#Sample data
set.seed(42)
DB = data.frame(Group =c(rep("1",16),
rep("2",4)) ,
Score1 = sample(1:20,20, replace = T),
Score2 = sample(1:20,20, replace = T),
Score3 = sample(1:20,20, replace = T),
Score4 = sample(1:20,20, replace = T))
I want to plot two bar charts comparing the mean of each score in both groups.
So the right side will be with a Title "Group 1 mean scores" and left side (left barchart) is "Group 2 mean scores"
Thanks.
You can pivot to long format and use stat = "summary"
library(tidyverse)
DB %>%
pivot_longer(-1, names_to = "Score") %>%
ggplot(aes(Group, value, fill = Score)) +
geom_bar(position = position_dodge(width = 0.8, preserve = "total"),
stat = "summary", fun = mean, width = 0.6) +
scale_fill_brewer(palette = "Set2") +
theme_minimal(base_size = 20)
Or if you prefer facets, you can do:
library(tidyverse)
DB %>%
pivot_longer(-1, names_to = "Score") %>%
mutate(Group = paste("Group", Group)) %>%
ggplot(aes(Score, value, fill = Score)) +
geom_bar(stat = "summary", fun = mean, width = 0.6) +
scale_fill_brewer(palette = "Set2", guide = "none") +
facet_grid(.~Group) +
theme_bw(base_size = 20)
Created on 2022-11-13 with reprex v2.0.2
Related
I would like to make a simple flow graph.
Here is my code:
## Data
x = tibble(qms = c("FLOW", "FLOW"),
move1 = c("Birth", "Birth"),
move2 = c("Direct", NA),
freq = c(100, 50))
## Graph
x %>%
mutate(id = qms) %>%
to_lodes_form(axis = 2:3, id = id) %>%
na.omit() %>%
ggplot(aes(x = x, stratum = stratum, alluvium = id,
y = freq, label = stratum)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow(aes(fill = qms),stat = "alluvium") +
geom_stratum(aes(fill = stratum), show.legend=FALSE) +
geom_text(stat = "stratum", size = 3)
This is the outcome:
My desired outcome is that:
How can I express the decreasing pattern with the missing value?
By slightly reshaping your data you can get what you want. I think the key is to map the alluvium to something fixed like 1 so that it will be a single flow, and mapping stratum to the same variable as x.
library(tidyverse)
library(ggalluvial)
x <- tibble(x = c("Birth", "Direct"),
y = c(100, 50))
x %>%
ggplot(aes(x, y, alluvium = 1, stratum = x)) +
geom_alluvium() +
geom_stratum()
Created on 2022-11-15 with reprex v2.0.2
I'm trying to combine two heatmaps. I want var_a and var_x on the y axis with for example: var_a first and then var_x. I don't know if I should do this by changing the dataframe or combining them, or if I can do this in ggplot.
Below I have some example code and a drawing of what I want (since I don't know if I explained it right).
I hope someone has ideas how I can do this either in the dataframe or in ggplot!
Example code:
df_one <- data.frame(
vars = c("var_a", "var_b", "var_c"),
corresponding_vars = c("var_x", "var_y", "var_z"),
expression_organ_1_vars = c(5, 10, 20),
expression_organ_2_vars = c(50, 2, 10),
expression_organ_3_vars = c(5, 10, 3)
)
df_one_long <- pivot_longer(df_one,
cols=3:5,
names_to = "tissueType",
values_to = "Expression")
expression.df_one <- ggplot(df_one_long,
mapping = aes(y=tissueType, x=vars, fill = Expression)) +
geom_tile()
expression.df_one
df_two <- data.frame(
corresponding_vars = c("var_x", "var_y", "var_z"),
expression_organ_1_corresponding_vars = c(100, 320, 120),
expression_organ_2_corresponding_vars = c(23, 30, 150),
expression_organ_3_corresponding_vars = c(89, 7, 200)
)
df_two_long <- pivot_longer(df_one,
cols=3:5,
names_to = "tissueType",
values_to = "Expression")
expression.df_two <- ggplot(df_two_long,
mapping = aes(y=tissueType, x=vars, fill = Expression)) +
geom_tile()
expression.df_two
Drawing:
You can bind your data frames together and pivot into a longer format so that vars and corresponding vars are in the same column, but retain a grouping variable to facet by:
df_two %>%
mutate(cor = corresponding_vars) %>%
rename_with(~sub('corresponding_', '', .x)) %>%
bind_rows(df_one %>% rename(cor = corresponding_vars)) %>%
pivot_longer(contains('expression'), names_to = 'organ') %>%
mutate(organ = gsub('expression_|_vars', '', organ)) %>%
group_by(cor) %>%
summarize(vars = vars, organ = organ, value = value,
cor = paste(sort(unique(vars)), collapse = ' cor ')) %>%
ggplot(aes(vars, organ, fill = value)) +
geom_tile(color = 'white', linewidth = 1) +
facet_grid(.~cor, scales = 'free_x', switch = 'x') +
scale_fill_viridis_c() +
coord_cartesian(clip = 'off') +
scale_x_discrete(expand = c(0, 0)) +
theme_minimal(base_size = 16) +
theme(strip.placement = 'outside',
axis.text.x = element_blank(),
axis.ticks.x.bottom = element_line(),
panel.spacing.x = unit(3, 'mm'))
Okay, so I solved the issue for my own project, which is to convert it to a scatter plot. I combined both datasets and then used a simple scatterplot.
df.combined <- dplyr::full_join(df_two_long, df_one_long,
by = c("vars", "corresponding_vars", "tissueType"))
ggplot(df.combined,
aes(x=vars, y=tissueType, colour=Expression.x, size = Expression.y)) +
geom_point()
It's not a solution with heatmaps, but I don't know how to do that at the moment.
I have below ggplot:
library(ggplot2)
data = rbind(data.frame('val' = c(10, 30, 15), 'name' = c('A', 'B', 'C'), group = 'gr1'), data.frame('val' = c(30, 40, 12), 'name' = c('A', 'B', 'C'), group = 'gr2'))
ggplot(data, # Draw barplot with grouping & stacking
aes(x = group,
y = val,
fill = name)) +
geom_bar(stat = "identity",
position = "stack", width = .1)
With this, I am getting below plot
However, I want to connect these bars with a curved area where the area would be equal to the value of the corresponding bar-component. A close example could be like,
Is there any way to achieve this with ggplot?
Any pointer will be very helpful.
This is something like an alluvial plot. There are various extension packages that could help you create such a plot, but it is possible to do it in ggplot directly using a bit of data manipulation.
library(tidyverse)
alluvia <- data %>%
group_by(name) %>%
summarize(x = seq(1, 2, 0.01),
val = pnorm(x, 1.5, 0.15) * diff(val) + first(val))
ggplot(data,
aes(x = as.numeric(factor(group)),
y = val,
fill = name)) +
geom_bar(stat = "identity",
position = "stack", width = .1) +
geom_area(data = alluvia, aes(x = x), position = "stack", alpha = 0.5) +
scale_x_continuous(breaks = 1:2, labels = levels(factor(data$group)),
name = "Group", expand = c(0.25, 0.25)) +
scale_fill_brewer(palette = "Set2") +
theme_light(base_size = 20)
EDIT
A more generalized solution for more than 2 groups would be
library(tidyverse)
alluvia <- data %>%
mutate(group = as.numeric(factor(group)),
name = factor(name)) %>%
arrange(group) %>%
group_by(name) %>%
mutate(next_group = lead(group),
next_val = lead(val)) %>%
filter(!is.na(next_val)) %>%
group_by(name, group) %>%
summarise(x = seq(group + 0.01, next_group - 0.01, 0.01),
val = (next_val - val) * pnorm(x, group + 0.5, 0.15) + val)
ggplot(data,
aes(x = as.numeric(factor(group)),
y = val,
fill = name)) +
geom_bar(stat = "identity",
position = "stack", width = .1) +
geom_area(data = alluvia, aes(x = x), position = "stack", alpha = 0.5) +
scale_x_continuous(breaks = seq(length(unique(data$group))),
labels = levels(factor(data$group)),
name = "Group", expand = c(0.25, 0.25)) +
scale_fill_brewer(palette = "Set2") +
theme_light(base_size = 20)
I am trying to create a pie chart to visualize percent abundance of 9 genera. However, the labels are all clumping together. How do I remedy this? Code included below:
generaabundance2020 <- c(883, 464, 1948, 1177, 2607, 962, 2073, 620, 2670)
genera2020 <- c("Andrena", "Ceratina", "Halictus",
"Hesperapis", "Lasioglossum", "Melissodes",
"Osmia", "Panurginus", "Other")
generabreakdown2020 <- data.frame(group = genera2020, value = generaabundance2020)
gb2020label <- generabreakdown2020 %>%
group_by(value) %>% # Variable to be transformed
count() %>%
ungroup() %>%
mutate(perc = `value` / sum(`value`)) %>%
arrange(perc) %>%
mutate(labels = scales::percent(perc))
generabreakdown2020 %>%
ggplot(aes(x = "", y = value, fill = group)) +
geom_col() +
coord_polar("y", start = 0) +
theme_void() +
geom_label_repel(aes(label = gb2020label$labels), position = position_fill(vjust = 0.5),
size = 5, show.legend = F, max.overlaps = 50) +
guides(fill = guide_legend(title = "Genera")) +
scale_fill_manual(values = c("brown1", "chocolate1",
"darkgoldenrod1", "darkgreen",
"deepskyblue", "darkslateblue",
"darkorchid4", "hotpink1",
"lightpink"))
Which produces the following:
Thanks for adding your data.
There are a few errors in your code. The main one is that you didn't precalculate where to place the labels (done here in the text_y variable). That variable needs to be passed as the y aesthetic for geom_label_repel.
The second is that you no longer need
group_by(value) %>% count() %>% ungroup() because the data you provided is already aggregated.
library(tidyverse)
library(ggrepel)
generaabundance2020 <- c(883, 464, 1948, 1177, 2607, 962, 2073, 620, 2670)
genera2020 <- c("Andrena", "Ceratina", "Halictus", "Hesperapis", "Lasioglossum", "Melissodes", "Osmia", "Panurginus", "Other")
generabreakdown2020 <- data.frame(group = genera2020, value = generaabundance2020)
gb2020label <-
generabreakdown2020 %>%
mutate(perc = value/ sum(value)) %>%
mutate(labels = scales::percent(perc)) %>%
arrange(desc(group)) %>% ## arrange in the order of the legend
mutate(text_y = cumsum(value) - value/2) ### calculate where to place the text labels
gb2020label %>%
ggplot(aes(x = "", y = value, fill = group)) +
geom_col() +
coord_polar(theta = "y") +
geom_label_repel(aes(label = labels, y = text_y),
nudge_x = 0.6, nudge_y = 0.6,
size = 5, show.legend = F) +
guides(fill = guide_legend(title = "Genera")) +
scale_fill_manual(values = c("brown1", "chocolate1",
"darkgoldenrod1", "darkgreen",
"deepskyblue", "darkslateblue",
"darkorchid4", "hotpink1",
"lightpink"))
If you want to arrange in descending order of frequency, you should remember to also set the factor levels of the group variable to the same order.
gb2020label <-
generabreakdown2020 %>%
mutate(perc = value/ sum(value)) %>%
mutate(labels = scales::percent(perc)) %>%
arrange(desc(perc)) %>% ## arrange in descending order of frequency
mutate(group = fct_rev(fct_inorder(group))) %>% ## also arrange the groups in descending order of freq
mutate(text_y = cumsum(value) - value/2) ### calculate where to place the text labels
gb2020label %>%
ggplot(aes(x = "", y = value, fill = group)) +
geom_col() +
coord_polar(theta = "y") +
geom_label_repel(aes(label = labels, y = text_y),
nudge_x = 0.6, nudge_y = 0.6,
size = 5, show.legend = F) +
guides(fill = guide_legend(title = "Genera")) +
scale_fill_manual(values = c("brown1", "chocolate1",
"darkgoldenrod1", "darkgreen",
"deepskyblue", "darkslateblue",
"darkorchid4", "hotpink1",
"lightpink"))
Created on 2021-10-27 by the reprex package (v2.0.1)
You didn't provide us with your data to work with so I'm using ggplot2::mpg here.
library(tidyverse)
library(ggrepel)
mpg_2 <-
mpg %>%
slice_sample(n = 20) %>%
count(manufacturer) %>%
mutate(perc = n / sum(n)) %>%
mutate(labels = scales::percent(perc)) %>%
arrange(desc(manufacturer)) %>%
mutate(text_y = cumsum(n) - n/2)
Chart without polar coordinates
mpg_2 %>%
ggplot(aes(x = "", y = n, fill = manufacturer)) +
geom_col() +
geom_label(aes(label = labels, y = text_y))
Chart with polar coordinates and geom_label_repel
mpg_2 %>%
ggplot(aes(x = "", y = n, fill = manufacturer)) +
geom_col() +
geom_label_repel(aes(label = labels, y = text_y),
force = 0.5,nudge_x = 0.6, nudge_y = 0.6) +
coord_polar(theta = "y")
But maybe your data isn’t dense enough to need repelling?
mpg_2 %>%
ggplot(aes(x = "", y = n, fill = manufacturer)) +
geom_col() +
geom_label(aes(label = labels, y = text_y), nudge_x = 0.6) +
coord_polar(theta = "y")
Created on 2021-10-26 by the reprex package (v2.0.1)
I'm making a plot with two different geoms, both use fill. I'd like one geom to have a legend, but the other to not. However adding show.legend=F to the required geom doesn't switch off the legend for that geom.
Example:
library(tidyverse)
library(ggalluvial)
x = tibble(qms = c("grass", "cereal", "cereal"),
move1 = "Birth",
move2 = c("Direct", "Market", "Slaughter"),
move3 = c("Slaughter", "Slaughter", NA),
freq = c(10, 5, 7))
x %>%
mutate(id = qms) %>%
to_lodes_form(axis = 2:4, id = id) %>%
na.omit() %>%
ggplot(aes(x = x, stratum = stratum, alluvium = id,
y = freq, label = stratum)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow(aes(fill = qms)) +
geom_stratum(aes(fill = stratum), show.legend=F) +
geom_text(stat = "stratum", size = 3) +
theme_void() +
labs(fill="")
Output:
Desired output:
Question:
How do I turn off the fill legend for one geom, but not the other? I can (if I have to) do this in inkscape/gimp, but would prefer a solution I can version control.
Have a look at the final line of code:
scale_fill_discrete(breaks = c("grass", "cereal"))
That defines the breaks for the fills to only include cereal and grass, as required.
library(tidyverse)
library(ggalluvial)
x = tibble(qms = c("grass", "cereal", "cereal"),
move1 = "Birth",
move2 = c("Direct", "Market", "Slaughter"),
move3 = c("Slaughter", "Slaughter", NA),
freq = c(10, 5, 7))
x %>%
mutate(id = qms) %>%
to_lodes_form(axis = 2:4, id = id) %>%
na.omit() %>%
ggplot(aes(x = x, stratum = stratum, alluvium = id,
y = freq, label = stratum)) +
scale_x_discrete(expand = c(.1, .1)) +
geom_flow(aes(fill = qms)) +
geom_stratum(aes(fill = stratum), show.legend=FALSE) +
geom_text(stat = "stratum", size = 3) +
theme_void() +
labs(fill="") +
scale_fill_discrete(breaks = c("grass", "cereal")) #<- This line!
Created on 2019-03-18 by the reprex package (v0.2.1)