ggrepel label fill color questions - r

I'm working with ggplot2 for the first time, and I'm having trouble making the colors of the labels I created with ggrepel change dynamically. Currently, my code looks like this:
ggplot(tstat) +
geom_point(aes(Mu, Sigma),size = 5, color = 'black') +
geom_label_repel(aes(Mu, Sigma, label = VarNames, fill = factor(Hemisphere)), fontface = 'bold', color = 'white',
box.padding = unit(0.25, 'lines'),point.padding = unit(0.5, 'lines')) +
geom_rangeframe() +
theme_tufte() +
xlab(expression(paste(mu, "*"))) +
ylab(expression(sigma)) +
theme(axis.title.x = element_text(vjust=-0.5), axis.title.y = element_text(vjust=1.5)) +
ggtitle("Model Sensitivity by Hemisphere")
In general, this works pretty well, except I strongly dislike the toothpaste green color it gives me for one of the two factors plotted. I want to dictate the specific colors of that fill = factor(Hemisphere)) line, but I don't know how.
I have already tried using the scale_colours_manual function, but when I include it within the geom_label_repel(.....) paratheses in line 3, the program complains that "ggplot2 doesn't know how to deal with data of class ScaleDiscrete/Scale/ggproto", and when I place the scale_colours_manual line outside of line 3, it has no effect at all, as in this example, which produced an identical plot to the one above:
ggplot(tstat) +
geom_point(aes(Mu, Sigma),size = 5, color = 'black') +
scale_colour_manual(values = c('blue', 'red')) +
geom_label_repel(aes(Mu, Sigma, label = VarNames, fill = factor(Hemisphere)), fontface = 'bold', color = 'white',
box.padding = unit(0.25, 'lines'),point.padding = unit(0.5, 'lines')) +
geom_rangeframe() +
theme_tufte() +
xlab(expression(paste(mu, "*"))) +
ylab(expression(sigma)) +
theme(axis.title.x = element_text(vjust=-0.5), axis.title.y = element_text(vjust=1.5)) +
ggtitle("Model Sensitivity by Hemisphere")
I know there has to be a way to do this, but I'm at a loss. Thanks for any help you've got!
EDIT: At request, I've attached a dput() of tstat. Not a big data frame.
structure(list(VarNames = structure(c(4L, 1L, 3L, 2L, 5L, 6L,
4L, 1L, 3L, 2L, 5L, 6L), .Label = c("Dry Deposition", "MEGAN Acetone",
"MEGAN Terpenes", "Monoterpene Yield", "Ocean", "Photolysis"), class = "factor"),
Mu = c(2703.09, 8066.01, 6566.6, 19741.7, 5809.6, 14231.8, 1493.56, 3067.54, 3631.32, 9951.06, 8748.95, 7967.93),
Sigma = c(3478.28, 8883.23, 7276.49, 18454.4, 6218.8, 14989.7, 1925.14, 3410.27, 4017.64, 9289.57, 9354.64, 8403.1),
Hemisphere = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L),
.Label = c("Northern", "Southern"), class = "factor")),
.Names = c("VarNames", "Mu", "Sigma", "Hemisphere"),
class = "data.frame", row.names = c(NA, -12L))


You can use scale_fill_manual:
tstat <- structure(list(VarNames = structure(c(4L, 1L, 3L, 2L, 5L, 6L,
4L, 1L, 3L, 2L, 5L, 6L), .Label = c("Dry Deposition", "MEGAN Acetone",
"MEGAN Terpenes", "Monoterpene Yield", "Ocean", "Photolysis"), class = "factor"),
Mu = c(2703.09, 8066.01, 6566.6, 19741.7, 5809.6, 14231.8, 1493.56, 3067.54, 3631.32, 9951.06, 8748.95, 7967.93),
Sigma = c(3478.28, 8883.23, 7276.49, 18454.4, 6218.8, 14989.7, 1925.14, 3410.27, 4017.64, 9289.57, 9354.64, 8403.1),
Hemisphere = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L),
.Label = c("Northern", "Southern"), class = "factor")),
.Names = c("VarNames", "Mu", "Sigma", "Hemisphere"),
class = "data.frame", row.names = c(NA, -12L))
library(ggplot2)
library(ggrepel)
library(ggthemes)
ggplot(tstat) +
geom_point(aes(Mu, Sigma),size = 5, color = 'black') +
geom_label_repel(aes(Mu, Sigma, label = VarNames, fill = factor(Hemisphere)), fontface = 'bold', color = 'white',
box.padding = unit(0.25, 'lines'),point.padding = unit(0.5, 'lines')) +
geom_rangeframe() +
theme_tufte() +
xlab(expression(paste(mu, "*"))) +
ylab(expression(sigma)) +
theme(axis.title.x = element_text(vjust=-0.5), axis.title.y = element_text(vjust=1.5)) +
ggtitle("Model Sensitivity by Hemisphere") +
scale_fill_manual(values = setNames(c("lightblue", "darkgreen"), levels(tstat$Hemisphere)))

Related

Creating raincloud plot from a data frame in R

I wanted a visualization something like this
I ended up getting like this one
I'm kind of close what I want to get except Im not able to separate them
Here is my data frame
dput(dat_red)
structure(list(FAB = structure(c(5L, 1L, 5L, 3L, 2L, 4L, 6L,
2L, 1L, 6L, 5L, 1L, 5L, 1L, 5L, 6L, 3L, 5L, 2L, 5L, 3L, 3L, 3L,
1L, 3L, 1L, 1L, 1L), .Label = c("M0", "M1", "M2", "M3", "M4",
"M5"), class = "factor"), Risk_Cyto = structure(c(2L, 3L, 2L,
2L, 3L, 1L, 2L, 2L, 3L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 3L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L), .Label = c("Good", "Intermediate",
"Poor"), class = "factor"), `TCGA-AB-2856` = c(0, 0.203446022561853,
0.057566971226641, 0.050525640210207, 0.050663468813024, 0.108022967842345,
0.03563961790061, 0.091955619434079, 0.09562601922977, 0.072990036124458,
0.05292549370956, 0.134908910498566, 0.056146007781438, 0.166755814327401,
0.072370918290216, 0.092982169160965, 0.053571132330207, 0.026946730545354,
0.096491482450314, 0.086393933157139, 0.086056971395349, 0.059872483122941,
0.05562972070039, 0.080629871622231, 0.06458076058265, 0.109295018454197,
0.15019108327262, 0.122208033564744), `TCGA-AB-2849` = c(0.203446022561853,
0, 0.138756102002674, 0.109150212934145, 0.130381628657973, 0.186028570196918,
0.201142265508601, 0.117008908236162, 0.07523492135779, 0.237542759238287,
0.154026516322799, 0.093169870680731, 0.174873827256869, 0.077917778705184,
0.217466101351585, 0.247196178178148, 0.139168631446623, 0.130879779506245,
0.094044964277672, 0.102330796604311, 0.115883670128914, 0.106007290303468,
0.124207778875499, 0.100051046626221, 0.096898638044544, 0.081075416500332,
0.066801569316824, 0.095571899845876), `TCGA-AB-2971` = c(0.057566971226641,
0.138756102002674, 0, 0.057153443556063, 0.049118618822663, 0.108803803345704,
0.038593571058361, 0.05623480754803, 0.061897696825206, 0.056921365921972,
0.027147582644049, 0.100579305160467, 0.031712766628694, 0.099623521686644,
0.043315406299788, 0.079156224894216, 0.070713735063067, 0.042797402350358,
0.064121331342957, 0.076245258448711, 0.057969352005916, 0.056411884330189,
0.029950269541688, 0.052538503817376, 0.053263317374002, 0.073813902166228,
0.081932722355952, 0.095255347468669), `TCGA-AB-2930` = c(0.050525640210207,
0.109150212934145, 0.057153443556063, 0, 0.040710142137316, 0.087506794353747,
0.076018856821365, 0.054334641613629, 0.043854827190482, 0.121490922447548,
0.060145981627256, 0.070829823037578, 0.0708179998993, 0.083561655580485,
0.106626803408534, 0.149000581782327, 0.049861493156012, 0.018112612744773,
0.05246829209315, 0.041582348253964, 0.053306367816997, 0.035373116643303,
0.042875256342202, 0.03406333799917, 0.036306618864362, 0.045647830531497,
0.084727864328183, 0.079147350281325), `TCGA-AB-2891` = c(0.050663468813024,
0.130381628657973, 0.049118618822663, 0.040710142137316, 0, 0.117167203965628,
0.057145523476846, 0.07089819966556, 0.058848771210843, 0.090222074046894,
0.052188574602838, 0.091623506635555, 0.053000329480576, 0.094592248885481,
0.082033497053918, 0.111240839210373, 0.065982245111563, 0.038618210190806,
0.063406266346048, 0.062231987650712, 0.067503749234478, 0.039970960455281,
0.042758552599394, 0.049740193805893, 0.04884538212911, 0.07959023948363,
0.090749468265183, 0.075792324166325)), class = "data.frame", row.names = c(NA,
-28L))
My code
dat_red = read.csv("JSD_test_map_.txt",sep = "\t",check.names = FALSE)
df_melt = melt(JSD_MAP, id.vars=c("FAB","Risk_Cyto")
)
To plot the above I used this tutorial
source("R_rainclouds.R")
df_melt %>% ggplot(aes(x=Risk_Cyto,y=value, fill = FAB)) +
geom_flat_violin(position = position_nudge(x = .2, y = 0),adjust =2, alpha = 0.5) +
geom_point(position = position_jitter(width = .15), size = .8) +
geom_boxplot(aes(x = Risk_Cyto, y = value, fill = FAB),outlier.shape = NA, alpha = .5, width = .1, colour = "black")+
#theme_jen() +
labs(title = "Raincloud plot of body mass by species", x = 'Risk_Cyto', y = 'JSD') +
easy_remove_legend()
So I have the following group in my metadata or patient info in this subset
> unique(dat_red$FAB)
[1] M4 M0 M2 M1 M3 M5
Levels: M0 M1 M2 M3 M4 M5
> unique(dat_red$Risk_Cyto)
[1] Intermediate Poor Good
Levels: Good Intermediate Poor
My objective is to show The Risk_Cyto as my main group similar to the first figure where They have shown ColonT HeartLV Liver Muscle etc and subsequently I have different FAB subtypes which i want to show similar to Young and Old
Right now everything is kind of stacked or rather messed up in single plot
Any help or suggestion is really appreciated

Put FAB on the x axis and facet by Risk_Cyto
df_melt %>%
ggplot(aes(FAB, value, fill = FAB)) +
geom_flat_violin(position = position_nudge(x = .2, y = 0),adjust =2,
alpha = 0.5) +
geom_point(position = position_jitter(width = .15), size = .8) +
geom_boxplot(outlier.shape = NA,
alpha = .5, width = .1, colour = "black")+
labs(title = "Raincloud plot of body mass by species",
x = 'Risk_Cyto', y = 'JSD') +
facet_grid(.~Risk_Cyto, scales = "free_x", space = "free_x") +
theme_bw(base_size = 16) +
theme(legend.position = "none",
strip.background = element_blank(),
strip.text = element_text(face = 2, size = 22))

Removing "False"-condition scales::dollar labels on ifelse within geom_label

trying to establish individual bar data labels ONLY if the value is negative. I was able to do it fine for a variable that comprised simple integers, but for a variable that needs to be formatted as dollar with the thousands separator, I can't seem to get rid of the "NA" label.
DolSumPlot <- ggplot(data = DolSums, aes(x = Group.1, fill = Group.2)) +
geom_bar(aes(weight = x), position = position_stack(reverse = TRUE)) +
coord_flip() +
labs(title = "Dollars Billed by Technician and Shop, Between 02/01/2018 and 05/31/2018",
y = "Dollars Billed", x = "Technician", fill = "Shop") +
scale_y_continuous(limits= c(NA,NA),
labels = scales::dollar,
breaks = seq(0, 50000 + 10000, 5000*2),
minor_breaks = seq(0,50000 + 10000, by = 5000)) +
scale_fill_brewer(palette = "Set1") +
geom_label(aes(label=scales::dollar(ifelse(DolSums$x < 0, DolSums$x,NA)),
y = DolSums$x),
show.legend = FALSE, size = 2.6, colour = "white", fontface = "bold")
Data:
DolSums = structure(list(Group.1 = c((names)), Group.2 = structure(c(4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
5L, 5L, 5L, 5L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Radio",
"Video", "Engineering", "800Mhz", "PSSRP", "Other"), class = "factor"),
x = c(4646, 16008.5, 48793.1, 4040, 14468.25, 13332, 1565.5,
6060, 6549.85, 2929, 4444, 3257.25, 5904, 2029.5, 3321, 6767,
8105.25, 8105.25, 8130.5, 3131, 5075.25, 3383.5, 4418.75,
23381.5, 1363.5, -2323, 29133.45, 2550.25, 505, 26042.85,
35203.55, 35940.85, 1641.25, 45066.2, 37541.7, 606, 45439.9
)), .Names = c("Group.1", "Group.2", "x"), row.names = c(NA,
-37L), class = "data.frame")

You can do this by using the data argument in geom_label and subsetting only rows with negative x. Also note that since you already have DolSums as input, there is no need to write DolSums$x. Instead, use column name to refer to a specific column directly:
library(ggplot2)
ggplot(data = DolSums, aes(x = Group.1, fill = Group.2)) +
geom_bar(aes(weight = x), position = position_stack(reverse = TRUE)) +
coord_flip() +
labs(title = "Dollars Billed by Technician and Shop, Between 02/01/2018 and 05/31/2018",
y = "Dollars Billed", x = "Technician", fill = "Shop") +
scale_y_continuous(limits= c(NA,NA),
labels = scales::dollar,
breaks = seq(0, 50000 + 10000, 5000*2),
minor_breaks = seq(0,50000 + 10000, by = 5000)) +
scale_fill_brewer(palette = "Set1") +
geom_label(data = DolSums[DolSums$x < 0,],
aes(label=scales::dollar(x),
y = x),
show.legend = FALSE, size = 2.6, colour = "white", fontface = "bold")

ggplot: how to add multiple legends for plot and vertical lines?

I've created a plot which shows the means of two groups and associated 95% confidence band, as below. For the plot, I've already used different line types, fillings, colors.
The data plot_band is as follows.
dput(plot_band)
structure(list(mean = c(0.0909296772008702, 0.0949102886382386,
0.0989192140983566, 0.102428753920507, 0.106190021551613, 0.109834234007574,
0.11282406874623, 0.116443987192088, 0.119646042014149, 0.122877131667032,
0.125734341129646, 0.129194412319665, 0.131921946416482, 0.13467000293138,
0.137801823091921, 0.140320771073742, 0.143300871011905, 0.145703574224808,
0.148502607395268, 0.151216269559201, 0.153957673466713, 0.15642722394871,
0.159399752204122, 0.16158535629103, 0.163992551285173, 0.166446319141126,
0.168796463238069, 0.17130024918415, 0.17319290052143, 0.175970079857704,
0.178037138778032, 0.180359643729028, 0.182563083353043, 0.184882067722455,
0.186933337196788, 0.18928611634363, 0.19095095692481, 0.193552969255731,
0.195137836881874, 0.197581990963152, 0.199824696342001, 0.201576167030431,
0.203292777876833, 0.205785273925517, 0.207611128924057, 0.209067294675698,
0.211624327477106, 0.213018027996152, 0.215073900329166, 0.21654896049152,
0.218432328738047, 0.220299232072702, 0.221520169903876, 0.224082916931098,
0.225373663731495, 0.227623092060467, 0.228971037740905, 0.230665903341562,
0.232255049713341, 0.233816039663021, 0.236156033603955, 0.237722706454038,
0.239326639984125, 0.241061288510212, 0.323782287073584, 0.325539303794681,
0.326575563604555, 0.327932235745535, 0.329326904419804, 0.330270965006864,
0.331794972975829, 0.332736401387824, 0.333736983920265, 0.334858878358806,
0.335995344145518, 0.336884010919713, 0.337760950823761, 0.338470035342276,
0.339694375762279, 0.340590586642847, 0.340934410282471, 0.342186505998774,
0.342699699846757, 0.343822718137376, 0.344352069575663, 0.345191547743302,
0.345986783878912, 0.346908459064914, 0.347636673707646, 0.3483601957891,
0.349017016236978, 0.349393026672962, 0.350215046428817, 0.350578051082168,
0.351357872622786, 0.351833990930714, 0.352451422717008, 0.352852417773313,
0.353786047124291, 0.354360144310735, 0.354804607588953, 0.355216156665893,
0.3556114518015, 0.356570758245453, 0.357097049535425, 0.357671243406622,
0.35787930232607, 0.358500009058086, 0.359107586207553, 0.359418346394681,
0.359923090516015, 0.360327770652831, 0.360646653761867, 0.361526704703965,
0.361860340596181, 0.362284616802613, 0.362408547406209, 0.363068975461424,
0.363173638916247, 0.363746165222553, 0.364318465554143, 0.364550369183249,
0.365263491228022, 0.365588246738469, 0.366124420845147, 0.366327320718437,
0.366730809501062, 0.367298014408034), p2.5 = c(0.00920236578162877,
0.0111305911426958, 0.0131257550019632, 0.015586474005665, 0.017588259827762,
0.0195835240844649, 0.021653464115484, 0.0245221378289171, 0.0263028370478539,
0.0283125178459841, 0.030809139661692, 0.034224299031932, 0.0351514351131448,
0.0374690177003245, 0.0401208217539481, 0.0416432632702995, 0.0436268495854353,
0.0455924496480308, 0.0481710615607138, 0.0498487868097217, 0.052013860735697,
0.0541864115090449, 0.0559355297931858, 0.0582185384506931, 0.0595049507852038,
0.0617291057747846, 0.0624904066599628, 0.064090526611587, 0.0665855608482458,
0.0681610015253132, 0.0689510143842853, 0.0714235246023074, 0.0730718365551066,
0.0733828347805513, 0.0749772653575311, 0.0775677990166739, 0.0782434582066251,
0.0809696065399504, 0.0800620502625316, 0.0822097262074474, 0.0837314882447324,
0.0836800886932387, 0.0843305338836378, 0.0862036703259026, 0.0874082656018874,
0.0881312854081838, 0.0887921830279765, 0.0892805555426737, 0.0901061351380764,
0.0914750995958728, 0.0913838119125662, 0.0926827936869315, 0.0929511644196126,
0.0940218350370357, 0.0944327299872979, 0.0953545299910439, 0.0948298565703383,
0.0957001873318579, 0.0961251564147676, 0.0971098251546806, 0.0974911491380601,
0.0986598120212823, 0.0982370236835561, 0.0987719638365328, 0.114148199394403,
0.125138552629865, 0.133069438084806, 0.140931059768343, 0.147647282172844,
0.155831735418124, 0.163154010787227, 0.16809087346053, 0.173413948644787,
0.178336300631342, 0.183561163161725, 0.189552221591194, 0.192350001446747,
0.19547327255232, 0.19824967633061, 0.202611107184988, 0.205071997319457,
0.206232495037667, 0.208471493073236, 0.209717390943683, 0.211692880593303,
0.213829033311537, 0.215383413348152, 0.216370831366554, 0.216980537940184,
0.217670415960084, 0.218147500129008, 0.219104770868165, 0.220215949003459,
0.219501167154474, 0.219635297722562, 0.220565169003312, 0.218821371303922,
0.218910618214851, 0.219518190869959, 0.219204079206471, 0.219448334243776,
0.219174641398391, 0.217619259716122, 0.217993716481521, 0.218343413130982,
0.217141573568049, 0.216438618727695, 0.215672180354215, 0.214841486865522,
0.214092486614703, 0.216084004877199, 0.213891621307228, 0.213397326450924,
0.212530621813324, 0.212650230928244, 0.211323326285971, 0.211512467761759,
0.209879967307571, 0.208388878793908, 0.209257043929222, 0.207665115418059,
0.207413292377895, 0.204980142991601, 0.206053394727878, 0.205039712521127,
0.203155679138143, 0.202289445844638, 0.201779149557556), p97.5 = c(0.240681337890249,
0.239988615023241, 0.239222274397932, 0.23882694927308, 0.239567463457127,
0.240035884370459, 0.239971640602537, 0.242348644629734, 0.244241554912481,
0.246794068956881, 0.248869825514075, 0.252843804762058, 0.254595507587193,
0.257498240756364, 0.26074636531938, 0.263991307688752, 0.268222101449506,
0.270245299020079, 0.278955701793892, 0.280366963871541, 0.286253886155709,
0.290942761721134, 0.29709853936211, 0.300641051539586, 0.307350564223005,
0.314475951046524, 0.31757563389217, 0.324250050938626, 0.326645521042049,
0.334746718583917, 0.341297900171566, 0.347056902406046, 0.352412986039391,
0.356409285744598, 0.364329251893085, 0.36882469705109, 0.373595444661095,
0.379308956442793, 0.388012909521406, 0.393418480355642, 0.399407258087214,
0.403270925317011, 0.407517084163824, 0.413742327029277, 0.42089783652825,
0.422996679448412, 0.430738094720356, 0.433915405828653, 0.438263395419797,
0.442376801773873, 0.450664409546504, 0.453854917168461, 0.455755257192578,
0.463879371708031, 0.470262095557133, 0.478816677993115, 0.478998770025097,
0.485204929246363, 0.490588733478761, 0.49747652543363, 0.498792119487052,
0.508008619470507, 0.51314092048762, 0.518568532547669, 0.579810955268174,
0.563256045407579, 0.55093710586083, 0.541241619905278, 0.532667775608687,
0.523824194956849, 0.518816497858615, 0.512618467188886, 0.506452368044292,
0.501653171003674, 0.499276681561068, 0.496002704329641, 0.494256887981196,
0.49200837587611, 0.490570113245846, 0.491077058931435, 0.487352049845066,
0.487927727831147, 0.487928022062059, 0.488900063808496, 0.488866145012628,
0.489808465409391, 0.491100206396406, 0.492044173457154, 0.494346147046575,
0.494980820850837, 0.49616843086841, 0.497216550345458, 0.499201695431901,
0.501160614633382, 0.502598288902507, 0.504203085629905, 0.50530488873578,
0.508449115699177, 0.508914783054669, 0.51306711977087, 0.51479783743171,
0.51648055644086, 0.518549503653961, 0.522859455223989, 0.522598786005884,
0.52736459871623, 0.527054294078792, 0.532359397607223, 0.532643025946804,
0.533817320437782, 0.535862852499484, 0.539613602346564, 0.54138065631686,
0.544340213112881, 0.545596882887723, 0.549029532028693, 0.546769636775625,
0.551728290583129, 0.552996735997194, 0.555676593069663, 0.559580922687426,
0.561700216317917, 0.562726465369815, 0.563527127546323, 0.567715046522725,
0.568850181180136, 0.56965258128659, 0.571847219713553), outcome = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 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, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("DLT",
"CB"), class = "factor"), exp_X_post = c(721.595263503532, 794.40305777437,
865.319646465533, 933.669956578678, 999.728550839186, 1062.12810757171,
1121.92986212885, 1186.37187215809, 1246.1267376175, 1305.33376392859,
1359.36602305224, 1421.23758898206, 1472.44041133326, 1520.62395309786,
1584.09764621781, 1634.01654454251, 1685.34860459111, 1735.26374323406,
1785.87871337346, 1840.42999799797, 1888.32905203148, 1937.38674685726,
1990.74583676908, 2041.61942276328, 2083.76909363497, 2134.07414000003,
2177.97560514382, 2227.25787768033, 2269.76501622686, 2319.50659548171,
2360.78992430352, 2404.37623851091, 2449.36656617313, 2500.80748523146,
2540.71467060956, 2588.5685157055, 2630.93535458068, 2675.04099554242,
2709.53185769419, 2763.12669881888, 2807.24737149465, 2849.03542063784,
2887.16961904492, 2927.78459960731, 2973.91123171086, 3006.0197134382,
3056.06581532434, 3089.41001229951, 3132.29020081068, 3177.35838641843,
3212.66669292569, 3256.19625640177, 3284.73766167032, 3330.28770837953,
3368.28973519186, 3409.05190043795, 3449.93435443996, 3485.59367731521,
3524.70884576068, 3557.60265444533, 3615.06476720162, 3648.55074883409,
3688.13510762386, 3727.38208940522, 721.595263503532, 794.40305777437,
865.319646465533, 933.669956578678, 999.728550839186, 1062.12810757171,
1121.92986212885, 1186.37187215809, 1246.1267376175, 1305.33376392859,
1359.36602305224, 1421.23758898206, 1472.44041133326, 1520.62395309786,
1584.09764621781, 1634.01654454251, 1685.34860459111, 1735.26374323406,
1785.87871337346, 1840.42999799797, 1888.32905203148, 1937.38674685726,
1990.74583676908, 2041.61942276328, 2083.76909363497, 2134.07414000003,
2177.97560514382, 2227.25787768033, 2269.76501622686, 2319.50659548171,
2360.78992430352, 2404.37623851091, 2449.36656617313, 2500.80748523146,
2540.71467060956, 2588.5685157055, 2630.93535458068, 2675.04099554242,
2709.53185769419, 2763.12669881888, 2807.24737149465, 2849.03542063784,
2887.16961904492, 2927.78459960731, 2973.91123171086, 3006.0197134382,
3056.06581532434, 3089.41001229951, 3132.29020081068, 3177.35838641843,
3212.66669292569, 3256.19625640177, 3284.73766167032, 3330.28770837953,
3368.28973519186, 3409.05190043795, 3449.93435443996, 3485.59367731521,
3524.70884576068, 3557.60265444533, 3615.06476720162, 3648.55074883409,
3688.13510762386, 3727.38208940522)), .Names = c("mean", "p2.5",
"p97.5", "outcome", "exp_X_post"), row.names = c("pi_A[1]", "pi_A[2]",
"pi_A[3]", "pi_A[4]", "pi_A[5]", "pi_A[6]", "pi_A[7]", "pi_A[8]",
"pi_A[9]", "pi_A[10]", "pi_A[11]", "pi_A[12]", "pi_A[13]", "pi_A[14]",
"pi_A[15]", "pi_A[16]", "pi_A[17]", "pi_A[18]", "pi_A[19]", "pi_A[20]",
"pi_A[21]", "pi_A[22]", "pi_A[23]", "pi_A[24]", "pi_A[25]", "pi_A[26]",
"pi_A[27]", "pi_A[28]", "pi_A[29]", "pi_A[30]", "pi_A[31]", "pi_A[32]",
"pi_A[33]", "pi_A[34]", "pi_A[35]", "pi_A[36]", "pi_A[37]", "pi_A[38]",
"pi_A[39]", "pi_A[40]", "pi_A[41]", "pi_A[42]", "pi_A[43]", "pi_A[44]",
"pi_A[45]", "pi_A[46]", "pi_A[47]", "pi_A[48]", "pi_A[49]", "pi_A[50]",
"pi_A[51]", "pi_A[52]", "pi_A[53]", "pi_A[54]", "pi_A[55]", "pi_A[56]",
"pi_A[57]", "pi_A[58]", "pi_A[59]", "pi_A[60]", "pi_A[61]", "pi_A[62]",
"pi_A[63]", "pi_A[64]", "qi_A[1]", "qi_A[2]", "qi_A[3]", "qi_A[4]",
"qi_A[5]", "qi_A[6]", "qi_A[7]", "qi_A[8]", "qi_A[9]", "qi_A[10]",
"qi_A[11]", "qi_A[12]", "qi_A[13]", "qi_A[14]", "qi_A[15]", "qi_A[16]",
"qi_A[17]", "qi_A[18]", "qi_A[19]", "qi_A[20]", "qi_A[21]", "qi_A[22]",
"qi_A[23]", "qi_A[24]", "qi_A[25]", "qi_A[26]", "qi_A[27]", "qi_A[28]",
"qi_A[29]", "qi_A[30]", "qi_A[31]", "qi_A[32]", "qi_A[33]", "qi_A[34]",
"qi_A[35]", "qi_A[36]", "qi_A[37]", "qi_A[38]", "qi_A[39]", "qi_A[40]",
"qi_A[41]", "qi_A[42]", "qi_A[43]", "qi_A[44]", "qi_A[45]", "qi_A[46]",
"qi_A[47]", "qi_A[48]", "qi_A[49]", "qi_A[50]", "qi_A[51]", "qi_A[52]",
"qi_A[53]", "qi_A[54]", "qi_A[55]", "qi_A[56]", "qi_A[57]", "qi_A[58]",
"qi_A[59]", "qi_A[60]", "qi_A[61]", "qi_A[62]", "qi_A[63]", "qi_A[64]"
), class = "data.frame")
Now I want to add some vertical dashed lines. I wish to use different color for each vertical line and have legend for those lines as well. The information for those vertical lines are in another data frame observed_mean:
dput(observed_mean)
structure(list(TRT = structure(1:9, .Label = c("A", "B", "C",
"D", "E", "F", "G", "H", "I"), class = "factor"), gmcmin = c(967.117632548,
1306.76729845833, 2394.519441584, 2404.73065902857, 3047.48745766364,
2550.12866139, 1863.6505272925, 3569.57489109, 3660.40695204)), .Names = c("TRT",
"gmcmin"), row.names = c(NA, -9L), class = "data.frame")
Here is the code to generate the plot:
range <- range(plot_band$exp_X_post)
range <- c(floor(range[1]), ceiling(range[2]))
step <- floor((range[2] - range[1]) / 10)
ggplot(plot_band, aes(x = exp_X_post, y = mean,
color = outcome, linetype = outcome)) +
geom_ribbon(aes(ymin = p2.5, ymax = p97.5, linetype = NA,
fill = outcome),
alpha = 0.4) +
geom_line(size = 1.5) +
xlab("Exposure") +
ylab("Proability of CB/DLT") +
scale_x_continuous(limits = range,
breaks = seq(range[1], range[2], by = step)
) +
geom_vline(xintercept = observed_mean$gmcmin,
linetype = 'longdash') +
theme_bw() +
theme(legend.position = 'top',
plot.margin = unit(c(1, 1, 3, 1), "lines"),
legend.title = element_text(size = 15),
axis.title.y = element_text(margin = margin(0, 15, 0, 0))) +
scale_color_discrete(name = "Probability (95% CI)") +
scale_fill_discrete(name = "Probability (95% CI)") +
scale_linetype_discrete(name = "Probability (95% CI)")
Note: the last three lines are used to change the legend title from variable name outcome to "Probability (95% CI)". NOT sure whether that's the right way though.
Questions:
I wish to put the current legend to the right, then below that I'd like to put the legend for vertical lines. Could anyone give me some clues how to do that?
As shown in the plot, there are two identical (not same color though) legends on top. The one below comes out if I change the order of the factor outcome with following code. I am not sure why that happens. How could I get rid of that?
plot_band$outcome <- factor(plot_band$outcome, levels = c("DLT", "CB"))
Thanks a lot for any comments/suggestions!!

The extra legend box is showing up because of the linetype = NA in the aes() of geom_ribbon moving the linetype out of the mapping will take care of that.
For the line labeling, you can perhaps just put the labels on the plot using geom_text
Here is a full plot that does something like that (now with ggrepel to place the labels more sensibly -- can't believe I didn't start there)
# install.packages("devtools")
# devtools::install_github("slowkow/ggrepel")
library(ggrepel)
ggplot(plot_band, aes(x = exp_X_post, y = mean,
color = outcome, linetype = outcome)) +
geom_ribbon(aes(ymin = p2.5, ymax = p97.5,
fill = outcome),
alpha = 0.4
, linetype = "blank") +
geom_line(size = 1.5) +
xlab("Exposure") +
ylab("Proability of CB/DLT") +
scale_x_continuous(limits = range,
breaks = seq(range[1], range[2], by = step)
) +
geom_vline(xintercept = observed_mean$gmcmin
, linetype = 'longdash') +
geom_text_repel(
mapping = aes(
x = gmcmin
, y = 0
, label = TRT
, color = NA
, linetype = NA)
, data = observed_mean
, show.legend = FALSE) +
theme_bw() +
theme(legend.position = 'top',
plot.margin = unit(c(1, 1, 3, 1), "lines"),
legend.title = element_text(size = 15),
axis.title.y = element_text(margin = margin(0, 15, 0, 0))) +
scale_color_discrete(name = "Probability (95% CI)") +
scale_fill_discrete(name = "Probability (95% CI)") +
scale_linetype_discrete(name = "Probability (95% CI)")
(Note: the mean labels overlap, so you may need to more careful position those, e.g., by adding another column to observed_mean giving the position where you want them plotted).
If you need the labels to be in a legend instead, you can use this code:
ggplot(plot_band, aes(x = exp_X_post, y = mean,
color = outcome)) +
geom_ribbon(aes(ymin = p2.5, ymax = p97.5,
fill = outcome),
alpha = 0.4
, linetype = "blank") +
geom_line(#aes(linetype = outcome)
#,
size = 1.5
# , show.legend = FALSE
) +
xlab("Exposure") +
ylab("Proability of CB/DLT") +
scale_x_continuous(breaks = pretty(range)) +
geom_vline(
mapping = aes(xintercept = gmcmin
, linetype = TRT)
, data = observed_mean) +
theme_bw() +
theme(legend.position = 'right',
plot.margin = unit(c(1, 1, 3, 1), "lines"),
legend.title = element_text(size = 15),
axis.title.y = element_text(margin = margin(0, 15, 0, 0))) +
scale_color_discrete(name = "Probability (95% CI)") +
scale_fill_discrete(name = "Probability (95% CI)") +
scale_linetype_discrete(name = "Treatment")
Note, that I removed the linetype from the main lines, as it was causing some weirdness with the vertical line. You can add it back by uncommenting the parts in geom_line() but note that it then shows up in the list with the treatments. There is probably a way to fix that if you absolutely need it, but my quick tries aren't working. I will note, however, that the linetypes are a bit hard to pick out.
Example plot with both the legend and the labels

How to fix the following output plot by R? [duplicate]

I have the following plot:
library(reshape)
library(ggplot2)
library(gridExtra)
require(ggplot2)
data2<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(15L, 11L, 29L, 42L, 0L, 5L, 21L,
22L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
p <- ggplot(data2, aes(x =factor(IR), y = value, fill = Legend, width=.15))
data3<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
q<- ggplot(data3, aes(x =factor(IR), y = value, fill = Legend, width=.15))
##the plot##
q + geom_bar(position='dodge', colour='black') + ylab('Frequency') + xlab('IR')+scale_fill_grey() +theme(axis.text.x=element_text(colour="black"), axis.text.y=element_text(colour="Black"))+ opts(title='', panel.grid.major = theme_blank(),panel.grid.minor = theme_blank(),panel.border = theme_blank(),panel.background = theme_blank(), axis.ticks.x = theme_blank())
I want the y-axis to display only integers. Whether this is accomplished through rounding or through a more elegant method isn't really important to me.

If you have the scales package, you can use pretty_breaks() without having to manually specify the breaks.
q + geom_bar(position='dodge', colour='black') +
scale_y_continuous(breaks= pretty_breaks())

This is what I use:
ggplot(data3, aes(x = factor(IR), y = value, fill = Legend, width = .15)) +
geom_col(position = 'dodge', colour = 'black') +
scale_y_continuous(breaks = function(x) unique(floor(pretty(seq(0, (max(x) + 1) * 1.1)))))

With scale_y_continuous() and argument breaks= you can set the breaking points for y axis to integers you want to display.
ggplot(data2, aes(x =factor(IR), y = value, fill = Legend, width=.15)) +
geom_bar(position='dodge', colour='black')+
scale_y_continuous(breaks=c(1,3,7,10))

You can use a custom labeller. For example, this function guarantees to only produce integer breaks:
int_breaks <- function(x, n = 5) {
l <- pretty(x, n)
l[abs(l %% 1) < .Machine$double.eps ^ 0.5]
}
Use as
+ scale_y_continuous(breaks = int_breaks)
It works by taking the default breaks, and only keeping those that are integers. If it is showing too few breaks for your data, increase n, e.g.:
+ scale_y_continuous(breaks = function(x) int_breaks(x, n = 10))

These solutions did not work for me and did not explain the solutions.
The breaks argument to the scale_*_continuous functions can be used with a custom function that takes the limits as input and returns breaks as output. By default, the axis limits will be expanded by 5% on each side for continuous data (relative to the range of data). The axis limits will likely not be integer values due to this expansion.
The solution I was looking for was to simply round the lower limit up to the nearest integer, round the upper limit down to the nearest integer, and then have breaks at integer values between these endpoints. Therefore, I used the breaks function:
brk <- function(x) seq(ceiling(x[1]), floor(x[2]), by = 1)
The required code snippet is:
scale_y_continuous(breaks = function(x) seq(ceiling(x[1]), floor(x[2]), by = 1))
The reproducible example from original question is:
data3 <-
structure(
list(
IR = structure(
c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L),
.Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"),
class = "factor"
),
variable = structure(
c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L),
.Label = c("Real queens", "Simulated individuals"),
class = "factor"
),
value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L),
Legend = structure(
c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L),
.Label = c("Real queens",
"Simulated individuals"),
class = "factor"
)
),
row.names = c(NA,-8L),
class = "data.frame"
)
ggplot(data3, aes(
x = factor(IR),
y = value,
fill = Legend,
width = .15
)) +
geom_col(position = 'dodge', colour = 'black') + ylab('Frequency') + xlab('IR') +
scale_fill_grey() +
scale_y_continuous(
breaks = function(x) seq(ceiling(x[1]), floor(x[2]), by = 1),
expand = expand_scale(mult = c(0, 0.05))
) +
theme(axis.text.x=element_text(colour="black", angle = 45, hjust = 1),
axis.text.y=element_text(colour="Black"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.ticks.x = element_blank())

I found this solution from Joshua Cook and worked pretty well.
integer_breaks <- function(n = 5, ...) {
fxn <- function(x) {
breaks <- floor(pretty(x, n, ...))
names(breaks) <- attr(breaks, "labels")
breaks
}
return(fxn)
}
q + geom_bar(position='dodge', colour='black') +
scale_y_continuous(breaks = integer_breaks())
The source is:
https://joshuacook.netlify.app/post/integer-values-ggplot-axis/

You can use the accuracy argument of scales::label_number() or scales::label_comma() for this:
fakedata <- data.frame(
x = 1:5,
y = c(0.1, 1.2, 2.4, 2.9, 2.2)
)
library(ggplot2)
# without the accuracy argument, you see .0 decimals
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::comma)
# with the accuracy argument, all displayed numbers are integers
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = ~ scales::comma(.x, accuracy = 1))
# equivalent
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::label_comma(accuracy = 1))
# this works with scales::label_number() as well
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::label_number(accuracy = 1))
Created on 2021-08-27 by the reprex package (v2.0.0.9000)

All of the existing answers seem to require custom functions or fail in some cases.
This line makes integer breaks:
bad_scale_plot +
scale_y_continuous(breaks = scales::breaks_extended(Q = c(1, 5, 2, 4, 3)))
For more info, see the documentation ?labeling::extended (which is a function called by scales::breaks_extended).
Basically, the argument Q is a set of nice numbers that the algorithm tries to use for scale breaks. The original plot produces non-integer breaks (0, 2.5, 5, and 7.5) because the default value for Q includes 2.5: Q = c(1,5,2,2.5,4,3).
EDIT: as pointed out in a comment, non-integer breaks can occur when the y-axis has a small range. By default, breaks_extended() tries to make about n = 5 breaks, which is impossible when the range is too small. Quick testing shows that ranges wider than 0 < y < 2.5 give integer breaks (n can also be decreased manually).

This answer builds on #Axeman's answer to address the comment by kory that if the data only goes from 0 to 1, no break is shown at 1. This seems to be because of inaccuracy in pretty with outputs which appear to be 1 not being identical to 1 (see example at the end).
Therefore if you use
int_breaks_rounded <- function(x, n = 5) pretty(x, n)[round(pretty(x, n),1) %% 1 == 0]
with
+ scale_y_continuous(breaks = int_breaks_rounded)
both 0 and 1 are shown as breaks.
Example to illustrate difference from Axeman's
testdata <- data.frame(x = 1:5, y = c(0,1,0,1,1))
p1 <- ggplot(testdata, aes(x = x, y = y))+
geom_point()
p1 + scale_y_continuous(breaks = int_breaks)
p1 + scale_y_continuous(breaks = int_breaks_rounded)
Both will work with the data provided in the initial question.
Illustration of why rounding is required
pretty(c(0,1.05),5)
#> [1] 0.0 0.2 0.4 0.6 0.8 1.0 1.2
identical(pretty(c(0,1.05),5)[6],1)
#> [1] FALSE

Google brought me to this question. I'm trying to use real numbers in a y scale. The y scale numbers are in Millions.
The scales package comma method introduces a comma to my large numbers. This post on R-Bloggers explains a simple approach using the comma method:
library(scales)
big_numbers <- data.frame(x = 1:5, y = c(1000000:1000004))
big_numbers_plot <- ggplot(big_numbers, aes(x = x, y = y))+
geom_point()
big_numbers_plot + scale_y_continuous(labels = comma)
Enjoy R :)

One answer is indeed inside the documentation of the pretty() function. As pointed out here Setting axes to integer values in 'ggplot2' the function contains already the solution. You have just to make it work for small values. One possibility is writing a new function like the author does, for me a lambda function inside the breaks argument just works:
... + scale_y_continuous(breaks = ~round(unique(pretty(.))
It will round the unique set of values generated by pretty() creating only integer labels, no matter the scale of values.

If your values are integers, here is another way of doing this with group = 1 and as.factor(value):
library(tidyverse)
data3<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
data3 %>%
mutate(value = as.factor(value)) %>%
ggplot(aes(x =factor(IR), y = value, fill = Legend, width=.15)) +
geom_col(position = 'dodge', colour='black', group = 1)
Created on 2022-04-05 by the reprex package (v2.0.1)

This is what I did
scale_x_continuous(labels = function(x) round(as.numeric(x)))

How to display only integer values on an axis using ggplot2

I have the following plot:
library(reshape)
library(ggplot2)
library(gridExtra)
require(ggplot2)
data2<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(15L, 11L, 29L, 42L, 0L, 5L, 21L,
22L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
p <- ggplot(data2, aes(x =factor(IR), y = value, fill = Legend, width=.15))
data3<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
q<- ggplot(data3, aes(x =factor(IR), y = value, fill = Legend, width=.15))
##the plot##
q + geom_bar(position='dodge', colour='black') + ylab('Frequency') + xlab('IR')+scale_fill_grey() +theme(axis.text.x=element_text(colour="black"), axis.text.y=element_text(colour="Black"))+ opts(title='', panel.grid.major = theme_blank(),panel.grid.minor = theme_blank(),panel.border = theme_blank(),panel.background = theme_blank(), axis.ticks.x = theme_blank())
I want the y-axis to display only integers. Whether this is accomplished through rounding or through a more elegant method isn't really important to me.

If you have the scales package, you can use pretty_breaks() without having to manually specify the breaks.
q + geom_bar(position='dodge', colour='black') +
scale_y_continuous(breaks= pretty_breaks())

This is what I use:
ggplot(data3, aes(x = factor(IR), y = value, fill = Legend, width = .15)) +
geom_col(position = 'dodge', colour = 'black') +
scale_y_continuous(breaks = function(x) unique(floor(pretty(seq(0, (max(x) + 1) * 1.1)))))

With scale_y_continuous() and argument breaks= you can set the breaking points for y axis to integers you want to display.
ggplot(data2, aes(x =factor(IR), y = value, fill = Legend, width=.15)) +
geom_bar(position='dodge', colour='black')+
scale_y_continuous(breaks=c(1,3,7,10))

You can use a custom labeller. For example, this function guarantees to only produce integer breaks:
int_breaks <- function(x, n = 5) {
l <- pretty(x, n)
l[abs(l %% 1) < .Machine$double.eps ^ 0.5]
}
Use as
+ scale_y_continuous(breaks = int_breaks)
It works by taking the default breaks, and only keeping those that are integers. If it is showing too few breaks for your data, increase n, e.g.:
+ scale_y_continuous(breaks = function(x) int_breaks(x, n = 10))

These solutions did not work for me and did not explain the solutions.
The breaks argument to the scale_*_continuous functions can be used with a custom function that takes the limits as input and returns breaks as output. By default, the axis limits will be expanded by 5% on each side for continuous data (relative to the range of data). The axis limits will likely not be integer values due to this expansion.
The solution I was looking for was to simply round the lower limit up to the nearest integer, round the upper limit down to the nearest integer, and then have breaks at integer values between these endpoints. Therefore, I used the breaks function:
brk <- function(x) seq(ceiling(x[1]), floor(x[2]), by = 1)
The required code snippet is:
scale_y_continuous(breaks = function(x) seq(ceiling(x[1]), floor(x[2]), by = 1))
The reproducible example from original question is:
data3 <-
structure(
list(
IR = structure(
c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L),
.Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"),
class = "factor"
),
variable = structure(
c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L),
.Label = c("Real queens", "Simulated individuals"),
class = "factor"
),
value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L),
Legend = structure(
c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L),
.Label = c("Real queens",
"Simulated individuals"),
class = "factor"
)
),
row.names = c(NA,-8L),
class = "data.frame"
)
ggplot(data3, aes(
x = factor(IR),
y = value,
fill = Legend,
width = .15
)) +
geom_col(position = 'dodge', colour = 'black') + ylab('Frequency') + xlab('IR') +
scale_fill_grey() +
scale_y_continuous(
breaks = function(x) seq(ceiling(x[1]), floor(x[2]), by = 1),
expand = expand_scale(mult = c(0, 0.05))
) +
theme(axis.text.x=element_text(colour="black", angle = 45, hjust = 1),
axis.text.y=element_text(colour="Black"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank(),
axis.ticks.x = element_blank())

I found this solution from Joshua Cook and worked pretty well.
integer_breaks <- function(n = 5, ...) {
fxn <- function(x) {
breaks <- floor(pretty(x, n, ...))
names(breaks) <- attr(breaks, "labels")
breaks
}
return(fxn)
}
q + geom_bar(position='dodge', colour='black') +
scale_y_continuous(breaks = integer_breaks())
The source is:
https://joshuacook.netlify.app/post/integer-values-ggplot-axis/

You can use the accuracy argument of scales::label_number() or scales::label_comma() for this:
fakedata <- data.frame(
x = 1:5,
y = c(0.1, 1.2, 2.4, 2.9, 2.2)
)
library(ggplot2)
# without the accuracy argument, you see .0 decimals
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::comma)
# with the accuracy argument, all displayed numbers are integers
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = ~ scales::comma(.x, accuracy = 1))
# equivalent
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::label_comma(accuracy = 1))
# this works with scales::label_number() as well
ggplot(fakedata, aes(x = x, y = y)) +
geom_point() +
scale_y_continuous(label = scales::label_number(accuracy = 1))
Created on 2021-08-27 by the reprex package (v2.0.0.9000)

All of the existing answers seem to require custom functions or fail in some cases.
This line makes integer breaks:
bad_scale_plot +
scale_y_continuous(breaks = scales::breaks_extended(Q = c(1, 5, 2, 4, 3)))
For more info, see the documentation ?labeling::extended (which is a function called by scales::breaks_extended).
Basically, the argument Q is a set of nice numbers that the algorithm tries to use for scale breaks. The original plot produces non-integer breaks (0, 2.5, 5, and 7.5) because the default value for Q includes 2.5: Q = c(1,5,2,2.5,4,3).
EDIT: as pointed out in a comment, non-integer breaks can occur when the y-axis has a small range. By default, breaks_extended() tries to make about n = 5 breaks, which is impossible when the range is too small. Quick testing shows that ranges wider than 0 < y < 2.5 give integer breaks (n can also be decreased manually).

This answer builds on #Axeman's answer to address the comment by kory that if the data only goes from 0 to 1, no break is shown at 1. This seems to be because of inaccuracy in pretty with outputs which appear to be 1 not being identical to 1 (see example at the end).
Therefore if you use
int_breaks_rounded <- function(x, n = 5) pretty(x, n)[round(pretty(x, n),1) %% 1 == 0]
with
+ scale_y_continuous(breaks = int_breaks_rounded)
both 0 and 1 are shown as breaks.
Example to illustrate difference from Axeman's
testdata <- data.frame(x = 1:5, y = c(0,1,0,1,1))
p1 <- ggplot(testdata, aes(x = x, y = y))+
geom_point()
p1 + scale_y_continuous(breaks = int_breaks)
p1 + scale_y_continuous(breaks = int_breaks_rounded)
Both will work with the data provided in the initial question.
Illustration of why rounding is required
pretty(c(0,1.05),5)
#> [1] 0.0 0.2 0.4 0.6 0.8 1.0 1.2
identical(pretty(c(0,1.05),5)[6],1)
#> [1] FALSE

Google brought me to this question. I'm trying to use real numbers in a y scale. The y scale numbers are in Millions.
The scales package comma method introduces a comma to my large numbers. This post on R-Bloggers explains a simple approach using the comma method:
library(scales)
big_numbers <- data.frame(x = 1:5, y = c(1000000:1000004))
big_numbers_plot <- ggplot(big_numbers, aes(x = x, y = y))+
geom_point()
big_numbers_plot + scale_y_continuous(labels = comma)
Enjoy R :)

One answer is indeed inside the documentation of the pretty() function. As pointed out here Setting axes to integer values in 'ggplot2' the function contains already the solution. You have just to make it work for small values. One possibility is writing a new function like the author does, for me a lambda function inside the breaks argument just works:
... + scale_y_continuous(breaks = ~round(unique(pretty(.))
It will round the unique set of values generated by pretty() creating only integer labels, no matter the scale of values.

If your values are integers, here is another way of doing this with group = 1 and as.factor(value):
library(tidyverse)
data3<-structure(list(IR = structure(c(4L, 3L, 2L, 1L, 4L, 3L, 2L, 1L
), .Label = c("0.13-0.16", "0.17-0.23", "0.24-0.27", "0.28-1"
), class = "factor"), variable = structure(c(1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L), .Label = c("Real queens", "Simulated individuals"
), class = "factor"), value = c(2L, 2L, 6L, 10L, 0L, 1L, 4L,
4L), Legend = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Real queens",
"Simulated individuals"), class = "factor")), .Names = c("IR",
"variable", "value", "Legend"), row.names = c(NA, -8L), class = "data.frame")
data3 %>%
mutate(value = as.factor(value)) %>%
ggplot(aes(x =factor(IR), y = value, fill = Legend, width=.15)) +
geom_col(position = 'dodge', colour='black', group = 1)
Created on 2022-04-05 by the reprex package (v2.0.1)

This is what I did
scale_x_continuous(labels = function(x) round(as.numeric(x)))

Resources