Add percentage (%) for a PieChart - r

Hello guys i am trying to do a pie chart like the next picture:
But i am getting a lot of problem
But this is the plot that I am getting:
ggpie(s, x="costes", label ="prop", lab.pos = "in", fill = "Implementation",
lab.font = list(size= 5)) + scale_fill_manual(values = c("dodgerblue2","blue"))
How i could add percentage to my labels like 98.9%...etc
data:
structure(list(Implementation = c("2", "1"), costes = c(6204670582.33, 70561379.07), prop = c(98.9, 1.1), lab.ypos = c(49.45, 99.45)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"))
Thanks so much for your time


per <- c(0.1,0.2,0.3,0.4)
labels <- c("a","b","c","d")
pie(per,labels = paste0(labels," (",round(per,digits = 3)*100,"%)"),
border="white",col = c("red","green","blue","yellow"))


You can add with 'labels = '. I named your data dummy.
> dummy
# A tibble: 2 x 4
Implementation costes prop lab.ypos
<chr> <dbl> <dbl> <dbl>
1 2 6204670582. 98.9 49.4
2 1 70561379. 1.1 99.4
dummy %>%
ggpie(x="costes", label ="prop", lab.pos = "in", fill = "Implementation",
lab.font = list(size= 5)) +
scale_fill_manual(values = c("dodgerblue2","blue"),
labels = paste(dummy$Implementation, (dummy$prop)))

Related

Remove specific markers from legend

Sorry if this question has already been answered but I could not find the solution to what I am after. I have a plot that uses both geom_line and geom_point. The result of this is that in the legend, it adds both a line and a point when they should have one or the other. I want to keep the circles for the data tg1 and tg2 and remove the line and then do the opposite to the data full i.e. keep the line but remove the circle. I have seen that something like this works where you want to remove dots from all of the legend entries but nothing to only do specifics Removing ggplot2's geom_point icons from the legend. Can anyone help? Thanks.
#code for plot
library(ggplot2)
library(tidypaleo)
ggplot(LGRSL, aes(x =mmsl , y = Age))+
coord_flip()+
theme_classic(12)+
geom_point(data=tg1,aes(x=mmslc,y=Year,col="Fort Denison 1"),pch=1,size=2)+
geom_point(data=tg2,aes(x=mmslc,y=Year,col="Fort Denison 2"),pch=1,size=2)+
geom_lineh(data = full, aes(x=Lutregalammslc,y=Year,col="Full budget"))+
scale_colour_manual(values=c("grey15","grey50","black"))
## data
## tg1
structure(list(Year = 1886:1891, SLR = c(6919L, 6935L, 6923L,
6955L, 6956L, 6957L), mmsl = c(-0.158, -0.142, -0.154, -0.122,
-0.121, -0.12), m = c(6.919, 6.935, 6.923, 6.955, 6.956, 6.957
), GIA.correction = c(-0.02814, -0.02793, -0.02772, -0.02751,
-0.0273, -0.02709), SLRc = c(6.89086, 6.90707, 6.89528, 6.92749,
6.9287, 6.92991), mmslc = c(-0.19667, -0.18046, -0.19225, -0.16004,
-0.15883, -0.15762)), row.names = c(NA, 6L), class = "data.frame")
##tg2
structure(list(Year = 1915:1920, SLR = c(7011L, 6929L, 6987L,
6945L, 6959L, 6951L), mmsl = c(-0.066, -0.148, -0.09, -0.132,
-0.118, -0.126), m = c(7.011, 6.929, 6.987, 6.945, 6.959, 6.951
), GIA.correction = c(-0.02205, -0.02184, -0.02163, -0.02142,
-0.02121, -0.021), SLRc = c(6.98895, 6.90716, 6.96537, 6.92358,
6.93779, 6.93), mmslc = c(-0.09858, -0.18037, -0.12216, -0.16395,
-0.14974, -0.15753)), row.names = c(NA, 6L), class = "data.frame")
##full
structure(list(Year = 1900:1905, Lutregala = c(-0.103609677,
-0.118603251, -0.134550791, -0.105553735, -0.103983082, -0.121731984
), Wapengo = c(-0.095213147, -0.096005337, -0.115700625, -0.097696891,
-0.084444784, -0.109161066), Tarra = c(-0.106672829, -0.109537943,
-0.135256365, -0.101357772, -0.089716518, -0.104258351), Lutregalammsl = c(-0.292863465,
-0.307857039, -0.323804579, -0.294807523, -0.29323687, -0.310985772
), Wapengommsl = c(-0.257028279, -0.257820469, -0.277515756,
-0.259512023, -0.246259916, -0.270976198), Tarrammsl = c(-0.30925682,
-0.312121933, -0.337840355, -0.303941762, -0.292300508, -0.306842342
), LgGIAc = c(-0.01921, -0.01904, -0.01887, -0.0187, -0.01853,
-0.01836), WapGIAc = c(-0.02486, -0.02464, -0.02442, -0.0242,
-0.02398, -0.02376), TarGIAc = c(-0.02373, -0.02352, -0.02331,
-0.0231, -0.02289, -0.02268), Lutregalammslc = c(-0.312073465,
-0.326897039, -0.342674579, -0.313507523, -0.31176687, -0.329345772
), Wapmmslc = c(-0.281888279, -0.282460469, -0.301935756, -0.283712023,
-0.270239916, -0.294736198), Tarmmslc = c(-0.33298682, -0.335641933,
-0.361150355, -0.327041762, -0.315190508, -0.329522342)), row.names = c(NA,
6L), class = "data.frame")
##LGRSL
structure(list(depths = c(0.5, 1.5, 2.5, 3.5, 4.5, 5.5), RSL = c(0.047746907,
0.025564293, 0.021733558, 0.007855661, -0.004909879, 0.01747051
), RSLerror = c(0.058158556, 0.057902654, 0.057988654, 0.057957388,
0.057905405, 0.057226072), Age = c(2017.456716, 2013.594255,
2006.92838, 1999.675523, 1994.729181, 1990.518154), Ageerror = c(0.373138707,
0.77640096, 1.430582242, 1.627131115, 3.222393394, 3.239674718
), mmsl = c(0.01993169, -0.002250924, -0.006081659, -0.019959556,
-0.032725096, -0.010344707)), row.names = c(NA, 6L), class = "data.frame")
##LGRSLgp
structure(list(Age = 1892:1897, mean = c(-0.298147401, -0.304630597,
-0.31023294, -0.315506983, -0.321225142, -0.327190675), error = c(0.051858047,
0.04985084, 0.047760525, 0.045624121, 0.043505044, 0.041477551
), min = c(-0.246289354, -0.254779758, -0.262472416, -0.269882862,
-0.277720098, -0.285713124), max = c(-0.350005447, -0.354481437,
-0.357993465, -0.361131103, -0.364730186, -0.368668226), x = c(-0.02125,
-0.02108, -0.02091, -0.02074, -0.02057, -0.0204), meangia = c(-0.276897401,
-0.283550597, -0.28932294, -0.294766983, -0.300655142, -0.306790675
), rate = c(NA, -4.967327, -4.946326, -4.964493, -4.977451, -4.911859
), raterror = c(NA, 3.581013, 3.796417, 4.022157, 4.226762, 4.255126
), mmsl = c(-0.325962618, -0.332445814, -0.338048157, -0.3433222,
-0.349040359, -0.355005892)), row.names = c(NA, 6L), class = "data.frame")

Here is a way.
Override the guide legend with a list of vectors of values for each of the aesthetics involved, shape and linetype. Note the different ways to specify what is to be removed.
I have also simplified the code a bit.
library(ggplot2)
library(dplyr)
colrs <- c("Fort Denison 1" = "grey15",
"Fort Denison 2" = "grey50",
"Full budget" = "black")
legnd <- list(shape = c(1, 1, NA),
linetype = c("blank", "blank", "solid"))
bind_rows(
tg1 %>% mutate(col = "Fort Denison 1"),
tg2 %>% mutate(col = "Fort Denison 2")
) %>%
ggplot(aes(x = mmslc, y = Year, colour = col)) +
geom_point(pch = 1, size = 2) +
geom_lineh(data = full, aes(x = Lutregalammslc, col = "Full budget"))+
scale_colour_manual(values = colrs,
guide = guide_legend(override.aes = legnd)) +
coord_flip() +
theme_classic(base_size = 12)

Plot multiple geom_line and geom_smooth objects in one plot

I have somewhat messy looking dataframes, like this one:
df0
# A tibble: 3 x 9
# Groups: Sequ [1]
Sequ Speaker Utterance A_intpl A_dur B_intpl B_dur C_intpl C_dur
<int> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2 ID16.A cool >wha… 31.44786152… 10.5,17,1… 32.86993284… 9.5,16,17… 58.3368399… 14,17,17…
2 2 NA (0.228) 32.75735987… 15.5,17,1… 30.83469006… 14.5,16.9… 26.0386462… 3,17,16,…
3 2 ID16.B u:m Tenne… 32.05752604… 4.5,17,16… 29.95825107… 3.5,16,17… 55.9298614… 8,17,17,…
I want to plot the *_intpl values for each speaker (A, B, or C) for each of the three Utterances in a single chart both as line charts and as trend lines.
I'm just half successful doing this:
library(tidyr)
library(ggplot2)
library(dplyr)
df0 %>%
pivot_longer(cols = contains("_"),
names_to = c("Event_by", ".value"),
names_pattern = "^(.*)_([^_]+$)") %>%
separate_rows(c(intpl, dur), sep = ",", convert = TRUE) %>%
mutate(Time = cumsum(dur)) %>%
mutate(Utterance = paste0(sub(".*(.)$", "\\1",Speaker), ": ", Utterance),
Utterance = factor(Utterance, levels = unique(Utterance))) %>%
ggplot(aes(x = Time, y = log2(intpl),
group = Event_by,
colour = Event_by)) +
geom_line()+
geom_smooth(method = 'lm', color = "red", formula = y~x)+
facet_wrap(~ Utterance, ncol = 1, scales= "free_x")
Half successful because the line plots and trend lines are side-by-side, as if in three columns, whereas they should be in rows, one below the other - how can that be achieved?
Reproducible data:
structure(list(Sequ = c(2L, 2L, 2L), Speaker = c("ID16.A", NA,
"ID16.B"), Utterance = c("cool >what part?<", "(0.228)", "u:m Tennessee="
), A_intpl = c("31.4478615210995,31.5797510648522,31.7143985369445,31.651083739602,31.5806035086034,36.8956763912703,36.2882129597292,35.2124499461012,34.1366869324732,34.1366869324732,32.1927035724058,30.2487202123383,28.3047368522709,26.3607534922035,30.5278334848495,30.5919390424853,30.8898529369568,31.578968913188,31.9011198738002,32.1543265113196,31.9708002079533,31.966536408565,31.8762658607759,31.8994741472105,31.4215913971938,32.1510578328563,31.7863350712876,32.4685052625667,31.7422271490296,32.3286054977263,31.9998974949481,32.5177992323864,32.4727499785435,32.9310888953766,32.7592010033585,33.2231711877427,33.1593949301066,33.2432973964816,33.2569729073414,33.492144800249,33.317650964723,33.4835787832119,33.2377190454279,32.9200836384356,32.9684568771567,32.6400987016883,27.5447101464944,29.3948945479171,35.3449171857603,33.5932932239592,31.8416692621581,30.0900453003569,32.7850431084597,32.7589003618266,32.8365550655013,32.386716057622,32.8420792704881,32.6909995562489,32.6269434402016,32.7370944106334,32.7529759209752,32.6528826975113,32.3663573764448,32.7326853004792,32.6930038462418,32.8975978772676,33.1752899475416,33.2034433355001,33.0667431432803,32.6322933080614,33.2503168843178,32.7573598713719",
"32.7573598713719,32.7531704791313,32.7366130631104,32.918942216354,32.8309939530596,32.3856893430525,32.5368873543441,32.5628510484821,32.5628510484821,32.5628510484821,32.5506564332008,32.7477119716583,32.3458470743288,32.0575260428013",
"32.0575260428013,32.1628824338111,32.0093334061923,32.1461460586991,31.9080762250966,31.9469105074833,31.7431187667232,31.7194255656503,31.7394296413187,31.8594986292975,31.7498243274746,31.9069142374258,32.0835520942767,31.6257067057109,31.757232379438,31.9036689124911,32.1319749301918,31.7203280774998,31.7877137245706,32.3030946636177,32.2800139298454,32.164646135728,32.3636504940227,32.5657818936495,32.3859453482697,32.4797898358193,32.5319835105237,32.92233491509,32.8240561109448,32.664496027779,33.1835064752029,33.0366413969703,33.0406288190821,33.3232964677672,33.2206260057731,33.1537134269402,33.2783471506207,33.2933281566788,33.5322350394609,33.3815736723684,33.7905544185063,33.6143820666896,33.7490659591585,33.7260102344634,34.0721931066557,34.0455026427054,34.3735788774521,34.2888420421073,34.3913721165542,34.5982135545306,34.4417202731001,34.6586347152449,31.1590521215434,31.3276405983897,28.2379253186548,31.133030931336,34.0715906921349,35.8967950760285,35.9334551147377,35.8565504335515,35.7446081905229,35.6300325834155,35.8390086948751,35.9711743270411,36.0029493274176,35.8891056768339"
), A_dur = c("10.5,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,0.5",
"15.5,17,17,16,17,17,16,17,17,16,17,17,16,12.5", "4.5,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,5.5"
), B_intpl = c("32.8699328424689,32.8154348109057,32.5454364786882,32.408257038977,32.5304564519672,32.3270203236281,31.9233218634346,32.0166346064182,31.7360745988363,31.7546527359571,31.8603220354065,31.6520061326962,31.5603191463274,31.3357561466519,31.0976090032219,31.1405090978825,31.1697180784961,31.0863999545386,31.3126984044729,30.580776446803,30.7137016246273,31.0801914571091,31.2343922096768,31.2749857511594,31.3488604642844,30.9327390960718,31.0750482778561,31.1849119826023,31.4180114886183,31.5284273181104,31.147361398529,31.1128597713973,31.5551385744611,31.7479939892741,31.5890352680344,31.5470790538009,31.5427330200078,31.3901913024084,31.5423214446953,31.4814325586741,31.4937336232021,31.3483738841556,31.2516462059018,31.2233881922543,31.2572951780583,31.0087226975291,31.1197589042273,31.053748381687,30.8202174718598,30.845143129195,30.8727194789634,30.4231467151428,30.7254093759809,30.2757746547116,30.6047530953025,29.6835591414008,28.257421076205,29.4634886416064,29.183064807185,28.6935506287734,29.3989017421637,30.8936090542518,30.6884831327852,30.805770713392,30.6938909098627,30.8317757801268,30.8509115577427,30.6836198471168,30.7979978629801,31.0260101704105,30.6248844591805,30.8346900656087",
"30.8346900656087,30.9826158466835,29.814086001996,29.7839590794955,30.7928804535206,31.1589874726521,31.0547403039501,31.2268131145794,31.155503802286,31.3036925274762,31.4782621660348,31.0928322383151,31.589958621025,29.9582510795225",
"29.9582510795225,29.9796434055214,29.9405638729798,30.2602098442174,30.5011865525849,30.6753859842987,28.9331380886365,30.7736467776919,30.8457967803438,30.843630408183,30.8767570425033,30.9178344980247,30.734598946287,30.8877440413271,30.9225051837881,30.9534076039184,31.0172861192043,30.9371712793451,30.9806052132295,31.0593603717961,31.1156928565737,30.4713263393479,26.028518302418,28.1426546887905,29.4308434671559,30.7190322455213,31.2289674937063,31.7389027418913,32.2488379900763,32.7587732382613,33.2687084864463,33.7786437346312,34.2885789828162,34.7985142310012,35.3084494791862,35.8183847273712,36.3283199755562,36.8382552237412,37.3481904719262,37.8581257201112,38.3680609682962,25.5986933949893,29.7968031963901,30.5336819967028,30.1876589408847,30.4260367500101,30.2997107671214,30.3429716412578,30.3537316791924,30.4111899964144,30.7293520851914,30.7778983966343,30.9712137067708,30.9072589183658,31.0696990205164,30.5713926084448,31.3458855877875,31.4169903025083,31.5148974986093,31.5972499257413,31.2293401943969,31.2033325602348,31.1657434266985,30.6784877073261,30.6991365599664,30.6763195188897"
), B_dur = c("9.5,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,2.5",
"14.5,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,13.4999999999854",
"3.5,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17.0000000000146,16.9999999999854,16,17,16.9999999999854,16.0000000000146,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,7.5"
), C_intpl = c("58.3368399069697,58.249224089011,59.5198368051218,58.8722012497097,58.4418996252205,58.5849059154389,59.2752163985494,52.8407480422202,51.6276603912397,48.0255346632529,44.753541512539,41.4815483618252,38.2095552111114,34.9375620603975,31.6655689096837,28.3935757589698,25.121582608256,19.4712933827274,22.0108873782783,24.5504813738291,24.8441573376901,24.6902151101703,24.4029572181118,24.9753161974674,24.8664406826514,24.8486668451201,25.1137001504163,25.1142578332509,25.4902077628339,25.4075561268027,25.6622548410237,61.2421678149908,25.1600975771354,25.6667198263373,25.442560744158,25.8736383423437,25.5859074180431,24.7860400673889,24.4337707697216,24.3214953242744,23.915753514736,23.7363185577661,23.7186569801299,23.4313514771952,23.5730151254578,62.5124513171595,23.3260531660862,23.4498217326665,23.2145314844252,57.5586745434594,63.4646233226955,23.0706406704345,23.3318690599491,62.044649715831,62.2720656330432,22.2532276715887,62.7059140614625,22.9511208849958,22.5603175709988,23.3456453893988,63.2523901625561,60.6655429980934,60.2358824325868,59.957910796633,57.3999702562457,54.8277282980263,43.0269305132552,31.2261327284841,19.425334943713,22.7319906068577,26.0386462700023",
"26.0386462700023,29.345301933147,32.6519575962917,35.9586132594364,48.3773995023798,60.7961857453232,49.4980424442242,55.9907960862667,57.2956837917999,58.1409925994177,59.025022056064,60.0098263540792,60.4028460580062,61.2629030450653,55.9298614021542",
"55.9298614021542,55.3877180252389,61.3547152702855,61.7847919095391,56.2457623439544,62.5477315546977,62.3078007189967,62.4272469013149,57.6479672147315,62.9844338801191,58.0081708266629,63.3872796098875,59.0138830718112,58.0612924481098,58.38680047729,58.687179350318,63.8724230039733,63.4126777597892,63.6865154626743,63.5670658627636,63.4496590540706,63.7595297692908,58.9069708176601,63.4547681163061,64.3198376700797,63.415319961042,64.0985879957056,64.1201809531605,63.677902665454,64.1934303628317,64.4682003346273,64.2868853545462,24.8444135816353,64.1579626357752,63.8897139146875,58.5472675827292,64.5784992977498,64.0848591719068,63.8841268679761,64.2901359712354,64.395692486112,64.5425896391638,64.8060565909917,64.3618830026368,64.7088481705444,64.5005944199885,64.5540289192148,64.7408010459365,63.378880767685,63.3415589069662,63.5362700331647,63.5924807719723,63.575801461932,63.6799360982113,64.0041021410894,64.3144923757986,63.8692943755376,63.8594574363473,64.2731841085802,63.3314657812309,64.2758880216293,64.1011768977101,64.0261661917799,64.2865302330478,63.724697791255,64.1202175712152"
), C_dur = c("14,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,14",
"3,17,16,17,17,16,17,17,16,17,17,16,17,17,8", "8,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,17,16,17,2"
)), row.names = c(NA, -3L), groups = structure(list(Sequ = 2L,
.rows = structure(list(1:3), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, -1L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))

There's a possible solution with use of grid.arrange() func from library(gridExtra) library(grid) packages.
I've wrapped your data into unique charts and combined them together into arranged chart.
df1 = df0 %>%
pivot_longer(cols = contains("_"),
names_to = c("Event_by", ".value"),
names_pattern = "^(.*)_([^_]+$)") %>%
separate_rows(c(intpl, dur), sep = ",", convert = TRUE) %>%
mutate(Time = cumsum(dur)) %>%
mutate(Utterance = paste0(sub(".*(.)$", "\\1",Speaker), ": ", Utterance),
Utterance = factor(Utterance, levels = unique(Utterance)))
Set chart objects into enviroment:
for (i in unique(df1$Event_by)){
for (j in levels(df1$Utterance)){
assign(x = paste0(i,j), value = ggplot(data = df1[df1$Event_by == i & df1$Utterance == j,], aes(x = Time, y = log2(intpl))) +
geom_line()+
geom_smooth(method = 'lm', color = "red", formula = y~x))
}
}
Create grided chart:
library(gridExtra) library(grid)
grid.arrange(
`AA: cool >what part?<`,
`AB: u:m Tennessee=` ,
`ANA: (0.228)` ,
`BA: cool >what part?<` ,
`BB: u:m Tennessee=` ,
`BNA: (0.228)` ,
`CA: cool >what part?<` ,
`CB: u:m Tennessee=` ,
`CNA: (0.228)` ,
nrow = 3)
Although i think there should be better solution for that.
You can also try to explore below articlesfor arranging plots:
http://www.sthda.com/english/articles/24-ggpubr-publication-ready-plots/81-ggplot2-easy-way-to-mix-multiple-graphs-on-the-same-page/
https://ggplot2-book.org/facet.html
Moreover, there's is no themming added to my solution

Multiple line 3D plot in R

I have 3 dataframes:
> head(ps_data)
mass value
1 1197.106 0.0003046761
2 1197.312 0.0002792939
3 1197.518 0.0002545125
4 1197.724 0.0002304614
5 1197.930 0.0002072700
6 1198.136 0.0001850678
> head(enf_data)
mass value
1 1252.358 0.0001400532
2 1252.560 0.0001380179
3 1252.761 0.0001360147
4 1252.963 0.0001336038
5 1253.165 0.0001310146
6 1253.367 0.0001278587
> head(uti_data)
mass value
1 1209.999 9.404051e-05
2 1210.204 9.176861e-05
3 1210.409 8.892953e-05
4 1210.614 8.613961e-05
5 1210.819 8.299913e-05
6 1211.024 8.038693e-05
I need to plot something close to this:
Where z axis will be the "value" column, y axis will be the "mass" column and the x axis will be each dataframe.
I tried to plot this using plotly package, but I'm not getting it right.
How can I do it?
EDIT: dput as requested.
structure(list(mass = c(1197.10568602095, 1197.31161534199, 1197.51756246145,
1197.72352737934, 1197.92951009569, 1198.1355106105), value = c(0.000304676093184434,
0.000279293920415841, 0.000254512541389108, 0.000230461422005283,
0.000207270028165387, 0.000185067825770437), group = c("PS",
"PS", "PS", "PS", "PS", "PS")), row.names = c(NA, 6L), class = "data.frame")
structure(list(mass = c(1252.3578527531, 1252.55956147119, 1252.76128739414,
1252.96303052216, 1253.16479085545, 1253.3665683942), value = c(0.000140053215421452,
0.000138017894050617, 0.00013601474884925, 0.000133603848925069,
0.000131014621271734, 0.000127858739055662), group = c("ENF",
"ENF", "ENF", "ENF", "ENF", "ENF")), row.names = c(NA, 6L), class = "data.frame")
structure(list(mass = c(1209.99938731277, 1210.20436650703, 1210.40936335465,
1210.61437785568, 1210.81941001019, 1211.02445981824), value = c(9.40405108642129e-05,
9.17686135352109e-05, 8.89295335433793e-05, 8.61396097238083e-05,
8.29991287322805e-05, 8.03869281229029e-05), group = c("UTI",
"UTI", "UTI", "UTI", "UTI", "UTI")), row.names = c(NA, 6L), class = "data.frame")
EDIT 2:
Got some progress using plotly:
ps_data["group"] <- "PS"
enf_data["group"] <- "ENF"
uti_data["group"] <- "UTI"
all_data <- rbind(ps_data,enf_data,uti_data)
all_long <- melt(all_data, id.vars=c("mass","group","value"))
fig <- plot_ly(all_long, x = ~group, y = ~mass, z = ~value, type = 'scatter3d', mode = 'lines',
opacity = 1, line = list(width = 6, color = ~group, reverscale = FALSE))
fig
But some strange lines appeared in x axis and the colors are not right.
EDIT 3:
I managed to plot something quite good.
My data looks like this:
> head(all_data)
mass value group
1 1197.106 0.0003046761 PS
2 1197.312 0.0002792939 PS
3 1197.518 0.0002545125 PS
4 1197.724 0.0002304614 PS
5 1197.930 0.0002072700 PS
6 1198.136 0.0001850678 PS
The dataframe is huge, with three groups (PS, ENF, UTI).
I can't fit all of it here, but I decided to place the head just for you to see the structure.
With this data I used this:
p3 <- plot_ly(all_data, x = ~group, y = ~mass, z = ~value, split = ~group, type = 'scatter3d', mode = 'lines',
line = list(width = 4))
Now I'm just trying to find some reliable way to save it in TIFF and change the axis titles.

Combine 4 bar-plots into one graph in R

I want to create a bar-plot using R, which will describe V gene frequency in 4 compartments in the body.
I have this table:
head(my_data)
# A tibble: 6 x 8
Tumor ...2 BM ...4 DLN ...6 Blood ...8
<chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 V hit frequency V hit frequency V hit frequency V hit frequency
2 IGHV3-1~ 0.54386205~ IGHV10-~ 0.22723742~ IGHV1-5~ 0.1132060~ IGHV5-~ 0.1417894~
3 IGHV5-1~ 0.16148068~ IGHV5-6~ 7.62620114~ IGHV5-1~ 0.1010986~ IGHV7-~ 0.1133675~
4 IGHV10-~ 3.18440869~ IGHV1-6~ 5.68199208~ IGHV1-6~ 8.1465889~ IGHV2-~ 6.4763474~
5 IGHV5-6~ 2.71468704~ IGHV3-1~ 5.24995831~ IGHV5-6~ 7.1625980~ IGHV5-~ 6.3008918~
6 IGHV6-3~ 2.71460485~ IGHV1-9~ 4.19517008~ IGHV1-7~ 4.7428361~ IGHV1-~ 5.0785188~
>
dput(my_data)
structure(list(Tumor = c("V hit", "IGHV3-1*00", "IGHV5-17*00",
"IGHV10-1*00", "IGHV5-6*00", "IGHV6-3*00", "IGHV2-9*00", "IGHV5-4*00",
"IGHV1-9*00"), ...2 = c("frequency", "0.54386205717535796", "0.161480687577157",
"3.1844086931792998E-2", "2.7146870412713998E-2", "2.7146048502561901E-2",
"2.4098405658687001E-2", "2.1746920713615302E-2", "1.6909157558532301E-2"
), BM = c("V hit", "IGHV10-3*00", "IGHV5-6*00", "IGHV1-62-3*00",
"IGHV3-1*00", "IGHV1-9*00", "IGHV10-1*00", "IGHV2-9*00", "IGHV4-2*00"
), ...4 = c("frequency", "0.22723742785161699", "7.62620114066965E-2",
"5.6819920833780603E-2", "5.2499583155365397E-2", "4.1951700840313098E-2",
"3.5214806321420301E-2", "3.2695465872415799E-2", "3.0610100659414E-2"
), DLN = c("V hit", "IGHV1-50*00", "IGHV5-17*00", "IGHV1-62-3*00",
"IGHV5-6*00", "IGHV1-7*00", "IGHV1-4*00", "IGHV6-3*00", "IGHV10-1*00"
), ...6 = c("frequency", "0.113206013467841", "0.101098647226429",
"8.1465889741680994E-2", "7.1625980782229995E-2", "4.7428361184553902E-2",
"4.4690299561054497E-2", "4.3051740808241597E-2", "3.9509373582839201E-2"
), Blood = c("V hit", "IGHV5-6*00", "IGHV7-3*00", "IGHV2-9*00",
"IGHV5-17*00", "IGHV1-67*00", "IGHV1-62-3*00", "IGHV1-7*00",
"IGHV1-9*00"), ...8 = c("frequency", "0.141789453276464", "0.113367584335014",
"6.4763474214811906E-2", "6.3008918185343196E-2", "5.0785188057386597E-2",
"5.0504071345482703E-2", "4.52113222179139E-2", "3.8183404420318E-2"
)), row.names = c(NA, -9L), class = c("tbl_df", "tbl", "data.frame"
))
(^this is just a little part of my entire data.)
Tumor,blood,BM, and DLN are my compartments, and each of them has its V genes and thier frequencies.
I want 1 bar-plot: X-axis will be V genes and for each v gene, I want 4 bars, 1 for each compartment.
Y-axis will be the frequencies.
I'm assuming I need to create df that has only one column of all v genes and multiple columns of frequencies in each of the compartments, but I don't know how to do that.
Any help will be appreciated !!
Thanks, Ligal.

Clean up data
df <- df[-1,] # remove unwanted row
compart <- names(df)[seq(1,8,2)] # compartment names
not_compart <- names(df)[seq(2,8,2)] # not compartment names
# melt data from wide to long
library('data.table')
setDT(df)[, id := 1:.N] # assign id
df <- melt(df, id.vars = 'id',
measure.vars = list(compart, not_compart ),
variable.name = "compartments",
value.name = c("genes", "frequency"))
# change names of compartments
df[, compartments := factor(compartments, levels = seq_along(compart), labels = compart)]
# change frequency values from character to numeric
df[, frequency := as.numeric(frequency)]
Data - output
head(df)
# id compartments genes frequency
# 1: 1 Tumor IGHV3-1*00 0.54386206
# 2: 2 Tumor IGHV5-17*00 0.16148069
# 3: 3 Tumor IGHV10-1*00 0.03184409
# 4: 4 Tumor IGHV5-6*00 0.02714687
# 5: 5 Tumor IGHV6-3*00 0.02714605
# 6: 6 Tumor IGHV2-9*00 0.02409841
Plot
library('ggplot2')
ggplot(data = df, mapping = aes(x = genes, y = frequency)) +
geom_bar(stat = "identity") +
coord_flip() +
facet_wrap(. ~ compartments, scales = "free_y" ) +
theme_bw()
Graph
Plot2
ggplot(data = df, mapping = aes(x = compartments, y = frequency)) +
geom_bar(stat = "identity") +
coord_flip() +
facet_wrap(. ~ genes, scales = "free_y" ) +
theme_bw()
Graph2
Plot-3
ggplot(data = df, mapping = aes(x = genes, y = frequency, color = compartments, fill = compartments, group = compartments)) +
geom_bar(stat = "identity", position = position_dodge(width = 0.9)) +
theme_bw() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Graph-3

Try this:
library(dplyr)
library(tidyr)
library(purrr)
library(ggplot2)
my_data <- structure(list(Tumor = c(
"V hit", "IGHV3-1*00", "IGHV5-17*00",
"IGHV10-1*00", "IGHV5-6*00", "IGHV6-3*00", "IGHV2-9*00", "IGHV5-4*00",
"IGHV1-9*00"
), ...2 = c(
"frequency", "0.54386205717535796", "0.161480687577157",
"3.1844086931792998E-2", "2.7146870412713998E-2", "2.7146048502561901E-2",
"2.4098405658687001E-2", "2.1746920713615302E-2", "1.6909157558532301E-2"
), BM = c(
"V hit", "IGHV10-3*00", "IGHV5-6*00", "IGHV1-62-3*00",
"IGHV3-1*00", "IGHV1-9*00", "IGHV10-1*00", "IGHV2-9*00", "IGHV4-2*00"
), ...4 = c(
"frequency", "0.22723742785161699", "7.62620114066965E-2",
"5.6819920833780603E-2", "5.2499583155365397E-2", "4.1951700840313098E-2",
"3.5214806321420301E-2", "3.2695465872415799E-2", "3.0610100659414E-2"
), DLN = c(
"V hit", "IGHV1-50*00", "IGHV5-17*00", "IGHV1-62-3*00",
"IGHV5-6*00", "IGHV1-7*00", "IGHV1-4*00", "IGHV6-3*00", "IGHV10-1*00"
), ...6 = c(
"frequency", "0.113206013467841", "0.101098647226429",
"8.1465889741680994E-2", "7.1625980782229995E-2", "4.7428361184553902E-2",
"4.4690299561054497E-2", "4.3051740808241597E-2", "3.9509373582839201E-2"
), Blood = c(
"V hit", "IGHV5-6*00", "IGHV7-3*00", "IGHV2-9*00",
"IGHV5-17*00", "IGHV1-67*00", "IGHV1-62-3*00", "IGHV1-7*00",
"IGHV1-9*00"
), ...8 = c(
"frequency", "0.141789453276464", "0.113367584335014",
"6.4763474214811906E-2", "6.3008918185343196E-2", "5.0785188057386597E-2",
"5.0504071345482703E-2", "4.52113222179139E-2", "3.8183404420318E-2"
)), row.names = c(NA, -9L), class = c("tbl_df", "tbl", "data.frame"))
# Tidy the dataset
my_data <- slice(my_data, -1)
## Separate the data columns for each compartment and put them in a list
df_tidy <- list(tumor = my_data[1:2], bm = my_data[3:4], dln = my_data[5:6], blood = my_data[7:8]) %>%
## Rename the data columns
map(~ rename(.x, v_hit = 1, freq = 2)) %>%
## Bind the four dfs together into one df
bind_rows(.id = "compartment") %>%
## Convert the frequencies to numeric values
mutate(freq = as.numeric(freq))
head(df_tidy)
#> # A tibble: 6 x 3
#> compartment v_hit freq
#> <chr> <chr> <dbl>
#> 1 tumor IGHV3-1*00 0.544
#> 2 tumor IGHV5-17*00 0.161
#> 3 tumor IGHV10-1*00 0.0318
#> 4 tumor IGHV5-6*00 0.0271
#> 5 tumor IGHV6-3*00 0.0271
#> 6 tumor IGHV2-9*00 0.0241
# Barplot
ggplot(df_tidy, aes(v_hit, freq, fill = compartment)) +
geom_col() +
coord_flip() +
facet_wrap(~compartment, scales = "free_y") +
guides(fill = FALSE)
Created on 2020-03-29 by the reprex package (v0.3.0)

How to plot multiple curves and color them as group using R ggplot

I have a data frame like this.
ID read1 read2 read3 read4 class
1 5820350 0.3791915 0.3747022 0.3729779 0.3724259 1
2 5820364 0.3758676 0.3711775 0.3695976 0.3693112 2
3 5820378 0.3885081 0.3823900 0.3804273 0.3797707 2
4 5820392 0.3779945 0.3729582 0.3714910 0.3709072 1
5 5820425 0.2954782 0.2971604 0.2973882 0.2973216 3
6 5820426 0.3376101 0.3368173 0.3360203 0.3359517 3
Each row represents one sample with four values,and the last column is the classification of this sample. I want to visualize each sample curve and set the class as the color.
I tried to reshape the data frame, but I then lost the class feature which I need.
Could you please give me some hint or show me how to do that in R?
Thanks in advance.

You are going to want to tidy your data first (shown below with tidyr::gather). Then, when you plot, you will want to set your group = ID and color = factor(class) (for discrete colors):
library(tidyr)
library(ggplot2)
df <- structure(list(ID = c(5820350L, 5820364L, 5820378L, 5820392L, 5820425L, 5820426L),
read1 = c(0.3791915, 0.3758676, 0.3885081, 0.3779945, 0.2954782, 0.3376101),
read2 = c(0.3747022, 0.3711775, 0.38239, 0.3729582, 0.2971604, 0.3368173),
read3 = c(0.3729779, 0.3695976, 0.3804273, 0.371491, 0.2973882, 0.3360203),
read4 = c(0.3724259, 0.3693112, 0.3797707, 0.3709072, 0.2973216, 0.3359517),
class = c(1L, 2L, 2L, 1L, 3L, 3L)),
.Names = c("ID", "read1", "read2", "read3", "read4", "class"),
class = "data.frame", row.names = c("1", "2", "3", "4", "5", "6"))
df <- gather(df, reading, value, -c(ID, class))
ggplot(df, aes(x = reading, y = value, color = factor(class))) +
geom_line(aes(group = ID))

Here's a function that may do what you want:
PlotMultiCurve = function(x, classes, cols = NULL, colSet = "Set1", ...) {
if(!is.factor(classes)) classes = as.factor(classes)
nClasses = length(levels(classes))
if(is.null(cols)) cols = brewer.pal(nClasses, colSet)
plot(1:ncol(x), x[1,], col = cols[classes[1]], type = "l",
ylim = range(x), xaxt = "n", ...)
axis(1, 1:ncol(x), 1:ncol(x))
for(i in 2:nrow(x)) {
par(new = T)
plot(1:ncol(x), x[i,], col = cols[classes[i]], type = "l",
ylim = range(x), axes = F, xlab = "", ylab = "")
}
}
It uses chooses colors automatically from the RColorBrewer package unless you provide the colors. I copied your data directly into a text file and then ran the following:
# Prepare data
require(RColorBrewer)
myData = read.table("Data.2016-05-03.txt")
x = myData[,2:5]
classes = as.factor(myData$class)
# Plot into PNG file[![enter image description here][1]][1]
png("Plot.2016-05-03.png", width = 1000, height = 1000, res = 300)
par(cex = 0.8)
PlotMultiCurve(x = x, classes = classes, xlab = "Read", ylab = "Response")
dev.off()

Resources