I want to use the below in rmarkdown word document but the bars are too long; the axis break is good. I want to compress the size of ggplot bars while maintaining readiblity
library(tidyverse)
library(scales)
library(patchwork)
options(scipen = 999)
df <- tribble(
~category, ~ numbers, ~value,
"category 1",8, 9901020,
"category 2",8 ,18629623,
"category 3",9 ,16471680,
"category 4",7 ,13661732,
"category 5",5 ,7173011,
"category 6",10, 18395574)
dfmod <- df%>%
dplyr::mutate(numbers_lable= numbers
,numbers = numbers * 1e6)
pl <- ggplot(data = dfmod,aes(x= fct_reorder(category,desc(value))
, y = value))
pl <- pl + geom_col(fill = "grey")
pl <- pl + geom_line(aes(y = numbers, group = 1), size = .8, color = "blue")
pl <- pl + geom_text(aes(label = paste0('Sales'
, scales::comma(value)
, '\n(Orders '
, numbers_lable,')'))
, vjust = -0.3
, size = 3)
pl <- pl + scale_y_continuous(name= "Sales revenue"
,labels = scales::comma_format(scale = 1e-6
,suffix = "M")
, sec.axis = sec_axis( trans= ~./1e6
, name = "Number of sales"
, breaks = c(0,2,4,6,8,10)))
pl <- pl + theme_bw()
pl <- pl + theme(axis.title.y = element_text(color = "grey")
,axis.title.y.right = element_text(color = "blue")
)
pl
tried fig.width/height, out.width/height whenever I change them they just chop the labels
in excel I would size the chart for example as 12 cm * 5 cm
and everything would be visible but with smaller space
Extend the upper limit of your y-axis, e.g.,
sec.axis = sec_axis(
trans= ~./1e6,
name = "Number of sales",
breaks = c(0, 2, 4, 6, 8, 10)),
limits = c(0, max(df$value) * 1.2)
)
Use fig.width/fig.height for output-dependent adjustment. The following looks fine for PDF output
```{r, echo=F, fig.width=8, fig.height=4}
<your figure code>
```
Related
I am running an mapply loop on a huge set of data to graph 13 parameters for 19 groups. This is working great except the p-value position. Due to the data varying for each plot I cannot assign position using label.y = 125 for example, in some plots it is in the middle of the bar/error bar. However, I can't assign it higher without having it way to high on other graphs. Is there a way to adjust to the data and error bars?
This is my graphing function and like I said the graph is great, except p-value position. Specifically, the stat compare means anova line.
ANOVA_plotter <- function(Variable, treatment, Grouping, df){
Inputdf <- df %>%
filter(Media == treatment, Group == Grouping) %>%
ggplot(aes_(x = ~ID, y = as.name(Variable))) +
geom_bar(aes(fill = ANOVA_Status), stat = "summary", fun = "mean", width = 0.9) +
stat_summary(geom = "errorbar", fun.data = "mean_sdl", fun.args = list(mult = 1), size = 1) +
labs(title = paste(Variable, "in", treatment, "in Group", Grouping, sep = " ")) +
theme(legend.position = "none",axis.title.x=element_blank(), axis.text = element_text(face="bold", size = 18 ), axis.text.x = element_text(angle = 45, hjust = 1)) +
stat_summary(geom = "errorbar", fun.data = "mean_sdl", fun.args = list(mult = 1), width = 0.2) +
stat_compare_means(method = "anova", label.y = 125) +
stat_compare_means(label = "p.signif", method = "t.test", paired = FALSE, ref.group = "Control")
}
I get graphs that look like this
(https://i.stack.imgur.com/hV9Ad.jpg)
But I can't assign it to label.y = 200 because of plots like this
(https://i.stack.imgur.com/uStez.jpg)
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
When I try to assign colours using colour = "" or fill = """, the graph changes its colour always to the same colour (some kind of weird orange tone). The specific code I used is this:
Plot <- ggplot(data, aes(ymin = 0)) + geom_rect(aes(xmin = left, xmax = right, ymax = a, colour = "#FDFEFE")).
Has anyone had this problem before? It doesn`t seem to matter whether I use the colour names or the HTML codes, the result stays the same.
Thank you!
I just wanted to add some explanation because this also tripped me up when I started using ggplot.
Some toy data:
data <- tibble(a = 1:10, left = 1:10 * 20, right = 1:10 * 20 + 10)
As explained by #stefan, you need to set the hard-coded color outside of the aestetics:
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a), fill = "#FDFEFE")
The aestetics are meant to link the plot to your data table. When you write this:
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a, fill = "#FDFEFE"))
It is like having the following:
data <- tibble(a = 1:10, left = 1:10 * 20, right = 1:10 * 20 + 10, col = "#FDFEFE")
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a, fill = col))
Except that ggplot understands "#FDFEFE" as a categorical value, not as a color. Having "#FDFEFE" or "banana" is the same to ggplot:
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a, fill = "banana"))
or
data <- tibble(a = 1:10, left = 1:10 * 20, right = 1:10 * 20 + 10, col = "banana")
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a, fill = col))
assign default colours to the categorical data.
As an extra, if you want to assign specific colors to different entries in the table, it is best to use a scale_*_manual layer:
data <- tibble(a = 1:10, left = 1:10 * 20, right = 1:10 * 20 + 10,
col = sample(c("banana", "orange", "coconut"), 10, replace = T))
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a, fill = col)) +
scale_fill_manual(values = c("banana" = "yellow2", "orange" = "orange2", "coconut" = "burlywood4"))
If you wanted to hard-code the colors in the table, you would have to use this column outside to the aestetics:
data <- tibble(a = 1:10, left = 1:10 * 20, right = 1:10 * 20 + 10,
col = sample(c("yellow2", "orange2", "burlywood4"), 10, replace = T))
ggplot(data, aes(ymin = 0)) +
geom_rect(aes(xmin = left, xmax = right, ymax = a), fill = data$col)
But it is best to use meaningful categorical values and assign the colors in the scale layer. This is what the grammar of graphics is all about!
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"))
)