I have a plot i wish to add another layer to
Th plot is below. I want to overlay another polar plot on it to see that the numbers "match up"
In the example below I have create the plot for one species of the iris dataset. I would like to overlay another plot of a different species
Thank you for your time
library(ggplot2)
library(dplyr)
mydf <- iris
plot.data <- tidyr::gather(mydf,key = attribute ,value = avg_score, Sepal.Length:Petal.Width)
plot.data <- plot.data %>%
filter(Species == 'setosa') %>%
group_by(attribute) %>%
summarise(attr_mean = mean(avg_score))
ggplot(plot.data, aes(x=attribute, y = attr_mean, col = attribute)) +
geom_bar(stat = "identity", fill = 'white') +
coord_polar(theta = "x") +
theme_bw()
This is quite the pedestrian way of doing things.
plot.setosa <- plot.data %>%
filter(Species == 'setosa') %>%
group_by(attribute) %>%
summarise(attr_mean = mean(avg_score))
plot.virginica <- plot.data %>%
filter(Species == 'virginica') %>%
group_by(attribute) %>%
summarise(attr_mean = mean(avg_score))
ggplot(plot.setosa, aes(x=attribute, y = attr_mean, col = attribute)) +
geom_bar(stat = "identity", fill = 'blue', alpha = 0.25) +
geom_bar(data = plot.virginica, stat = "identity", fill= "green", alpha = 0.25,
aes(x = attribute, y = attr_mean, col = attribute)) +
coord_polar(theta = "x") +
theme_bw()
And a slightly less pedestrian.
xy <- plot.data %>%
group_by(Species, attribute) %>%
summarise(attr_mean = mean(avg_score))
ggplot(xy, aes(x = attribute, y = attr_mean, color = attribute, fill = Species)) +
theme_bw() +
geom_bar(stat = "identity", alpha = 0.25) +
coord_polar(theta = "x")
Related
I have been attempting to add a label on top of each bar to represent the proportion that each ethnic group makes up in referrals.
For some reason I cannot get the labels to be placed at the top of each bar. How do I fix this?
My code below
freq <- df %>%
group_by(ethnicity) %>%
summarise(n = n()) %>%
mutate(f = round((n/sum(n)*100, 1))
df %>%
group_by(pathway) %>%
count(ethnicity) %>%
ggplot(aes(x = ethnicity, y = n , fill = pathway)) +
geom_bar(stat = "identity", position = "stack") +
geom_text(data = freq,
aes(x= ethnicity, y = f, label = f),
inherit.aes = FALSE) +
theme(legend.position = "bottom") +
scale_fill_manual(name = "",
values = c("light blue", "deepskyblue4"),
labels = "a", "b") +
xlab("") +
ylab("Number of Referrals") +
scale_y_continuous(breaks = seq(0, 2250, 250), expand = c(0,0)
Here is what it currently looks like
Since you are using the count as your y-axis position in geom_bar, you need to use the same thing in your geom_text to get the labels in the right place. Below is an example using mtcars dataset. Using vjust = -1 I put a little bit of space between the label and the bars to make it more legible and aesthetically pleasing.
library(tidyverse)
mtcars %>%
group_by(carb) %>%
summarise(n = n()) %>%
mutate(f = round(proportions(n) * 100, 1)) -> frq
mtcars %>%
group_by(gear) %>%
count(carb) -> df
df %>%
ggplot(aes(x = carb, y = n, fill = gear)) +
geom_bar(stat = "identity", position = "stack") +
geom_text(data = frq,
vjust = -1,
aes(x= carb, y = n, label = f),
inherit.aes = FALSE)
Created on 2022-10-31 by the reprex package (v2.0.1)
I am plotting a geom_point for several groups (Loc) and want in addition a line that indicates the mean of the points for each group. The groups should be ordered based on the mean of the Size for each group. I am trying to do this by reorder(Loc, Size.Mean) but it does not reorder.
ggplot(data,aes(Loc,Size,color=Loc)) +
geom_point() +
geom_point(data %>%
group_by(Loc) %>%
summarise(Size.Mean = mean(Size)),
mapping = aes(y = Size.Mean, x = reorder(Loc, Size.Mean)),
color = "black", shape = '-') +
theme_pubr(base_size=8) +
scale_y_continuous(trans="log10") +
theme(axis.text.x = element_text(angle = 90,hjust = 1)) +
theme(legend.position = "none")
ggplot orders discrete x ticks according to their level if the variable is a factor:
library(tidyverse)
iris_means <-
iris %>%
group_by(Species) %>%
summarise(mean = mean(Sepal.Length)) %>%
arrange(-mean)
iris %>%
mutate(Species = Species %>% factor(levels = iris_means$Species)) %>%
ggplot(aes(Species, Sepal.Length)) +
geom_point() +
geom_crossbar(data = iris_means, mapping = aes(y = mean, ymin = mean, ymax = mean), color = "red")
Created on 2021-09-10 by the reprex package (v2.0.1)
I am trying to create faceted geom_bar graphs with the following charactaristics:
The proportion of each answer per question is shown
Each bar is colored according to the response
The plot is faceted by question
I seem to be able to do any two of the conditions, but not all 3.
Question:
Is there a way to facet and calculate proportions using one variable, but colour/fill based on another variable?
Code:
df <- data.frame(
Question = rep(c('A', 'B', 'C'), each = 5),
Resp = sample(c('Yes', 'No', 'Unsure', NA), 15, T, c(0.3,0.3,0.3,0.1)),
stringsAsFactors = F
)
# Plot 1: grouping by question to get the right proportions, but has no colour
ggplot(df, aes(x = Resp, fill = Resp)) +
stat_count(aes(y = ..prop.., group = Question)) +
scale_y_continuous(labels = scales::percent_format()) +
facet_wrap(~ Question)
# Plot 2: grouping by response to get colour, but has wrong proportions
ggplot(df, aes(x = Resp, fill = Resp)) +
stat_count(aes(y = ..prop.., group = Resp)) +
scale_y_continuous(labels = scales::percent_format()) +
facet_wrap(~ Question)
Outputs:
This is a "ggplot2-only" option:
ggplot(df, aes(x = Resp)) +
geom_bar(aes(y = ..prop.., group = Question, fill = factor(..x..)), position = "dodge") +
scale_y_continuous(labels = scales::percent_format()) +
scale_fill_discrete(name = "Response", labels = c("No", "Unsure", "Yes", "NA")) +
facet_wrap(~ Question)
One way could be to calculate the proportions and then plot.
library(dplyr)
library(ggplot2)
df %>%
count(Question, Resp) %>%
group_by(Question) %>%
mutate(n = n/sum(n) * 100) %>%
ggplot() + aes(Resp, n, fill = Resp) +
geom_col() +
facet_wrap(~Question)
Plot without facet
df$n <- 1
df <- df %>% group_by(Question, Resp) %>% summarise(n = sum(n))
ggplot(df, aes(x=factor(Question), y=n, fill=Resp)) + geom_col()
Plot with facet
df <- df %>% group_by(Question, Resp) %>% summarise(n = sum(n)) %>% mutate(prop = n/5)
ggplot(df, aes(x=factor(Resp), y=prop, fill=Resp)) + geom_col() + facet_wrap(~Question)
I'm trying to plot an area with two different set of points with ggplot2 but I get always two different legends. I've read this and this but I still have two legends.
Below the code and the chart.
Thank you very much
library(ggplot2)
library(dplyr)
set.seed(1)
df <- data.frame(x = letters,
y = 1:26 +runif(26),
z = 2*(1:26) + runif(26),
jj = 1:26,
hh = 1:26*2,
x1 = 1:26)
some_names <- df %>%
filter(row_number() %% 10 == 1) %>%
select(x,x1)
p <- df %>%
ggplot(aes(x1)) +
geom_ribbon(aes(ymin = y, ymax = z, fill = "area")) +
geom_point(aes(y = jj, colour = "points1")) +
geom_point(aes(y = hh, colour = "points2")) +
scale_x_continuous(breaks = some_names %>% select(x1) %>% unlist %>% unname,
labels = some_names %>% select(x) %>% unlist %>% unname )
p + scale_fill_manual(name = "legend",
values = c("area" = "red","points1" = NA,"points2" = NA)) +
scale_colour_manual(name = "legend",
values = c("area" = NA ,"points1" = "blue","points2" = "purple"))
You could do something in the veins of
library(tidyverse)
packageVersion("ggplot2")
# [1] ‘2.2.1’
df %>%
gather(var, val, jj, hh) %>%
ggplot(aes(x1, val, ymin=y, ymax=z, color=var, fill=var)) +
geom_ribbon(color=NA) +
geom_point() +
scale_color_manual(values=c("blue","purple"), name="leg", labels = c("lab1","lab2")) +
scale_fill_manual(values = rep("red", 2), name="leg", labels= c("lab1","lab2"))
or
library(tidyverse)
df %>%
gather(var, val, jj, hh) %>%
bind_rows(data.frame(x=NA,y=NA,z=NA,x1=NA,var="_dummy",val=NA)) %>%
ggplot(aes(x1, val, ymin=y, ymax=z, color=var, fill=var)) +
geom_ribbon(color=NA) +
geom_ribbon(color=NA, fill="red") +
geom_point() +
scale_color_manual(
values=c("#FFFFFF00", "blue","purple"), name="leg", labels = c("lab1","lab2","lab3")) +
scale_fill_manual(
values = c("red", rep(NA, 2)), name="leg", labels= c("lab1","lab2","lab3"))
One option is to use an interior fill for each element. There may be a way to use override.aes to get the points to be a point in the legend, but I wasn't able to get that with any quick experimentation.
p <- df %>%
ggplot(aes(x1)) +
geom_ribbon(aes(ymin = y, ymax = z, fill = "area")) +
geom_point(aes(y = jj, fill = "points1"), shape=21, colour="blue") +
geom_point(aes(y = hh, fill = "points2"), shape=21, colour="purple") +
scale_x_continuous(breaks = some_names %>% select(x1) %>% unlist %>% unname,
labels = some_names %>% select(x) %>% unlist %>% unname ) +
scale_fill_manual(name = "legend",
values = c("area" = "red","points1" = "blue","points2" = "purple"),
guide = guide_legend(override.aes=aes(colour=NA)))
p
Using the code below, I'm generating a set of simple histogram:
data(mtcars); Vectorize(require)(package = c("ggplot2", "ggthemes", "dplyr"))
mtcars %>%
add_rownames(var = "model") %>%
gather(var, value, -model, -am) %>%
filter(var %in% c("hp")) %>%
# Define chart
ggplot(aes(value)) +
geom_histogram(aes(y = ..ncount..), colour = "black", fill = "gray58",
binwidth = 15) +
geom_density(aes(y = ..scaled..), colour = "red") +
facet_wrap( ~am, ncol = 3, scales = "free")
I would like to maintain scale that is produced when generating a histogram without the ..ncount.. special variable, as in the example:
mtcars %>%
add_rownames(var = "model") %>%
gather(var, value, -model, -am) %>%
filter(var %in% c("hp")) %>%
# Define chart
ggplot(aes(value)) +
geom_histogram(colour = "black", fill = "gray58",
binwidth = 15) +
geom_density(aes(y = ..scaled..), colour = "red") +
facet_wrap( ~am, ncol = 3, scales = "free")
But it makes the geom_density look poor.
Task
So what I want boils down to:
keep scale of y axis from the second one
keep graphics from the first one