base R plot to ggplot - r

Question

I am trying to put a base R plot I have into ggplot format. The base R version looks great but I have a lot of white space and when I try to save to PDF it keeps the white space and doesn't fit in well in a document.
I like the plot the way it is but I would also like to add a title, annotations and label the x and y axis along with being able to apply a ggplot theme.
(I am happy to remain in base R for this but I have more familiarity with ggplot) - any help would be great in translating this plot into ggplot since the plot is created in a for loop I am not sure how this translates to a data frame suitable for plotting in ggplot.
plot(0,0,xlim=c(0,28),ylim=c(0,1),
xaxt="n",yaxt="n",bty="n",xlab="",ylab="",type="n")
i <- 1
j = 1
for(j in 1:7)
{
test <- (6+j):13
train <- (0+j):(5+j)
arrows(0,1-j/20,15,1-j/20,0.05)
x_dark <- seq(0,min(train)-1, by = 1)
y_dark <- rep(1-j/20,length(x_dark))
points(x_dark,y_dark,pch = 19,col = "black")
points(train,rep(1-j/20,length(train)),pch=19,col="blue")
if(length(test) >= i)
points(test[i], 1-j/20, pch=19, col="red")
if(length(test) >= i)
points(test[-i], rep(1-j/20,length(test)-1), pch=19, col="gray")
else
points(test, rep(1-j/20,length(test)), pch=19, col="gray")
}
text(17,.95," time")
The result:

Answer 1

In ggplot you usually keep data for symbols of the same type in one data frame. Here you have dots and arrows, which means two data frames should be the ideal organization. Adding of the text is left as an exercise for the reader. I believe that the code is much more legible like this:
library(tidyverse)
tibble(y = 1:7, x = 1, xend = 16) %>%
mutate(y = -y, yend = y) ->
darrows
expand.grid(x = 1:14, y = 1:7) %>%
mutate(color = case_when(
x < y + 1 ~ "black",
x < y + 7 ~ "blue",
x < y + 8 ~ "red",
T ~ "gray70"
),
y = -y) %>%
ggplot(aes(x, y)) +
geom_segment(aes(xend = xend, yend = yend), data = darrows,
lineend = "butt", linejoin = "mitre",
arrow = arrow(length = unit(.1, "inches"), type = "closed")) +
geom_point(aes(color = color), size = 3) +
coord_equal() +
scale_color_identity() +
theme_void()
The result

Answer 2

Your data looks like it's born from a matrix, where all nodes in a square are used/defined.
There are many ways you could take "some data source" into a matrix like this. I just typed numbers quickly into excel and then copied it into R, resulting in this:
m <- structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 4L, 3L, 2L, 2L, 2L,
2L, 2L, 4L, 4L, 3L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 3L, 2L, 2L, 2L,
4L, 4L, 4L, 4L, 3L, 2L, 2L, 4L, 4L, 4L, 4L, 4L, 3L, 2L, 4L, 4L,
4L, 4L, 4L, 4L, 3L), .Dim = c(7L, 14L))
While the next few lines convert these numbers to solid colors, the same effect could be done with ggplot2::scale_color_manual. After converting to literal colors, I convert into a 3-column frame using reshape2::melt (also works with data.table::melt, might work with tidyr:: funcs).
m[] <- c("black", "blue", "red", "gray")[m]
m[1:3, 1:3]
# [,1] [,2] [,3]
# [1,] "black" "blue" "blue"
# [2,] "black" "black" "blue"
# [3,] "black" "black" "black"
d <- reshape2::melt(t(m))
head(d)
# Var1 Var2 value
# 1 1 1 black
# 2 2 1 blue
# 3 3 1 blue
# 4 4 1 blue
# 5 5 1 blue
# 6 6 1 blue
From here:
d %>%
ggplot(aes(x = Var1, y = -Var2)) +
geom_segment(data = arrows, aes(x = xmin, xend = xmax, yend = -Var2),
arrow = arrow(length = unit(0.01, "npc"))) +
geom_point(aes(color = value), size = 3) +
scale_color_identity() +
geom_text(data = data.frame(Var1 = ncol(m) + 2L, Var2 = 1, label = "time"),
aes(label = label)) +
labs(x = NULL, y = NULL) +
theme_void()

Answer 3

An alternative way is to use a similar for loop than the one you use for building your base plot to build your dataframe as this:
y_dark <- NULL
y_blue <- NULL
y_red <- NULL
y_grey <- NULL
x_dark <- NULL
x_blue <- NULL
x_red <- NULL
x_grey <- NULL
for(x in 1:6)
{
# Sequence for black points
y_dark <- c(y_dark,1:x)
x_dark <- c(x_dark,rep(x,x))
# Sequence for blue points
j <- x+1
jmax <- j+6
y_blue <- c(y_blue,j:jmax)
x_blue <- c(x_blue, rep(x,length(j:jmax)))
# Sequence for red points
r <- jmax +1
y_red <- c(y_red,r)
x_red <- c(x_red, rep(x,length(r)))
# sequence for grey points
g <- r+1
if(g > 14)
{
}
else
{
y_grey <- c(y_grey,g:14)
x_grey <- c(x_grey, rep(x,length(g:14)))
}
}
df_dark <- data.frame(x = x_dark, y = y_dark, color = "black")
df_blue <- data.frame(x = x_blue, y = y_blue, color = "blue")
df_red <- data.frame(x = x_red, y = y_red, color = "red")
df_grey <- data.frame(x = x_grey, y = y_grey, color = "grey")
And then, you can plot it using:
library(tidyverse)
DF <- bind_rows(df_dark, df_blue, df_red, df_grey)
DF_arrow <- data.frame(x = 1:6, x_end = 1:6,
y = rep(1,6), y_end = rep(15,6))
ggplot() +
geom_segment(data = DF_arrow,
aes(x = -x, xend = -x_end, y = y, yend = y_end),
arrow = arrow(length = unit(0.03, "npc")))+
geom_point(imherit.aes = FALSE, data = DF, aes(x = -x, y = y, color = color),
size = 4)+
coord_flip()+
scale_color_identity()+
theme(axis.text = element_blank(),
axis.title = element_blank())+
annotate(geom = "text", x = -1, y = 16, label = "time")