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")
I have dataframe which represents sales by model within 2 different years. 'change' column stands for absolute change by models from 2020 to 2021 while 'chng.percent' measures this change in percentages.
However, I am struggling to apply the given Code of slope plot to my data.
df <- data.frame (model = c("A", "A", "B","B"),
year = c(2020,2021,2020,2021),
sale =c(105,190,110,180),
chang = c(85,NA,70,NA),
chng.percent = c(80.9,NA, 63.6,NA))
Expected outcome (Like this)
Here's a way to do it all within ggplot using your existing data:
ggplot(df, aes(year, sale, color = model)) +
geom_line(arrow = arrow(type = "closed", angle = 20),
key_glyph = draw_key_point) +
geom_vline(aes(xintercept = year)) +
geom_text(aes(label = sale, hjust = ifelse(year == 2020, 1.3, -0.3)),
color = "black",
size = 6) +
geom_text(aes(x = min(df$year) + 0.25, y = 105,
label = paste0("+", chang[1], "; ", chng.percent[1], "%"),
color = "A"), size = 5) +
geom_text(aes(x = max(df$year) - 0.25, y = 150,
label = paste0("+", chang[3], "; ", chng.percent[3], "%"),
color = "B"), size = 5) +
theme_void(base_size = 16) +
coord_cartesian(clip = "off") +
scale_x_continuous(breaks = c(2020, 2021)) +
guides(color = guide_legend(override.aes = list(size = 5))) +
scale_color_brewer(palette = "Set1") +
theme(plot.margin = margin(30, 30, 30, 30),
aspect.ratio = 1.5,
axis.text.x = element_text(size = 20))
you can try something like this :
df <- data.frame(model = c("A", "B"),
sale_2020 =c(105,110),
sale_2021 =c(190,180),
chang = c(85,70),
chng.percent = c(80.9, 63.6))
df %>%
ggplot() +
geom_segment(aes(x = 1, xend = 2,
y = sale_2020,
yend = sale_2021,
group = model,
col = model),
size = 1.2) +
# set the colors
scale_color_manual(values = c("#468189", "#9DBEBB"), guide = "none") +
# remove all axis stuff
theme_classic() +
theme(axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank()) +
geom_text(aes(x = x, y = y, label = label),
data = data.frame(x = 1:2,
y = 10 + max(df$sale_2021),
label = c("2020", "2021")),
col = "grey30",
size = 6) +
# add vertical lines that act as axis for 2020
geom_segment(x = 1, xend = 1,
y = min(df$sale_2020) -10,
yend = max(df$sale_2020) + 81,
col = "grey70", size = 1.5) +
# add vertical lines that act as axis for 2021
geom_segment(x = 2, xend = 2,
y = min(df$sale_2021) - 80,
yend = max(df$sale_2021) + 1,
col = "grey70", size = 1.5) +
# add the success rate next to each point on 2021 axis
geom_text(aes(x = 2 + 0.08,
y = sale_2021,
label = paste0(round(sale_2021, 1))),
col = "grey30") +
# add the success rate next to each point on 2021 axis
geom_text(aes(x = 1 - 0.08,
y = sale_2020,
label = paste0(round(sale_2020, 1))),
col = "grey30") +
# add the success rate next to each point on 2020 axis
geom_text(aes(x = 2 - 0.5,
y = c(156, 135),
label = paste0(round(chng.percent, 1), "%")),
col = "grey30")
I am trying to align significance asterisks (* or ** or ***) to the points of a geom point graph with position dodge to indicate the significance of a value using ggplot2. I wasn't able to find any similar questions and answers with similar issue.
Here is data frame 'df':
df<-data.frame(conc=c(1,10,100,1, 10,100,1, 10, 100),
mean=c( 0.9008428,0.8278645,0.7890388,0.9541905,
0.8537885,0.8212504,1.3828724,0.7165685, 0.7985398),
Treatment=c("A","A","A","B", "B", "B","C","C", "C"),
upper =c(1.0990144, 0.9505348, 0.8273494, 1.0389074, 0.9227461, 0.9657371, 1.6864420, 0.7401891, 0.9046951),
lower=c(0.7026713, 0.7051941, 0.7507282, 0.9528077, 0.7848309, 0.6767638, 1.0793029, 0.6929479, 0.6923846),
p.value=c(0.0003, 0.6500, 1,0.02,0.0400,
0.3301,0.100,0.023, 0.05))
I made a plot with an automatic asterisk, but it is not aligned how i want to, and i believe it's because of position_dodge, but i have too many points in one concentration, so i have to use it (given data frame is minimal).
legend_title <- "Treatment"
breaks_y =c(0, 0.25, 0.5, 0.75, 1, 1.25, 1.5)
breaks = c(1, 10, 100)
df$Label <- NA
df$Label[df$p.value<0.001]<-'***'
df$Label[df$p.value<0.01 & is.na(df$Label)]<-'**'
df$Label[df$p.value<0.05 & is.na(df$Label)]<-'*'
ggplot(df, aes(x = conc, y = mean, color = Treatment)) +
geom_errorbar(aes(ymax = upper, ymin = lower, width = 0),position = position_dodge(width=0.5)) +
geom_point(aes(shape = Treatment, fill = Treatment), size = 4, position = position_dodge(width=0.5)) +
geom_text(aes(label = Label),size = 4, position = position_dodge(width =0.5), color = "black") +
scale_shape_manual(values = c(22, 21, 23)) +
scale_color_manual(values=c('blue','coral1', 'darkgreen' )) +
scale_fill_manual(values=c('blue','coral1', 'darkgreen')) +
labs(x = "Concentration (\u03BCM)", y = "Abs", title = "Viability", fill = "Treatment") +
scale_x_continuous(trans="log10", limits = c(0.5, 170), breaks = breaks) +
scale_y_continuous(limits = c(0, 1.5), breaks = breaks_y) +
theme_light() +
ggpubr::rotate_x_text(angle = 70) +
theme(axis.text = element_text(size = 12, face = "bold"),
axis.title.y = element_text(size = 12, face ="bold"),
axis.title.x = element_text(size = 12, face ="bold"))
How can I align the asterisk automatically to be directly above the correct dot with position_dodge?
My legend is not showing correctly when I am doing my graph in R using ggplot2. One column of my dataset is represented by a geom_bar and the two others are represented by geom_points (one shape each). The circle and the diamond shape are showing for both 2000 and 2008, the circle being in the diamong for both year. However, the graph works totally fine...
Here is a screenshot:
I have created a simplified version of my dataset:
order_var <- c(1, 4, 3, 5, 6, 2)
alt_name <- c('Agriculture', 'Mining', 'Food products',' Manufacture', 'Chemicals', 'Machinery')
y2000 <- c(20, 40, 50, 80, 30, 70)
y2008 <- c(40, 50, 80, 70, 30, 60)
y2018 <- c(10, 30, 80, 50, 40, 50)
datatest <- data.frame("order_var" = order_var, "alt_name" = alt_name, "y2000" = y2000, "y2008" = y2008, "y2018" = y2018)
And the code for my graph:
datatest %>% ggplot(aes(x = reorder(alt_name, order_var))) +
geom_bar(stat = "identity", aes(y = `y2018`, fill = "2018"), width = 0.7, col = "black") +
geom_point(aes(y = `y2008`, col = "2008"), shape = 23, fill = "white", size = 5) +
geom_point(aes(y = `y2000`, col = "2000"), shape = 19, fill = "black", size = 3) +
xlab("Industry") +
ylab("Percentage") +
theme(legend.position = "top") +
scale_fill_manual(name = '', values = c("2018" = "#4F81BD"), breaks = c("2018")) +
scale_colour_manual(name = '', values = c("2008" = "black", "2000" = "orange"))
If you know how to correct this problem, I would be very grateful!!
Thank you :)
That's a very tricky plot you are trying to make because you are in essence mapping the same aesthetics to different geoms.
The first thing you should do is to reshape your data to the long format. I also divided your dataset between 2018 (the bar), and 2000, 2008 (the points).
df2 <- datatest %>%
pivot_longer(cols = -c(order_var, alt_name)) %>%
mutate(bar = if_else(name == "y2018", 1, 0))
data_bar <- df2 %>% filter(bar == 1)
data_point <- df2 %>% filter(bar != 1)
I also find it useful to add a dodge to your points to avoid overlapping one inside the other as in the case of chemicals with position = position_dodge(width = 0.6).
The first solution gives what you want, but it is a bit of a hack, and I wouldn't recommend doing it as a general strategy. You basically add an aesthetics that you are not going to use to the bars (in this case, linetype), and then override it, as suggested in this answer.
ggplot(data_bar, aes(x = reorder(alt_name, order_var))) +
geom_bar(aes(y = value, linetype = name), fill = "#4F81BD", stat = 'identity', color = 'black') +
geom_point(data = data_point, position=position_dodge(width=0.6), aes(y = value, color = name, shape = name, size = name, fill = name)) +
scale_colour_manual(values = c("orange", "black"), labels = c("2000", "2008")) +
scale_fill_manual(values = c("orange", "white"), labels = c("2000", "2008")) +
scale_shape_manual(values = c(19, 23), labels = c("2000", "2008")) +
scale_size_manual(values = c(3, 5), labels = c("2000", "2008")) +
scale_linetype_manual(values = 1, guide = guide_legend(override.aes = list(fill = c("#4F81BD"))), labels = c("2018")) +
theme(legend.position = "top", legend.title = element_blank()) +
labs(x = "Industry", y = "Percentage")
Another solution, more general, is to avoid using the fill aesthetics for the geom_point and changing the shape to a solid one instead:
ggplot(data_bar, aes(x = reorder(alt_name, order_var))) +
geom_bar(aes(y = value, fill = name), stat = 'identity', color = "black") +
geom_point(data = data_point, position=position_dodge(width=0.6), aes(y = value, color = name, shape = name, size = name)) +
scale_fill_manual(values = c("#4F81BD"), labels = c("2018")) +
scale_colour_manual(values = c("orange", "white"), labels = c("2000", "2008")) +
scale_shape_manual(values = c(19, 18), labels = c("2000", "2008")) +
scale_size_manual(values = c(4, 6), labels = c("2000", "2008")) +
theme(legend.position = "top", legend.title = element_blank()) +
labs(x = "Industry", y = "Percentage")
This is my first question to StackExchange, and I've searched for answers that have been helpful, but haven't really gotten me to where I'd like to be.
This is a stacked bar chart, combined with a point chart, combined with a line.
Here's my code:
theme_set(theme_light())
library(lubridate)
FM <- as.Date('2018-02-01')
x.range <- c(FM - months(1) - days(1) - days(day(FM) - 1), FM - days(day(FM) - 1) + months(1))
x.ticks <- seq(x.range[1] + days(1), x.range[2], by = 2)
#populate example data
preds <- data.frame(FM = FM, DATE = seq(x.range[1] + days(1), x.range[2] - days(1), by = 1))
preds <- data.frame(preds, S_O = round(seq(1, 1000000, by = 1000000/nrow(preds))))
preds <- data.frame(preds, S = round(ifelse(month(preds$FM) == month(preds$DATE), day(preds$DATE) / 30.4, 0) * preds$S_O))
preds <- data.frame(preds, O = preds$S_O - preds$S)
preds <- data.frame(preds, pred_sales = round(1000000 + rnorm(nrow(preds), 0, 10000)))
preds$ma <- with(preds, stats::filter(pred_sales, rep(1/5, 5), sides = 1))
y.max <- ceiling(max(preds$pred_sales) / 5000) * 5000 + 15000
line.cols <- c(O = 'palegreen4', S = 'steelblue4',
P = 'maroon', MA = 'blue')
fill.cols <- c(O = 'palegreen3', S = 'steelblue3',
P = 'red')
p <- ggplot(data = preds,
mapping = aes(DATE, pred_sales))
p <- p +
geom_bar(data = reshape2::melt(preds[,c('DATE', 'S', 'O')], id.var = 'DATE'),
mapping = aes(DATE, value, group = 1, fill = variable, color = variable),
width = 1,
stat = 'identity',
alpha = 0.5) +
geom_point(mapping = aes(DATE, pred_sales, group = 2, fill = 'P', color = 'P'),
shape = 22, #square
alpha = 0.5,
size = 2.5) +
geom_line(data = preds[!is.na(preds$ma),],
mapping = aes(DATE, ma, group = 3, color = 'MA'),
alpha = 0.8,
size = 1) +
geom_text(mapping = aes(DATE, pred_sales, label = formatC(pred_sales / 1000, format = 'd', big.mark = ',')),
angle = 90,
size = 2.75,
hjust = 1.25,
vjust = 0.4) +
labs(title = sprintf('%s Sales Predictions - %s', 'Overall', format(FM, '%b %Y')),
x = 'Date',
y = 'Volume in MMlbs') +
theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1, size = 8),
panel.grid.major.x = element_blank(),
panel.grid.minor.x = element_blank(),
legend.title = element_blank(),
legend.position = 'bottom',
legend.text = element_text(size = 8),
legend.margin = margin(t = 0.25, unit = 'cm')) +
scale_x_date(breaks = x.ticks,
date_labels = '%b %e',
limits = x.range) +
scale_y_continuous(limits = c(0, y.max),
labels = function(x) { formatC(x / 1000, format='d', big.mark=',') }) +
scale_color_manual(values = line.cols,
breaks = c('MA'),
labels = c(MA = 'Mvg Avg (5)')) +
scale_fill_manual(values = fill.cols,
breaks = c('P', 'O', 'S'),
labels = c(O = 'Open Orders', S = 'Sales', P = 'Predictions'))
p
The chart it generates is this:
As you can see, the legend does a couple of funky things. It's close, but not quite there. I only want boxes with exterior borders for Predictions, Open Orders, and Sales, and only a blue line for the Mvg Avg (5).
Any advice would be appreciated.
Thanks!
Rather late, but if you are still interested to understand this problem, the following should work. Explanations are included as comments within the code:
library(dplyr)
preds %>%
# scale the values for ALL numeric columns in the dataset, before
# passing the dataset to ggplot()
mutate_if(is.numeric, ~./1000) %>%
# since x / y mappings are stated in the top level ggplot(), there's
# no need to repeat them in the subsequent layers UNLESS you want to
# override them
ggplot(mapping = aes(x = DATE, y = pred_sales)) +
# 1. use data = . to inherit the top level data frame, & modify it on
# the fly for this layer; this is neater as you are essentially
# using a single data source for the ggplot object.
# 2. geom_col() is a more succinct way to say geom_bar(stat = "identity")
# (I'm using tidyr rather than reshape package, since ggplot2 is a
# part of the tidyverse packages, & the two play together nicely)
geom_col(data = . %>%
select(S, O, DATE) %>%
tidyr::gather(variable, value, -DATE),
aes(y = value, fill = variable, color = variable),
width = 1, alpha = 0.5) +
# don't show legend for this layer (o/w the fill / color legend would
# include a square shape in the centre of each legend key)
geom_point(aes(fill = 'P', color = 'P'),
shape = 22, alpha = 0.5, size = 2.5, show.legend = FALSE) +
# use data = . %>% ... as above.
# since the fill / color aesthetic mappings from the geom_col layer would
# result in a border around all fill / color legends, avoid it all together
# here by hard coding the line color to "blue", & map its linetype instead
# to create a separate linetype-based legend later.
geom_line(data = . %>% na.omit(),
aes(y = ma, linetype = 'MA'),
color = "blue", alpha = 0.8, size = 1) +
# scales::comma is a more succinct alternative to formatC for this use case
geom_text(aes(label = scales::comma(pred_sales)),
angle = 90, size = 2.75, hjust = 1.25, vjust = 0.4) +
labs(title = sprintf('%s Sales Predictions - %s', 'Overall', format(FM, '%b %Y')),
x = 'Date',
y = 'Volume in MMlbs') +
theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1, size = 8),
panel.grid.major.x = element_blank(),
panel.grid.minor.x = element_blank(),
legend.title = element_blank(),
legend.position = 'bottom',
legend.text = element_text(size = 8),
legend.margin = margin(t = 0.25, unit = 'cm')) +
scale_x_date(breaks = x.ticks,
date_labels = '%b %e',
limits = x.range) +
# as above, scales::comma is more succinct
scale_y_continuous(limits = c(0, y.max / 1000),
labels = scales::comma) +
# specify the same breaks & labels for the manual fill / color scales, so that
# a single legend is created for both
scale_color_manual(values = line.cols,
breaks = c('P', 'O', 'S'),
labels = c(O = 'Open Orders', S = 'Sales', P = 'Predictions')) +
scale_fill_manual(values = fill.cols,
breaks = c('P', 'O', 'S'),
labels = c(O = 'Open Orders', S = 'Sales', P = 'Predictions')) +
# create a separate line-only legend using the linetype mapping, with
# value = 1 (i.e. unbroken line) & specified alpha / color to match the
# geom_line layer
scale_linetype_manual(values = 1,
label = 'Mvg Avg (5)',
guide = guide_legend(override.aes = list(alpha = 1,
color = "blue")))