so imagine the following example
mtcars %>%
ggplot(aes(mpg,hp)) + geom_point()
How can I add labels to both extremities of my axes without changing the title of my x and y axes?
For instance:
bottom right: "MPG increases"
bottom left (for x axis) : "MPG decreases"
bottom left (for y axis) : "HP decreases"
top left : "HP increases"
Does anyone have any leads on how to do this?
Thank you!
You can try something like this:
library(dplyr)
library(ggplot2)
mtcars %>% ggplot(aes(mpg,hp)) +
geom_point() + annotate("text", x = 33, y = 10,
label = "MPG increases",
hjust=1.1, vjust=-1.1, col="black",
cex=5, fontface = "bold", alpha = 0.8)+
annotate("text", x = 17, y = 10,
label = "MPG decreases",
hjust=1.1, vjust=-1.1, col="black",
cex=5, fontface = "bold", alpha = 0.8)+
annotate("text", x = 17, y = 100,
label = "HP decreases",
hjust=1.1, vjust=-1.1, col="black",
cex=5, fontface = "bold", alpha = 0.8)+
annotate("text", x = 17, y = 310,
label = "HP increases",
hjust=1.1, vjust=-1.1, col="black",
cex=5, fontface = "bold", alpha = 0.8)
Here's one way to do this keeping within the maximum and minimum limits of the data. And picks up on #Tjebo suggestion to include the labelling text within a data frame.
Although not in the question have included arrows to see if this would help distinguish the HP and MPG decreases labels. The code for this can easily be disregarded.
If you want to use this presentation regularly it would pay to make a function.
library(ggplot2)
library(tibble)
mtcars %>%
ggplot(aes(mpg,hp)) +
geom_point()+
geom_text(data = df_lab, aes(x, y, label = lab), vjust = df_lab$vj, hjust = df_lab$hj)+
geom_segment(data = df_ar, aes(x = x, y = y, xend = xend, yend = yend),
lineend = "square", linejoin = "mitre", size = 1, arrow = arrow(length = unit(2, "mm")))
Data
# tibble for labels
df_lab <-
tibble(lab = c("HP increases", "HP decreases", "MPG decreases", "MPG increases"),
x = c(rep(min(mtcars$mpg), 3), max(mtcars$mpg)),
y = c(max(mtcars$hp), rep(min(mtcars$hp), 3)),
vj = rep(c("bottom", "top") , each = 2),
hj = c(rep("left", 3), "right"))
# postitioning helpers for arrows
x_len <- 2
y_len <- 40
y_off <- 15
x_off <- 0.5
# tibble for arrows
df_ar <-
tibble(xend = c(rep(min(mtcars$mpg) - x_off, 2), min(mtcars$mpg), max(mtcars$mpg)),
yend = c(max(mtcars$hp), min(mtcars$hp), rep(min(mtcars$hp) - y_off, 2)),
x = c(rep(min(mtcars$mpg) - x_off, 2), min(mtcars$mpg) + x_len, max(mtcars$mpg) - x_len),
y = c(max(mtcars$hp) - y_len, min(mtcars$hp) + y_len, rep(min(mtcars$hp) - y_off, 2)))
Created on 2020-05-12 by the reprex package (v0.3.0)
Related
I have this data frame :
Raw.Score = c(0,1,2,3,4,5,6,7,8)
Severity = c(-3.56553994,-2.70296933,-1.63969850,-0.81321707,-0.04629182,
0.73721320,1.61278518,2.76647043,3.94804472)
x = data.frame(Raw.Score = Raw.Score, Severity = Severity)
Raw.score are raw numbers from 0 to 8 (let's consider them as the labels of the severity numbers)
Severity are relative numbres that represent the locations of the scores in the diagram
I want to graphically present the results as in the following example using ggplot (the example includes different numbers but I want something similar)
As a fun exercise in ggplot-ing here is one approach to achieve or come close to your desired result.
Raw.Score = c(0,1,2,3,4,5,6,7,8)
Severity = c(-3.56553994,-2.70296933,-1.63969850,-0.81321707,-0.04629182,
0.73721320,1.61278518,2.76647043,3.94804472)
dat <- data.frame(Raw.Score, Severity)
library(ggplot2)
dat_tile <- data.frame(
Severity = seq(-4.1, 4.1, .05)
)
dat_axis <- data.frame(
Severity = seq(-4, 4, 2)
)
tile_height = .15
ymax <- .5
ggplot(dat, aes(y = 0, x = Severity, fill = Severity)) +
# Axis line
geom_hline(yintercept = -tile_height / 2) +
# Colorbar
geom_tile(data = dat_tile, aes(color = Severity), height = tile_height) +
# Sgements connecting top and bottom labels
geom_segment(aes(xend = Severity, yend = -ymax, y = ymax), color = "orange") +
# Axis ticks aka dots
geom_point(data = dat_axis,
y = -tile_height / 2, shape = 21, stroke = 1, fill = "white") +
# ... and labels
geom_text(data = dat_axis, aes(label = Severity),
y = -tile_height / 2 - .1, vjust = 1, fontface = "bold") +
# Bottom labels
geom_label(aes(y = -ymax, label = scales::number(Severity, accuracy = .01))) +
# Top labels
geom_point(aes(y = ymax, color = Severity), size = 8) +
geom_text(aes(y = ymax, label = Raw.Score), fontface = "bold") +
# Colorbar annotations
annotate(geom = "text", fontface = "bold", label = "MILD", color = "black", x = -3.75, y = 0) +
annotate(geom = "text", fontface = "bold", label = "SEVERE", color = "white", x = 3.75, y = 0) +
# Fixing the scales
scale_x_continuous(expand = c(0, 0)) +
scale_y_continuous(limits = c(-ymax, ymax)) +
# Color gradient
scale_fill_gradient(low = "orange", high = "red", guide = "none") +
scale_color_gradient(low = "orange", high = "red", guide = "none") +
# Get rid of all non-data ink
theme_void() +
# Add some plot margin
theme(plot.margin = rep(unit(10, "pt"), 4)) +
coord_cartesian(clip = "off")
See this plot:
tibble(x = 0:10, y = rnorm(11)) %>%
ggplot(aes(x,y)) +
geom_point() +
scale_x_continuous(breaks = c(seq(0,10,2)/10, seq(2,10,1)))
The labels in the beginning of the axis are very crowded. Is there a way to push down only some labels (e.g. those of c(0.2, 0.6, 0.8)) so that all labels would be readable? Bonus: add a vertical line from ticks to those labels which have been pushed down (in other words make the tick longer).
I know I can use vjust = -5 as in + theme(axis.text.x = element_text(vjust = -5)) but that would push down all labels.
Here is a very simple method that pushes down the axis text by adding a new line character \n before the label in the vector x_ticks.
library(tidyverse)
x_ticks <- c(seq(0,10,2)/10, seq(2,10,1))
tibble(x = 0:10, y = rnorm(11)) %>%
ggplot(aes(x,y)) +
geom_point() +
scale_x_continuous(breaks = x_ticks,
labels = ifelse(x_ticks %in% c(0.2, 0.6, 0.8),
paste0("\n", x_ticks), x_ticks))
Created on 2022-03-30 by the reprex package (v2.0.1)
This is how to do it the hard way, if you really want those long ticks
tibble(x = 0:10, y = rnorm(11)) %>%
ggplot(aes(x,y)) +
geom_vline(xintercept = seq(2, 10, 4)/10, color = "white", size = 0.5) +
geom_point() +
scale_x_continuous(breaks = c(seq(0,10,4)/10, seq(2,10,1))) +
coord_cartesian(clip = "off", ylim = c(-2, 2)) +
annotate("text", label = format(seq(2, 10, 4)/10, nsmall = 1),
x = seq(2, 10, 4)/10, y = -2.4,
size = 3) +
annotate("segment", x = seq(2, 10, 4)/10, xend = seq(2, 10, 4)/10,
y = -2.33, yend = -2.2, size = 0.2) +
theme(axis.text = element_text(color = "black"))
I am trying to add labels to a ggplot object. The labels do not look neat and tidy due to their positioning. I have tried using various geom_label_repel and geom_text_repel options but am not having much luck.
I cannot share the data unfortunately, but I have inserted one of my codes below and a screenshot of one section of the redacted graph. The graph has multiple peaks that need labelling. Each label has 2 lines.
I would like the lines connecting the labels to be directly above each peak on the x axis, then turn at a right angle and the line continue horizontally slightly. I would then like the label to sit on top of this horizontal section of the line.
Some peaks are very close together, so the labels will end up being pushed up the y axis so they are able to stack up neatly.
I hope that description makes sense. I would appreciate it if anyone is able to help.
Thank you!
library(ggplot2)
library(ggrepel)
library(dplyr)
upper_plot <- ggplot() +
geom_point(data = plot_data[which(analysis == "Analysis1"),],
aes(x = rel_pos, y = logged_p, color = as.factor(chr)),
size = 0.25) +
scale_color_manual(values = rep(my_upper_colors, nrow(axis_df))) +
geom_point(data=upper_highlight_pos2_old,
aes(x = rel_pos, y = logged_p),
color= c('grey'),
size=0.75,
pch = 16) +
geom_point(data=upper_labels_old,
aes(x = rel_pos, y = logged_p),
color='dark grey',
size=2,
pch = 18) +
geom_point(data=upper_highlight_pos2_novel,
aes(x = rel_pos, y = logged_p),
color= c('black'),
size=0.75,
pch = 16) +
geom_point(data=upper_labels_novel,
aes(x = rel_pos, y = logged_p),
color='black',
size=2,
pch = 18) +
scale_x_continuous(labels = axis_df$chr,
breaks = axis_df$chr_center,
expand = expansion(mult = 0.01)) +
scale_y_continuous(limits = c(0, maxp),
expand = expansion(mult = c(0.02, 0.06))) +
# geom_hline(yintercept = -log10(1e-5), color = "red", linetype = "dashed",
# size = 0.3) +
geom_hline(yintercept = -log10(5e-8), color = "black", linetype = "dashed",
size = 0.3) +
labs(x = "", y = bquote(atop('GWAS', '-log'[10]*'(p)'))) +
theme_classic() +
theme(legend.position = "none",
axis.title.x = element_blank(),
plot.margin = margin(t=5, b = 5, r=5, l = 10)) +
geom_label_repel(data = upper_labels,
aes(x = rel_pos, y = logged_p, label = label),
ylim = c(maxp / 3, NA),
size = 2,
force_pull = 0,
nudge_x = 0.5,
box.padding = 0.5,
nudge_y = 0.5,
min.segment.length = 0, # draw all lines no matter how short
segment.size = 0.2,
segment.curvature = -0.1,
segment.ncp = 3,
segment.angle = 45,
label.size=NA, #no border/box
fill = NA, #no background
)
This is my current untidy layout...
EDIT:
This is the sort of layout I am after. The lines will need to be flexible and either be right-handed or left-handed depending on space (source: https://www.nature.com/articles/s41588-020-00725-7)
I would like to produce a graphic combining four facets of a graph with insets in each facet showing a detail of the respective plot. This is one of the things I tried:
#create data frame
n_replicates <- c(rep(1:10,15),rep(seq(10,100,10),15),rep(seq(100,1000,100),15),rep(seq(1000,10000,1000),15))
sim_years <- rep(sort(rep((1:15),10)),4)
sd_data <- rep (NA,600)
for (i in 1:600) {
sd_data[i]<-rnorm(1,mean=exp(0.1 * sim_years[i]), sd= 1/n_replicates[i])
}
max_rep <- sort(rep(c(10,100,1000,10000),150))
data_frame <- cbind.data.frame(n_replicates,sim_years,sd_data,max_rep)
#do first basic plot
library(ggplot2)
plot1<-ggplot(data=data_frame, aes(x=sim_years,y=sd_data,group =n_replicates, col=n_replicates)) +
geom_line() + theme_bw() +
labs(title ="", x = "year", y = "sd")
plot1
#make four facets
my_breaks = c(2, 10, 100, 1000, 10000)
facet_names <- c(
`10` = "2, 3, ..., 10 replicates",
`100` = "10, 20, ..., 100 replicates",
`1000` = "100, 200, ..., 1000 replicates",
`10000` = "1000, 2000, ..., 10000 replicates"
)
plot2 <- plot1 +
facet_wrap( ~ max_rep, ncol=2, labeller = as_labeller(facet_names)) +
scale_colour_gradientn(name = "number of replicates", trans = "log",
breaks = my_breaks, labels = my_breaks, colours = rainbow(20))
plot2
#extract inlays (this is where it goes wrong I think)
library(ggpmisc)
library(tibble)
library(dplyr)
inset <- tibble(x = 0.01, y = 10.01,
plot = list(plot2 +
facet_wrap( ~ max_rep, ncol=2, labeller = as_labeller(facet_names)) +
coord_cartesian(xlim = c(13, 15),
ylim = c(3, 5)) +
labs(x = NULL, y = NULL, color = NULL) +
scale_colour_gradient(guide = FALSE) +
theme_bw(10)))
plot3 <- plot2 +
expand_limits(x = 0, y = 0) +
geom_plot_npc(data = inset, aes(npcx = x, npcy = y, label = plot)) +
annotate(geom = "rect",
xmin = 13, xmax = 15, ymin = 3, ymax = 5,
linetype = "dotted", fill = NA, colour = "black")
plot3
That leads to the following graphic:
As you can see, the colours in the insets are wrong, and all four of them appear in each of the facets even though I only want the corresponding inset of course. I read through a lot of questions here (to even get me this far) and also some examples in the ggpmisc user guide but unfortunately I am still a bit lost on how to achieve what I want. Except maybe to do it by hand extracting four insets and then combining them with plot2. But I hope there will be a better way to do this. Thank you for your help!
Edit: better graphic now thanks to this answer, but problem remains partially unsolved:
The following code does good insets, but unfortunately the colours are not preserved. As in the above version each inset does its own rainbow colours anew instead of inheriting the partial rainbow scale from the facet it belongs to. Does anyone know why and how I could change this? In comments I put another (bad) attempt at solving this, it preserves the colors but has the problem of putting all four insets in each facet.
library(ggpmisc)
library(tibble)
library(dplyr)
# #extract inlays: good colours, but produces four insets.
# fourinsets <- tibble(#x = 0.01, y = 10.01,
# x = c(rep(0.01, 4)),
# y = c(rep(10.01, 4)),
# plot = list(plot2 +
# facet_wrap( ~ max_rep, ncol=2) +
# coord_cartesian(xlim = c(13, 15),
# ylim = c(3, 5)) +
# labs(x = NULL, y = NULL, color = NULL) +
# scale_colour_gradientn(name = "number of replicates", trans = "log", guide = FALSE,
# colours = rainbow(20)) +
# theme(
# strip.background = element_blank(),
# strip.text.x = element_blank()
# )
# ))
# fourinsets$plot
library(purrr)
pp <- map(unique(data_frame$max_rep), function(x) {
plot2$data <- plot2$data %>% filter(max_rep == x)
plot2 +
coord_cartesian(xlim = c(12, 14),
ylim = c(3, 4)) +
labs(x = NULL, y = NULL) +
theme(
strip.background = element_blank(),
strip.text.x = element_blank(),
legend.position = "none",
axis.text=element_blank(),
axis.ticks=element_blank()
)
})
#pp[[2]]
inset_new <- tibble(x = c(rep(0.01, 4)),
y = c(rep(10.01, 4)),
plot = pp,
max_rep = unique(data_frame$max_rep))
final_plot <- plot2 +
geom_plot_npc(data = inset_new, aes(npcx = x, npcy = y, label = plot, vp.width = 0.3, vp.height =0.6)) +
annotate(geom = "rect",
xmin = 12, xmax = 14, ymin = 3, ymax = 4,
linetype = "dotted", fill = NA, colour = "black")
#final_plot
final_plot then looks like this:
I hope this clarifies the problem a bit. Any ideas are very welcome :)
Modifying off #user63230's excellent answer:
pp <- map(unique(data_frame$max_rep), function(x) {
plot2 +
aes(alpha = ifelse(max_rep == x, 1, 0)) +
coord_cartesian(xlim = c(12, 14),
ylim = c(3, 4)) +
labs(x = NULL, y = NULL) +
scale_alpha_identity() +
facet_null() +
theme(
strip.background = element_blank(),
strip.text.x = element_blank(),
legend.position = "none",
axis.text=element_blank(),
axis.ticks=element_blank()
)
})
Explanation:
Instead of filtering the data passed into plot2 (which affects the mapping of colours), we impose a new aesthetic alpha, where lines belonging to the other replicate numbers are assigned 0 for transparency;
Use scale_alpha_identity() to tell ggplot that the alpha mapping is to be used as-is: i.e. 1 for 100%, 0 for 0%.
Add facet_null() to override plot2's existing facet_wrap, which removes the facet for the inset.
Everything else is unchanged from the code in the question.
I think this will get you started although its tricky to get the size of the inset plot right (when you include a legend).
#set up data
library(ggpmisc)
library(tibble)
library(dplyr)
library(ggplot2)
# create data frame
n_replicates <- c(rep(1:10, 15), rep(seq(10, 100, 10), 15), rep(seq(100,
1000, 100), 15), rep(seq(1000, 10000, 1000), 15))
sim_years <- rep(sort(rep((1:15), 10)), 4)
sd_data <- rep(NA, 600)
for (i in 1:600) {
sd_data[i] <- rnorm(1, mean = exp(0.1 * sim_years[i]), sd = 1/n_replicates[i])
}
max_rep <- sort(rep(c(10, 100, 1000, 10000), 150))
data_frame <- cbind.data.frame(n_replicates, sim_years, sd_data, max_rep)
# make four facets
my_breaks = c(2, 10, 100, 1000, 10000)
facet_names <- c(`10` = "2, 3, ..., 10 replicates", `100` = "10, 20, ..., 100 replicates",
`1000` = "100, 200, ..., 1000 replicates", `10000` = "1000, 2000, ..., 10000 replicates")
Get overall plot:
# overall facet plot
overall_plot <- ggplot(data = data_frame, aes(x = sim_years, y = sd_data, group = n_replicates, col = n_replicates)) +
geom_line() +
theme_bw() +
labs(title = "", x = "year", y = "sd") +
facet_wrap(~max_rep, ncol = 2, labeller = as_labeller(facet_names)) +
scale_colour_gradientn(name = "number of replicates", trans = "log", breaks = my_breaks, labels = my_breaks, colours = rainbow(20))
#plot
overall_plot
which gives:
Then from the overall plot you want to extract each plot, see here. We can map over the list to extract one at a time:
pp <- map(unique(data_frame$max_rep), function(x) {
overall_plot$data <- overall_plot$data %>% filter(max_rep == x)
overall_plot + # coord_cartesian(xlim = c(13, 15), ylim = c(3, 5)) +
labs(x = NULL, y = NULL) +
theme_bw(10) +
theme(legend.position = "none")
})
If we look at one of these (I've removed the legend) e.g.
pp[[1]]
#pp[[2]]
#pp[[3]]
#pp[[4]]
Gives:
Then we want to add these inset plots into a dataframe so that each plot has its own row:
inset <- tibble(x = c(rep(0.01, 4)),
y = c(rep(10.01, 4)),
plot = pp,
max_rep = unique(data_frame$max_rep))
Then merge this into the overall plot:
overall_plot +
expand_limits(x = 0, y = 0) +
geom_plot_npc(data = inset, aes(npcx = x, npcy = y, label = plot, vp.width = 0.8, vp.height = 0.8))
Gives:
Here is a solution based on Z. Lin's answer, but using ggforce::facet_wrap_paginate() to do the filtering and keeping colourscales consistent.
First, we can make the 'root' plot containing all the data with no facetting.
library(ggpmisc)
library(tibble)
library(dplyr)
n_replicates <- c(rep(1:10,15),rep(seq(10,100,10),15),rep(seq(100,1000,100),15),rep(seq(1000,10000,1000),15))
sim_years <- rep(sort(rep((1:15),10)),4)
sd_data <- rep (NA,600)
for (i in 1:600) {
sd_data[i]<-rnorm(1,mean=exp(0.1 * sim_years[i]), sd= 1/n_replicates[i])
}
max_rep <- sort(rep(c(10,100,1000,10000),150))
data_frame <- cbind.data.frame(n_replicates,sim_years,sd_data,max_rep)
my_breaks = c(2, 10, 100, 1000, 10000)
facet_names <- c(
`10` = "2, 3, ..., 10 replicates",
`100` = "10, 20, ..., 100 replicates",
`1000` = "100, 200, ..., 1000 replicates",
`10000` = "1000, 2000, ..., 10000 replicates"
)
base <- ggplot(data=data_frame,
aes(x=sim_years,y=sd_data,group =n_replicates, col=n_replicates)) +
geom_line() +
theme_bw() +
scale_colour_gradientn(
name = "number of replicates",
trans = "log10", breaks = my_breaks,
labels = my_breaks, colours = rainbow(20)
) +
labs(title ="", x = "year", y = "sd")
Next, the main plot will be just the root plot with facet_wrap().
main <- base + facet_wrap(~ max_rep, ncol = 2, labeller = as_labeller(facet_names))
Then the new part is to use facet_wrap_paginate with nrow = 1 and ncol = 1 for every max_rep, which we'll use as insets. The nice thing is that this does the filtering and it keeps colour scales consistent with the root plot.
nmax_rep <- length(unique(data_frame$max_rep))
insets <- lapply(seq_len(nmax_rep), function(i) {
base + ggforce::facet_wrap_paginate(~ max_rep, nrow = 1, ncol = 1, page = i) +
coord_cartesian(xlim = c(12, 14), ylim = c(3, 4)) +
guides(colour = "none", x = "none", y = "none") +
theme(strip.background = element_blank(),
strip.text = element_blank(),
axis.title = element_blank(),
plot.background = element_blank())
})
insets <- tibble(x = rep(0.01, nmax_rep),
y = rep(10.01, nmax_rep),
plot = insets,
max_rep = unique(data_frame$max_rep))
main +
geom_plot_npc(data = insets,
aes(npcx = x, npcy = y, label = plot,
vp.width = 0.3, vp.height = 0.6)) +
annotate(geom = "rect",
xmin = 12, xmax = 14, ymin = 3, ymax = 4,
linetype = "dotted", fill = NA, colour = "black")
Created on 2020-12-15 by the reprex package (v0.3.0)
I was trying to plot some predicted vs. actual data, something that resembles the following:
# Some random data
x <- seq(1: 10)
y_pred <- runif(10, min = -10, max = 10)
y_obs <- y_pred + rnorm(10)
# Faking a CI
Lo.95 <- y_pred - 1.96
Hi.95 <- y_pred + 1.96
my_df <- data.frame(x, y_pred, y_obs, Lo.95, Hi.95)
ggplot(my_df, aes(x = x, y = y_pred)) +
geom_line(aes(colour = "Forecasted Data"), size = 1.2) +
geom_point(aes(x = x, y = y_obs, colour = "Actual Data"), size = 3) +
geom_ribbon(aes(ymin=Lo.95, ymax=Hi.95, x=x, linetype = NA, colour = "Confidence Interval"), alpha=0.2) +
theme_grey() +
scale_colour_manual(
values = c("gray30", "blue", "red"),
guide = guide_legend(override.aes = list(
border=c(NA, NA, NA),
fill=c("gray30", "white", "white"),
linetype = c("blank", "blank", "solid"),
shape = c(NA, 19, NA))))
The plot looks like this:
The only issue I have with this plot is the red border surrounding the legend item symbol for the line (i.e. the forecasted data). Is there any way I can remove it without breaking the rest of my plot?
I think geom_ribbon was the problem. If we take its color & fill out of aes, everything looks fine
library(ggplot2)
# Some random data
x <- seq(1: 10)
y_pred <- runif(10, min = -10, max = 10)
y_obs <- y_pred + rnorm(10)
# Faking a CI
Lo.95 <- y_pred - 1.96
Hi.95 <- y_pred + 1.96
my_df <- data.frame(x, y_pred, y_obs, Lo.95, Hi.95)
m1 <- ggplot(my_df, aes(x = x, y = y_pred)) +
geom_point(aes(x = x, y = y_obs, colour = "Actual"), size = 3) +
geom_line(aes(colour = "Forecasted"), size = 1.2) +
geom_ribbon(aes(x = x, ymin = Lo.95, ymax = Hi.95),
fill = "grey30", alpha = 0.2) +
scale_color_manual("Legend",
values = c("blue", "red"),
labels = c("Actual", "Forecasted")) +
guides( color = guide_legend(
order = 1,
override.aes = list(
color = c("blue", "red"),
fill = c("white", "white"),
linetype = c("blank", "solid"),
shape = c(19, NA)))) +
theme_bw() +
# remove legend key border color & background
theme(legend.key = element_rect(colour = NA, fill = NA),
legend.box.background = element_blank())
m1
As we leave Confidence Interval out of aes, we no longer have its legend. One workaround is to create an invisible point and take one unused geom to manually create a legend key. Here we can use size/shape (credit to this answer)
m2 <- m1 +
geom_point(aes(x = x, y = y_obs, size = "Confidence Interval", shape = NA)) +
guides(size = guide_legend(NULL,
order = 2,
override.aes = list(shape = 15,
color = "lightgrey",
size = 6))) +
# Move legends closer to each other
theme(legend.title = element_blank(),
legend.justification = "center",
legend.spacing.y = unit(0.05, "cm"),
legend.margin = margin(0, 0, 0, 0),
legend.box.margin = margin(0, 0, 0, 0))
m2
Created on 2018-03-19 by the reprex package (v0.2.0).
A better way to address this question would be to specify show.legend = F option in the geom_ribbon(). This will eliminate the need for the second step for adding and merging the legend key for the confidence interval. Here is the code with slight modifications.
ggplot(my_dff, aes(x = x, y = y_pred)) +
geom_line(aes(colour = "Forecasted Data"), size = 1) +
geom_point(aes(x = x, y = y_obs, colour = "Actual Data"), size = 1) +
geom_ribbon(aes(ymin=Lo.95, ymax=Hi.95, x=x, linetype = NA, colour = "Confidence Interval"), alpha=0.2, show.legend = F) +
theme_grey() +
scale_colour_manual(
values = c("blue", "gray30", "red"))+
guides(color = guide_legend(
override.aes = list(linetype = c(1, 1, 0)),
shape = c(1, NA, NA),
reverse = T))
My plot
Credit to https://stackoverflow.com/users/4282026/marblo
for their answer to similar question.