问题
I have xy
grouped data that I'm plotting using R
's ggplot2
geom_violin
adding regression trend lines:
Here are the data:
library(dplyr)
library(plotly)
library(ggplot2)
set.seed(1)
df <- data.frame(value = c(rnorm(500,8,1),rnorm(600,6,1.5),rnorm(400,4,0.5),rnorm(500,2,2),rnorm(400,4,1),rnorm(600,7,0.5),rnorm(500,3,1),rnorm(500,3,1),rnorm(500,3,1)),
age = c(rep("d3",500),rep("d8",600),rep("d24",400),rep("d3",500),rep("d8",400),rep("d24",600),rep("d3",500),rep("d8",500),rep("d24",500)),
group = c(rep("A",1500),rep("B",1500),rep("C",1500))) %>%
dplyr::mutate(time = as.integer(age)) %>%
dplyr::arrange(group,time) %>%
dplyr::mutate(group_age=paste0(group,"_",age))
df$group_age <- factor(df$group_age,levels=unique(df$group_age))
And my current plot:
ggplot(df,aes(x=group_age,y=value,fill=age,color=age,alpha=0.5)) +
geom_violin() + geom_boxplot(width=0.1,aes(fill=age,color=age,middle=mean(value))) +
geom_smooth(data=df,mapping=aes(x=group_age,y=value,group=group),color="black",method='lm',size=1,se=T) + theme_minimal()
My questions are:
- How do I get rid of the
alpha
part of thelegend
? - I would like the
x-axis
ticks
to bedf$group
rather thandf$group_age
, which means atick
per eachgroup
at the center of thatgroup
where the label isgroup
. Consider a situation where not allgroup
s have allage
s - for example, if a certaingroup
has only two of theage
s and I'm pretty sureggplot
will only present only these twoage
s, I'd like thetick
to still be centered between their twoage
s.
One more question:
It would also be nice to have the p-values of each fitted slope plotted on top of each group
.
I tried:
library(ggpmisc)
my.formula <- value ~ group_age
ggplot(df,aes(x=group_age,y=value,fill=age,color=age,alpha=0.5)) +
geom_violin() + geom_boxplot(width=0.1,aes(fill=age,color=age,middle=mean(value))) +
geom_smooth(data=df,mapping=aes(x=group_age,y=value,group=group),color="black",method='lm',size=1,se=T) + theme_minimal() +
stat_poly_eq(formula = my.formula,aes(label=stat(p.value.label)),parse=T)
But I get the same plot as above with the following warning
message:
Warning message:
Computation failed in `stat_poly_eq()`:
argument "x" is missing, with no default
回答1:
geom_smooth()
fits a line, while stat_poly_eqn()
issues an error. A factor
is a categorical variable with unordered levels. A trend against a factor is undefined. geom_smooth()
may be taking the levels and converting them to "arbitrary" numerical values, but these values are just indexes rather than meaningful values.
To obtain a plot similar to what is described in the question but using code that provides correct linear regression lines and the corresponding p-values I would use the code below. The main change is that the numerical variable time
is mapped to x
making the fitting of a regression a valid operation. To allow for a linear fit an x-scale with a log10 transformation is used, with breaks and labels at the ages for which data is available.
library(dplyr)
library(ggplot2)
library(ggpmisc)
set.seed(1)
df <-
data.frame(
value = c(
rnorm(500, 8, 1), rnorm(600, 6, 1.5), rnorm(400, 4, 0.5),
rnorm(500, 2, 2), rnorm(400, 4, 1), rnorm(600, 7, 0.5),
rnorm(500, 3, 1), rnorm(500, 3, 1), rnorm(500, 3, 1)
),
age = c(
rep("d3", 500), rep("d8", 600), rep("d24", 400),
rep("d3", 500), rep("d8", 400), rep("d24", 600),
rep("d3", 500), rep("d8", 500), rep("d24", 500)
),
group = c(rep("A", 1500), rep("B", 1500), rep("C", 1500))
) %>%
mutate(time = as.integer(gsub("d", "", age))) %>%
arrange(group, time) %>%
mutate(age = factor(age, levels = c("d3", "d8", "d24")),
group = factor(group))
my_formula = y ~ x
ggplot(df, aes(x = time, y = value)) +
geom_violin(aes(fill = age, color = age), alpha = 0.3) +
geom_boxplot(width = 0.1,
aes(color = age), fill = NA) +
geom_smooth(color = "black", formula = my_formula, method = 'lm') +
stat_poly_eq(aes(label = stat(p.value.label)),
formula = my_formula, parse = TRUE,
npcx = "center", npcy = "bottom") +
scale_x_log10(name = "Age", breaks = c(3, 8, 24)) +
facet_wrap(~group) +
theme_minimal()
Which creates the following figure:
回答2:
Here is a solution. The alpha - legend issue is easy. Anything you place into the aes()
functioning will get placed in a legend. This feature should be used when you want a feature of the data to be used as an aestetic. Putting alpha
outside of an aes
will remove it from the legend.
I'm not sure the x legend is what you wanted but i did it manually so it should be easy to configure.
Regarding the p.values, i did separate linear regressions and store the p.value in three different vectors which can be called into the ggplot using the annotate. For two of the groups the p.value was <.001 so the round
functioning will round it to 0. Therefore, i just added p. <.001
Good luck with this!
library(dplyr)
library(ggplot2)
set.seed(1)
df <- data.frame(value = c(rnorm(500,8,1),rnorm(600,6,1.5),rnorm(400,4,0.5),rnorm(500,2,2),rnorm(400,4,1),rnorm(600,7,0.5),rnorm(500,3,1),rnorm(500,3,1),rnorm(500,3,1)),
age = c(rep("d3",500),rep("d8",600),rep("d24",400),rep("d3",500),rep("d8",400),rep("d24",600),rep("d3",500),rep("d8",500),rep("d24",500)),
group = c(rep("A",1500),rep("B",1500),rep("C",1500))) %>%
dplyr::mutate(time = as.integer(age)) %>%
dplyr::arrange(group,time) %>%
dplyr::mutate(group_age=paste0(group,"_",age))
df$group_age <- factor(df$group_age,levels=unique(df$group_age))
mod1 <- lm(value ~ time,df\[df$group == 'A',\])
mod1 <- summary(mod1)$coefficients\[8\] %>% round(2)
mod2 <- lm(value ~ time,df\[df$group == 'B',\])
mod2 <- summary(mod2)$coefficients\[8\] %>% round(2)
mod3 <- lm(value ~ time,df\[df$group == 'C',\])
mod3 <- summary(mod3)$coefficients\[8\] %>% round(2)
ggplot(df,aes(x=group_age,y=value,fill=age,color=age)) +
geom_violin(alpha=0.5) +
geom_boxplot(width=0.1,aes(fill=age,color=age,middle=mean(value))) +
geom_smooth(mapping=aes(x=group_age,y=value,group=group),color="black",method='lm',size=1,se=T) +
scale_x_discrete(labels = c('','A','','','B','','','C','')) +
annotate('text',x = 2,y = -1,label = paste('pvalue: <.001')) +
annotate('text',x = 6,y = 10,label = paste('pvalue: <.001')) +
annotate('text',x = 8,y = -1.2,label = paste('pvalue:',mod3))+
theme_minimal()
来源:https://stackoverflow.com/questions/62974766/adding-trend-lines-across-groups-and-setting-tick-labels-in-a-grouped-violin-plo