Related
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))
My theme(aspect.ratio) is not having any effect on my graph and I am wondering why. When I take it off it stretches the graph too much. I want to have control so I tune my graph. Currently I am getting a wide width but unable to manipulate the height of the graph
tgc <- structure(list(Group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L), .Label = c("Visible", "Remembered"), class = "factor"),
Condition = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L
), .Label = c("CEN", "IPS", "CTL"), class = "factor"), test = structure(c(1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L), .Label = c("Pre-test", "Post-test"
), class = "factor"), Session = structure(c(1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L), .Label = c("Adaptation", "Post-adaptation"
), class = "factor"), N = c(12, 12, 12, 12, 12, 12, 12, 12,
12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,
12), Abs_IDE = c(23.7992344166667, 13.0386095591667, 15.7028633063333,
19.84749675725, 18.1572712615, 11.68093831675, 16.1626619356667,
22.9018392689167, 25.980293756, 13.45901734025, 24.4302041906667,
12.0791439846667, 22.4191223275, 8.96559583341667, 16.7862310038333,
18.9797044311667, 20.1929425604167, 11.7699855065833, 13.56023988325,
19.73171153625, 33.5879796116667, 14.6798949093333, 26.1433479941667,
8.74572327816667), sd = c(8.04062173855832, 9.0782958352921,
6.90557155294788, 10.7770226212508, 9.90142743265505, 6.13623590788893,
9.72344405555326, 11.4928324154261, 14.7569847333998, 8.68503337334045,
14.1914679614007, 8.09149043273921, 8.16863922288962, 7.04528824438605,
5.65528757276849, 10.2612900552688, 8.59034167901021, 9.73347852641845,
6.85089019152845, 10.7480537432634, 14.6034318371352, 7.50792731288404,
10.5564213216697, 4.75186261300342), se = c(2.3211275626043,
2.62067827214448, 1.99346679750134, 3.11105845572093, 2.85829589680247,
1.77137872661536, 2.80691652146197, 3.31769494439875, 4.25997455412779,
2.5071531780095, 4.09672392385531, 2.33581208974363, 2.35808302712413,
2.0337995322074, 1.63254090124132, 2.96217928782113, 2.4798180404037,
2.80981322368957, 1.97768164813376, 3.10269586096884, 4.21564765113117,
2.16735192757487, 3.04737634587255, 1.37174457938482), ci = c(5.10876731997174,
5.76807398636459, 4.38759083843585, 6.84739349321937, 6.29106685201305,
3.89877829018243, 6.17798160935384, 7.3021973383327, 9.37614077600327,
5.51820693887549, 9.01682856139793, 5.14108774628837, 5.19010574896418,
4.4763625889898, 3.59319829687477, 6.51971265402513, 5.45804270665608,
6.18435720796999, 4.35284795892798, 6.82898754627016, 9.27857792031489,
4.7703094292883, 6.70723011447976, 3.01918946266214)), row.names = c(NA,
-24L), class = "data.frame")
library(ggh4x)
p <- ggplot(tgc, aes(x = Condition, y = Abs_IDE), fill = test) +
geom_errorbar(aes(ymin=Abs_IDE-se, ymax=Abs_IDE+se, group = test), position = position_dodge(0.5), width=.1) +
geom_bar(aes(fill = test), stat = "identity", width = 0.5, color = "black", position='dodge') + ylim(0,38.5) + theme_bw() + theme(
axis.text.x = element_text(size = 12,face="bold"),#, angle = 10, hjust = .5, vjust = .5),
axis.text.y = element_text(size = 12, face = "bold"),
axis.title.y = element_text(vjust= 1.8, size = 20),
axis.title.x = element_text(vjust= -0.5, size = 20),
axis.title = element_text(face = "bold")) + xlab("space") + ylab("Plot title") + theme(legend.position="top") +
scale_fill_manual(values = c("grey80", "grey20")) +
facet_nested(. ~ Session + Group )
p + guides(fill=guide_legend(title="Test:")) + theme(legend.text=element_text(size=16),legend.title=element_text(size=16) ) +
theme(strip.text = element_text(face="bold", size=12)) + theme(aspect.ratio = 1)
I think I fixed the bug, at least the following should work now with the current github branch:
library(ggplot2)
library(ggh4x) # devtools::install_github("teunbrand/ggh4x")
# tgc <- structure(...) # omitted for brevity
p <- ggplot(tgc, aes(x = Condition, y = Abs_IDE), fill = test) +
geom_errorbar(aes(ymin=Abs_IDE-se, ymax=Abs_IDE+se, group = test), position = position_dodge(0.5), width=.1) +
geom_bar(aes(fill = test), stat = "identity", width = 0.5, color = "black", position='dodge') + ylim(0,38.5) + theme_bw() + theme(
axis.text.x = element_text(size = 12,face="bold"),#, angle = 10, hjust = .5, vjust = .5),
axis.text.y = element_text(size = 12, face = "bold"),
axis.title.y = element_text(vjust= 1.8, size = 20),
axis.title.x = element_text(vjust= -0.5, size = 20),
axis.title = element_text(face = "bold")) + xlab("space") + ylab("Plot title") + theme(legend.position="top") +
scale_fill_manual(values = c("grey80", "grey20")) +
facet_nested(. ~ Session + Group )
p + guides(fill=guide_legend(title="Test:")) + theme(legend.text=element_text(size=16),legend.title=element_text(size=16) ) +
theme(strip.text = element_text(face="bold", size=12)) + theme(aspect.ratio = 2)
Created on 2021-10-28 by the reprex package (v2.0.1)
Getting an error message that reads ' Error: All unnamed arguments must be length 1'. I am trying to differentiate my line by the shape of the point and I keep getting the errors above. I want to use all solid lines but differentiated by shape. The journal I want to public my work requires black and white instead of color
The plot I want to modify:
tgc <- structure(
list(
GROUP = structure(
c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L),
.Label = c("LLL", "LRL", "RLR", "RRR"),
class = "factor"
),
condition = structure(
c(1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 2L, 2L, 3L, 3L, 1L, 1L, 2L, 2L, 3L, 3L),
.Label = c("Midline", "No Midline crossing", "Midline crossing"),
class = "factor"
),
names = structure(
c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L),
.Label = c("102", "104"),
class = "factor"
),
Trial_type = structure(
c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L),
.Label = c("retention", "transfer"),
class = "factor"
),
Training = structure(
c(2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L),
.Label = c("right", "left"),
class = "factor"
),
N = c(8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8),
NormalizedJerk = c(2060.1571177375, 1092.701687475,
2981.812368875, 1508.28547575, 2089.925186675, 1269.6704558875,
1391.97364445, 914.38364425, 3900.4119165625, 2335.7186722875,
4015.516784, 2563.16723475, 1411.2016892375, 847.952527975,
1853.413925525, 1394.847246875, 6830.81906275, 3915.019566375,
2310.5893110125, 1023.1702538875, 1340.4653657625, 765.2752940875,
5617.967587, 1705.629421875
),
sd = c(1507.9737264907, 946.522319997832,
1403.37144167604, 813.034284948276, 1383.95826055979, 915.414811222361,
580.358119711544, 361.141583497209, 3283.59638643298, 1471.60790379469,
1178.5979495842, 806.56121914288, 701.001824354642, 324.415375522303,
2103.42765701483, 1208.14874080532, 4671.80701687463, 2861.85154237875,
2130.92970547315, 813.649686635084, 489.544827982279, 256.250905151245,
5305.91963495324, 878.475841087918
),
se = c(533.14922392636,
334.646175507445, 496.166731466336, 287.451028112041, 489.303135460484,
323.648010306967, 205.187580982353, 127.682831329662, 1160.9266357632,
520.291964010475, 416.697301221774, 285.16245374901, 247.841571812654,
114.6981559765, 743.673980005258, 427.145083652716, 1651.73321101347,
1011.8173161826, 753.397422485958, 287.668605464989, 173.080233780536,
90.5983763588182, 1875.92587715314, 310.588112170911
),
ci = c(1260.69758461414,
791.31246230768, 1173.24788605882, 679.713672219011, 1157.01806049025,
765.305934151606, 485.191530116531, 301.92191947415, 2745.15527724569,
1230.29499600801, 985.332544042271, 674.302053778614, 586.052191261077,
271.218041235005, 1758.50952839896, 1010.03762375384, 3905.72840792368,
2392.56776402689, 1781.50181629779, 680.228160904389, 409.269718268804,
214.231117892992, 4435.85982330679, 734.424182295757
)
),
row.names = c(NA, -24L),
class = "data.frame"
)
tgc <- summarySE(
data10,
measurevar = "NormalizedJerk",
groupvars = c("GROUP", "condition", "names","Trial_type", "Training")
)
pd <- position_dodge2(0.2)
p <-ggplot(
gc,
aes(
names,
NormalizedJerk,
group = interaction(Training, Trial_type),
color = interaction(Training, Trial_type),
linetype = interaction(Training, Trial_type),
shape = Training
)
) +
geom_errorbar(
aes(ymin = NormalizedJerk - se, ymax = NormalizedJerk + se),
width = .3,
position = pd
) +
geom_line(
position = pd,
size = 1
) +
geom_point(
aes(shape = Training),
position = pd,
size = 1
)+
scale_colour_manual(
name = "Experimental group",
values = c("#999999","#999999","#000000","#000000")
labels = c("RRR","LLL","LRL","RLR")
) +
scale_shape_manual(
name = "Experimental group",
values = c("19","18","19","18")
) +
scale_linetype_manual(
name = "Experimental group",
values = c("solid","solid","solid","solid"),
labels = c("RRR","LLL","LRL","RLR")
) +
theme_bw() +
facet_wrap(.~condition) +
theme(
axis.title.y = element_text(vjust= 1.8, size = 14),
axis.title.x = element_text(vjust= -0.5, size = 14),
axis.title = element_text(face = "bold")
) +
xlab("Block of trials") +
ylab("Normalized Jerk")
p +
scale_x_discrete(
breaks=c("102","104"),
labels=c("Pretest","Posttest")
)
I modified your code a little. Thanks to Nic3500 for formatting the code.
You needed to add the same labels to the shape manual override as the others and turn the error bar legend off. I also increased the size of the legend because the default seems too small when showing different line types.
ggplot(tgc,
aes(
names,
NormalizedJerk,
group = interaction(Training, Trial_type),
color = interaction(Training, Trial_type),
linetype = interaction(Training, Trial_type),
shape = Training
)
) +
geom_errorbar(aes(ymin=NormalizedJerk-se, ymax=NormalizedJerk+se),
show.legend=FALSE, # <- here
width=.3, position=pd) +
geom_line(position=pd, size = 1) +
geom_point(position=pd, size= 2) +
scale_colour_manual(name = "Experimental group",
values=c("#999999","#999999","#000000","#000000"),
labels=c("RRR","LLL","LRL","RLR")) +
scale_shape_manual(name = "Experimental group", values=c(19,18,19,18),
labels=c("RRR","LLL","LRL","RLR")) + # <- here
scale_linetype_manual(name = "Experimental group",
values=c("solid","dashed","solid","dashed"),
labels=c("RRR","LLL","LRL","RLR")) +
theme_bw()+
facet_wrap(.~condition) +
theme(axis.title.y = element_text(vjust= 1.8, size = 14),
axis.title.x = element_text(vjust= -0.5, size = 14),
axis.title = element_text(face = "bold"),
legend.key.width = grid::unit(1.25, "cm")) + # <- here
xlab("Block of trials") + ylab("Normalized Jerk")
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
My question is related to this question. I want "2014" in the 4-year facet. I tried to repeat but my code doesn't give what I want.
Annotating text on individual facet in ggplot2
This is my data
structure(list(Rot = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("2-year",
"3-year", "4-year"), class = "factor"), Rot.Herb = structure(c(3L,
3L, 4L, 4L, 13L, 13L, 14L, 14L, 5L, 5L, 6L, 6L, 9L, 9L, 10L,
10L, 15L, 15L, 16L, 16L, 1L, 1L, 2L, 2L, 7L, 7L, 8L, 8L, 11L,
11L, 12L, 12L, 17L, 17L, 18L, 18L), .Label = c("A4-conv", "A4-low",
"C2-conv", "C2-low", "C3-conv", "C3-low", "C4-conv", "C4-low",
"O3-conv", "O3-low", "O4-conv", "O4-low", "S2-conv", "S2-low",
"S3-conv", "S3-low", "S4-conv", "S4-low"), class = "factor"),
variable = structure(c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L), .Label = c("Diversity",
"Evenness"), class = "factor"), N = c(4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4), value = c(0.78537789925, 0.613408315,
1.305194686, 0.79519430975, 0.4481728555, 0.30608817425,
1.20978861475, 0.8580643725, 0.92387324875, 0.630166121,
0.945954185, 0.561172324, 1.43952456275, 0.8616864655, 1.23679146725,
0.831737624, 1.033474108, 0.80689293925, 0.9910142125, 0.79342098075,
1.175512223, 0.6293940245, 0.981614832, 0.62342189825, 1.351710013,
0.805075937, 1.6598348325, 0.7983622545, 1.01606920875, 0.5751418795,
1.0500365255, 0.56408326225, 1.07162937725, 0.6756859865,
0.45699816625, 0.44444147325), sd = c(0.354077266902404,
0.208934910331856, 0.169501822767995, 0.0774319459391732,
0.737366460962239, 0.40697977697835, 0.494107033311986, 0.11906912863268,
0.491492768082854, 0.34236657107712, 0.219739438843007, 0.205905593411204,
0.319301583035043, 0.0696484379979274, 0.0563293598951725,
0.0978700910274188, 0.446850757364563, 0.175073468716825,
0.426859848850874, 0.180469101499932, 0.526842123835502,
0.200470277385505, 0.574885944755375, 0.27189545397305, 0.39621771945215,
0.150798258847229, 0.275863362594154, 0.111178397407429,
0.254811233135664, 0.158920851982914, 0.198698241334475,
0.0730606635175717, 0.717706309307313, 0.453776579066358,
0.574276936403411, 0.513758415496589), se = c(0.177038633451202,
0.104467455165928, 0.0847509113839974, 0.0387159729695866,
0.368683230481119, 0.203489888489175, 0.247053516655993,
0.0595345643163399, 0.245746384041427, 0.17118328553856,
0.109869719421504, 0.102952796705602, 0.159650791517521,
0.0348242189989637, 0.0281646799475863, 0.0489350455137094,
0.223425378682282, 0.0875367343584126, 0.213429924425437,
0.090234550749966, 0.263421061917751, 0.100235138692753,
0.287442972377688, 0.135947726986525, 0.198108859726075,
0.0753991294236146, 0.137931681297077, 0.0555891987037145,
0.127405616567832, 0.0794604259914568, 0.0993491206672376,
0.0365303317587859, 0.358853154653656, 0.226888289533179,
0.287138468201705, 0.256879207748294), ci = c(0.563415944919255,
0.332462066715199, 0.26971522480343, 0.123211505132525, 1.1733145846647,
0.647595643784969, 0.786234551289211, 0.189465554245211,
0.782074671929471, 0.544781614588516, 0.349654482635521,
0.327641747494367, 0.508080071600555, 0.110826207087643,
0.089632581638694, 0.155733154793995, 0.71103927089404, 0.278580956835532,
0.679229274424713, 0.287166612643164, 0.838323385234058,
0.318992946792351, 0.914771825423139, 0.432646341459985,
0.630470808679215, 0.23995368085579, 0.438960169525453, 0.176909640028318,
0.40546153371869, 0.252878539112781, 0.316173242000635, 0.116255819336536,
1.14203089616693, 0.722059798737006, 0.91380275723334, 0.817504285602766
)), .Names = c("Rot", "Rot.Herb", "variable", "N", "value",
"sd", "se", "ci"), row.names = c(NA, -36L), class = "data.frame")
and the code to graph
p <- ggplot(Shannon.long2, aes(x=Rot.Herb, y=value, fill=factor(variable)))+
geom_bar(stat="identity", position="dodge")+
scale_fill_brewer(palette = "Set1")+
theme_bw() +
theme(panel.grid.major=element_blank()) +
facet_grid(~Rot, scales = "free_x", space="free_x")+
theme(legend.title=element_blank(),legend.text=element_text(size=20),legend.position="top")+
geom_errorbar(aes(ymin=value-se, ymax=value+se), size=0.5, width=.25,position=position_dodge(.9))+
xlab("\nTreatment") +
theme(axis.title = element_text(size=24,face="bold", vjust=4), axis.text.x = element_text(size=20,angle = 90, hjust = 1)) +
ylab("Shannon's H' and E'") +
theme(axis.title = element_text(size=24,face="bold", vjust=2), axis.text.y = element_text(size=20, color="black"))+
theme(strip.text.x = element_text(colour = "black", size = 20), strip.background = element_rect(fill = "white"))
produced graph (please don't mind the "2014" on the y-axis).
New code to annotate 2014, with help from eipi10
ann_text <- data.frame(x = "S4-conv",y = 1.75,lab = "2014", Rot.Herb=NA,
value=NA, variable=NA,
N=NA, sd=NA, se=NA, ci=NA,
Rot = factor("4-year",levels = c("2-year","3-year","4-year")))
I got an error saying Error: Discrete value supplied to continuous scale after I run p + geom_text(data = ann_text,label = "2014"). Please see what have been wrong with my code and data format. Thanks.
It turns out the issue is that when you include value=NA in ann_text it gets interpreted as logical (rather than numeric, which is its mode in Shannon.long2), causing the error because ggplot expects a numeric variable rather than a categorical one. Set value=NA_real_ (in addition to NA, R has class-specific missing value constants; see ?NA for more info) in ann_text to ensure value is interpreted as numeric and resolve the error. Or set value to any number, e.g., value=0.
In the example below, I've removed all of the theme and lab statements to shorten the code down to the essentials:
p = ggplot(Shannon.long2, aes(x=Rot.Herb, y=value, fill=factor(variable))) +
geom_bar(stat="identity", position="dodge") +
geom_errorbar(aes(ymin=value-se, ymax=value+se), size=0.5, width=.25,position=position_dodge(.9)) +
facet_grid(~Rot, scales = "free_x", space="free_x")
ann_text <- data.frame(x = "S4-conv", y = 1.75, lab = "2014", Rot.Herb=NA,
value=NA_real_, variable=NA)
p + geom_text(data = ann_text, aes(label=lab, x, y))
Note that you also need to feed x and y values to geom_text to provide the label location.
Another option would be to just use the same x and y variable names as in your original data frame, since ggplot already knows these names and has scaled the graph based on them. Now the only missing column we need to add is variable:
ann_text <- data.frame(Rot.Herb = "S4-conv", value = 1.75, lab = "2014", variable=NA)
p + geom_text(data = ann_text, aes(label=lab, Rot.Herb, value))