Related
I want to automate adding brackets/braces to a ggplot object and then convert it to plotly using ggplotly.
library(tidyverse)
library(plotly)
#devtools::install_github("NicolasH2/ggbrace")
library(ggbrace)
set.seed(10)
mydata <- data.frame(xx = c(1:10), yy = sample(0:10, 10))
my_bracket_data <- data.frame(start = c(1, 4, 6),
end = c(3, 5, 9),
info = c("first", "second", "third"),
y_bottom = rep(11, 3),
y_top = rep(12, 3))
I can do this by using geom_brace but it involves manually typing it out for each brace rather than using the data that is already stored in a data.frame:
plot_geom_brace <- ggplot(data = mydata, aes(xx, yy)) +
geom_line(size = 1.5) +
geom_brace(aes(x = c(1, 3), y = c(11, 12), label = "first"), inherit.data = F, labelsize = 5) +
geom_brace(aes(x = c(4, 5), y = c(11, 12), label = "second"), inherit.data = F, labelsize = 5) +
geom_brace(aes(x = c(6, 9), y = c(11, 12), label = "third"), inherit.data = F, labelsize = 5)
plot_geom_brace
ggplotly(plot_geom_brace)
Is there a way that I can do this without repeatedly writing geom_brace layers for each brace (and instead access the data from my_bracket_data directly)?
As an aside this can be automated using geom_bracket but this is not supported by plotly yet.
library(ggpubr)
plot_geom_bracket <- ggplot(data = mydata, aes(xx, yy)) +
geom_line(size = 1.5) +
geom_bracket(xmin = my_bracket_data$start,
xmax = my_bracket_data$end,
y.position = rep(11, 3),
label = my_bracket_data$info,
inherit.aes = FALSE)
plot_geom_bracket
ggplotly(plot_geom_bracket)
# Warning message:
# In geom2trace.default(dots[[1L]][[1L]], dots[[2L]][[1L]], dots[[3L]][[1L]]) :
# geom_GeomBracket() has yet to be implemented in plotly.
# If you'd like to see this geom implemented,
# Please open an issue with your example code at
# https://github.com/ropensci/plotly/issues
Any suggestions?
Thanks
An option could be by creating two dataframes of your bracket data. One dataframe for the geom_braces by converting the data to a longer format with pivot_longer to create three geom braces through the aes. To get the labels you can create a small summarise table with the x and y positions per group of info. Here is some reproducible code:
library(tidyverse)
library(plotly)
#devtools::install_github("NicolasH2/ggbrace")
library(ggbrace)
set.seed(10)
mydata <- data.frame(xx = c(1:10), yy = sample(0:10, 10))
my_bracket_data <- data.frame(start = c(1, 4, 6),
end = c(3, 5, 9),
info = c("first", "second", "third"),
y_bottom = rep(11, 3),
y_top = rep(12, 3))
# Data for geom_brace
my_bracket_data_long <- my_bracket_data %>%
pivot_longer(cols = c(start, end), values_to = "x_value", names_to = "x_names") %>%
pivot_longer(cols = c(y_bottom, y_top), values_to = "y_value", names_to = "y_names")
# data for labels braces
my_bracket_data_labels <- my_bracket_data_long %>%
group_by(info) %>%
summarise(x_pos = mean(x_value),
y_pos = mean(y_value) + 1)
# plot
plot_geom_brace <- ggplot(data = mydata, aes(xx, yy)) +
geom_line(size = 1.5) +
geom_brace(data = my_bracket_data_long, aes(x = x_value, y = y_value, group = info)) +
geom_text(data = my_bracket_data_labels, aes(x = x_pos, y = y_pos, group = info, label = info))
ggplotly(plot_geom_brace)
Created on 2023-01-07 with reprex v2.0.2
special ggplot2 libraries like ggpubr usually don't play along well with conversion to plotly objects.
If you dont want to type out each geom_bracet call you could loop over the rows of the dataframe, create the geom statement using paste and pass it to the existing plot object using eval in the following line:
m<- data.frame(s = c(1, 4, 6), ## = my_bracket_data
e = c(3, 5, 9),
i = c("first", "second", "third"),
y_b = rep(11, 3),
y_t = rep(12, 3))
p<- ggplot(data = mydata, aes(xx, yy)) + geom_line(size = 1.5)
for (i in 1:NROW(my_bracket_data)) {
input = paste('geom_brace(aes(x =c(',m[i,]$s,',',m[i,]$e'),c(',m[i,]$y_b,',',
m[i,]$y_t,'),label=',m[i,]$i,'), inherit.data = F, labelsize = 5)',sep='')
p = p + eval(parse(text=input))
}
p
However this is more of a hacky solution, but that's what R tends to become if you incorporate/mix different styles like for example apply functions with tidyr syntax (or in this case ggplot, which could be seen as an ancestor of tidyr) and more programming style approaches (for, while , func...[yes you can programm in R]) and also want to let it automatically converse the whole thing to a Javascript thing (aka plotly) . .. its a beautiful mess .
I would like to link variables I have in a dataframe i.e. ('prop1', 'prop2', 'prop3') to specific colours and shapes in the plot. However, I also want to exclude data (using dplyr::filter) to customise the plot display WITHOUT changing the points and shapes used for a specific variable. A minimal example is given below.
library(ggplot2)
library(dplyr)
library(magrittr)
obj <- c("cmpd 1","cmpd 1","cmpd 1","cmpd 2","cmpd 2")
x <- c(1, 2, 4, 7, 3)
var <- c("prop1","prop2","prop3","prop2","prop3")
y <- c(1, 2, 3, 2.5, 4)
col <- c("#E69F00","#9E0142","#56B4E9","#9E0142","#56B4E9")
shp <- c(0,1,2,1,2)
df2 <- cbind.data.frame(obj,x,var,y,col,shp)
plot <- ggplot(data = df2 %>%
filter(obj %in% c(
"cmpd 1",
"cmpd 2"
)),
aes(x = x,
y = y,
colour = as.factor(var),
shape = as.factor(var))) +
geom_point(size=2) +
#scale_shape_manual(values=shp) +
#scale_color_manual(values=col) +
facet_grid(.~obj)
plot
However, when I redact cmpd1 (just hashing in code) the colour and shape of prop2 and prop3 for cmpd2 change (please see plot2).
To this end, I tried adding in scale_shape_manual and scale_color_manual to the code (currently hashed) and linked these to specific vars (col and shp) in the dataframe (df2), but the same problem arises that both the shape and color of these variables changes when excluding one of the conditions?
Any and all help appreciated.
Try something like this:
library(tidyverse)
obj <- c("cmpd 1","cmpd 1","cmpd 1","cmpd 2","cmpd 2")
x <- c(1, 2, 4, 7, 3)
var <- c("prop1","prop2","prop3","prop2","prop3")
y <- c(1, 2, 3, 2.5, 4)
df2 <- cbind.data.frame(obj,x,var,y)
col <- c("prop1" = "#E69F00",
"prop2" = "#9E0142",
"prop3" = "#56B4E9")
shp <- c("prop1" = 0,
"prop2" = 1,
"prop3" = 2)
plot <- ggplot(data = df2 %>%
filter(obj %in% c(
"cmpd 1",
"cmpd 2"
)),
aes(x = x,
y = y,
colour = var,
shape = var)) +
geom_point(size=2) +
scale_shape_manual(values=shp) +
scale_color_manual(values=col) +
facet_grid(.~obj)
plot
In R, using gganimate, one can make an animated plot where events appear and disappear with time. For example:
library(lubridate)
library(gganimate)
df=data.frame(
x=c(1,2,3,4),
y=c(1,2,3,4),
start=c(1,2,3,4),
end=c(5,6,7,8),
en=as_date(1),
ex=as_date(1))
ggplot(data=df, aes(x=x,y=y))+
geom_point()+
gganimate::transition_events(
start=start,
end=end,
enter_length = as.numeric(en),
exit_length = as.numeric(ex))
This produces a plot in which points appear according to column "start" and desappear according to column "end".
I wonder if there is an easy way to achieve the same in with plotly (preferably using ggplotly()), getting a slider to move along the time.
Here is an example using ggplotly. The result however isn't exactly the same:
library(plotly)
library(lubridate)
df = data.frame(
x = c(1, 2, 3, 4),
y = c(1, 2, 3, 4),
start = c(1, 2, 3, 4),
end = c(5, 6, 7, 8),
en = as_date(1),
ex = as_date(1)
)
frame_list <- Map(seq, from = df$start, to = df$end)
DF <- data.frame(x = rep(df$x, times = lengths(frame_list)),
y = rep(df$y, times = lengths(frame_list)),
frame = unlist(frame_list))
p <- ggplot(DF, aes(x, y)) +
geom_point(aes(size = y, frame = frame))
fig <- ggplotly(p)
fig %>%
animation_opts(
frame = 0,
easing = "linear",
redraw = FALSE,
mode = "immediate"
)
fig
I have a data frame.
id <- c(1:5)
count_big <- c(15, 25, 7, 0, 12)
count_small <- c(15, 9, 22, 11, 14)
count_black <- c(7, 12, 5, 2, 6)
count_yellow <- c(2, 0, 7, 4, 3)
count_red <- c(8, 4, 4, 2, 5)
count_blue <- c(5, 9, 6, 1, 7)
count_green <- c(8, 9, 7, 2, 5)
df <- data.frame(id, count_big, count_small, count_black, count_yellow, count_red, count_blue, count_green)
How can I display the following in ggplot2 and which geom should I use:
a breakdown of big and small variable by id
a breakdown of colors by id
This is just a subset of the data set that has around 1000 rows.
Can I use this df in ggplot2, or do I need to transform it into tidy data with tidyr? (don't know data.table yet)
You need to first restructure the data from wide to long with tidyr.
library(tidyr)
library(ggplot2)
df <- gather(df, var, value, starts_with("count"))
# remove count_
df$var <- sub("count_", "", df$var)
# plot big vs small
df_size <- subset(df, var %in% c("big", "small"))
ggplot(df_size, aes(x = id, y = value, fill = var)) +
geom_bar(stat = "identity", position = position_dodge())
# same routine for colors
df_color <- subset(df, !(var %in% c("big", "small")))
ggplot(df_color, aes(x = id, y = value, fill = var)) +
geom_bar(stat = "identity", position = position_dodge())
Use stat = "identity" to prevent it from doing a row count. position = position_dodge() is used to place the bars next to each other rather than stacked.
ID <- 1:10
group <- c(1,1,1,2,2,2,3,3,3,3)
var1 <- c(6:15)
var2 <- c(7:16)
var3 <- c(6:11, NA, NA, NA, NA)
var4 <- c(4:9, NA, NA, NA, NA)
data <- data.frame(ID, group, var1, var2, var3, var4)
library(dplyr)
data %>% group_by(group) %>% boxplot(var1, var2)
The last line does not work as i wish. The idea is to get 4 boxplots in one graphic. Two for each variable. Maybe i need to use ggplot2?
You need to reorganize the data if you want to get both variables in the same plot. Here is a ggplot2 solution:
# load library
library(ggplot2)
library(tidyr)
library(ggthemes)
# reorganize data
df <- gather(data, "ID","group")
#rename columns
colnames(df) <- c("ID","group","var","value")
# plot
ggplot(data=df) +
geom_boxplot( aes(x=factor(group), y=value, fill=factor(var)), position=position_dodge(1)) +
scale_x_discrete(breaks=c(1, 2, 3), labels=c("A", "B", "C")) +
theme_minimal() +
scale_fill_grey()
Making boxplots with the same width is a whole different question (solution here), but one simple alternative would be like this:
# recode column `group` in the `data.frame`.
df <- transform(df, group = ifelse(group==1, 'A', ifelse(group==2, 'B', "C")))
# plot
ggplot(data=df) +
geom_boxplot( aes(x=factor(var), y=value, fill=factor((var))), position=position_dodge(1)) +
geom_jitter(aes(x=factor(var), y=value, color=factor((var)))) +
facet_grid(.~group, scales = "free_x") +
theme_minimal()+
scale_fill_grey() +
theme(axis.text.x=element_blank(),
axis.title.x=element_blank(),
axis.ticks=element_blank())
You might try melting the data frame (mentioned in comment by #lukeA) first and then sticking to base graphics. ggplot2 or lattice are other good options.
library(reshape2)
DF <- melt(data, id.vars = c("ID", "group"), measure.vars = c("var1", "var2"))
boxplot(value ~ group + variable, DF)
Alternate lattice code, also using DF:
bwplot(~ value | variable + group, data = DF)
Alternate ggplot2 code, also using DF:
ggplot(DF, aes(x = factor(group), y = value, fill = variable)) + geom_boxplot()
Although quite late, a found a great base-R solution here
# Create some data, e.g. from https://en.wikipedia.org/wiki/One-way_analysis_of_variance#Example
df <- as.data.frame(matrix(c(6, 8, 13, 8, 12, 9, 4, 9, 11, 5, 11, 8, 3, 6, 7, 4, 8, 12),ncol = 3, byrow = TRUE))
df <- reshape(data = df, direction = "long", idvar=1:3, varying=1:3, sep = "", timevar = "Treatment")
df$Treatment <- as.factor(df$Treatment)
rownames(df) <- NULL
par(mfrow = c(2, 1))
par(mar=c(1,4,4,2) + 0.1) # mar=c(b,l,t,r)
boxplot(V ~ Treatment, data = df, xlab = NULL, xaxt = "n",
ylab = "V", main = "One-way anova with 3 different levels of one factor")
stripchart(V ~ Treatment, # Points
data = df, # Data
method = "jitter", # Random noise
pch = 19, # Pch symbols
col = 4, # Color of the symbol
vertical = TRUE, # Vertical mode
add = TRUE) # Add it over
par(mar=c(5,4,0,2) + 0.1)
boxplot(V ~ Treatment, data = df, xlab = "Treatment",
ylab = "V", main = NULL)
stripchart(V ~ Treatment, # Points
data = df, # Data
method = "overplot", # Random noise
pch = 19, # Pch symbols
col = 4, # Color of the symbol
vertical = TRUE, # Vertical mode
add = TRUE) # Add it over
par(mfrow = c(1, 1))
Result: