Add second x-axis to ggplot - r

I build this plot:
df_ebf <- df_ebf %>%
map_df(rev)
labels.minor <- c("nie","selten","manchmal", "mehrmals", "oft", "sehr oft", "immerzu")
ggplot(data=df_ebf, aes(x=forcats::fct_inorder(Skalen), y=Werte, group="")) +
geom_line(color = "#003560") +
geom_point(color = "#003560") +
coord_flip() +
labs(x="EBF-Skalen") +
scale_y_continuous(limits = c(0, 6), breaks = c(0,1,2,3,4,5,6), sec.axis = dup_axis(),expand = c(0,0)) +
scale_x_discrete(expand = c(0,0)) +
theme(panel.grid.major.y = element_blank(),panel.grid.minor.x = element_blank(),axis.line.x = element_line(size = 1, colour = "black", linetype=1),axis.title=element_blank())
Now I want to add a second x-axis below the lower x-axis with the labels.minor.
I found this and this when looking for a solution in the forum, but it didn't work for my case.


If your labels.minor are at the exact position of the breaks, you can simply paste together the labels with a newline character. Example below:
library(ggplot2)
df <- data.frame(
x = runif(10, min = 0, max = 6),
y = letters[1:10]
)
labels.minor <- c("nie","selten","manchmal", "mehrmals", "oft", "sehr oft", "immerzu")
ggplot(df, aes(x, y)) +
geom_path(aes(group = -1)) +
geom_point() +
scale_x_continuous(limits = c(0, 6), breaks = 0:6,
labels = paste0(0:6, "\n", labels.minor),
sec.axis = sec_axis(~.x, breaks = 0:6))
Created on 2021-04-10 by the reprex package (v1.0.0)

Related

How to make log10 ONLY first y-axis (not secondary y-axis) in ggplot in R

I would like to plot ONLY y-axis1 DATA (left axis, Var1, dotted line) as a log10 scale. The dotted line would therefore look higher on the y-axis and differences between 1 and 2 would be noticeable.
I have tried several things, but does not work ( I believe I am using them in the wrong order/place) such as:
+coord_trans(y='log10')--> empty plot
scale_y_continuous(trans = log10_trans(),... --> makes both Var1 and Var 2 log10
scale_y_log10(breaks = trans_breaks("log10", function(x) 10^x),labels = trans_format("log10", math_format(10^.x)))--> makes both y axis log10 and removes y-axis2 (Var2)
data<- data.frame(
Day=c(1,2,3,1,2,3,1,2,3),
Name=rep(c(rep("a",3),rep("b",3),rep("c",3))),
Var1=c(1090,484,64010,1090,484,64010,1090,484,64010),
Var2= c(4,16,39,2,22,39,41,10,3))
ggplot(data) +
geom_bar(aes(fill=Name, y=Var2*1000, x=Day),stat="identity", colour="black", position= position_stack(reverse = TRUE))+
geom_line(aes(x=Day, y=Var1),stat="identity",color="black", linetype="dotted", size=0.8)+
geom_point(aes(Day, Var1), shape=8)+
labs(title= "",
x="",y=expression('Var1'))+
scale_y_continuous(
sec.axis=sec_axis(~./1000, name= expression(paste("Var2"))))+
theme_classic()+
scale_fill_grey(start = 1, end=0.1,name = "", labels = c("a", "b", "c"))

I think the easiest way is to have the primary axis be the linear one, but put it on the right side of the plot. Then, you can have the secondary one be your log-transformed axis.
library(ggplot2)
data<- data.frame(
Day=c(1,2,3,1,2,3,1,2,3),
Name=rep(c(rep("a",3),rep("b",3),rep("c",3))),
Var1=c(1090,484,64010,1090,484,64010,1090,484,64010),
Var2= c(4,16,39,2,22,39,41,10,3))
# Max of secondary divided by max of primary
upper <- log10(3e6) / 80
breakfun <- function(x) {
10^scales::extended_breaks()(log10(x))
}
ggplot(data) +
geom_bar(aes(fill=Name, y=Var2, x=Day),
stat="identity", colour="black", position= position_stack(reverse = TRUE))+
geom_line(aes(x=Day, y=log10(Var1) / upper),
stat="identity",color="black", linetype="dotted", size=0.8)+
geom_point(aes(Day, log10(Var1) / upper), shape=8)+
labs(title= "",
x="",y=expression('Var1'))+
scale_y_continuous(
position = "right",
name = "Var2",
sec.axis = sec_axis(~10^ (. * upper), name= expression(paste("Var1")),
breaks = breakfun)
)+
theme_classic() +
scale_fill_grey(start = 1, end=0.1,name = "", labels = c("a", "b", "c"))
Created on 2022-02-09 by the reprex package (v2.0.1)

Here is a custom breaks function:
br <- function(limits) {
10^(seq(ifelse(limits[1] <= 0,
0,
trunc(log10(limits[1]))),
trunc(log10(limits[2])),
by = 1))}
ggplot(data) +
geom_bar(aes(fill = Name, y = Var2 * 1000, x = Day),
stat = "identity",
colour = "black",
position = position_stack(reverse = TRUE))+
geom_line(aes(x=Day, y=Var1),
stat = "identity",
color = "black",
linetype = "dotted",
size = 0.8)+
geom_point(aes(Day, Var1),
shape = 8)+
labs(title = "",
x = "",
y = expression('Var1'))+
scale_y_continuous(
breaks = br,
sec.axis = sec_axis(~./1000, name= expression(paste("Var2"))))+
theme_classic()+
scale_fill_grey(start = 1,
end = 0.1,
name = "",
labels = c("a", "b", "c"))
Results aren't so pretty but you can customize the breaks as you wish.

You absolutely should read the answer #teunbrand linked to in the comment to your question. But for the matter of displaying log values on the left and original values on the right, you can use:
tibble(Day = 1:10,
Val1 =10*Day) %>%
ggplot(aes(x = Day, y = log10(Val1))) +
geom_col() +
scale_y_log10(name = "log(Val1)",
sec.axis = sec_axis(~ 10^., name = "Val1"))

How do I plot multiple ecdf lines in one graph

How do I plot one graph with lines that are ecdf_Q2<- 50,40,30,20, and 10 instead of just 50?? I need the ggplots to overlap each other. Thank you!
ecdf_Q2 <- **50** %>%
ecdf.shift(ratio_threshold, .) %>%
filter(nobs > 20) %>%
ggplot(aes( x = OUR_ratio_cutoff, y = prob)) +
geom_line() +
geom_point() +
theme_bw(base_size = 12) +
theme(panel.grid = element_blank()) +
scale_y_continuous(limits = c(0,100),
breaks = seq(0,300, by = 10),
expand = c(0,0)) +
scale_x_continuous(limits = c(0,2),
breaks = seq(0,3, by = 0.1),
expand = c(0,0))

r - column wise heatmap using ggplot2

I would really appreciate if anyone could guide me with the following challenge.
I am trying to build column wise heatmap. For each column, I want the lowest value to be green and highest value to be red. The current solution takes a matrix wide approach.
I saw the solution on Heat map per column with ggplot2. As you can see, I implemented the same code but I am not getting the desired result [picture below]
df <- data.frame(
F1 = c(0.66610194649319, 0.666123551800434,
0.666100611954119, 0.665991102703081,
0.665979885730484),
acc_of_pred = c(0.499541627510021, 0.49960260221954,
0.499646067768102, 0.499447308828986,
0.499379552967265),
expected_mean_return = c(2.59756065316356e-07, 2.59799087404167e-07,
2.86466725381146e-07, 2.37977452007967e-07,
2.94242908573705e-07),
win_loss_ratio = c(0.998168189343307, 0.998411671274781,
0.998585272507726, 0.997791676357902,
0.997521287688458),
corr_pearson = c(0.00161443345430616, -0.00248811119331013,
-0.00203407575954095, -0.00496817102369628,
-0.000140531627184482),
corr_spearman = c(0.00214838517340878, -0.000308343671725617,
0.00228492127281917, -0.000359577740835049,
0.000608090759428587),
roc_vec = c(0.517972308828151, 0.51743161463546,
0.518033230192484, 0.518033294993802,
0.517931553535524)
)
combo <- data.frame(combo = c("baseline_120", "baseline_20",
"baseline_60", "baseline_288",
"baseline_5760"))
df.scaled <- scale(df)
df.scaled <- cbind(df.scaled,combo)
df.melt <- melt(df.scaled, id.vars = "combo")
ggplot(df.melt, aes(combo, variable)) +
geom_tile(aes(fill = value), colour = "white") +
scale_fill_gradient(low = "green", high = "red") +
geom_text(aes(label=value)) +
theme_grey(base_size = 9) +
labs(x = "", y = "") + scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) +
theme(legend.position = "none", axis.ticks = element_blank(),
axis.text.x = element_text(size = 9 * 0.8,
angle = 0, hjust = 0, colour = "grey50"))

You are nearly correct. The code you implemented is the same for plotting. But the person who asked the question did one step in data preparation, he added a scaling variable.
If you scale your variable before plotting it and using the scaled factor as fill argument it works (i just added the rescale in scale_fill_gradient in ggplot after calculating it):
df.melt <- melt(df.scaled, id.vars = "combo")
df.melt<- ddply(df.melt, .(combo), transform, rescale = rescale(value))
ggplot(df.melt, aes(combo, variable)) +
geom_tile(aes(fill = rescale), colour = "white") +
scale_fill_gradient( low= "green", high = "red") +
geom_text(aes(label=round(value,4))) +
theme_grey(base_size = 9) +
labs(x = "", y = "") + scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) +
theme(legend.position = "none", axis.ticks = element_blank(),
axis.text.x = element_text(size = 9 * 0.8,
angle = 0, hjust = 0, colour = "grey50"))
giving the plot:

Delete the symbol a from legend

I need to delete that symbol 'a' that is coming in the legend, plus I would like to know if there is a possibility to place the label on the top of the bars.
This my example file:
Residue,Position,Weight,SVM Count,Odd,Ttest,lower,upper,Resistance
G163R,163,0.357,49,19.9453848,6.978518E-82,5.6628402,70.2925768,Accessory
V165I,165,0.268,49,2.98167788,1.60934E-80,1.25797484,7.06728692,Novel
N155H,155,0.253,50,38.6089584,1.089188E-83,9.5815554,155.7070612,Major
library(ggplot2)
m <- read.csv('example.csv', header=T, row.names=1)
boxOdds = m$Odd
df <- data.frame(
yAxis = length(boxOdds):1,
boxnucleotide = m$Position,
boxCILow = m$lower,
boxCIHigh = m$upper,
Mutation = m$Resistance)
ticksy<-c(seq(0,0.3,by=.1), seq(0, 1, by =.5), seq(0, 20, by =5), seq(0, 150, by =50))
ticksx<-c(seq(0,300,by=25))
p <- ggplot(df, aes(x = boxnucleotide, y = boxOdds, colour=Mutation,label=rownames(m)))
p1 <- p + geom_errorbar(aes(ymax = boxCIHigh, ymin = boxCILow), size = .5, height = .01) +
geom_point(size = 1) +
theme_bw() +
theme(panel.grid.minor = element_blank()) +
scale_y_continuous(breaks=ticksy, labels = ticksy) +
scale_x_continuous(breaks=ticksx, labels = ticksx) +
coord_trans(y = "log10") +
ylab("Odds ratio (log scale)") +
scale_color_manual(values=c("#00BFC4","#F8766D","#619CFF")) +
xlab("Integrase nucleotide position") +
geom_text(size=4,hjust=0, vjust=0)+
theme(legend.position = c(0.9, 0.9))
p1
I already tried all possible solutions from Remove 'a' from legend when using aesthetics and geom_text but none worked out

Showing median value in grouped boxplot in R

I have created boxplots using ggplot2 with this code.
plotgraph <- function(x, y, colour, min, max)
{
plot1 <- ggplot(dims, aes(x = x, y = y, fill = Region)) +
geom_boxplot()
#plot1 <- plot1 + scale_x_discrete(name = "Blog Type")
plot1 <- plot1 + labs(color='Region') + geom_hline(yintercept = 0, alpha = 0.4)
plot1 <- plot1 + scale_y_continuous(breaks=c(seq(min,max,5)), limits = c(min, max))
plot1 <- plot1 + labs(x="Blog Type", y="Dimension Score") + scale_fill_grey(start = 0.3, end = 0.7) + theme_grey()
plot1 <- plot1 + theme(legend.justification = c(1, 1), legend.position = c(1, 1))
return(plot1)
}
plot1 <- plotgraph (Blog, Dim1, Region, -30, 25)
A part of data I use is reproduced here.
Blog,Region,Dim1,Dim2,Dim3,Dim4
BlogsInd.,PK,-4.75,13.47,8.47,-1.29
BlogsInd.,PK,-5.69,6.08,1.51,-1.65
BlogsInd.,PK,-0.27,6.09,0.03,1.65
BlogsInd.,PK,-2.76,7.35,5.62,3.13
BlogsInd.,PK,-8.24,12.75,3.71,3.78
BlogsInd.,PK,-12.51,9.95,2.01,0.21
BlogsInd.,PK,-1.28,7.46,7.56,2.16
BlogsInd.,PK,0.95,13.63,3.01,3.35
BlogsNews,PK,-5.96,12.3,6.5,1.49
BlogsNews,PK,-8.81,7.47,4.76,1.98
BlogsNews,PK,-8.46,8.24,-1.07,5.09
BlogsNews,PK,-6.15,0.9,-3.09,4.94
BlogsNews,PK,-13.98,10.6,4.75,1.26
BlogsNews,PK,-16.43,14.49,4.08,9.91
BlogsNews,PK,-4.09,9.88,-2.79,5.58
BlogsNews,PK,-11.06,16.21,4.27,8.66
BlogsNews,PK,-9.04,6.63,-0.18,5.95
BlogsNews,PK,-8.56,7.7,0.71,4.69
BlogsNews,PK,-8.13,7.26,-1.13,0.26
BlogsNews,PK,-14.46,-1.34,-1.17,14.57
BlogsNews,PK,-4.21,2.18,3.79,1.26
BlogsNews,PK,-4.96,-2.99,3.39,2.47
BlogsNews,PK,-5.48,0.65,5.31,6.08
BlogsNews,PK,-4.53,-2.95,-7.79,-0.81
BlogsNews,PK,6.31,-9.89,-5.78,-5.13
BlogsTech,PK,-11.16,8.72,-5.53,8.86
BlogsTech,PK,-1.27,5.56,-3.92,-2.72
BlogsTech,PK,-11.49,0.26,-1.48,7.09
BlogsTech,PK,-0.9,-1.2,-2.03,-7.02
BlogsTech,PK,-12.27,-0.07,5.04,8.8
BlogsTech,PK,6.85,1.27,-11.95,-10.79
BlogsTech,PK,-5.21,-0.89,-6,-2.4
BlogsTech,PK,-1.06,-4.8,-8.62,-2.42
BlogsTech,PK,-2.6,-4.58,-2.07,-3.25
BlogsTech,PK,-0.95,2,-2.2,-3.46
BlogsTech,PK,-0.82,7.94,-4.95,-5.63
BlogsTech,PK,-7.65,-5.59,-3.28,-0.54
BlogsTech,PK,0.64,-1.65,-2.36,-2.68
BlogsTech,PK,-2.25,-3,-3.92,-4.87
BlogsTech,PK,-1.58,-1.42,-0.38,-5.15
Columns,PK,-5.73,3.26,0.81,-0.55
Columns,PK,0.37,-0.37,-0.28,-1.56
Columns,PK,-5.46,-4.28,2.61,1.29
Columns,PK,-3.48,2.38,12.87,3.73
Columns,PK,0.88,-2.24,-1.74,3.65
Columns,PK,-2.11,4.51,8.95,2.47
Columns,PK,-10.13,10.73,9.47,-0.47
Columns,PK,-2.08,1.04,0.11,0.6
Columns,PK,-4.33,5.65,2,-0.77
Columns,PK,1.09,-0.24,-0.92,-0.17
Columns,PK,-4.23,-4.01,-2.32,6.26
Columns,PK,-1.46,-1.53,9.83,5.73
Columns,PK,9.37,-1.32,1.27,-4.12
Columns,PK,5.84,-2.42,-5.21,1.07
Columns,PK,8.21,-9.36,-5.87,-3.21
Columns,PK,7.34,-7.3,-2.94,-5.86
Columns,PK,1.83,-2.77,1.47,-4.02
BlogsInd.,PK,14.39,-0.55,-5.42,-4.7
BlogsInd.,US,22.02,-1.39,2.5,-3.12
BlogsInd.,US,4.83,-3.58,5.34,9.22
BlogsInd.,US,-3.24,2.83,-5.3,-2.07
BlogsInd.,US,-5.69,15.17,-14.27,-1.62
BlogsInd.,US,-22.92,4.1,5.79,-3.88
BlogsNews,US,0.41,-2.03,-6.5,2.81
BlogsNews,US,-4.42,8.49,-8.04,2.04
BlogsNews,US,-10.72,-4.3,3.75,11.74
BlogsNews,US,-11.29,2.01,0.67,8.9
BlogsNews,US,-2.89,0.08,-1.59,7.06
BlogsNews,US,-7.59,8.51,3.02,12.33
BlogsNews,US,-7.45,23.51,2.79,0.48
BlogsNews,US,-12.49,15.79,-9.86,18.29
BlogsTech,US,-11.59,6.38,11.79,-7.28
BlogsTech,US,-4.6,4.12,7.46,3.36
BlogsTech,US,-22.83,2.54,10.7,5.09
BlogsTech,US,-4.83,3.37,-8.12,-0.9
BlogsTech,US,-14.76,29.21,6.23,9.33
Columns,US,-15.93,12.85,19.47,-0.88
Columns,US,-2.78,-1.52,8.16,0.24
Columns,US,-16.39,13.08,11.07,7.56
Even though I have tried to add detailed scale on y-axis, it is hard for me to pinpoint exact median score for each boxplot. So I need to print median value within each boxplot. There was another answer available (for faceted boxplot) which does not work for me as the printed values are not within the boxes but jammed together in the middle. It will be great to be able to print them within (middle and above the median line of) boxplots.
Thanks for your help.
Edit: I make a grouped graph as below.
Add

library(dplyr)
dims=dims%>%
group_by(Blog,Region)%>%
mutate(med=median(Dim1))
plotgraph <- function(x, y, colour, min, max)
{
plot1 <- ggplot(dims, aes(x = x, y = y, fill = Region)) +
geom_boxplot()+
labs(color='Region') +
geom_hline(yintercept = 0, alpha = 0.4)+
scale_y_continuous(breaks=c(seq(min,max,5)), limits = c(min, max))+
labs(x="Blog Type", y="Dimension Score") + scale_fill_grey(start = 0.3, end = 0.7) +
theme_grey()+
theme(legend.justification = c(1, 1), legend.position = c(1, 1))+
geom_text(aes(y = med,x=x, label = round(med,2)),position=position_dodge(width = 0.8),size = 3, vjust = -0.5,colour="blue")
return(plot1)
}
plot1 <- plotgraph (Blog, Dim1, Region, -30, 25)
Which gives (the text colour can be tweaked to something less tacky):
Note: You should consider using non-standard evaluation in your function rather than having it require the use of attach()
Edit:
One liner, not as clean I wanted it to be since I ran into problems with dplyr not properly aggregating the data even though it says the grouping was performed.
This function assume the dataframe is always called dims
library(ggplot2)
library(reshape2)
plotgraph <- function(x, y, colour, min, max)
{
plot1 <- ggplot(dims, aes_string(x = x, y = y, fill = colour)) +
geom_boxplot()+
labs(color=colour) +
geom_hline(yintercept = 0, alpha = 0.4)+
scale_y_continuous(breaks=c(seq(min,max,5)), limits = c(min, max))+
labs(x="Blog Type", y="Dimension Score") +
scale_fill_grey(start = 0.3, end = 0.7) +
theme_grey()+
theme(legend.justification = c(1, 1), legend.position = c(1, 1))+
geom_text(data= melt(with(dims, tapply(eval(parse(text=y)),list(eval(parse(text=x)),eval(parse(text=colour))), median)),varnames=c("Blog","Region"),value.name="med"),
aes_string(y = "med",x=x, label = "med"),position=position_dodge(width = 0.8),size = 3, vjust = -0.5,colour="blue")
return(plot1)
}
plot1 <- plotgraph ("Blog", "Dim1", "Region", -30, 25)

Assuming that Blog is your dataframe, the following should work:
min <- -30
max <- 25
meds <- aggregate(Dim1~Region, Blog, median)
plot1 <- ggplot(Blog, aes(x = Region, y = Dim1, fill = Region)) +
geom_boxplot()
plot1 <- plot1 + labs(color='Region') + geom_hline(yintercept = 0, alpha = 0.4)
plot1 <- plot1 + scale_y_continuous(breaks=c(seq(min,max,5)), limits = c(min, max))
plot1 <- plot1 + labs(x="Blog Type", y="Dimension Score") + scale_fill_grey(start = 0.3, end = 0.7) + theme_grey()
plot1 + theme(legend.justification = c(1, 1), legend.position = c(1, 1)) +
geom_text(data = meds, aes(y = Dim1, label = round(Dim1,2)),size = 5, vjust = -0.5, color='white')

Resources