Related
I have a df:
test<- data.frame (Metrics = c("PCT_PF_READS (%)" , "PCT_Q30_R1 (%)" , "PCT_Q30_R2 (%)"),
LowerLimit = c(80,80,80),
Percent = c(93.1,95.1,92.4)
)
> test
Metrics LowerLimit Percent
1 PCT_PF_READS (%) 80 93.1
2 PCT_Q30_R1 (%) 80 95.1
3 PCT_Q30_R2 (%) 80 92.4
I am trying to plot in ggplot2 but I want to specify the yaxis.
If I do:
ggplot(data=test3, aes(x= Metrics,y=Percent,)) +
geom_bar(stat="identity" )
If I try to set the yaxis to start at 75, I get a blank plot:
ggplot(data=test3, aes(x= Metrics,y=Percent,)) +
geom_bar(stat="identity" ) + scale_y_continuous(limits = c(75,100))
with the message
Warning message:
Removed 3 rows containing missing values (geom_bar)
But the values are in range????
Does this answer your question?
library(tidyverse)
test<- data.frame (Metrics = c("PCT_PF_READS (%)" , "PCT_Q30_R1 (%)" , "PCT_Q30_R2 (%)"),
LowerLimit = c(80,80,80),
Percent = c(93.1,95.1,92.4)
)
# Starting plot:
ggplot(data = test, aes(x = Metrics, y = Percent)) +
geom_bar(stat = "identity")
# If you cut off any of the bar using "limit" the bar is removed,
# E.g. this removes the middle bar (Percent = 95.1)
ggplot(data = test, aes(x = Metrics, y = Percent)) +
geom_bar(stat = "identity") +
scale_y_continuous(limits = c(0,95))
#> Warning: Removed 1 rows containing missing values (position_stack).
# A better solution is to use "coord_cartesian()"
ggplot(data = test, aes(x = Metrics, y = Percent)) +
geom_bar(stat = "identity") +
coord_cartesian(ylim = c(75, 100))
# Although it's generally advised to keep the whole axis,
# as 'chopping off' the bottom can be misleading
# Another alternative is to write the percentages on the plot:
ggplot(data = test, aes(x = Metrics, y = Percent)) +
geom_bar(stat = "identity") +
geom_text(aes(label = paste0(Percent, "%")),
nudge_y = 2)
Created on 2022-10-19 by the reprex package (v2.0.1)
I have a dataframe (dat) with two columns 1) Month and 2) Value. I would like to highlight that the x-axis is not continuous in my boxplot by interrupting the x-axis with two angled lines on the x-axis that are empty between the angled lines.
Example Data and Boxplot
library(ggplot2)
set.seed(321)
dat <- data.frame(matrix(ncol = 2, nrow = 18))
x <- c("Month", "Value")
colnames(dat) <- x
dat$Month <- rep(c(1,2,3,10,11,12),3)
dat$Value <- rnorm(18,20,2)
ggplot(data = dat, aes(x = factor(Month), y = Value)) +
geom_boxplot() +
labs(x = "Month") +
theme_bw() +
theme(panel.grid = element_blank(),
text = element_text(size = 16),
axis.text.x = element_text(size = 14, color = "black"),
axis.text.y = element_text(size = 14, color = "black"))
The ideal figure would look something like below. How can I make this discontinuous axis in ggplot?
You could make use of the extended axis guides in the ggh4x package. Alas, you won't easily be able to create the "separators" without a hack similar to the one suggested by user Zhiqiang Wang
guide_axis_truncated accepts vectors to define lower and upper trunks. This also works for units, by the way, then you have to pass the vector inside the unit function (e.g., trunc_lower = unit(c(0,.45), "npc") !
library(ggplot2)
library(ggh4x)
set.seed(321)
dat <- data.frame(matrix(ncol = 2, nrow = 18))
x <- c("Month", "Value")
colnames(dat) <- x
dat$Month <- rep(c(1,2,3,10,11,12),3)
dat$Value <- rnorm(18,20,2)
# this is to make it slightly more programmatic
x1end <- 3.45
x2start <- 3.55
p <-
ggplot(data = dat, aes(x = factor(Month), y = Value)) +
geom_boxplot() +
labs(x = "Month") +
theme_classic() +
theme(axis.line = element_line(colour = "black"))
p +
guides(x = guide_axis_truncated(
trunc_lower = c(-Inf, x2start),
trunc_upper = c(x1end, Inf)
))
Created on 2021-11-01 by the reprex package (v2.0.1)
The below is taking user Zhiqiang Wang's hack a step further. You will see I am using simple trigonometry to calculate the segment coordinates. in order to make the angle actually look as it is defined in the function, you would need to set coord_equal.
# a simple function to help make the segments
add_separators <- function(x, y = 0, angle = 45, length = .1){
add_y <- length * sin(angle * pi/180)
add_x <- length * cos(angle * pi/180)
## making the list for your segments
myseg <- list(x = x - add_x, xend = x + add_x,
y = rep(y - add_y, length(x)), yend = rep(y + add_y, length(x)))
## this function returns an annotate layer with your segment coordinates
annotate("segment",
x = myseg$x, xend = myseg$xend,
y = myseg$y, yend = myseg$yend)
}
# you will need to set limits for correct positioning of your separators
# I chose 0.05 because this is the expand factor by default
y_sep <- min(dat$Value) -0.05*(min(dat$Value))
p +
guides(x = guide_axis_truncated(
trunc_lower = c(-Inf, x2start),
trunc_upper = c(x1end, Inf)
)) +
add_separators(x = c(x1end, x2start), y = y_sep, angle = 70) +
# you need to set expand to 0
scale_y_continuous(expand = c(0,0)) +
## to make the angle look like specified, you would need to use coord_equal()
coord_cartesian(clip = "off", ylim = c(y_sep, NA))
I think it is possible to get what you want. It may take some work.
Here is your graph:
library(ggplot2)
set.seed(321)
dat <- data.frame(matrix(ncol = 2, nrow = 18))
x <- c("Month", "Value")
colnames(dat) <- x
dat$Month <- rep(c(1,2,3,10,11,12),3)
dat$Value <- rnorm(18,20,2)
p <- ggplot(data = dat, aes(x = factor(Month), y = Value)) +
geom_boxplot() +
labs(x = "Month") +
theme_bw() +
theme(panel.grid = element_blank(),
text = element_text(size = 16),
axis.text.x = element_text(size = 14, color = "black"),
axis.text.y = element_text(size = 14, color = "black"))
Here is my effort:
p + annotate("segment", x = c(3.3, 3.5), xend = c(3.6, 3.8), y = c(14, 14), yend = c(15, 15))+
coord_cartesian(clip = "off", ylim = c(15, 25))
Get something like this:
If you want to go further, it may take several tries to get it right:
p + annotate("segment", x = c(3.3, 3.5), xend = c(3.6, 3.8), y = c(14, 14), yend = c(15, 15))+
annotate("segment", x = c(0, 3.65), xend = c(3.45, 7), y = c(14.55, 14.55), yend = c(14.55, 14.55)) +
coord_cartesian(clip = "off", ylim = c(15, 25)) +
theme_classic()+
theme(axis.line.x = element_blank())
Just replace axis with two new lines. This is a rough idea, it may take some time to make it perfect.
You could use facet_wrap. If you assign the first 3 months to one group, and the other months to another, then you can produce two plots that are side by side and use a single y axis.
It's not exactly what you want, but it will show the data effectively, and highlights the fact that the x axis is not continuous.
dat$group[dat$Month %in% c("1", "2", "3")] <- 1
dat$group[dat$Month %in% c("10", "11", "12")] <- 2
ggplot(data = dat, aes(x = factor(Month), y = Value)) +
geom_boxplot() +
labs(x = "Month") +
theme_bw() +
theme(panel.grid = element_blank(),
text = element_text(size = 16),
axis.text.x = element_text(size = 14, color = "black"),
axis.text.y = element_text(size = 14, color = "black")) +
facet_wrap(~group, scales = "free_x")
* Differences in the plot are likely due to using different versions of R where the set.seed gives different result
Following codes generate a grid of plots shown in the figure below:
library(tidyverse)
library(cowplot)
p1 <- cars %>%
ggplot(aes(x = speed, y = dist)) +
geom_point() +
theme_bw()
p2 <- cars %>%
ggplot(aes(x = speed, y = dist)) +
geom_point() +
scale_y_continuous(trans = "log2", breaks = c(2, 4, 8, 16, 32, 64, 128),
limits = c(2, 128)) +
annotation_logticks(sides = "l") +
theme_bw()
p3 <- diamonds %>%
ggplot(aes(x = carat, y = price, colour = clarity)) +
geom_point() +
theme_bw() +
theme(legend.position = c(0.8, 0.4))
p4 <- plot_grid(p1, p1, nrow = 2, labels = c("B", "C"))
p5 <- plot_grid(p3, p4, nrow = 2, align = "hv", axis = "lb", rel_heights = c(0.5, 1),
labels = c("A", ""))
p6 <- plot_grid(p1, p2, nrow = 2, align = "h", rel_heights = c(0.5, 1),
labels = c("D", "E"))
p7 <- plot_grid(p5, p6, ncol = 2, align = "b")
p7
I wish to align the bottom axis of (A) with top axes of (B, C) respectively, and align bottom axis of (C) with the bottom axis of (E). This should stretch the (B,C) grid plot across the height of (E) and width of (A). I have tried several alignment options.
I have found queries similar to this problem which allow to either get the width or the height alignment right but not both!
I will also add that this reproducible example is the closest I can get to my actual plot. Here I have managed to align the width with panel (A) but am unable to align the height of (B,C) with (E).
May I suggest to use patchwork instead? I find that it handles the alignment of panels more elegantly than anything else around.
library(tidyverse)
library(cowplot)
p1 <- cars %>%
ggplot(aes(x = speed, y = dist)) +
geom_point() +
theme_bw()
p2 <- cars %>%
ggplot(aes(x = speed, y = dist)) +
geom_point() +
scale_y_continuous(trans = "log2", breaks = c(2, 4, 8, 16, 32, 64, 128),
limits = c(2, 128)) +
annotation_logticks(sides = "l") +
theme_bw()
p3 <- diamonds %>%
ggplot(aes(x = carat, y = price, colour = clarity)) +
geom_point() +
theme_bw() +
theme(legend.position = c(0.8, 0.4))
library(patchwork)
#>
#> Attaching package: 'patchwork'
#> The following object is masked from 'package:cowplot':
#>
#> align_plots
p3 + p1 + p1 + p1 + p2 +
plot_layout(
design = "
AD
BE
CE
"
) +
plot_annotation(tag_levels = "A")
Created on 2022-01-05 by the reprex package (v2.0.1)
library(tidyverse)
set.seed(12345)
dat <- data.frame(year = c(rep(1990, 100), rep(1991, 100), rep(1992, 100)),
fish_length = sample(x = seq(from = 10, 131, by = 0.1), 300, replace = F),
nb_caught = sample(x = seq(from = 1, 200, by = 0.1), 300, replace = T),
stringsAsFactors = F) %>%
mutate(age = ifelse(fish_length < 20, 1,
ifelse(fish_length >= 20 & fish_length < 100, 2,
ifelse(fish_length >= 100 & fish_length < 130, 3, 4)))) %>%
arrange(year, fish_length)
head(dat)
year fish_length nb_caught age
1 1990 10.1 45.2 1
2 1990 10.7 170.0 1
3 1990 10.9 62.0 1
4 1990 12.1 136.0 1
5 1990 14.1 80.8 1
6 1990 15.0 188.9 1
dat %>% group_by(year) %>% summarise(ages = n_distinct(age)) # Only 1992 has age 4 fish
# A tibble: 3 x 2
year ages
<dbl> <int>
1 1990 3
2 1991 3
3 1992 4
dat %>% filter(age == 4) # only 1 row for age 4
year fish_length nb_caught age
1 1992 130.8 89.2 4
Here:
year = year of sampling
fish_length = length of the fish in cm
nb_caught = number of fish caught following the use of an age-length key, hence explaining the presence of decimals
age = age of the fish
graph1: geom_violin not using the weight aesthetic.
Here, I got to copy each line of dat according to the value found in nb_caught.
dim(dat) # 300 rows
dat_graph1 <- dat[rep(1:nrow(dat), floor(dat$nb_caught)), ]
dim(dat_graph1) # 30932 rows
dat_graph1$nb_caught <- NULL # useless now
sum(dat$nb_caught) - nrow(dat_graph1) # 128.2 rows lost here
Since I have decimal values of nb_caught, I took the integer value to create dat_graph1. I lost 128.2 "rows" in the process.
Now for the graph:
dat_tile <- data.frame(year = sort(unique(dat$year))[sort(unique(dat$year)) %% 2 == 0])
# for the figure's background
graph1 <- ggplot(data = dat_graph1,
aes(x = as.factor(year), y = fish_length, fill = as.factor(age),
color = as.factor(age), .drop = F)) +
geom_tile(data = dat_tile, aes(x = factor(year), y = 1, height = Inf, width = 1),
fill = "grey80", inherit.aes = F) +
geom_violin(draw_quantiles = c(0.05, 0.5, 0.95), color = "black",
scale = "width", position = "dodge") +
scale_x_discrete(expand = c(0,0)) +
labs(x = "Year", y = "Fish length", fill = "Age", color = "Age", title = "graph1") +
scale_fill_brewer(palette = "Paired", drop = F) + # drop = F for not losing levels
scale_color_brewer(palette = "Paired", drop = F) + # drop = F for not losing levels
scale_y_continuous(expand = expand_scale(mult = 0.01)) +
theme_bw()
graph1
graph1
Note here that I have a flat bar for age 4 in year 1992.
dat_graph1 %>% filter(year == 1992, age == 4) %>% pull(fish_length) %>% unique
[1] 130.8
That is because I only have one length for that particular year-age combination.
graph2: geom_violin using the weight aesthetic.
Now, instead of copying each row of dat by the value of number_caught, let's use the weight aesthetic.
Let's calculate the weight wt that each line of dat will have in the calculation of the density curve of each year-age combinations.
dat_graph2 <- dat %>%
group_by(year, age) %>%
mutate(wt = nb_caught / sum(nb_caught)) %>%
as.data.frame()
head(dat_graph2)
year fish_length nb_caught age wt
1 1990 10.1 45.2 1 0.03573123
2 1990 10.7 170.0 1 0.13438735
3 1990 10.9 62.0 1 0.04901186
4 1990 12.1 136.0 1 0.10750988
5 1990 14.1 80.8 1 0.06387352
6 1990 15.0 188.9 1 0.14932806
graph2 <- ggplot(data = dat_graph2,
aes(x = as.factor(year), y = fish_length, fill = as.factor(age),
color = as.factor(age), .drop = F)) +
geom_tile(data = dat_tile, aes(x = factor(year), y = 1, height = Inf, width = 1),
fill = "grey80", inherit.aes = F) +
geom_violin(aes(weight = wt), draw_quantiles = c(0.05, 0.5, 0.95), color = "black",
scale = "width", position = "dodge") +
scale_x_discrete(expand = c(0,0)) +
labs(x = "Year", y = "Fish length", fill = "Age", color = "Age", title = "graph2") +
scale_fill_brewer(palette = "Paired", drop = F) + # drop = F for not losing levels
scale_color_brewer(palette = "Paired", drop = F) + # drop = F for not losing levels
scale_y_continuous(expand = expand_scale(mult = 0.01)) +
theme_bw()
graph2
dat_graph2 %>% filter(year == 1992, age == 4)
year fish_length nb_caught age wt
1 1992 130.8 89.2 4 1
graph2
Note here that the flat bar for age 4 in year 1992 seen on graph1 has been dropped here even though the line exists in dat_graph2.
My questions
Why is the age 4 in 1992 level dropped when using the weight aesthetic? How can I overcome this?
Why are the two graphs not visually alike even though they used the same data?
Thanks in advance for your help!
1.
Problem 1 is not related to using the weight aesthetic. You can check this by dropping the weight aesthetic in the code for your second graph. The problem is, that the algorithm for computing the density fails, when there are too less observations.
That is the reason, why group 4 shows up in graph 1 with the expanded dataset (grpah 1). Here you increase the number of observations by replicating the number of obs.
Unfortunately, geom_violin gives no warning in your specific case. However, if you filter dat_graph2 for age == 4 geom_violin gives you the warning
Warning message:
Computation failed in `stat_ydensity()`:
replacement has 1 row, data has 0
geom_density is much clearer on this issue, giving a warning, that groups with less than two obs have been dropped.
Unfortunately, I have no solution to overcome this, besides working with the expanded dataset.
2.
Concerning problem 2 I have no convincing answer except that I guess that this is related to the details of the kernel density estimator used by geom_violin, geom_density, ... and perhaps also somehow related to the number of data points.
My input data looks like:
COMPANY DOMAIN REVIEW PROGRESS
Company A Service Good +
Company A Response Good +
Company A Delay Very Good
Company A Cost Poor -
Company B Service Poor -
Company B Delay Average
Company B Cost Good +
Company C Service Very Poor +
Company C Cost Average
I produced a heat map in which I add some text (value of the "PROGRESS" variable - i.e. plus or minus sign).
Here is my code:
require("ggplot2")
graph <- read.table("input.tab", header=T, sep="\t")
ggplot(data=graph, aes(x=COMPANY, y=DOMAIN, group=REVIEW, fill=REVIEW)) +
geom_tile() +
geom_text(aes(x=COMPANY, y=DOMAIN, label=PROGRESS)) +
scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) +
geom_vline(xintercept=seq(1.5, length(graph$COMPANY)+0.5)) +
geom_hline(yintercept=seq(1.5, length(graph$DOMAIN)+0.5)) +
theme(
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
axis.line = element_blank(),
axis.ticks = element_blank(),
panel.background = element_blank(),
plot.background = element_blank(),
axis.title=element_blank(),
axis.text.x = element_text(angle=45, size=12, hjust=1)
)
However I am struggling adding (see figure modified manually below):
(1) the following "PROGRESS" legend as part of the color code already listed:
+ Better
- Worse
(2) the count of data available on each row between the right side of the plot and the legend
(3) the count of data available on each column on top of the plot
Any advice?
Here's my proposed solution, I added comments in the code for you to understand what I did. There is probably a better way of generating the grid, though. Hope it helps.
graph <- read_csv(
"COMPANY ,DOMAIN ,REVIEW ,PROGRESS
Company A ,Service ,Good ,+
Company A ,Response ,Good ,+
Company A ,Delay ,Very Good ,
Company A ,Cost ,Poor ,-
Company B ,Service ,Poor ,-
Company B ,Delay ,Average ,
Company B ,Cost ,Good ,+
Company C ,Service ,Very Poor ,+
Company C ,Cost ,Average ,")
ggplot() +
# moved aesthetics and data to each geom,
# if you keep them in the ggplot call,
# you have to specify `inherit.aes = FALSE` in the rest of the geoms
geom_tile(data = graph,
aes(x = COMPANY,
y = DOMAIN,
fill = REVIEW)) +
# changed from `geom_text` to `geom_point` with custom shapes
geom_point(data = graph,
aes(x = COMPANY,
y = DOMAIN,
shape = factor(PROGRESS, labels = c("Worse", "Better"))),
size = 3) +
# custom shape scale
scale_shape_manual(name = "", values = c("-", "+")) +
# calculate marginal totals "on the fly"
# top total
geom_text(data = summarize(group_by(graph, COMPANY),
av_data = length(!is.na(PROGRESS))),
aes(x = COMPANY,
y = length(unique(graph$DOMAIN)) + 0.7,
label = av_data)) +
# right total
geom_text(data = summarize(group_by(graph, DOMAIN),
av_data = length(!is.na(PROGRESS))),
aes(x = length(unique(graph$COMPANY)) + 0.7,
y = DOMAIN, label = av_data)) +
# expand the plotting area to accomodate for the marginal totals
scale_x_discrete(expand = c(0, 0.8)) +
scale_y_discrete(expand = c(0, 0.8)) +
# changed to `geom_segment` to generate the grid, otherwise grid extends
# beyond the heatmap
# horizontal lines
geom_segment(aes(y = rep(0.5, 1 + length(unique(graph$COMPANY))),
yend = rep(length(unique(graph$DOMAIN)) + 0.5,
1 + length(unique(graph$COMPANY))),
x = seq(0.5, 1 + length(unique(graph$COMPANY))),
xend = seq(0.5, 1 + length(unique(graph$COMPANY))))) +
# vertical lines
geom_segment(aes(x = rep(0.5, 1 + length(unique(graph$DOMAIN))),
xend = rep(length(unique(graph$COMPANY)) + 0.5,
1 + length(unique(graph$DOMAIN))),
y = seq(0.5, 1 + length(unique(graph$DOMAIN))),
yend = seq(0.5, 1 + length(unique(graph$DOMAIN))))) +
# custom legend order
guides(fill = guide_legend(order = 1),
shape = guide_legend(order = 2)) +
# theme tweaks
theme(
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
axis.line = element_blank(),
axis.ticks = element_blank(),
panel.background = element_blank(),
plot.background = element_blank(),
axis.title = element_blank(),
axis.text.x = element_text(angle = 45,
size = 12,
hjust = 1,
# move text up 20 pt
margin = margin(-20,0,0,0, "pt")),
# move text right 20 pt
axis.text.y = element_text(margin = margin(0,-20,0,0, "pt"))
)