Related
I have a dataframe where the x value (discrete) is present and want to include on the x-axis in the plot; however, its y value is NA
I still want to show the x value even though y is NA. Is there a way to do this in ggplot2?
Currently, it simply skips the first two rows that has the NA value.
ggplot(tChartDF()[['df']], aes(
x = factor(tChartDF()[['df']][['Rare event date']], levels = unique(tChartDF()[['df']][['Rare event date']])),
y = unlist(tChartDF()[['df']][['days_between']]),
)) +
geom_hline(yintercept = unlist(tChartDF()[['timeScaleCL']]), color = input$tChartCLColour, lwd = input$tChartCLWidth) +
geom_hline(yintercept = unlist(tChartDF()[['timeScaleUL']]), linetype = 'dashed', lwd = 1, color = 'red') +
geom_hline(yintercept = unlist(tChartDF()[['timeScaleLL']]), linetype = 'dashed', lwd = 1, color = 'red') +
scale_x_discrete(expand = c(0,0)) +
theme_classic() +
geom_line(aes(group = 1), lwd = input$tChartLineWidth, color= input$tChartLineColour) +
geom_point(size = input$tChartMarkerSize, color = input$tChartMarkerColour) +
labs(title = input$tChartPlotTitle, x = input$tChartPlotXLabel, y = input$tChartPlotYLabel) +
theme(
plot.title = element_text(size = 24, face = 'bold', family = 'Arial', hjust = 0.5),
plot.margin = margin(0, 1, 0, 0, "cm"),
axis.title = element_text(size = 20, face = 'bold', family = 'Arial'),
axis.text = element_text(size = 16, face = 'bold', family = 'Arial'),
axis.text.x = element_text(angle = as.numeric(input$tChartXOrientation), vjust = 0.5),
axis.ticks.length = unit(.25, 'cm'),
) +
coord_cartesian(clip = 'off')
As seen, it only starts plotting at date: 2022/12/15 (ignoring the previous values in the table) columns y and mr have the NA values.
For the plot, I only care about the first two columns (Rare events and days_between). I tried selecting only those two columns and plotting but it still ignores the first two rows.
Desired result:
If we start with something like
mt <- mtcars
mt$mpg[c(3,6,9)] <- NA
and plot the line as in
ggplot(mt, aes(disp, mpg)) +
geom_line()
we don't see the missing points (not a surprise). We can add them this way:
transform(mt, mpg2 = ifelse(is.na(mpg), max(mpg, na.rm = TRUE) + 1, mpg)) |>
ggplot(aes(disp, mpg)) +
geom_line() +
geom_point(aes(y = mpg2), data = ~ subset(., is.na(mpg)), shape = 1)
This can easily be adapted to be at the bottom, using different shapes/colors, perhaps even on an explicitly-gray background (top/bottom ribbon).
I am trying to generate overlay density plots over time, comparing densities of males vs. females. Here is my output:
I am following the Australian athletes height example from https://cran.r-project.org/web/packages/ggridges/vignettes/gallery.html.
Here is my code:
ggplot(math_dat, aes(x = order_math, y = time, color = gender, point_color = gender, fill = gender)) +
geom_density_ridges(
jittered_points = TRUE, scale = .95, rel_min_height = .01,
point_shape = "|", point_size = 3, size = 0.25,
position = position_points_jitter(height = 0)
) +
scale_y_discrete(expand = c(0, 0)) +
scale_x_continuous(expand = c(0, 0), name = "Rankings") +
scale_fill_manual(values = c("#D55E0050", "#0072B250"), labels = c("female", "male")) +
scale_color_manual(values = c("#D55E00", "#0072B2"), guide = "none") +
scale_discrete_manual("point_color", values = c("#D55E00", "#0072B2"), guide = "none") +
coord_cartesian(clip = "off") +
guides(fill = guide_legend(
override.aes = list(
fill = c("#D55E00A0", "#0072B2A0"),
color = NA, point_color = NA)
)
) +
ggtitle("Ranks over time") +
theme_ridges(center = TRUE)
My problem is I am unable to generate any Y axis tick values and the example doesn't display any either. Any ideas how to get Y axis tick marks to display?
Here is some sample data similar to mine:
## generating dataset
order_math<-c(1,2,1,2,3,3,1,2,3,1,2,3)
gender<-c("M","F","M","M","M","F","F","M","F","M","M","F")
time<-c(1,1,2,3,3,2,1,2,3,2,3,1)
sample<-data.frame(order_math,gender,time)
UPdate:
After #Tomasu's suggestions I have updated my code, but it does not run:
ggplot(math_dat, aes(x = order_math, y = time, color = gender, point_color = gender, fill = gender)) +
geom_density_ridges(
jittered_points = TRUE, scale = .95, rel_min_height = .01,
point_shape = "|", point_size = 3, size = 0.25,
position = position_points_jitter(height = 0)
) +
scale_y_reverse(limits = c(1000, 500, 100),expand = c(0, 0)) +
scale_x_continuous(expand = c(0, 0), name = "Rankings") +
scale_fill_manual(values = c("#D55E0050", "#0072B250"), labels = c("female", "male")) +
scale_color_manual(values = c("#D55E00", "#0072B2"), guide = "none") +
scale_discrete_manual("point_color", values = c("#D55E00", "#0072B2"), guide = "none") +
coord_cartesian(clip = "off") +
guides(fill = guide_legend(
override.aes = list(
fill = c("#D55E00A0", "#0072B2A0"),
color = NA, point_color = NA)
)
) +
ggtitle("Ranks over time") +
theme_ridges(center = TRUE)+
theme(
axis.ticks = element_line(size=0.5), # turn ticks back on
axis.ticks.length = grid::unit(5, "pt"), # set length
axis.ticks.y = element_line(colour = "red"), # define tick line color
axis.text.y = element_text(vjust = .4) # center text with tick
)
An easy solution to this problem would be to use a theme_ that includes the axis ticks as theme_ridges() has them turned off. Just removing that theme all together and using the base ggplot2 theme achieves the desired outcome.
However, let's say we still want to use theme_ridges() and just turn ticks back on. This can be achieved with a theme() edit after the theme_ridges().
I'm using the example in the link provided as I couldn't get your sample data to work properly.
library(ggplot2)
library(ggplot2movies)
library(ggridges)
ggplot(movies[movies$year>1912,], aes(x = length, y = year, group = year)) +
geom_density_ridges(scale = 10, size = 0.25, rel_min_height = 0.03) +
theme_ridges() +
theme(
axis.ticks = element_line(size=0.5), # turn ticks back on
axis.ticks.length = grid::unit(5, "pt"), # set length
axis.ticks.y = element_line(colour = "red"), # define tick line color
axis.text.y = element_text(vjust = .4) # center text with tick
) +
scale_x_continuous(limits = c(1, 200), expand = c(0, 0)) +
scale_y_reverse(
breaks = c(2000, 1980, 1960, 1940, 1920, 1900),
expand = c(0, 0)
) +
coord_cartesian(clip = "off")
Created on 2021-05-11 by the reprex package (v1.0.0)
I think your problem is that you need to specify the group.
Related thread: geom_density_ridges requires the following missing aesthetics: y
Extending on code from user tomasu's answer +1
library(ggridges)
library(ggplot2)
order_math<-c(1,2,1,2,3,3,1,2,3,1,2,3)
gender<-c("M","F","M","M","M","F","F","M","F","M","M","F")
time<-c(1,1,2,3,3,2,1,2,3,2,3,1)
sample<-data.frame(order_math,gender,time)
ggplot(sample, aes(x = order_math, y = time, group = time,
color = gender, point_color = gender, fill = gender)) +
geom_density_ridges() +
theme(
axis.ticks = element_line(size=0.5), # turn ticks back on
axis.ticks.length = grid::unit(5, "pt"), # set length
axis.ticks.y = element_line(colour = "red"), # define tick line color
axis.text.y = element_text(vjust = .4) # center text with tick
)
#> Picking joint bandwidth of 0.555
Created on 2021-05-12 by the reprex package (v2.0.0)
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 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)
I am trying to generate a barplot with dual Y-axis and error bars. I have successfully generated a plot with error bars for one variable but I don't know how to add error bars for another one. My code looks like this. Thanks.
library(ggplot2)
#Data generation
Year <- c(2014, 2015, 2016)
Response <- c(1000, 1100, 1200)
Rate <- c(0.75, 0.42, 0.80)
sd1<- c(75, 100, 180)
sd2<- c(75, 100, 180)
df <- data.frame(Year, Response, Rate,sd1,sd2)
df
# The errorbars overlapped, so use position_dodge to move them horizontally
pd <- position_dodge(0.7) # move them .05 to the left and right
png("test.png", units="in", family="Times", width=2, height=2.5, res=300) #pointsize is font size| increase image size to see the key
ggplot(df) +
geom_bar(aes(x=Year, y=Response),stat="identity", fill="tan1", colour="black")+
geom_errorbar(aes(x=Year, y=Response, ymin=Response-sd1, ymax=Response+sd1),
width=.2, # Width of the error bars
position=pd)+
geom_line(aes(x=Year, y=Rate*max(df$Response)),stat="identity",color = 'red', size = 2)+
geom_point(aes(x=Year, y=Rate*max(df$Response)),stat="identity",color = 'black',size = 3)+
scale_y_continuous(name = "Left Y axis", expand=c(0,0),limits = c(0, 1500),breaks = seq(0, 1500, by=500),sec.axis = sec_axis(~./max(df$Response),name = "Right Y axis"))+
theme(
axis.title.y = element_text(color = "black"),
axis.title.y.right = element_text(color = "blue"))+
theme(
axis.text=element_text(size=6, color = "black",family="Times"),
axis.title=element_text(size=7,face="bold", color = "black"),
plot.title = element_text(color="black", size=5, face="bold.italic",hjust = 0.5,margin=margin(b = 5, unit = "pt")))+
theme(axis.text.x = element_text(angle = 360, hjust = 0.5, vjust = 1.2,color = "black" ))+
theme(axis.line = element_line(size = 0.2, color = "black"),axis.ticks = element_line(colour = "black", size = 0.2))+
theme(axis.ticks.length = unit(0.04, "cm"))+
theme(plot.margin=unit(c(1,0.1,0.1,0.4),"mm"))+
theme(axis.title.y = element_text(margin = margin(t = 0, r = 4, b = 0, l = 0)))+
theme(axis.title.x = element_text(margin = margin(t = 0, r = 4, b = 2, l = 0)))+
theme(
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank())+
ggtitle("SRG3")+
theme(legend.position="top")+
theme( legend.text=element_text(size=4),
#legend.justification=c(2.5,1),
legend.key = element_rect(size = 1.5),
legend.key.size = unit(0.3, 'lines'),
legend.position=c(0.79, .8), #width and height
legend.direction = "horizontal",
legend.title=element_blank())
dev.off()
and my plot is as follows:
A suggestion for future questions: your example is far from being a minimal reproducible example. All the visuals an the annotations are not related to your problem but render the code overly complex which makes it harder for others to work with it.
The following would be sufficient:
ggplot(df) +
geom_bar(aes(x = Year, y = Response),
stat = "identity", fill = "tan1",
colour = "black") +
geom_errorbar(aes(x = Year, ymin = Response - sd1, ymax = Response + sd1),
width = .2,
position = pd) +
geom_line(aes(x = Year, y = Rate * max(df$Response)),
color = 'red', size = 2) +
geom_point(aes(x = Year, y = Rate * max(df$Response)),
color = 'black', size = 3)
(Notice that I've removed stat = "identity" in all geom_s because this is set by default. Furthermore, y is not a valid aestetic for geom_errorbar() so I omitted that, too.)
Assuming that the additional variable you would like to plot error bars for is Rate * max(df$Response)) and that the relevant standard deviation is sd2, you may simply append
+ geom_errorbar(aes(x = Year, ymin = Rate * max(df$Response) - sd2,
ymax = Rate * max(df$Response) + sd2),
colour = "green",
width = .2)
to the code chunk above. This yields the output below.