I have data and a plot like this,
x = c(1,2,3,4,5,6,7,8,9,10,11,12)
y1 = x^2-5
y2 = -x^2+1
data <- data.frame(x,y1,y2)
data1 = data.frame(pivot_longer(data,2:3))
ggplot(data1, aes(x, y = value, color = name))+
geom_point()+
geom_smooth(method = 'lm',se = FALSE)
Is there a way to have the trendline only applying to values for x greater than a certain number, like 3?
You can do this:
ggplot(data1, aes(x, y = value, color = name))+
geom_point()+
geom_smooth(data=dplyr::filter(data1,x>3), method = 'lm',se = FALSE)
You can apply the current aes to geom_point only, and create a new column (i.e. x2 in my code) for mapping to geom_smooth.
library(tidyverse)
x = c(1,2,3,4,5,6,7,8,9,10,11,12)
y1 = x^2-5
y2 = -x^2+1
data <- data.frame(x,y1,y2)
data1 = data.frame(pivot_longer(data,2:3))
data1 %>% mutate(x2 = ifelse(x > 3, x, NA)) %>%
ggplot()+
geom_point(aes(x, y = value, color = name)) +
geom_smooth(aes(x2, y = value, color = name), method = 'lm',se = FALSE)
Created on 2022-05-07 by the reprex package (v2.0.1)
Similar to both above just using subset:
ggplot(data1, aes(x, y = value, color = name))+
geom_point()+
geom_smooth(data=subset(data1, x > 3), method = 'lm',se = FALSE)
Related
I am trying to differentiate the linetype and/or color in stacked geom_area by group. How can I do that? Simply geom_area(linetype = type) or color = type does not work. Only think that works changes the values for both groups: geom_area(color = "white"). How can I modify the color and linetype by group?
My dummy example:
dat <- data.frame(x = c(1:5,1:5),
y = c(9:5, 10,7,5,3,1),
type = rep(c("a", "b"), each = 5))
My geom_area:
library(dplyr)
dat %>%
ggplot(aes(fill = type,
x = x,
y = y)) +
geom_area(position="stack",
stat="identity",
alpha = 0.5,
color = "white")
Add some extra aesthetics and a geom_line()
dat %>%
ggplot(aes(fill = type,
x = x,
y = y,
color = type,
linetype = type)) +
geom_area(position="stack",
stat="identity",
alpha = 0.5) +
geom_line(position = "stack", size = 2)
I would suggest this approach. You can work around aes() to define the color using a variable (type) and then you can apply same method for aes() in geom_area() to define linetype. I added a large size so that the difference can be seen:
#Data
dat <- data.frame(x = c(1:5,1:5),
y = c(9:5, 10,7,5,3,1),
type = rep(c("a", "b"), each = 5))
library(dplyr)
library(ggplot2)
#Plot
dat %>%
ggplot(aes(fill = type,
x = x,
y = y,color=type)) +
geom_area(position="stack",
stat="identity",
alpha = 0.5,aes(linetype=type),size=3)
Output:
I am trying to create a line plot with 2 types of measurements, but my data is missing some x values. In Line break when no data in ggplot2 I have found how to create plot that will make a break when there is now data, but id does not allow to plot 2 lines (one for each Type).
1) When I try
ggplot(Data, aes(x = x, y = y, group = grp)) + geom_line()
it makes only one line, but with break when there is no data
2) When I try
ggplot(Data, aes(x = x, y = y, col = Type)) +
geom_line()
it makes 2 lines, but with break when there is no data
3) When I try
ggplot(Data, aes(x = x, y = y, col = Type, group = grp)) +
geom_line()
it makes unreadyble chart
4) of course I could combine the Type and grp to make new variable, but then the legend is not nice, and I get 4 groups (and colours) insted of 2.
5) also I could make something like that, but it dose not produce a legend, and in my real dataset i have way to many Types to do that
ggplot() +
geom_line(data = Data[Data$Type == "A",], aes(x = x, y = y, group = grp), col = "red") +
geom_line(data = Data[Data$Type == "B",], aes(x = x, y = y, group = grp), col = "blue")
Data sample:
Data <- data.frame(x = c(1:100, 201:300), y = rep(c(1, 2), 100), Type = rep(c("A", "B"), 100), grp = rep(c(1, 2), each = 100))
One way is to use interaction() to specify a grouping of multiple columns:
library(ggplot2)
Data <- data.frame(x = c(1:100, 201:300), y = rep(c(1, 2), 100), Type = rep(c("A", "B"), 100), grp = rep(c(1, 2), each = 100))
ggplot(Data, aes(x = x, y = y, col = Type, group = interaction(grp,Type))) +
geom_line()
I'm trying to create a boxplot using ggplot2 with :
X as a continuous variable
Colors for different groups
Here is an example :
x <- sample(c(1,2,5),300,replace = TRUE)
y <- sapply(x,function(mu) rnorm(1,mean = mu))
color <- sample(c("color 1","color 2"),300,replace = TRUE)
data <- data.frame(x, y, color)
I can either have colors and x as a factor :
ggplot(data = data) + geom_boxplot(aes(x = factor(x),y = y,col = color))
or x as a continuous variable and no colors :
ggplot(data = data) + geom_boxplot(aes(x = x,y = y,group = x))
But not both.
Does somebody know how to do this ?
Thanks
I think you need one more column for group, which is the combination of color and x. For example, how about simply paste()ing them?
set.seed(1)
x <- sample(c(1,2,5),300,replace = TRUE)
y <- sapply(x,function(mu) rnorm(1,mean = mu))
color <- sample(c("color 1","color 2"),300,replace = TRUE)
data <- data.frame(x, y, color)
library(ggplot2)
ggplot(data = data) +
geom_boxplot(aes(x = x, y = y, col = color, group = paste(color, x)))
You can use scales to change the x-axis scale.
library(ggplot2)
library(scales)
x <- sample(c(1,2,5),300,replace = TRUE)
y <- sapply(x,function(mu) rnorm(1,mean = mu))
color <- sample(c("color 1","color 2"),300,replace = TRUE)
data <- data.frame(x, y, color)
ggplot(data = data) + geom_boxplot(aes(x = factor(x),y = y,col = color)) + scale_x_discrete(limit = c('1','2','3','4','5'))
Hack for dynamic limits:
min = min(data$x)
max = max(data$x)
limits <- as.character(seq(min:max))
ggplot(data = data) + geom_boxplot(aes(x = factor(x),y = y,col = color)) + scale_x_discrete(limit = limits)
You could misuse the fill aesthetic:
ggplot(data = data) +
geom_boxplot(aes(x = x, y = y, col = color, fill = factor(x))) +
scale_fill_manual(values = rep(NA, 3), guide = "none")
I have a ggplot graph defined like this:
x <- seq(0, 10, by = 0.1)
y1 <- cos(x)
y2 <- sin(x)
df1 <- data.frame(x = x, y = y1, type = "sin", id = 1)
df2 <- data.frame(x = x, y = y2, type = "cos", id = 2)
df3 <- data.frame(x = 2, y = 0.5, type = "constant", id = 3)
df4 <- data.frame(x = 4, y = 0.2, type = "constant", id = 4)
combined <- rbind(df1, df2, df3, df4)
ggplot(combined, aes(x, y, colour = interaction(type, id))) + geom_line() +
geom_point(data = subset(combined, type == "constant"))
This works very well as illustrated below:
Now I would like to extract the interaction in a variable to reuse it later (e.g. customize the legend style or labels).
I did that in a very naïve way:
my.interaction <- interaction(combined$type, combined$id)
ggplot(combined, aes(x, y, colour = my.interaction)) + geom_line() +
geom_point(data = subset(combined, type == "constant"))
But then I have an error:
Error: Aesthetics must be either length 1 or the same as the data (2):
x, y, colour
Edit:
Here is the kind of manipulation I could do: edit the linetype of the legend
displayed <- levels(factor(my.interaction))
line.style <- rep(1, length.out = length(displayed))
line.style[grep("constant", displayed)] <- 0
That works:
ggplot(combined, aes(x, y, colour = interaction(type, id))) + geom_line() +
geom_point(data = subset(combined, type == "constant")) +
guides(colour=guide_legend(override.aes=list(linetype = line.style)))
That does not:
ggplot(combined, aes(x, y, colour = my.interation) + geom_line() +
geom_point(data = subset(combined, type == "constant")) +
guides(colour=guide_legend(override.aes=list(linetype = line.style)))
In the end, I could also edit the shapes or the legend labels (e.g. "Id: 1 / Type: sin" or any other advanced transformation of the labels based on the interaction values).
This'll work. What's wrong with adding a column to your data frame?
combined %>% mutate(my.interaction = paste(type, id, sep='.')) %>%
ggplot(aes(x, y, colour = my.interaction)) + geom_line() +
geom_point(data = subset(combined, type == "constant"))
I have the following dataframe:
data <- data.frame(x = c(5,1,3,2,5,7,12), y = c(5,7,6,1,3,5,6))
I can plot these coordinates with the ggplot function and draw a line between these coordinates:
ggplot(data, aes(x, y)) + geom_point(size = 3) + geom_line()
So far, no problems. But instead of a single line though the coordinates, I want that a line is drawn between all the coordinates. Creating a sort of spider web between all the coordinates. Is this possible in the ggplot2 package?
If you want to do this in ggplot2, then you could use geom_segment for this. But before you can make such a plot, you have to create a dataframe which connencts each observation to the other observations. You could approach it as follows:
library(ggplot2)
library(dplyr)
library(tidyr)
dat %>%
complete(nesting(x,y), id) %>% # create the combinations
select(id, xend=x, yend=y) %>% # rename the new variables as end-points
left_join(dat, ., by = 'id') %>% # join with the original dataframe
filter(!(x==xend & y==yend)) %>% # remove the endpoints that are the same as the start points
ggplot(., aes(x, y)) +
geom_segment(aes(x = x, y = y, xend = xend, yend = yend)) +
geom_label(aes(x = x, y = y, label = id, color = factor(id)), show.legend = FALSE) +
theme_minimal(base_size = 14) +
theme(axis.title = element_blank())
which gives:
Used data:
dat <- data.frame(x = c(5,1,3,2,5,7,12), y = c(5,7,6,1,3,5,6))
dat$id <- 1:nrow(dat)
Alternatively, you can also add the row-id on the fly without doing it beforehand:
dat %>%
mutate(id = row_number()) %>% # add a row id
complete(nesting(x,y), id) %>% # create the combinations
select(id, xend=x, yend=y) %>% # rename the new variables as end-points
left_join(dat %>% mutate(id = row_number()), .,
by = 'id') %>% # join with the original dataframe (also with an added row id)
filter(!(x==xend & y==yend)) %>% # remove the endpoints that are the same as the start points
ggplot(., aes(x, y)) +
geom_segment(aes(x = x, y = y, xend = xend, yend = yend)) +
geom_label(aes(x = x, y = y, label = id, color = factor(id)), show.legend = FALSE) +
theme_minimal(base_size = 14) +
theme(axis.title = element_blank())
Using base plotting:
plot(data)
sapply(combn(nrow(data), 2L, simplify = FALSE),
function(x) do.call("segments", as.list(c(t(data[x, ])))))
Add bells and whistles to taste.
You may also use the FUN argument in combn:
plot(data)
combn(nrow(data), 2L, simplify = FALSE, FUN = function(cm){
segments(x0 = data[cm[1L], 1L],
y0 = data[cm[1L], 2L],
x1 = data[cm[2L], 1L],
y1 = data[cm[2L], 2L])
})