4,25530,0.015667842 > CID_13,Deinococcus-Thermus,2,25530,0.007833921 > CID_13,Thermotogae,2,25530,0.007833921 > CID_2,Cyanobacteria,43812,94826,46.202518297 > CID_2,Proteobacteria,22180,94826,23.390209436 > CID_2,Bacteroidetes,16993,94826,17.920190665 > CID_2,Verrucomicrobia,4779,94826,5.039757029 > CID_2,Acidobacteria,1728,94826,1.822285027 > CID_2,Firmicutes,1385,94826,1.460569886 > CID_2,Planctomycetes,815,94826,0.859468922 > CID_2,Actinobacteria,677,94826,0.713939215 > CID_2,Gemmatimonadetes,625,94826,0.659101934 > CID_2,Chloroflexi,416,94826,0.438698247 > CID_2,Spirochaetes,415,94826,0.437643684 > CID_2,Lentisphaerae,221,94826,0.233058444 > CID_2,Ignavibacteriae,180,94826,0.189821357 > CID_2,Fibrobacteres,155,94826,0.163457280 > CID_2,Chlorobi,112,94826,0.118111067 > CID_2,Elusimicrobia,111,94826,0.117056503 > CID_2,Tenericutes,75,94826,0.079092232 > CID_2,Nitrospinae,40,94826,0.042182524 > CID_2,Nitrospirae,31,94826,0.032691456 > CID_2,Deinococcus-Thermus,17,94826,0.017927573 > CID_2,Armatimonadetes,17,94826,0.017927573 > CID_2,Synergistetes,16,94826,0.016873010 > CID_2,Fusobacteria,15,94826,0.015818446 > CID_2,Deferribacteres,7,94826,0.007381942 > CID_2,Caldiserica,2,94826,0.002109126 > CID_2,Thermotogae,2,94826,0.002109126 > CID_3,Cyanobacteria,18888,46181,40.899937204 > CID_3,Proteobacteria,12532,46181,27.136701241 > CID_3,Bacteroidetes,9070,46181,19.640111734 > CID_3,Verrucomicrobia,2291,46181,4.960914662 > CID_3,Acidobacteria,689,46181,1.491955566 > CID_3,Firmicutes,631,46181,1.366362790 > CID_3,Actinobacteria,470,46181,1.017734566 > CID_3,Spirochaetes,366,46181,0.792533726 > CID_3,Planctomycetes,326,46181,0.705918018 > CID_3,Chloroflexi,282,46181,0.610640740 > CID_3,Gemmatimonadetes,194,46181,0.420086183 > CID_3,Fibrobacteres,116,46181,0.251185552 > CID_3,Ignavibacteriae,109,46181,0.236027804 > CID_3,Nitrospinae,46,46181,0.099608064 > CID_3,Nitrospirae,44,46181,0.095277279 > CID_3,Tenericutes,40,46181,0.086615708 > CID_3,Lentisphaerae,38,46181,0.082284922 > CID_3,Chlorobi,16,46181,0.034646283 > CID_3,Elusimicrobia,14,46181,0.030315498 > CID_3,Fusobacteria,10,46181,0.021653927 > CID_3,Armatimonadetes,7,46181,0.015157749 > CID_3,Synergistetes,2,46181,0.004330785 > CID_4,Proteobacteria,433,1005,43.084577114 > CID_4,Bacteroidetes,301,1005,29.950248756 > CID_4,Actinobacteria,111,1005,11.044776119 > CID_4,Cyanobacteria,44,1005,4.378109453 > CID_4,Acidobacteria,28,1005,2.786069652 > CID_4,Chloroflexi,24,1005,2.388059701 > CID_4,Nitrospirae,21,1005,2.089552239 > CID_4,Verrucomicrobia,12,1005,1.194029851 > CID_4,Gemmatimonadetes,12,1005,1.194029851 > CID_4,Firmicutes,7,1005,0.696517413 > CID_4,Spirochaetes,5,1005,0.497512438 > CID_4,Ignavibacteriae,5,1005,0.497512438 > CID_4,Elusimicrobia,2,1005,0.199004975 > CID_5,Proteobacteria,5002,11914,41.984220245 > CID_5,Bacteroidetes,1512,11914,12.690951821 > CID_5,Verrucomicrobia,1361,11914,11.423535337 > CID_5,Acidobacteria,1207,11914,10.130938392 > CID_5,Cyanobacteria,721,11914,6.051703878 > CID_5,Planctomycetes,635,11914,5.329864026 > CID_5,Actinobacteria,398,11914,3.340607688 > CID_5,Nitrospirae,314,11914,2.635554809 > CID_5,Chloroflexi,313,11914,2.627161323 > CID_5,Firmicutes,195,11914,1.636729898 > CID_5,Gemmatimonadetes,129,11914,1.082759778 > CID_5,Chlorobi,31,11914,0.260198086 > CID_5,Armatimonadetes,22,11914,0.184656706 > CID_5,Ignavibacteriae,21,11914,0.176263220 > CID_5,Fusobacteria,14,11914,0.117508813 > CID_5,Deinococcus-Thermus,10,11914,0.083934867 > CID_5,Lentisphaerae,9,11914,0.075541380 > CID_5,Elusimicrobia,7,11914,0.058754407 > CID_5,Nitrospinae,7,11914,0.058754407 > CID_5,Synergistetes,4,11914,0.033573947 > CID_5,Spirochaetes,2,11914,0.016786973 > CID_6,Cyanobacteria,6462,17852,36.197624916 > CID_6,Proteobacteria,5036,17852,28.209724401 > CID_6,Bacteroidetes,3906,17852,21.879901412 > CID_6,Verrucomicrobia,1016,17852,5.691239077 > CID_6,Acidobacteria,317,17852,1.775711405 > CID_6,Actinobacteria,286,17852,1.602061394 > CID_6,Firmicutes,234,17852,1.310777504 > CID_6,Planctomycetes,134,17852,0.750616177 > CID_6,Gemmatimonadetes,112,17852,0.627380686 > CID_6,Spirochaetes,97,17852,0.543356487 > CID_6,Chloroflexi,77,17852,0.431324221 > CID_6,Lentisphaerae,56,17852,0.313690343 > CID_6,Ignavibacteriae,35,17852,0.196056464 > CID_6,Nitrospirae,23,17852,0.128837105 > CID_6,Nitrospinae,19,17852,0.106430652 > CID_6,Tenericutes,12,17852,0.067219359 > CID_6,Chlorobi,8,17852,0.044812906 > CID_6,Armatimonadetes,7,17852,0.039211293 > CID_6,Fibrobacteres,7,17852,0.039211293 > CID_6,Elusimicrobia,4,17852,0.022406453 > CID_6,Fusobacteria,2,17852,0.011203227 > CID_6,Deferribacteres,2,17852,0.011203227 > CID_7,Cyanobacteria,11046,30425,36.305669680 > CID_7,Proteobacteria,8418,30425,27.668036154 > CID_7,Bacteroidetes,6197,30425,20.368118324 > CID_7,Verrucomicrobia,1745,30425,5.735414955 > CID_7,Firmicutes,732,30425,2.405916187 > CID_7,Acidobacteria,582,30425,1.912900575 > CID_7,Actinobacteria,365,30425,1.199671323 > CID_7,Fusobacteria,344,30425,1.130649137 > CID_7,Planctomycetes,253,30425,0.831552999 > CID_7,Chloroflexi,221,30425,0.726376335 > CID_7,Gemmatimonadetes,131,30425,0.430566968 > CID_7,Spirochaetes,127,30425,0.417419885 > CID_7,Lentisphaerae,88,30425,0.289235826 > CID_7,Ignavibacteriae,69,30425,0.226787182 > CID_7,Nitrospinae,37,30425,0.121610518 > CID_7,Nitrospirae,21,30425,0.069022186 > CID_7,Chlorobi,17,30425,0.055875103 > CID_7,Elusimicrobia,15,30425,0.049301561 > CID_7,Fibrobacteres,9,30425,0.029580937 > CID_7,Armatimonadetes,4,30425,0.013147083 > CID_7,Deferribacteres,4,30425,0.013147083 > CID_8,Cyanobacteria,14446,43589,33.141388883 > CID_8,Proteobacteria,13270,43589,30.443460506 > CID_8,Bacteroidetes,8834,43589,20.266581018 > CID_8,Verrucomicrobia,2529,43589,5.801922503 > CID_8,Firmicutes,1176,43589,2.697928376 > CID_8,Acidobacteria,780,43589,1.789442290 > CID_8,Actinobacteria,542,43589,1.243432976 > CID_8,Spirochaetes,406,43589,0.931427654 > CID_8,Planctomycetes,295,43589,0.676776251 > CID_8,Chloroflexi,277,43589,0.635481429 > CID_8,Ignavibacteriae,243,43589,0.557480098 > CID_8,Lentisphaerae,230,43589,0.527656060 > CID_8,Gemmatimonadetes,162,43589,0.371653399 > CID_8,Fusobacteria,106,43589,0.243180619 > CID_8,Tenericutes,57,43589,0.130766937 > CID_8,Nitrospirae,51,43589,0.117001996 > CID_8,Chlorobi,50,43589,0.114707839 > CID_8,Nitrospinae,36,43589,0.082589644 > CID_8,Fibrobacteres,34,43589,0.078001331 > CID_8,Elusimicrobia,29,43589,0.066530547 > CID_8,Armatimonadetes,19,43589,0.043588979 > CID_8,Aquificae,8,43589,0.018353254 > CID_8,Deferribacteres,7,43589,0.016059097 > CID_8,Dictyoglomi,2,43589,0.004588314 > CID_9,Proteobacteria,26463,77120,34.314056017 > CID_9,Cyanobacteria,20329,77120,26.360217842 > CID_9,Bacteroidetes,15956,77120,20.689834025 > CID_9,Verrucomicrobia,3323,77120,4.308869295 > CID_9,Firmicutes,2726,77120,3.534751037 > CID_9,Spirochaetes,1644,77120,2.131742739 > CID_9,Acidobacteria,1634,77120,2.118775934 > CID_9,Actinobacteria,1200,77120,1.556016598 > CID_9,Chloroflexi,1128,77120,1.462655602 > CID_9,Planctomycetes,872,77120,1.130705394 > CID_9,Ignavibacteriae,578,77120,0.749481328 > CID_9,Lentisphaerae,264,77120,0.342323651 > CID_9,Gemmatimonadetes,263,77120,0.341026971 > CID_9,Fibrobacteres,170,77120,0.220435685 > CID_9,Nitrospirae,148,77120,0.191908714 > CID_9,Nitrospinae,136,77120,0.176348548 > CID_9,Chlorobi,74,77120,0.095954357 > CID_9,Tenericutes,71,77120,0.092064315 > CID_9,Elusimicrobia,46,77120,0.059647303 > CID_9,Armatimonadetes,27,77120,0.035010373 > CID_9,Fusobacteria,25,77120,0.032417012 > CID_9,Aquificae,13,77120,0.016856846 > CID_9,Synergistetes,12,77120,0.015560166 > CID_9,Deferribacteres,8,77120,0.010373444 > CID_9,Thermotogae,7,77120,0.009076763 > CID_9,Chrysiogenetes,3,77120,0.003890041 > ") > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >
Here's a solution using the plyr library:
####################
library(plyr)
dat <- read.table(header=TRUE, sep=",", as.is=TRUE, ######
<---- as.is=TRUE
text="site,tax_name,count,countTotal,countPercentage
CID_1,Cyanobacteria,46295,123509,37.483098398
CID_1,Proteobacteria,36120,123509,29.244832360
CID_1,Bacteroidetes,19546,123509,15.825567368
CID_1,Verrucomicrobia,7886,123509,6.384959801
CID_1,Firmicutes,2843,123509,2.301856545
... <lines deleted here>
CID_9,Armatimonadetes,27,77120,0.035010373
CID_9,Fusobacteria,25,77120,0.032417012
CID_9,Aquificae,13,77120,0.016856846
CID_9,Synergistetes,12,77120,0.015560166
CID_9,Deferribacteres,8,77120,0.010373444
CID_9,Thermotogae,7,77120,0.009076763
CID_9,Chrysiogenetes,3,77120,0.003890041.
")
summ_cid = function(frm) {
# grab at most 6 rows from data frame
toprows = head(frm, 6)
# add a 7th row
toprows[nrow(toprows)+1,] = c(toprows[1,1], "", NA, NA,
sum(toprows$countPercentage))
# all done
return(toprows)
}
result = ddply(dat, "site", summ_cid)
####################
Notes:
1. I needed to add the as.is=TRUE option to read.table()
2. The invocation of ddply() does *not* use summarize()
3. Because there is no use of summarize(), I have not figured out how to use
the dplyr package in this context.
-John
> -----Original Message-----
> From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of Chel Hee
> Lee
> Sent: Sunday, December 07, 2014 11:43 AM
> To: Morway, Eric; R mailing list
> Subject: Re: [R] Condensing data.frame
>
> > datBySite <- split(dat, dat$site)
> > output <- lapply(datBySite, function(x){
> + x$idx <- seq_len(nrow(x))
> + x$grp <- ifelse(x$idx < 7, x$idx, 7)
> + rval <- tapply(x$countPercentage, x$grp, sum) x$grp <- x$count
<-
> + x$countTotal <- NULL x <- x[seq_len(7), ] x$tax_name <-
> + as.character(x$tax_name) x$tax_name[7] <- "Others"
> + x$new <- rval
> + return(x)
> + })
> >
> > head(do.call(rbind, output), 14)
> site tax_name countPercentage idx new
> CID_1.1 CID_1 Cyanobacteria 37.483098 1 37.483098
> CID_1.2 CID_1 Proteobacteria 29.244832 2 29.244832
> CID_1.3 CID_1 Bacteroidetes 15.825567 3 15.825567
> CID_1.4 CID_1 Verrucomicrobia 6.384960 4 6.384960
> CID_1.5 CID_1 Firmicutes 2.301857 5 2.301857
> CID_1.6 CID_1 Acidobacteria 2.075152 6 2.075152
> CID_1.7 CID_1 Others 1.675182 7 6.684533
> CID_10.27 CID_10 Proteobacteria 35.366606 1 35.366606
> CID_10.28 CID_10 Bacteroidetes 25.188484 2 25.188484
> CID_10.29 CID_10 Cyanobacteria 23.294828 3 23.294828
> CID_10.30 CID_10 Verrucomicrobia 6.970592 4 6.970592
> CID_10.31 CID_10 Acidobacteria 1.988448 5 1.988448
> CID_10.32 CID_10 Actinobacteria 1.644548 6 1.644548
> CID_10.33 CID_10 Others 1.582823 7 5.546493
> >
>
> I hope this helps.
>
> Chel Hee Lee
>
> On 12/07/2014 08:21 AM, Morway, Eric wrote:
> > Using the dataset "dat" (found below), I'm seeking a way
to condense
> > down the data.frame such that each "site" (i.e.,
"CID_1"..."CID_13")
> > has a maximum of 7 rows of post-processed data, where the first 6 have
> > the highest "countPercentage" and the 7th row is the sum of
> "countPercentage"
> > from all other rows within that "site", and it is assigned
the name
> > "Other". So, for the first two sites in the provided
data.frame,
> > CID_1 & CID_10, they would reduce to:
> >
> > CID_1 Cyanobacteria 37.48
> > CID_1 Proteobacteria 29.24
> > CID_1 Bacteroidetes 15.83
> > CID_1 Verrucomicrobia 6.38
> > CID_1 Firmicutes 2.30
> > CID_1 Acidobacteria 2.08
> > CID_1 Other 6.68
> > CID_10 Proteobacteria 35.37
> > CID_10 Bacteroidetes 25.19
> > CID_10 Cyanobacteria 23.29
> > CID_10 Verrucomicrobia 6.97
> > CID_10 Acidobacteria 1.99
> > CID_10 Actinobacteria 1.64
> > CID_10 Other 5.55
> >
> >
> > dat <- read.table(header=TRUE, sep=",",
> > text="site,tax_name,count,countTotal,countPercentage
> > CID_1,Cyanobacteria,46295,123509,37.483098398
> > CID_1,Proteobacteria,36120,123509,29.244832360
> > CID_1,Bacteroidetes,19546,123509,15.825567368
> > CID_1,Verrucomicrobia,7886,123509,6.384959801
> > CID_1,Firmicutes,2843,123509,2.301856545
> > CID_1,Acidobacteria,2563,123509,2.075152418
> > CID_1,Actinobacteria,2069,123509,1.675181566
> > CID_1,Planctomycetes,1481,123509,1.199102899
> > CID_1,Chloroflexi,1181,123509,0.956205621
> > CID_1,Gemmatimonadetes,956,123509,0.774032662
> > CID_1,Spirochaetes,688,123509,0.557044426
> > CID_1,Lentisphaerae,526,123509,0.425879895
> > CID_1,Ignavibacteriae,324,123509,0.262329061
> > CID_1,Chlorobi,238,123509,0.192698508
> > CID_1,Nitrospirae,230,123509,0.186221247
> > CID_1,Nitrospinae,169,123509,0.136832134
> > CID_1,Elusimicrobia,131,123509,0.106065145
> > CID_1,Tenericutes,114,123509,0.092300966
> > CID_1,Fibrobacteres,72,123509,0.058295347
> > CID_1,Thermotogae,21,123509,0.017002810
> > CID_1,Fusobacteria,21,123509,0.017002810
> > CID_1,Armatimonadetes,15,123509,0.012144864
> > CID_1,Synergistetes,10,123509,0.008096576
> > CID_1,Deinococcus-Thermus,6,123509,0.004857946
> > CID_1,Deferribacteres,2,123509,0.001619315
> > CID_1,Caldiserica,2,123509,0.001619315
> > CID_10,Proteobacteria,16043,45362,35.366606411
> > CID_10,Bacteroidetes,11426,45362,25.188483753
> > CID_10,Cyanobacteria,10567,45362,23.294828270
> > CID_10,Verrucomicrobia,3162,45362,6.970592126
> > CID_10,Acidobacteria,902,45362,1.988448481
> > CID_10,Actinobacteria,746,45362,1.644548300
> > CID_10,Firmicutes,718,45362,1.582822627
> > CID_10,Gemmatimonadetes,358,45362,0.789206825
> > CID_10,Planctomycetes,357,45362,0.787002337
> > CID_10,Chloroflexi,265,45362,0.584189410
> > CID_10,Spirochaetes,235,45362,0.518054759
> > CID_10,Ignavibacteriae,177,45362,0.390194436
> > CID_10,Lentisphaerae,108,45362,0.238084741
> > CID_10,Nitrospinae,75,45362,0.165336625
> > CID_10,Nitrospirae,58,45362,0.127860324
> > CID_10,Chlorobi,44,45362,0.096997487
> > CID_10,Elusimicrobia,28,45362,0.061725673
> > CID_10,Fibrobacteres,26,45362,0.057316697
> > CID_10,Armatimonadetes,15,45362,0.033067325
> > CID_10,Deinococcus-Thermus,13,45362,0.028658348
> > CID_10,Tenericutes,10,45362,0.022044883
> > CID_10,Synergistetes,9,45362,0.019840395
> > CID_10,Fusobacteria,9,45362,0.019840395
> > CID_10,Deferribacteres,6,45362,0.013226930
> > CID_10,Thermotogae,3,45362,0.006613465
> > CID_10,Caldiserica,2,45362,0.004408977
> > CID_11,Proteobacteria,10019,31387,31.920858954
> > CID_11,Cyanobacteria,8811,31387,28.072131774
> > CID_11,Bacteroidetes,7930,31387,25.265237200
> > CID_11,Verrucomicrobia,1750,31387,5.575556759
> > CID_11,Firmicutes,806,31387,2.567942142
> > CID_11,Acidobacteria,548,31387,1.745945774
> > CID_11,Actinobacteria,434,31387,1.382738076
> > CID_11,Chloroflexi,203,31387,0.646764584
> > CID_11,Planctomycetes,197,31387,0.627648389
> > CID_11,Gemmatimonadetes,192,31387,0.611718227
> > CID_11,Ignavibacteriae,87,31387,0.277184822
> > CID_11,Spirochaetes,80,31387,0.254882595
> > CID_11,Tenericutes,71,31387,0.226208303
> > CID_11,Fusobacteria,67,31387,0.213464173
> > CID_11,Lentisphaerae,54,31387,0.172045751
> > CID_11,Chlorobi,40,31387,0.127441297
> > CID_11,Nitrospinae,33,31387,0.105139070
> > CID_11,Armatimonadetes,22,31387,0.070092714
> > CID_11,Fibrobacteres,15,31387,0.047790487
> > CID_11,Nitrospirae,13,31387,0.041418422
> > CID_11,Elusimicrobia,13,31387,0.041418422
> > CID_11,Deinococcus-Thermus,2,31387,0.006372065
> > CID_12,Cyanobacteria,241,644,37.422360248
> > CID_12,Bacteroidetes,210,644,32.608695652
> > CID_12,Proteobacteria,118,644,18.322981366
> > CID_12,Verrucomicrobia,38,644,5.900621118
> > CID_12,Acidobacteria,11,644,1.708074534
> > CID_12,Ignavibacteriae,6,644,0.931677019
> > CID_12,Lentisphaerae,5,644,0.776397516
> > CID_12,Firmicutes,5,644,0.776397516
> > CID_12,Planctomycetes,3,644,0.465838509
> > CID_12,Fusobacteria,3,644,0.465838509
> > CID_12,Tenericutes,2,644,0.310559006
> > CID_12,Actinobacteria,2,644,0.310559006
> > CID_13,Cyanobacteria,8581,25530,33.611437524
> > CID_13,Bacteroidetes,6878,25530,26.940853897
> > CID_13,Proteobacteria,5341,25530,20.920485703
> > CID_13,Verrucomicrobia,1244,25530,4.872698786
> > CID_13,Firmicutes,1148,25530,4.496670584
> > CID_13,Acidobacteria,548,25530,2.146494320
> > CID_13,Spirochaetes,477,25530,1.868390129
> > CID_13,Ignavibacteriae,298,25530,1.167254211
> > CID_13,Actinobacteria,227,25530,0.889150020
> > CID_13,Planctomycetes,184,25530,0.720720721
> > CID_13,Chloroflexi,181,25530,0.708969839
> > CID_13,Gemmatimonadetes,121,25530,0.473952213
> > CID_13,Lentisphaerae,93,25530,0.364277321
> > CID_13,Tenericutes,61,25530,0.238934587
> > CID_13,Fibrobacteres,47,25530,0.184097141
> > CID_13,Nitrospinae,28,25530,0.109674892
> > CID_13,Nitrospirae,26,25530,0.101840971
> > CID_13,Chlorobi,18,25530,0.070505288
> > CID_13,Elusimicrobia,13,25530,0.050920486
> > CID_13,Synergistetes,8,25530,0.031335684
> > CID_13,Fusobacteria,4,25530,0.015667842
> > CID_13,Deinococcus-Thermus,2,25530,0.007833921
> > CID_13,Thermotogae,2,25530,0.007833921
> > CID_2,Cyanobacteria,43812,94826,46.202518297
> > CID_2,Proteobacteria,22180,94826,23.390209436
> > CID_2,Bacteroidetes,16993,94826,17.920190665
> > CID_2,Verrucomicrobia,4779,94826,5.039757029
> > CID_2,Acidobacteria,1728,94826,1.822285027
> > CID_2,Firmicutes,1385,94826,1.460569886
> > CID_2,Planctomycetes,815,94826,0.859468922
> > CID_2,Actinobacteria,677,94826,0.713939215
> > CID_2,Gemmatimonadetes,625,94826,0.659101934
> > CID_2,Chloroflexi,416,94826,0.438698247
> > CID_2,Spirochaetes,415,94826,0.437643684
> > CID_2,Lentisphaerae,221,94826,0.233058444
> > CID_2,Ignavibacteriae,180,94826,0.189821357
> > CID_2,Fibrobacteres,155,94826,0.163457280
> > CID_2,Chlorobi,112,94826,0.118111067
> > CID_2,Elusimicrobia,111,94826,0.117056503
> > CID_2,Tenericutes,75,94826,0.079092232
> > CID_2,Nitrospinae,40,94826,0.042182524
> > CID_2,Nitrospirae,31,94826,0.032691456
> > CID_2,Deinococcus-Thermus,17,94826,0.017927573
> > CID_2,Armatimonadetes,17,94826,0.017927573
> > CID_2,Synergistetes,16,94826,0.016873010
> > CID_2,Fusobacteria,15,94826,0.015818446
> > CID_2,Deferribacteres,7,94826,0.007381942
> > CID_2,Caldiserica,2,94826,0.002109126
> > CID_2,Thermotogae,2,94826,0.002109126
> > CID_3,Cyanobacteria,18888,46181,40.899937204
> > CID_3,Proteobacteria,12532,46181,27.136701241
> > CID_3,Bacteroidetes,9070,46181,19.640111734
> > CID_3,Verrucomicrobia,2291,46181,4.960914662
> > CID_3,Acidobacteria,689,46181,1.491955566
> > CID_3,Firmicutes,631,46181,1.366362790
> > CID_3,Actinobacteria,470,46181,1.017734566
> > CID_3,Spirochaetes,366,46181,0.792533726
> > CID_3,Planctomycetes,326,46181,0.705918018
> > CID_3,Chloroflexi,282,46181,0.610640740
> > CID_3,Gemmatimonadetes,194,46181,0.420086183
> > CID_3,Fibrobacteres,116,46181,0.251185552
> > CID_3,Ignavibacteriae,109,46181,0.236027804
> > CID_3,Nitrospinae,46,46181,0.099608064
> > CID_3,Nitrospirae,44,46181,0.095277279
> > CID_3,Tenericutes,40,46181,0.086615708
> > CID_3,Lentisphaerae,38,46181,0.082284922
> > CID_3,Chlorobi,16,46181,0.034646283
> > CID_3,Elusimicrobia,14,46181,0.030315498
> > CID_3,Fusobacteria,10,46181,0.021653927
> > CID_3,Armatimonadetes,7,46181,0.015157749
> > CID_3,Synergistetes,2,46181,0.004330785
> > CID_4,Proteobacteria,433,1005,43.084577114
> > CID_4,Bacteroidetes,301,1005,29.950248756
> > CID_4,Actinobacteria,111,1005,11.044776119
> > CID_4,Cyanobacteria,44,1005,4.378109453
> > CID_4,Acidobacteria,28,1005,2.786069652
> > CID_4,Chloroflexi,24,1005,2.388059701
> > CID_4,Nitrospirae,21,1005,2.089552239
> > CID_4,Verrucomicrobia,12,1005,1.194029851
> > CID_4,Gemmatimonadetes,12,1005,1.194029851
> > CID_4,Firmicutes,7,1005,0.696517413
> > CID_4,Spirochaetes,5,1005,0.497512438
> > CID_4,Ignavibacteriae,5,1005,0.497512438
> > CID_4,Elusimicrobia,2,1005,0.199004975
> > CID_5,Proteobacteria,5002,11914,41.984220245
> > CID_5,Bacteroidetes,1512,11914,12.690951821
> > CID_5,Verrucomicrobia,1361,11914,11.423535337
> > CID_5,Acidobacteria,1207,11914,10.130938392
> > CID_5,Cyanobacteria,721,11914,6.051703878
> > CID_5,Planctomycetes,635,11914,5.329864026
> > CID_5,Actinobacteria,398,11914,3.340607688
> > CID_5,Nitrospirae,314,11914,2.635554809
> > CID_5,Chloroflexi,313,11914,2.627161323
> > CID_5,Firmicutes,195,11914,1.636729898
> > CID_5,Gemmatimonadetes,129,11914,1.082759778
> > CID_5,Chlorobi,31,11914,0.260198086
> > CID_5,Armatimonadetes,22,11914,0.184656706
> > CID_5,Ignavibacteriae,21,11914,0.176263220
> > CID_5,Fusobacteria,14,11914,0.117508813
> > CID_5,Deinococcus-Thermus,10,11914,0.083934867
> > CID_5,Lentisphaerae,9,11914,0.075541380
> > CID_5,Elusimicrobia,7,11914,0.058754407
> > CID_5,Nitrospinae,7,11914,0.058754407
> > CID_5,Synergistetes,4,11914,0.033573947
> > CID_5,Spirochaetes,2,11914,0.016786973
> > CID_6,Cyanobacteria,6462,17852,36.197624916
> > CID_6,Proteobacteria,5036,17852,28.209724401
> > CID_6,Bacteroidetes,3906,17852,21.879901412
> > CID_6,Verrucomicrobia,1016,17852,5.691239077
> > CID_6,Acidobacteria,317,17852,1.775711405
> > CID_6,Actinobacteria,286,17852,1.602061394
> > CID_6,Firmicutes,234,17852,1.310777504
> > CID_6,Planctomycetes,134,17852,0.750616177
> > CID_6,Gemmatimonadetes,112,17852,0.627380686
> > CID_6,Spirochaetes,97,17852,0.543356487
> > CID_6,Chloroflexi,77,17852,0.431324221
> > CID_6,Lentisphaerae,56,17852,0.313690343
> > CID_6,Ignavibacteriae,35,17852,0.196056464
> > CID_6,Nitrospirae,23,17852,0.128837105
> > CID_6,Nitrospinae,19,17852,0.106430652
> > CID_6,Tenericutes,12,17852,0.067219359
> > CID_6,Chlorobi,8,17852,0.044812906
> > CID_6,Armatimonadetes,7,17852,0.039211293
> > CID_6,Fibrobacteres,7,17852,0.039211293
> > CID_6,Elusimicrobia,4,17852,0.022406453
> > CID_6,Fusobacteria,2,17852,0.011203227
> > CID_6,Deferribacteres,2,17852,0.011203227
> > CID_7,Cyanobacteria,11046,30425,36.305669680
> > CID_7,Proteobacteria,8418,30425,27.668036154
> > CID_7,Bacteroidetes,6197,30425,20.368118324
> > CID_7,Verrucomicrobia,1745,30425,5.735414955
> > CID_7,Firmicutes,732,30425,2.405916187
> > CID_7,Acidobacteria,582,30425,1.912900575
> > CID_7,Actinobacteria,365,30425,1.199671323
> > CID_7,Fusobacteria,344,30425,1.130649137
> > CID_7,Planctomycetes,253,30425,0.831552999
> > CID_7,Chloroflexi,221,30425,0.726376335
> > CID_7,Gemmatimonadetes,131,30425,0.430566968
> > CID_7,Spirochaetes,127,30425,0.417419885
> > CID_7,Lentisphaerae,88,30425,0.289235826
> > CID_7,Ignavibacteriae,69,30425,0.226787182
> > CID_7,Nitrospinae,37,30425,0.121610518
> > CID_7,Nitrospirae,21,30425,0.069022186
> > CID_7,Chlorobi,17,30425,0.055875103
> > CID_7,Elusimicrobia,15,30425,0.049301561
> > CID_7,Fibrobacteres,9,30425,0.029580937
> > CID_7,Armatimonadetes,4,30425,0.013147083
> > CID_7,Deferribacteres,4,30425,0.013147083
> > CID_8,Cyanobacteria,14446,43589,33.141388883
> > CID_8,Proteobacteria,13270,43589,30.443460506
> > CID_8,Bacteroidetes,8834,43589,20.266581018
> > CID_8,Verrucomicrobia,2529,43589,5.801922503
> > CID_8,Firmicutes,1176,43589,2.697928376
> > CID_8,Acidobacteria,780,43589,1.789442290
> > CID_8,Actinobacteria,542,43589,1.243432976
> > CID_8,Spirochaetes,406,43589,0.931427654
> > CID_8,Planctomycetes,295,43589,0.676776251
> > CID_8,Chloroflexi,277,43589,0.635481429
> > CID_8,Ignavibacteriae,243,43589,0.557480098
> > CID_8,Lentisphaerae,230,43589,0.527656060
> > CID_8,Gemmatimonadetes,162,43589,0.371653399
> > CID_8,Fusobacteria,106,43589,0.243180619
> > CID_8,Tenericutes,57,43589,0.130766937
> > CID_8,Nitrospirae,51,43589,0.117001996
> > CID_8,Chlorobi,50,43589,0.114707839
> > CID_8,Nitrospinae,36,43589,0.082589644
> > CID_8,Fibrobacteres,34,43589,0.078001331
> > CID_8,Elusimicrobia,29,43589,0.066530547
> > CID_8,Armatimonadetes,19,43589,0.043588979
> > CID_8,Aquificae,8,43589,0.018353254
> > CID_8,Deferribacteres,7,43589,0.016059097
> > CID_8,Dictyoglomi,2,43589,0.004588314
> > CID_9,Proteobacteria,26463,77120,34.314056017
> > CID_9,Cyanobacteria,20329,77120,26.360217842
> > CID_9,Bacteroidetes,15956,77120,20.689834025
> > CID_9,Verrucomicrobia,3323,77120,4.308869295
> > CID_9,Firmicutes,2726,77120,3.534751037
> > CID_9,Spirochaetes,1644,77120,2.131742739
> > CID_9,Acidobacteria,1634,77120,2.118775934
> > CID_9,Actinobacteria,1200,77120,1.556016598
> > CID_9,Chloroflexi,1128,77120,1.462655602
> > CID_9,Planctomycetes,872,77120,1.130705394
> > CID_9,Ignavibacteriae,578,77120,0.749481328
> > CID_9,Lentisphaerae,264,77120,0.342323651
> > CID_9,Gemmatimonadetes,263,77120,0.341026971
> > CID_9,Fibrobacteres,170,77120,0.220435685
> > CID_9,Nitrospirae,148,77120,0.191908714
> > CID_9,Nitrospinae,136,77120,0.176348548
> > CID_9,Chlorobi,74,77120,0.095954357
> > CID_9,Tenericutes,71,77120,0.092064315
> > CID_9,Elusimicrobia,46,77120,0.059647303
> > CID_9,Armatimonadetes,27,77120,0.035010373
> > CID_9,Fusobacteria,25,77120,0.032417012
> > CID_9,Aquificae,13,77120,0.016856846
> > CID_9,Synergistetes,12,77120,0.015560166
> > CID_9,Deferribacteres,8,77120,0.010373444
> > CID_9,Thermotogae,7,77120,0.009076763
> > CID_9,Chrysiogenetes,3,77120,0.003890041
> > ")
> >
> > [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> > http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.