I have a dataframe of single column with multiple values. I was using basic rplot function like plot() and points(). I successfully plotted the lineplot but I was unable to write point values from the dataframe onto the plot field. Is there anyway to add data values onto the plot?
Below is the following code for test
> x = data.frame(A = rnorm(10))
> plot(x$A, type = "o", pch = 20)**
Sorry, I made an edit to make my question clearer.
Here below is the example plot for 10 random numbers
Plot lines, then add text:
#data
set.seed(1); x = data.frame(A = rnorm(10))
#base plot
plot(x$A, type = "o", pch = 20, ylim = range(x$A * 1.3))
text(x = seq_along(x$A), y = x$A + 0.3, labels = round(x$A, 2), srt = 90)
Or using ggplot with ggrepel for pretty labels:
#ggplot
library(ggplot2)
library(ggrepel) # pretty labels, avoid overlap:
ggplot(cbind(x = seq_along(x$A), x),
aes(x = x, y = A, label = round(A, 2))) +
geom_line() +
geom_point() +
geom_label_repel()
#geom_text_repel()
Probably this is more than what you are asking, but you can add labels to the values you have in your line plot using ggplot:
library(ggplot2)
x = data.frame(A = rnorm(10),
pos = runif(10, 0.1, 0.7))
ggplot(x) +
geom_point(aes(x = A),
y = 0) +
geom_line(aes(x = A),
y = 0) +
geom_segment(aes(x = A,
xend = A,
y = 0,
yend = pos),
linetype = 2) +
geom_label(aes(x = A,
y = pos,
label = round(A, 2)),
size = 3) +
scale_y_continuous(name = "",
limits = c(0, 0.8)) +
guides(y = "none") +
theme_bw()
You could make a base R "type b" equivalent.
The OP hasn't specified that every y value should be set to zero.
library(ggh4x)
#> Loading required package: ggplot2
set.seed(1)
x = data.frame(A = rnorm(10))
ggplot(x, aes(1:10, A)) +
geom_pointpath(shape = NA) +
geom_text(aes(label = round(A,2))) +
labs(x= "Index")
Created on 2022-05-27 by the reprex package (v2.0.1)
Related
Suppose we want to plot this data:
library(ggplot2)
library(sf)
library(raster)
library(colorRamps)
min_lon <- 10
max_lon <- 17
min_lat <- 8
max_lat <- 17
grid_size <- 0.5
lon_grids <- 1 + ((max_lon - min_lon)/grid_size)
lat_grids <- 1 + ((max_lat - min_lat)/grid_size)
points <- data.frame(lon = rep(seq(min_lon, max_lon, grid_size), lat_grids), lat = rep(seq(min_lat, max_lat, grid_size), each = lon_grids))
points$Var <- runif(min= 10, max = 48, 285)
points$value <-cut(points$Var, breaks= seq(10.08, 47.80, length.out = 13), dig.lab = 1)
ggplot() +
coord_sf(xlim = c(min_lon, max_lon), ylim = c(min_lat, max_lat)) +
theme_bw()+
geom_raster(data = points, aes(x = lon, y = lat, fill = value), interpolate = FALSE) +
labs(x="Longitude", y="Latitude")+
scale_fill_manual(values = matlab.like(n = 13), name = "[m]",
labels = sprintf("%.2f", seq(10.08, 47.80, length.out = 13)),
guide = guide_legend(reverse = TRUE))+theme(legend.position = "bottom")
This code produces the following graph:
Two problems I am facing here:
To make it discrete, I used the cut function. I chose the breaks= seq(10.08, 47.80, length.out = 13) arbitrary based on the minimum and maximum values with a random length of 13. Is there any criteria to decide the correct range?
Is there any way to make the legend look like this?
One option would be to use e.g. scale_fill_stepsn with guide_binswhich does not require to manually discretize the variable mapped on fill. Additionally I use a custom function to set the breaks of the legend instead of the default mechanism to set the number of breaks.
set.seed(123)
library(ggplot2)
library(colorRamps)
base <- ggplot() +
coord_sf(xlim = c(min_lon, max_lon), ylim = c(min_lat, max_lat)) +
theme_bw() +
geom_raster(data = points, aes(x = lon, y = lat), interpolate = FALSE) +
labs(x = "Longitude", y = "Latitude") +
theme(legend.position = "bottom")
base +
aes(fill = Var) +
scale_fill_stepsn(colors = matlab.like(n = 13), name = "[m]",
breaks = function(x) seq(x[[1]], x[[2]], length.out = 13),
labels = ~ sprintf("%.0f", .x),
guide = guide_bins(axis = FALSE,
show.limits = TRUE))
I have a large number of variables and would like to create scatterplots comparing all variables to a single variable. I have been able to do this in base R using lapply, but I cannot complete the same task in ggplot2 using lapply.
Below is an example dataset.
df <- data.frame("ID" = 1:16)
df$A <- c(1,2,3,4,5,6,7,8,9,10,11,12,12,14,15,16)
df$B <- c(5,6,7,8,9,10,13,15,14,15,16,17,18,18,19,20)
df$C <- c(11,12,14,16,10,12,14,16,10,12,14,16,10,12,14,16)
I define the variables I would like to generate scatterplots with, using the code below:
df_col_names <- df %>% select(A:C) %>% colnames(.)
Below is how I have been able to successfully complete the task of plotting all variables against variable A, using lapply in base R:
lapply(df_col_names, function(x) {
tiff(filename=sprintf("C:\\Documents\\%s.tiff", x),
width = 1000, height = 1000, res=200)
plot(df$A, df[[x]],
pch=19,
cex = 1.5,
ylab = x,
ylim = c(0, 20),
xlim = c(0, 20))
dev.off()
})
Below is my attempt at completing the task in ggplot2 without any success. It generates the tiff images, although they are empty.
lapply(df_col_names, function(x) {
tiff(filename=sprintf("C:\\Documents\\%s.tiff", x),
width = 1000, height = 1000, res=200)
ggplot(df) +
geom_point(data = df,
aes(x = A, y = df_col_names[[x]], size = 3)) +
geom_smooth(aes(x = A, y = df_col_names[[x]], size = 0), method = "lm", size=0.5) +
coord_fixed(ratio = 1, xlim = c(0, 20), ylim = c(0, 20)) +
guides(size = FALSE, color = FALSE) +
theme_bw(base_size = 14)
dev.off()
})
It works for me with ggsave. Also note that you are passing string column names to ggplot so use .data to refer to actual column values.
library(ggplot2)
lapply(df_col_names, function(x) {
ggplot(df) +
geom_point( aes(x = A, y = .data[[x]], size = 3)) +
geom_smooth(aes(x = A, y = .data[[x]], size = 0), method = "lm", size=0.5) +
coord_fixed(ratio = 1, xlim = c(0, 20), ylim = c(0, 20)) +
guides(size = FALSE, color = FALSE) +
theme_bw(base_size = 14) -> plt
ggsave(sprintf("%s.tiff", x), plt)
})
I have a data.frame in R 4.0.2 with a continuous variable in one column and two possible values of a categorical variable (variable 'type': known or novel) in another, which I use to color them differently (using a palette from ggsci 2.9 package). I represent an histogram (stat_bin) with ggplot2 3.3.2 and I want to use the facet_zoom function of ggforce 0.3.2 to zoom only the data belonging to one of the 'types' (using the option zoom.data, as it is done in the volcano example on http://cran.univ-paris1.fr/web/packages/ggforce/vignettes/Visual_Guide.html#contextual-zoom), however I get this error:
Error: Aesthetics must be either length 1 or the same as the data (2000): x
Reproducible example:
library(ggplot2)
library(ggsci)
library(ggforce)
testdata <- as.data.frame(sort(rnorm(1000)))
testdata$type <- "known"
testdata[501:1000,2] <- "novel"
# Working code
ggplot(testdata) +
stat_bin(aes(x=testdata[,1], fill = type), binwidth = 1, color="white") +
scale_fill_npg() + theme_light() +
facet_zoom(xlim = c(0, 4), ylim = c(0, 300), horizontal = TRUE, zoom.size = 0.3)
# Desired code
ggplot(testdata) +
stat_bin(aes(x=testdata[,1], fill = type), data = cbind(testdata, zoom = FALSE), binwidth = 1, color="white") +
stat_bin(aes(x=testdata[testdata$type == "novel",1]), data = cbind(testdata, zoom = TRUE), binwidth = 0.5) +
scale_fill_npg() + theme_light() +
facet_zoom(xlim = c(0, 4), ylim = c(0, 300), horizontal = TRUE, zoom.size = 0.3, zoom.data = zoom)
Thanks!
The issue is that you pass the whole dataset as data in the second stat_bin. Simply pass the subsetted df instead of trying to subset in aes():
BTW: I also renamed the first variable in your data as x.
library(ggplot2)
library(ggsci)
library(ggforce)
set.seed(42)
testdata <- data.frame(x = sort(rnorm(1000)))
testdata$type <- "known"
testdata[501:1000,2] <- "novel"
# Desired code
ggplot(testdata) +
stat_bin(aes(x = x, fill = type), data = cbind(testdata, zoom = FALSE), binwidth = 1, color="white") +
stat_bin(aes(x = x), data = cbind(testdata[testdata$type == "novel", ], zoom = TRUE), binwidth = 0.5) +
scale_fill_npg() + theme_light() +
facet_zoom(xlim = c(0, 4), ylim = c(0, 300), horizontal = TRUE, zoom.size = 0.3, zoom.data = zoom)
To only show the type == "novel" data in the zoomed plot, try this:
library(tidyverse)
library(ggsci)
library(ggforce)
testdata <- data.frame(values = sort(rnorm(1000)))
testdata$type <- "known"
testdata[501:1000,2] <- "novel"
# Desired code
ggplot(testdata) +
stat_bin(aes(x = values, fill = type),
binwidth = 1, color="white") +
scale_fill_npg() + theme_light() +
facet_zoom(zoom.data = ifelse(type == "novel", NA, FALSE),
xlim = c(0, 4), ylim = c(0, 300),
horizontal = TRUE)
Sorry for the possibly simple question. I'm a programmer, though I rarely deal with graphics, and after tearing my hair out for hours with this problem, it's time to get some help. I'm creating a multi-panel plot in r using ggplot, but I cannot find a way to display figure labels, outside of the figure, when using ggplot.
Here is what I want my code to do:
par(mfrow = c(1, 2), pty = "s", las = 1, mgp = c(2, 0.4, 0), tcl = -0.3)
qqnorm(rnorm(100), main = "")
mtext("a", side = 3, line = 1, adj = 0, cex = 1.1)
qqnorm(rnorm(100), main = "")
mtext("b", side = 3, line = 1, adj = 0, cex = 1.1)
How would I get those "a" and "b" labels, in the location that they are in for the figure created by the above code, into this type of code:
df = data.frame(gp = factor(rep(letters[1:3], each = 10)), y = rnorm(30))
p = ggplot(df) + geom_point(aes(x = gp, y = y))
p2 = ggplot(df) + geom_point(aes(x = y, y = gp))
grid.arrange(p, p2, ncol = 2)
Thank you in advance for your help!
You could use ggtitle and theme:
df = data.frame(gp = factor(rep(letters[1:3], each = 10)), y = rnorm(30))
p = ggplot(df) + geom_point(aes(x = gp, y = y)) + ggtitle('a') + theme(plot.title=element_text(hjust=0))
p2 = ggplot(df) + geom_point(aes(x = y, y = gp)) + ggtitle('b') + theme(plot.title=element_text(hjust=0))
grid.arrange(p, p2, ncol = 2)
Two (less than ideal) options:
#Use faceting, similar to Matthew's ggtitle option
df = data.frame(gp = factor(rep(letters[1:3], each = 10)), y = rnorm(30))
df$lab1 <- 'a'
df$lab2 <- 'b'
p = ggplot(df) + geom_point(aes(x = gp, y = y)) + facet_wrap(~lab1)
p2 = ggplot(df) + geom_point(aes(x = y, y = gp)) + facet_wrap(~lab2)
j <- theme(strip.text = element_text(hjust = 0.05))
grid.arrange(p + j, p2 + j, ncol = 2)
#Use grid.text
grid.text(letters[1:2],x = c(0.09,0.59),y = 0.99)
For the grid.text option, if you delve into the ggplot object you can probably avoid having to tinker to get those values right manually.
How do I change the geom_text legend key symbol? In the example below, I'd like to change the symbol in the legend key from a lower case "a" to, say, an upper case "N". I've looked at an example for doing something similar here, but couldn't get that example to work.
# Some toy data
df <- expand.grid(x = factor(seq(1:5)), y = factor(seq(1:5)), KEEP.OUT.ATTRS = FALSE)
df$Count = seq(1:25)
# An example plot
library(ggplot2)
ggplot(data = df, aes( x = x, y = y, label = Count, size = Count)) +
geom_text() +
scale_size(range = c(2, 10))
EDIT: updating for ggplot version 0.9.2
The original answer (see below) broke at about version 0.9.0 or 0.9.1. The following works in 0.9.2
# Some toy data
df <- expand.grid(x = factor(seq(1:5)), y = factor(seq(1:5)), KEEP.OUT.ATTRS = FALSE)
df$Count = seq(1:25)
# A plot
library(ggplot2)
p = ggplot(data = df, aes( x = x, y = y, label = Count, size = Count)) +
geom_point(colour = NA) +
geom_text(show.legend = FALSE) +
guides(size = guide_legend(override.aes = list(colour = "black", shape = utf8ToInt("N")))) +
scale_size(range = c(2, 10))
p
Original answer
Answering my own question and using the snippet of code in #kohske's comment above:
# Some toy data
df <- expand.grid(x = factor(seq(1:5)), y = factor(seq(1:5)), KEEP.OUT.ATTRS = FALSE)
df$Count = seq(1:25)
# A plot
library(ggplot2)
p = ggplot(data = df, aes( x = x, y = y, label = Count, size = Count)) +
geom_text() +
scale_size(range = c(2, 10))
p
library(grid)
grid.gedit("^key-[-0-9]+$", label = "N")
With gtable version 0.2.0 (ggplot2 v 2.1.0) installed, Kohske's original solution (see the comments) can be made to work.
# Some toy data
df <- expand.grid(x = factor(seq(1:5)), y = factor(seq(1:5)), KEEP.OUT.ATTRS = FALSE)
df$Count = seq(1:25)
# Load packages
library(ggplot2)
library(grid)
# A plot
p = ggplot(data = df, aes( x = x, y = y, label = Count, size = Count)) +
geom_text() +
scale_size(range = c(2, 10))
p
grid.ls(grid.force())
grid.gedit("key-[-0-9]-1-1", label = "N")
Or, to work on a grob object:
# Get the ggplot grob
gp = ggplotGrob(p)
grid.ls(grid.force(gp))
# Edit the grob
gp = editGrob(grid.force(gp), gPath("key-[1-9]-1-1"), grep = TRUE, global = TRUE,
label = "N")
# Draw it
grid.newpage()
grid.draw(gp)
Another option
Modify the geom
# Some toy data
df <- expand.grid(x = factor(seq(1:5)), y = factor(seq(1:5)), KEEP.OUT.ATTRS = FALSE)
df$Count = seq(1:25)
# Load packages
library(ggplot2)
library(grid)
# A plot
p = ggplot(data = df, aes( x = x, y = y, label = Count, size = Count)) +
geom_text() +
scale_size(range = c(2, 10))
p
GeomText$draw_key <- function (data, params, size) {
pointsGrob(0.5, 0.5, pch = "N",
gp = gpar(col = alpha(data$colour, data$alpha),
fontsize = data$size * .pt)) }
p