I am trying to plot a curve with the following command but I need to limit the y-axis until 100, so can anybody help me find out how to do it?
Thanks in advance
ggplot(file1, aes(x=f11,colour=time, alpha=time, size=time))+
geom_line(aes(y = S1))+scale_color_manual(values =c("t1"="red","t2"="magenta","t3"="coral4","t5"=cl[8]),
labels=labels1 ,name="Time")+
scale_alpha_manual(values=c(1, 1, 1, 1),labels=labels1)+
scale_size_manual(values = c(.6, .61, .61, .61),labels=labels1)+
guides(colour = guide_legend(title=title),
alpha = guide_legend(title=title),
size = guide_legend(title=title))+
labs(title="Column 1")+ theme_bw()+theme(plot.title=element_text(size=12,hjust=0.5,face="bold"))+
theme(aspect.ratio = 1)+ theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank())+
xlab( growth)+ylab(nutrient )+
scale_x_continuous(breaks = seq(0, 0.5, by=0.10), limits=c(0,0.5))+
scale_y_continuous(trans='log10')
You can use the function scale_y_log10 and set limits like in the following code:
library(ggplot2)
ggplot(data = df,aes(x = x, y =y)) +
geom_point() +
scale_y_log10(limits = c(1,100))
Output:
Data
df <- data.frame(x = 1:10, y = seq(1,150,length.out = 10))
Related
I have modified the colors of my x axis labels according to their group.
For that, I have used the following pseudocode:
library(ggsci)
library(ggplot2)
x_cols = pal_jco()(length(unique(melted_df$Group)))
names(x_cols) = unique(melted_df$Group)
ggplot(melted_df, ... + theme(axis.text.x = element_text(colour = x_cols))
I would like to add a legend to the plot (if possible, outside the plot), that explains the colouring of the x axis labels.
melted_df dataframe looks like this:
Here the full code:
#Generate color mapping
x_cols = pal_jco()(length(unique(melted_df$Group)))
names(x_cols) = unique(melted_df$Group)
melted_df$mycolors = sapply(as.character(melted_df$Group), function(x) x_cols[x])
#Plot
ggplot(melted_df, aes(fill=variable, y=value, x=fct_inorder(id))) +
geom_bar(position="stack", stat = "identity") + ggtitle("Barplot") +
theme_bw() +
xlab("samples") + ylab("Counts") +
theme(axis.title.y=element_text(size=10), axis.title.x=element_text(size=10),
plot.title = element_text(face = "bold", size = (15), hjust = 0.5),
axis.text.x = element_text(distinct(samples_melt[c("id", "mycolors")])$mycolors)) +
guides(fill=guide_legend(title="Columns"))
In the absence of a reproducible example, here is how you might do it with the built-in iris data set:
library(ggplot2)
ggplot(iris, aes(Species, Sepal.Length)) +
stat_summary(fun = mean, geom = "col", aes(fill = Species)) +
geom_point(aes(color = Species), alpha = 0, key_glyph = draw_key_text) +
theme_bw(base_size = 20) +
labs(color = "") +
guides(color = guide_legend(override.aes = list(alpha = 1, size = 8))) +
theme(axis.text.x = element_text(color = scales::hue_pal()(3), face = 2))
I addressed the issue using Legend() constructor, provided by ComplexHeatmap library.
I first used the code provided above under the EDIT section, and then I added the following code in order to draw an additional legend explaining the x-axis colouring.
lgd = Legend(labels = names(x_cols), title = "Group", labels_gp = gpar(fontsize = 8), nrow = 1, legend_gp = gpar(fill = x_cols))
draw(lgd, x = unit(1.8, "cm"), y = unit(0.3, "cm"), just = c("left", "bottom"))
I am trying to create a plot like the one below. I'd like the order the points in each category in such a way that they form an s-shape. Is it possible to do this in ggplot?
Similar data available here
What I have so far:
somatic.variants <- read.delim("data/Lawrence.S2.txt", stringsAsFactors=T)
cancer_rates <- tapply(somatic.variants$logn_coding_mutations, somatic.variants$tumor_type, median)
cancer_rates <- cancer_rates[order(cancer_rates, decreasing=F)]
somatic.variants$tumor_type <- factor(somatic.variants$tumor_type, levels = names(cancer_rates))
library(ggplot2)
library(GGally)
ggplot(data = somatic.variants,
mapping = aes(x = tumor_type,
y = log10(n_coding_mutations))) +
geom_point(position = position_dodge2()) +
scale_x_discrete(position = "top") +
scale_y_continuous(labels = c(0,10,100,1000,10000), expand = c(0,0)) +
geom_stripped_cols() +
theme_bw() +
theme(axis.title.x = element_blank(),
axis.text.x = element_text(angle = 315, hjust = 1, size = 12),
panel.grid = element_blank()) +
labs(y = "Coding mutations count") +
stat_summary(fun = median,
geom="crossbar",
size = 0.25,
width = 0.9,
group = 1,
show.legend = FALSE,
color = "#FF0000")
This could be achieved by
grouping the data by x-axis categories
arranging by the y-axis value
which ensures that the points are plotted in ascending order of the values for each category.
somatic.variants <- read.delim("https://gist.githubusercontent.com/wudustan/57deecdaefa035c1ecabf930afde295a/raw/1594d51a1e3b52f674ff746caace3231fd31910a/Lawrence.S2.txt", stringsAsFactors=T)
cancer_rates <- tapply(somatic.variants$logn_coding_mutations, somatic.variants$tumor_type, median)
cancer_rates <- cancer_rates[order(cancer_rates, decreasing=F)]
somatic.variants$tumor_type <- factor(somatic.variants$tumor_type, levels = names(cancer_rates))
library(ggplot2)
library(GGally)
library(dplyr)
somatic.variants <- somatic.variants %>%
group_by(tumor_type) %>%
arrange(n_coding_mutations)
ggplot(data = somatic.variants,
mapping = aes(x = tumor_type,
y = log10(n_coding_mutations))) +
geom_point(position = position_dodge2(.9), size = .25) +
scale_x_discrete(position = "top") +
scale_y_continuous(labels = c(0,10,100,1000,10000), expand = c(0,0)) +
geom_stripped_cols() +
theme_bw() +
theme(axis.title.x = element_blank(),
axis.text.x = element_text(angle = 315, hjust = 1, size = 12),
panel.grid = element_blank()) +
labs(y = "Coding mutations count") +
stat_summary(fun = median,
geom="crossbar",
size = 0.25,
width = 0.9,
group = 1,
show.legend = FALSE,
color = "#FF0000")
#> Warning: Removed 29 rows containing non-finite values (stat_summary).
I want to recreate the following plot which only shows tick marks on y and x axis at the start and the end of the line.
Picture of Plot.
I have the following code so far:
elevation_plot <- StradeBianche%>%
ggplot(aes(x = `Accumulated Distance in Km`))+
geom_area(aes(y = elevation), fill = "grey")+
coord_cartesian(ylim = c(100,500))+
scale_y_continuous(expand = c(0,0), limits = c(0, 500), labels = label_number(suffix = " m"))+
scale_x_continuous(expand = c(0,0), breaks = seq(0, 180, 20), labels = label_number(suffix = ".0 km"))+
theme(panel.grid.minor = element_blank())+
theme(panel.grid.major = element_blank())+
theme(panel.background = element_rect(fill = "white"))+
theme(panel.border = element_blank())+
theme(axis.title = element_blank())+
theme(axis.ticks = element_blank())
The result is this:Picture of result. It comes quite close but the ticks are still missing...
I can either remove all axis ticks or none. But I can not manage to set only certain axis ticks without removing the x and y values along the axis.
Any help is greatly appreciated!
You could use the pretty_breaks function from the scales library:
ggplot(dat, aes(x,y)) + geom_point() +
scale_x_continuous(breaks = scales::pretty_breaks(n = 10)) +
scale_y_continuous(breaks = scales::pretty_breaks(n = 10))
Where n defines the number of ticks
Check out https://stackoverflow.com/a/31408489/15235792
You can immitate ticks behaviour if you place geom_segment()s at the right coordinates and turn off the clipping of the data. The downside is that you cannot place the segment endpoints relative to the first in absolute units, so you'd have to fiddle with the offset and text margins. Example below:
library(ggplot2)
xlim <- c(1, 5)
ylim <- c(4, 8)
offset <- 0.05
seg <- data.frame(
x = xlim[c(1,2,1,1)],
xend = xlim[c(1,2,1,1)] - c(0, 0, offset, offset),
y = ylim[c(1,1,2,1)],
yend = ylim[c(1,1,2,1)] - c(offset, offset, 0, 0)
)
ggplot(iris, aes(Sepal.Width, Sepal.Length)) +
geom_point(aes(colour = Species)) +
geom_segment(data = seg, aes(x = x, y = y, xend = xend, yend = yend)) +
coord_cartesian(clip = "off",
xlim = xlim,
ylim = ylim,
expand = FALSE) +
theme(axis.ticks = element_blank(),
axis.line = element_line(),
axis.text.x = element_text(margin = margin(t = 8)),
axis.text.y = element_text(margin = margin(r = 8)))
Created on 2021-03-25 by the reprex package (v1.0.0)
I am trying to shade the 0.025 and 0.975 quantiles on this graph that has three lines. I have tried geom_area, geom_ribbon, and I cannot highlight every quantile in every line.
Please note that "y" was ignored in this density graph.
example <-data.frame(source=c("Leaflitter","Leaflitter","Leaflitter","Leaflitter",
"Leaflitter","Leaflitter","Leaflitter","Leaflitter","Leaflitter","Leaflitter",
"Biofilm","Biofilm","Biofilm","Biofilm","Biofilm","Biofilm","Biofilm","Biofilm",
"Biofilm","Biofilm","Algae","Algae","Algae","Algae","Algae","Algae","Algae","Algae",
"Algae","Algae"), n=c(1,2,3,4,5,6,7,8,9,10,1,2,3,4,5,6,7,8,9,10,1,2,3,4,5,6,7,8,9,10),
density=c(0.554786934, 0.650578421, 0.039317168, 0.53537613,0.435081982,0.904056941,0.556284164,0.855319434,
0.399169622,0.570246304,0.076722032,0.257427999,0.172736928,0.447424473,0.520976948,0.011720494,0.311348655,
0.120698996,0.016336661,0.331741377, 0.368491034,0.09199358,0.787945904,0.017199397,0.04394107,
0.084222564,0.132367181,0.023981569,0.584493716,0.098012319))
example
One subgroup and quantiles
L <- filter(QPA_G_Feb17, source == "Leaflitter")
L <-as.data.frame(L)
Lq025 <- quantile(L$density, .025)
Lq975 <- quantile(L$density, .975)
ggplot(QPA_G_Feb17, aes(x=density, color=source)) +
labs(y="Density", x="Sorce contribution") +
geom_density(aes(linetype = source), size=1.2) +
scale_color_manual(values=c("#31a354", "#2c7fb8", "#d95f0e")) +
scale_linetype_manual(values = c("solid", "dotted", "longdash")) +
theme_classic()+
ylim(0, 5)+
theme(axis.text.y=element_text(angle=0, size=12, vjust=0.5, color="black")) +
theme(axis.text.x =element_text(angle=0, size=12, vjust=0.5, color="black")) +
theme(axis.title.x = element_text(color="black", size=14))+
theme(axis.title.y = element_text(color="black", size=14))
I would appreciate your help since I have looked in other forums, and there is information to highlight when there is only 1 line.
I think this data is a bit more representative of the data displayed in your plot:
set.seed(50)
QPA_G_Feb17 <- data.frame(density = c(rgamma(400, 2, 10),
rgamma(400, 2.25, 9),
rgamma(400, 5, 7)),
source = rep(c("Algae", "Biofilm", "Leaflitter"),
each = 400))
I find that when you are trying to do something complex or non-standard in ggplot, the best thing to do is calculate the data you wish to plot ahead of time. In this case, we can calculate the density curves and the cumulative densities, including their 0.025 and 0.975 quantiles, and putting them all in a data frame like this:
dens <- lapply(split(QPA_G_Feb17, QPA_G_Feb17$source),
function(x) density(x$density, from = 0, to = 1))
df <- do.call(rbind, mapply(function(x, y) {
data.frame(x = x$x, y = x$y, source = y)
}, dens, names(dens), SIMPLIFY = FALSE))
df <- df %>%
group_by(source) %>%
mutate(cdf = cumsum(y * mean(diff(x))),
lower = cdf < 0.025,
upper = cdf > 0.975)
Now it is easy to plot using geom_area:
ggplot(df, aes(x, y, color = source)) +
geom_area(data = df[df$lower,], aes(fill = source), alpha = 0.5,
position = "identity") +
geom_area(data = df[df$upper,], aes(fill = source), alpha = 0.5,
position = "identity") +
labs(y = "Density", x = "Source contribution") +
geom_line(aes(linetype = source), size = 1.2) +
scale_fill_manual(values = c("#31a354", "#2c7fb8", "#d95f0e")) +
scale_color_manual(values = c("#31a354", "#2c7fb8", "#d95f0e")) +
scale_linetype_manual(values = c("solid", "dotted", "longdash")) +
theme_classic() +
ylim(0, 5) +
xlim(0, 1) +
theme(axis.text.y = element_text(size = 12, vjust = 0.5),
axis.text.x = element_text(size = 12, vjust = 0.5),
axis.title.x = element_text(size = 14),
axis.title.y = element_text(size = 14))
Here, the 2.5% and 97.5% extremeties of each density curve are shaded below each line. The exception is in the "Leaflitter` line, which clearly extends out of the 0-1 range that has been plotted in your example.
I am trying to create a boxplot with a log y axis as I have some very small values and then some much higher values which do not work well in a boxplot with a continuous y axis. However, I have negative values which obviously do not work with a log scale. I was wondering if there was a way around this so that I can display my data on a boxplot which is still easy to interpret but has a more appropriate scale on the y axis.
p <- ggplot(data = Elstow.monthly.fluxes, aes(x = Month1, y = CH4.Flux)) + stat_boxplot(geom = "errorbar", linetype = 1, width = 0.5) + geom_boxplot() +
xlab(expression("Month")) + ylab(expression(~CH[4]~Flux~(µg~CH[4]~m^{-2}~d^{-1}))) +
scale_y_continuous(breaks = seq(-5000,40000,5000), limits = c(-5000,40000))+
theme(axis.text.x = element_text(colour = "black")) + theme(axis.text.y = element_text(colour =
"black")) +
theme(panel.background = element_rect("white", "black")) +
theme(panel.border = element_rect(colour = "black", fill=NA, size=0.5)) +
theme(axis.text = element_text(size = 12))+ theme(axis.title = element_text(size = 14))+
theme(axis.title.y = element_text(margin = margin(t = 0, r = 15, b = 0, l = 0))) +
theme(axis.title.x = element_text(margin = margin(t = 15, r = 0, b = 0, l = 0))) +
geom_hline(yintercept = 0, linetype ="dashed", colour = "black")
While you could indeed use the secondary axis to get the labels you want as Zhiqiang suggests, you could also use a transformation that fits your needs.
Consider the following skewed boxplots:
df <- data.frame(
x = rep(letters[1:2], each = 500),
y = rlnorm(1000) - 2
)
ggplot(df, aes(x, y)) +
geom_boxplot()
Instead, you could use the pseudo-log transformation to visualise your data:
ggplot(df, aes(x, y)) +
geom_boxplot() +
scale_y_continuous(trans = scales::pseudo_log_trans())
Alternatively, you could make any transformation you want. I personally like the inverse hyperbolic sine transformation, which is very much like the pseudo-log:
asinh_trans <- scales::trans_new(
"inverse_hyperbolic_sine",
transform = function(x) {asinh(x)},
inverse = function(x) {sinh(x)}
)
ggplot(df, aes(x, y)) +
geom_boxplot() +
scale_y_continuous(trans = asinh_trans)
I have a silly solution: trick the secondary axis to re-scale y axis. I do not have your data, just made up some numbers for the purpose of demonstration.
First convert y values as logy = log(y + 5000). When generating the graph, transform the values back to the original scale. I borrow the second axis to display the values. I am pretty sure others may have more elegant ways to do this.
I was lazy for not trying to find the right way to remove the primary y axis tick labels, just used breaks = c(0).
df<-data.frame(y = runif(33, min=-5000, max=40000),
x = rep(c("Aug", "Sep", "Oct"),33))
library(tidyverse)
df$logy = log(df$y+5000)
p <- ggplot(data = df, aes(x = x, y = logy)) +
stat_boxplot(geom = "errorbar", linetype = 1, width = 0.5) +
geom_boxplot() +
xlab(expression("Month")) +
ylab(expression(~CH[4]~Flux~(µg~CH[4]~m^{-2}~d^{-1}))) +
scale_y_continuous(sec.axis = sec_axis(~(exp(.) -5000),
breaks = c(-4000, 0, 5000, 10000, 20000, 40000)),
breaks = c(0))+
theme(axis.text.x = element_text(colour = "black")) +
theme(axis.text.y = element_text(colour = "black")) +
theme(panel.background = element_rect("white", "black")) +
theme(panel.border = element_rect(colour = "black", fill=NA, size=0.5)) +
theme(axis.text = element_text(size = 12))+
theme(axis.title = element_text(size = 14))+
theme(axis.title.y = element_text(margin = margin(t = 0, r = 15, b = 0, l = 0))) +
theme(axis.title.x = element_text(margin = margin(t = 15, r = 0, b = 0, l = 0))) +
geom_hline(yintercept = log(5000), linetype ="dashed", colour = "black")
p
coord_trans() is applied after the statistics are calculated (unlike scale). This can be combined with the pseudo_log_trans to cope with negatives.
library(plotly)
set.seed(1234)
dat <- data.frame(cond = factor(rep(c("A","B"), each=200)), rating = c(rnorm(200),rnorm(200, mean=500)))
pseudoLog <- scales::pseudo_log_trans(base = 10)
p <- ggplot(dat, aes(x=cond, y=rating)) + geom_boxplot() + coord_trans(y=pseudoLog)