I have the following ggplot code that renders the box plot show below.
ggplot(comparisonData, aes(Group,score)) +
geom_boxplot(notch = TRUE, varwidth = TRUE, aes(colour = Group)) +
geom_jitter(width = 0.2, aes(colour = Group)) +
theme(legend.position = "none") +
labs(title="User Engagement Score", x="Condition", y="Score (max 140)")
In this plot I want the groups 1 and 2 on the x-axis to be renamed as "Stealth" and "Non-stealth", but I am not able to find a way to do so. Is it possible without changing the group names in data?
You can change the labels via the scale, e.g.
library(tidyverse)
library(palmerpenguins)
penguins %>%
na.omit() %>%
mutate(species = factor(ifelse(species == "Adelie", 1, 2))) %>%
ggplot(aes(x = species, y = bill_length_mm)) +
geom_boxplot(aes(colour = species), notch = TRUE, varwidth = TRUE) +
geom_jitter(width = 0.2, aes(colour = species)) +
theme(legend.position = "none") +
labs(title="User Engagement Score", x="Condition", y="Score (max 140)") +
scale_x_discrete(label = c("Stealth", "Non-stealth"))
Related
In order to make a dynamic visualization, for example in a dashboard, I want to display the label colors (percentages or totals) depending on their real values in black or white.
As you can see from my reprex below, I changed the color of the label with the highest percentage manually to black, in order gain a better visability.
Is there a was, to automatically implement the label color? The label with the highest percentage corresponding should always be black, if data is changing over time.
library(ggplot2)
library(dplyr)
set.seed(3)
reviews <- data.frame(review_star = as.character(sample.int(5,400, replace = TRUE)),
stars = 1)
df <- reviews %>%
group_by(review_star) %>%
count() %>%
ungroup() %>%
mutate(perc = `n` / sum(`n`)) %>%
arrange(perc) %>%
mutate(labels = scales::percent(perc))
ggplot(df, aes(x = "", y = perc, fill = review_star)) +
geom_col(color = "black") +
geom_label(aes(label = labels), color = c( "white", "white","white",1,"white"),
position = position_stack(vjust = 0.5),
show.legend = FALSE) +
guides(fill = guide_legend(title = "Answer")) +
scale_fill_viridis_d() +
coord_polar(theta = "y") +
theme_void()
you can set the colors using replace(rep('white', nrow(df)), which.max(df$perc), 'black').
ggplot(df, aes(x = "", y = perc, fill = review_star)) +
geom_col(color = "black") +
geom_label(aes(label = labels),
color = replace(rep('white', nrow(df)), which.max(df$perc), 'black'),
position = position_stack(vjust = 0.5),
show.legend = FALSE) +
guides(fill = guide_legend(title = "Answer")) +
scale_fill_viridis_d() +
coord_polar(theta = "y") +
theme_void()
I have been trying to access the value of ..count.. in ggplot2 is there anyway to access this value? At the moment I'm getting the following error:
Error: Aesthetics must be valid computed stats. Problematic
aesthetic(s): label = ..count... Did you map your stat in the wrong
layer?
How can I access that value that has been computed before? Here's the code:
transfusion %>%
mutate(Group = ifelse(whether.he.she.donated.blood.in.March.2007 == 0, "Didn't donate", "Donated")) %>%
ggplot(aes(x=Group, fill = Group)) +
scale_y_continuous(breaks = seq(0, 500, by = 100)) +
ylab("Count of people") +
ggtitle("People who donated blood in march 2007") +
geom_bar(aes(y = (..count..))) +
geom_label(aes(label = ..count..))
This is a solution using ..count... All you have to do is to ask geom_label to compute it.
library(dplyr)
library(ggplot2)
transfusion %>%
mutate(Group = ifelse(whether.he.she.donated.blood.in.March.2007 == 0, "Didn't donate", "Donated")) %>%
ggplot(aes(x = Group, fill = Group)) +
geom_bar(position = "dodge") +
geom_label(stat = 'count', aes(label = ..count..),
vjust = -0.1,
show.legend = FALSE) +
scale_y_continuous(breaks = seq(0, 500, by = 100)) +
ylab("Count of people") +
ggtitle("People who donated blood in march 2007") +
theme(plot.margin = margin(2, 0.8, 2, 0.8))
Data
set.seed(1234)
transfusion <- data.frame(
whether.he.she.donated.blood.in.March.2007 = rbinom(800, 1, prob = c(0.3, 0.7))
)
Using mtcars as example data this can be achieved by using stat = "count" inside geom_label and using after_stat (new in ggplot2 3.3.0) to map count on label
library(ggplot2)
#mutate(Group = ifelse(whether.he.she.donated.blood.in.March.2007 == 0, "Didn't donate", "Donated")) %>%
ggplot(mtcars, aes(x = factor(cyl), fill = factor(cyl))) +
#scale_y_continuous(breaks = seq(0, 500, by = 100)) +
#ylab("Count of people") +
#ggtitle("People who donated blood in march 2007") +
geom_bar() +
geom_label(aes(label = after_stat(count)), stat = "count")
Created on 2020-04-15 by the reprex package (v0.3.0)
I would like to add summary statistics (e.g. mean) to the boxplot which have two factors. I have tried this:
library(ggplot2)
ggplot(ToothGrowth, aes(x = factor(dose), y = len)) +
stat_boxplot(geom = "errorbar", aes(col = supp, fill=supp), position = position_dodge(width = 0.85)) +
geom_boxplot(aes(col = supp, fill=supp), notch=T, notchwidth = 0.5, outlier.size=2, position = position_dodge(width = 0.85)) +
stat_summary(fun.y=mean, aes(supp,dose), geom="point", shape=20, size=7, color="violet", fill="violet") +
scale_color_manual(name = "SUPP", values = c("blue", "darkgreen")) +
scale_fill_manual(name = "SUPP", values = c("lightblue", "green"))
I got this picture:
It is possible somehow put the sample size of each box (e.g. top of the whiskers)? I have tried this:
ggplot(ToothGrowth, aes(x = factor(dose), y = len)) +
stat_boxplot(geom = "errorbar", aes(col = supp, fill=supp), position = position_dodge(width = 0.85)) +
geom_boxplot(aes(col = supp, fill=supp), notch=T, notchwidth = 0.5, outlier.size=2, position = position_dodge(width = 0.85)) +
stat_summary(fun.y=mean,aes(supp,dose),geom="point", shape=20, size=7, color="violet", fill="violet") +
scale_color_manual(name = "SUPP", values = c("blue", "darkgreen")) +
scale_fill_manual(name = "SUPP", values = c("lightblue", "green")) +
geom_text(data = ToothGrowth,
group_by(dose, supp),
summarize(Count = n(),
q3 = quantile(ToothGrowth, 0.75),
iqr = IQR(ToothGrowth),
aes(x= dose, y = len,label = paste0("n = ",Count, "\n")), position = position_dodge(width = 0.75)))
You can state the aesthetics just once by putting them in the main ggplot call and then they will apply to all of the geom layers: ggplot(ToothGrowth, aes(x = factor(dose), y = len, color=supp, fill=supp))
For the count of observations: The data summary step in geom_text isn't coded properly. Also, to set len (the y-value) for the text placement, the summarize function needs to output values for len.
To add the mean values in the correct locations on the x-axis, use stat_summary with the exact same aesthetics as the other geoms and stats. I've overridden the color aesthetic by setting the color to yellow so that the point markers will be visible on top of the box plot fill colors.
The code to implement the plot is below:
library(tidyverse)
pd = position_dodge(0.85)
ggplot(ToothGrowth, aes(x = factor(dose), y = len, color=supp, fill=supp)) +
stat_boxplot(geom = "errorbar", position = pd) +
geom_boxplot(notch=TRUE, notchwidth=0.5, outlier.size=2, position=pd) +
stat_summary(fun.y=mean, geom="point", shape=3, size=2, colour="yellow", stroke=1.5,
position=pd, show.legend=FALSE) +
scale_color_manual(name = "SUPP", values = c("blue", "darkgreen")) +
scale_fill_manual(name = "SUPP", values = c("lightblue", "green")) +
geom_text(data = ToothGrowth %>% group_by(dose, supp) %>%
summarize(Count = n(),
len=max(len) + 0.05 * diff(range(ToothGrowth$len))),
aes(label = paste0("n = ", Count)),
position = pd, size=3, show.legend = FALSE) +
theme_bw()
Note that the notch goes outside the hinges for all of the box plots. Also, having the sample size just above the maximum of each boxplot seems distracting and unnecessary to me. You could place all of the text annotations at the bottom of the plot like this:
geom_text(data = ToothGrowth %>% group_by(dose, supp) %>%
summarize(Count = n()) %>%
ungroup %>%
mutate(len=min(ToothGrowth$len) - 0.05 * diff(range(ToothGrowth$len))),
aes(label = paste0("n = ", Count)),
position = pd, size=3, show.legend = FALSE) +
Using mtcars as an example, I've produced some violin plots. I wanted to add two things to this chart:
for each group, list n
for each group, sum a third variable (e.g. wt)
I can do (1) with the geom_text code below although (n) is actually plotted on the x axis rather than off to the side.
But I can't work out how to do (2).
Any help much appreciated!
library(ggplot2)
library(gridExtra)
library(ggthemes)
result <- mtcars
ggplot(result, aes(x = gear, y = drat, , group=gear)) +
theme_tufte(base_size = 15) + theme(line=element_blank()) +
geom_violin(fill = "white") +
geom_boxplot(fill = "black", alpha = 0.3, width = 0.1) +
ylab("drat") +
xlab("gear") +
coord_flip()+
geom_text(stat = "count", aes(label = ..count.., y = ..count..))
You can add both of these annotations by creating them in your dataframe temporarily prior to graphing. Using the dplyr package, you can create two new columns, one with the count for each group, and one with the sum of wt for each group. This can then be piped directly into your ggplot using %>% (alternatively, you could save the new dataset and insert it into ggplot the way you have it). Then with some minor edits to your geom_text call and adding a second one, we can create the plot you want. The code looks like this:
library(ggplot2)
library(gridExtra)
library(ggthemes)
library(magrittr)
library(dplyr)
result <- mtcars
result %>%
group_by(gear) %>%
mutate(count = n(), sum_wt = sum(wt)) %>%
ggplot(aes(x = gear, y = drat, , group=gear)) +
theme_tufte(base_size = 15) + theme(line=element_blank()) +
geom_violin(fill = "white") +
geom_boxplot(fill = "black", alpha = 0.3, width = 0.1) +
ylab("drat") +
xlab("gear") +
coord_flip()+
geom_text(aes(label = paste0("n = ", count),
x = (gear + 0.25),
y = 4.75)) +
geom_text(aes(label = paste0("sum wt = ", sum_wt),
x = (gear - 0.25),
y = 4.75))
The new graph looks like this:
Alternatively, if you create a summary data frame named result_sum, then you can manually add that into the geom_text calls.
result <- mtcars %>%
mutate(gear = factor(as.character(gear)))
result_sum <- result %>%
group_by(gear) %>%
summarise(count = n(), sum_wt = sum(wt))
ggplot(result, aes(x = gear, y = drat, , group=gear)) +
theme_tufte(base_size = 15) +
theme(line=element_blank()) +
geom_violin(fill = "white") +
geom_boxplot(fill = "black", alpha = 0.3, width = 0.1) +
ylab("drat") +
xlab("gear") +
coord_flip()+
geom_text(data = result_sum, aes(label = paste0("n = ", count),
x = (as.numeric(gear) + 0.25),
y = 4.75)) +
geom_text(data = result_sum, aes(label = paste0("sum wt = ", sum_wt),
x = (as.numeric(gear) - 0.25),
y = 4.75))
This gives you this:
The benefit to this second method is that the text isn't bold like in the first graph. The bold effect occurs in the first graph due to the text being printed over itself for all observations in the dataframe.
Thanks to those who helped.... I used this in the end which plots the calculated values, one set of classes being text based so using vjust to position the vertical offset.
thanks again!
library(ggplot2)
library(gridExtra)
library(ggthemes)
results <- mtcars
results$gear <- as.factor(as.character(results$gear)) #Turn 'gear' to text to simulate classes, then factorise
result_sum <- results %>%
group_by(gear) %>%
summarise(count = n(), sum_wt = sum(wt))
ggplot(results, aes(x = gear, y = drat, group=gear)) +
theme_tufte(base_size = 15) + theme(line=element_blank()) +
geom_violin(fill = "white") +
geom_boxplot(fill = "black", alpha = 0.3, width = 0.1) +
ylab("drat") +
xlab("gear") +
coord_flip()+
geom_text(data = result_sum, aes(label = paste0("n = ", count), x = (gear), vjust= 0, y = 5.25)) +
geom_text(data = result_sum, aes(label = paste0("sum wt = ", round(sum_wt,0)), x = (gear), vjust= -2, y = 5.25))
I'm plotting a stacked bar graph and use geom_text to insert the value and name of each stack. The problem is some stacks are very small/narrow, so that the text of two stacks overlap each other and hence is not very readable. How can I modify the code to solve this issue.
Type<-c("ddddddddddd","ddddddddddd","bbbbbbbbbbbbb","ddddddddddd","eeeeeeeeeeeeee","bbbbbbbbbbbbb","ddddddddddd","bbbbbbbbbbbbb","ddddddddddd",
"eeeeeeeeeeeeee","mmmmmmmmmmmmmmmmmmm","bbbbbbbbbbbbb","ddddddddddd","bbbbbbbbbbbbb","eeeeeeeeeeeeee")
Category<-c("mmmmm","mmmmm","gggggggggggggggggg","ffffffffffff","ffffffffffff","ffffffffffff","sanddddddddd","sanddddddddd","yyyyyyyyyyy",
"yyyyyyyyyyy","yyyyyyyyyyy","sssssssssssssss","sssssssssssssss","sssssssssssssss","ttttttttttttt")
Frequency<-c(4,1,30,7,127,11,1,1,6,9,1,200,3,4,5)
Data <- data.frame(Type, Category, Frequency)
p <- ggplot(Data, aes(x = Type, y = Frequency)) +
geom_bar(aes(fill = Category), stat="identity", show.legend = FALSE) +
geom_text(aes(label = Frequency), size = 3) +
geom_text(aes(label = Category), size = 3)
Considering your data, a facetted plot might be a better approach:
# summarise your data
library(dplyr)
d1 <- Data %>%
mutate_each(funs(substr(.,1,2)),Type,Category) %>%
group_by(Type,Category) %>%
summarise(Freq = sum(Frequency)) %>%
mutate(lbl = paste(Category,Freq)) # create a label by pasting the 'Category' and the 'Freq' variables together
# plot
ggplot(d1, aes(x = Category, y = Freq, fill = Category)) +
geom_bar(stat="identity", width = 0.7, position = position_dodge(0.8)) +
geom_text(aes(label = lbl), angle = 90, size = 5, hjust = -0.1, position = position_dodge(0.8)) +
scale_y_continuous(limits = c(0,240)) +
guides(fill = FALSE) +
facet_grid(.~Type, scales = "free", space = "free") +
theme_bw(base_size = 14)
which gives:
In the above plot I shortened the labels on purpose. If you don't want to do that, you could consider this:
d2 <- Data %>%
group_by(Type,Category) %>%
summarise(Freq = sum(Frequency)) %>%
mutate(lbl = paste(Category,Freq))
ggplot(d2, aes(x = Category, y = Freq, fill = Category)) +
geom_bar(stat="identity", width = 0.7, position = position_dodge(0.8)) +
geom_text(aes(y = 5, label = lbl), alpha = 0.6, angle = 90, size = 5, hjust = 0, position = position_dodge(0.8)) +
scale_y_continuous(limits = c(0,240)) +
guides(fill = FALSE) +
facet_grid(.~Type, scales = "free", space = "free") +
theme_bw(base_size = 14) +
theme(axis.text.x = element_blank(),
axis.ticks.x = element_blank())
which gives: