Add macron to letter in faceting label - r

As the title says, I want to add a macron to a faceting label. An example:
library(tidyverse)
# subset data
df2 <- diamonds %>%
sample_n(500)
# plot
ggplot(df2,aes(x = carat, y = price)) +
geom_point() +
facet_wrap(~cut)
Now I want to add a macron over the a in Fair
# attempt to recode Fair to Fāir
df2 <- df2 %>%
mutate(cut2 = fct_recode(cut, "F\u0101ir" = "Fair"))
# doesn't work - produces exactly the same plot as above.
ggplot(df2,aes(x = carat, y = price)) +
geom_point() +
facet_wrap(~cut2)
Any tips would be greatly appreciated.

Looks like it's a problem with fct_recode rather than ggplot2. This seems to work just fine
df2 <- diamonds %>%
sample_n(500)
df2$cut2 <- df2$cut
levels(df2$cut2)[1] <- "F\u0101ir"
ggplot(df2,aes(x = carat, y = price)) +
geom_point() +
facet_wrap(~cut2)
Actually I guess it has to do with all parameter names in R. It doesn't look like you can use unicode names (at least not in 4.0.5 which I tested with)
foo <- function(...) {
print(match.call())
}
foo("F\u0101ir" = 1)
# foo(Fair = 1)
foo(Fāir = 1)
# foo(Fair = 1)
Seems the values are just converted to ASCII

Related

Represent dataset in column bar in R using ggplot [duplicate]

I have a csv file which looks like the following:
Name,Count1,Count2,Count3
application_name1,x1,x2,x3
application_name2,x4,x5,x6
The x variables represent numbers and the applications_name variables represent names of different applications.
Now I would like to make a barplot for each row by using ggplot2. The barplot should have the application_name as title. The x axis should show Count1, Count2, Count3 and the y axis should show the corresponding values (x1, x2, x3).
I would like to have a single barplot for each row, because I have to store the different plots in different files. So I guess I cannot use "melt".
I would like to have something like:
for each row in rows {
print barplot in file
}
Thanks for your help.
You can use melt to rearrange your data and then use either facet_wrap or facet_grid to get a separate plot for each application name
library(ggplot2)
library(reshape2)
# example data
mydf <- data.frame(name = paste0("name",1:4), replicate(5,rpois(4,30)))
names(mydf)[2:6] <- paste0("count",1:5)
# rearrange data
m <- melt(mydf)
# if you are wanting to export each plot separately
# I used facet_wrap as a quick way to add the application name as a plot title
for(i in levels(m$name)) {
p <- ggplot(subset(m, name==i), aes(variable, value, fill = variable)) +
facet_wrap(~ name) +
geom_bar(stat="identity", show_guide=FALSE)
ggsave(paste0("figure_",i,".pdf"), p)
}
# or all plots in one window
ggplot(m, aes(variable, value, fill = variable)) +
facet_wrap(~ name) +
geom_bar(stat="identity", show_guide=FALSE)
I didn't see #user20650's nice answer before preparing this. It's almost identical, except that I use plyr::d_ply to save things instead of a loop. I believe dplyr::do() is another good option (you'd group_by(Name) first).
yourData <- data.frame(Name = sample(letters, 10),
Count1 = rpois(10, 20),
Count2 = rpois(10, 10),
Count3 = rpois(10, 8))
library(reshape2)
yourMelt <- melt(yourData, id.vars = "Name")
library(ggplot2)
# Test a function on one piece to develope graph
ggplot(subset(yourMelt, Name == "a"), aes(x = variable, y = value)) +
geom_bar(stat = "identity") +
labs(title = subset(yourMelt, Name == 'a')$Name)
# Wrap it up, with saving to file
bp <- function(dat) {
myPlot <- ggplot(dat, aes(x = variable, y = value)) +
geom_bar(stat = "identity") +
labs(title = dat$Name)
ggsave(filname = paste0("path/to/save/", dat$Name, "_plot.pdf"),
myPlot)
}
library(plyr)
d_ply(yourMelt, .variables = "Name", .fun = bp)

Same variables from 2 separate data.frames sided by side in ggplot2

I want to plot the exact same variable names (ses & math) from 2 separate data.frames (dat1 & dat2) but side by side so I can visually compare them.
I have tried the following but it places both data.frames on top of each other.
Is there a function within ggplot2 to plot ses vs. math from dat1 and the same from dat2 side by side and placed on the same axes scales?
library(ggplot2)
dat1 <- read.csv('https://raw.githubusercontent.com/rnorouzian/e/master/hsb.csv')
dat2 <- read.csv('https://raw.githubusercontent.com/rnorouzian/e/master/sm.csv')
ggplot(dat1, aes(x = ses, y = math, colour = factor(sector))) +
geom_point() +
geom_point(data = dat2, aes(x = ses, y = math, colour = factor(sector)))
You can try faceting combining the two datasets :
library(dplyr)
library(ggplot2)
list(dat1 = dat1 %>%
select(sector,ses, math) %>%
mutate(sector = as.character(sector)) ,
dat2 = dat2 %>% select(sector,ses, math)) %>%
bind_rows(.id = 'name') %>%
ggplot() +
aes(x = ses, y = math, colour = factor(sector)) +
geom_point() +
facet_wrap(.~name)
Another option is to create list of plots and arrange them with grid.arrange :
list_plots <- lapply(list(dat1, dat2), function(df) {
ggplot(df, aes(x = ses, y = math, colour = factor(sector))) + geom_point()
})
do.call(gridExtra::grid.arrange, c(list_plots, ncol = 2))

Plot multiple distributions by year using ggplot Boxplot

I'm trying to evaluate the above data in a boxplot similar to this: https://www.r-graph-gallery.com/89-box-and-scatter-plot-with-ggplot2.html
I want the x axis to reflect my "Year" variable and each boxplot to evaluate the 8 methods as a distribution. Eventually I'd like to pinpoint the "Selected" variable in relation to that distribution but currently I just want this thing to render!
I figure out how to code my y variable and I get various errors no matter what I try. I think the PY needs to be as.factor but I've tried some code that way and I just get other errors.
anyway here is my code (Send Help):
# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)
library(ggplot2)
library(readxl) # For reading in Excel files
library(lubridate) # For handling dates
library(dplyr) # for mutate and pipe functions
# Path to current and prior data folders
DataPath_Current <- "C:/R Projects/Box Plot Test"
Ult_sum <- read_excel(path = paste0(DataPath_Current, "/estimate.XLSX"),
sheet = "Sheet1",
range = "A2:J12",
guess_max = 100)
# just want to see what my table looks like
Ult_sum
# create a dataset - the below is code I commented out
# data <- data.frame(
# name=c(Ult_sum[,1]),
# value=c(Ult_sum[1:11,2:8])
#)
value <- Ult_sum[2,]
# Plot
Ult_sum %>%
ggplot( aes(x= Year, y= value, fill=Year)) +
geom_boxplot() +
scale_fill_viridis(discrete = TRUE, alpha=0.6) +
geom_jitter(color="black", size=0.4, alpha=0.9) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("A boxplot with jitter") +
xlab("")
I do not see how your code matches the screenshot of your dataset. However, just a general hint: ggplot likes data in long format. I suggest you reshape your data using tidyr::reshape_long oder data.table::melt. This way you get 3 columns: year, method, value, of which the first two should be a factor. The resulting dataset can then be neatly used in aes() as aes(x=year, y=value, fill=method).
Edit: Added an example. Does this do what you want?
library(data.table)
library(magrittr)
library(ggplot2)
DT <- data.table(year = factor(rep(2010:2014, 10)),
method1 = rnorm(50),
method2 = rnorm(50),
method3 = rnorm(50))
DT_long <- DT %>% melt(id.vars = "year")
ggplot(DT_long, aes(x = year, y = value, fill = variable)) +
geom_boxplot()

R: Unexplainable behavior of ggplot inside a function

I have composed a function that develops histograms using ggplot2 on the numerical columns of a dataframe that will be passed to it. The function stores these plots into a list and then returns the list.
However when I run the function I get the same plot again and again.
My code is the following and I provide also a reproducible example.
hist_of_columns = function(data, class, variables_to_exclude = c()){
library(ggplot2)
library(ggthemes)
data = as.data.frame(data)
variables_numeric = names(data)[unlist(lapply(data, function(x){is.numeric(x) | is.integer(x)}))]
variables_not_to_plot = c(class, variables_to_exclude)
variables_to_plot = setdiff(variables_numeric, variables_not_to_plot)
indices = match(variables_to_plot, names(data))
index_of_class = match(class, names(data))
plots = list()
for (i in (1 : length(variables_to_plot))){
p = ggplot(data, aes(x= data[, indices[i]], color= data[, index_of_class], fill=data[, index_of_class])) +
geom_histogram(aes(y=..density..), alpha=0.3,
position="identity", bins = 100)+ theme_economist() +
geom_density(alpha=.2) + xlab(names(data)[indices[i]]) + labs(fill = class) + guides(color = FALSE)
name = names(data)[indices[i]]
plots[[name]] = p
}
plots
}
data(mtcars)
mtcars$am = factor(mtcars$am)
data = mtcars
variables_to_exclude = 'mpg'
class = 'am'
plots = hist_of_columns(data, class, variables_to_exclude)
If you check the list plots you will discover that it contains the same plot repeated.
Simply use aes_string to pass string variables into the ggplot() call. Right now, your plot uses different data sources, not aligned with ggplot's data argument. Below x, color, and fill are separate, unrelated vectors though they derive from same source but ggplot does not know that:
ggplot(data, aes(x= data[, indices[i]], color= data[, index_of_class], fill=data[, index_of_class]))
However, with aes_string, passing string names to x, color, and fill will point to data:
ggplot(data, aes_string(x= names(data)[indices[i]], color= class, fill= class))
Here is strategy using tidyeval that does what you are after:
library(rlang)
library(tidyverse)
hist_of_cols <- function(data, class, drop_vars) {
# tidyeval overhead
class_enq <- enquo(class)
drop_enqs <- enquo(drop_vars)
data %>%
group_by(!!class_enq) %>% # keep the 'class' column always
select(-!!drop_enqs) %>% # drop any 'drop_vars'
select_if(is.numeric) %>% # keep only numeric columns
gather("key", "value", -!!class_enq) %>% # go to long form
split(.$key) %>% # make a list of data frames
map(~ ggplot(., aes(value, fill = !!class_enq)) + # plot as usual
geom_histogram() +
geom_density(alpha = .5) +
labs(x = unique(.$key)))
}
hist_of_cols(mtcars, am, mpg)
hist_of_cols(mtcars, am, c(mpg, wt))

Single barplot for each row of dataframe

I have a csv file which looks like the following:
Name,Count1,Count2,Count3
application_name1,x1,x2,x3
application_name2,x4,x5,x6
The x variables represent numbers and the applications_name variables represent names of different applications.
Now I would like to make a barplot for each row by using ggplot2. The barplot should have the application_name as title. The x axis should show Count1, Count2, Count3 and the y axis should show the corresponding values (x1, x2, x3).
I would like to have a single barplot for each row, because I have to store the different plots in different files. So I guess I cannot use "melt".
I would like to have something like:
for each row in rows {
print barplot in file
}
Thanks for your help.
You can use melt to rearrange your data and then use either facet_wrap or facet_grid to get a separate plot for each application name
library(ggplot2)
library(reshape2)
# example data
mydf <- data.frame(name = paste0("name",1:4), replicate(5,rpois(4,30)))
names(mydf)[2:6] <- paste0("count",1:5)
# rearrange data
m <- melt(mydf)
# if you are wanting to export each plot separately
# I used facet_wrap as a quick way to add the application name as a plot title
for(i in levels(m$name)) {
p <- ggplot(subset(m, name==i), aes(variable, value, fill = variable)) +
facet_wrap(~ name) +
geom_bar(stat="identity", show_guide=FALSE)
ggsave(paste0("figure_",i,".pdf"), p)
}
# or all plots in one window
ggplot(m, aes(variable, value, fill = variable)) +
facet_wrap(~ name) +
geom_bar(stat="identity", show_guide=FALSE)
I didn't see #user20650's nice answer before preparing this. It's almost identical, except that I use plyr::d_ply to save things instead of a loop. I believe dplyr::do() is another good option (you'd group_by(Name) first).
yourData <- data.frame(Name = sample(letters, 10),
Count1 = rpois(10, 20),
Count2 = rpois(10, 10),
Count3 = rpois(10, 8))
library(reshape2)
yourMelt <- melt(yourData, id.vars = "Name")
library(ggplot2)
# Test a function on one piece to develope graph
ggplot(subset(yourMelt, Name == "a"), aes(x = variable, y = value)) +
geom_bar(stat = "identity") +
labs(title = subset(yourMelt, Name == 'a')$Name)
# Wrap it up, with saving to file
bp <- function(dat) {
myPlot <- ggplot(dat, aes(x = variable, y = value)) +
geom_bar(stat = "identity") +
labs(title = dat$Name)
ggsave(filname = paste0("path/to/save/", dat$Name, "_plot.pdf"),
myPlot)
}
library(plyr)
d_ply(yourMelt, .variables = "Name", .fun = bp)

Resources