Ggplot2 > Basic Charts > Scatter Plots
Suggest an edit to this page

Scatter Plots in ggplot2

How to make Scatter Plots in ggplot2 with Plotly.


New to Plotly?

Plotly is a free and open-source graphing library for R. We recommend you read our Getting Started guide for the latest installation or upgrade instructions, then move on to our Plotly Fundamentals tutorials or dive straight in to some Basic Charts tutorials.

Default point plot

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(wt, mpg))
p <-  p + geom_point()

ggplotly(p)

Add colour

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(wt, mpg))
p <-  p + geom_point(aes(colour = factor(cyl)))

ggplotly(p)

Changing shapes of data points

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(wt, mpg))
p <-  p + geom_point(aes(shape = factor(cyl)))

ggplotly(p)

Changing size of data points

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(wt, mpg))
p <-  p + geom_point(aes(size = qsec))

ggplotly(p)

Manually setting aesthetics

library(plotly)
library(ggplot2)

p <-  ggplot(mtcars, aes(wt, mpg)) + geom_point(colour = "red", size = 3)

ggplotly(p)

Optional shape arguments

For shapes that have a border (like shape 21), you can colour the inside and outside separately. Use the stroke aesthetic to modify the width of the border.

library(plotly)
library(ggplot2)

p <-    
 ggplot(mtcars, aes(wt, mpg)) +
  geom_point(shape = 21, colour = "black", fill = "white", size = 5, stroke = 5)

ggplotly(p)

Mix multiples shapes

You can create interesting shapes by layering multiple points of different sizes.

Default plot:

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(mpg, wt, shape = factor(cyl)))
p <-    
 p +
  geom_point(aes(colour = factor(cyl)), size = 4) +
  geom_point(colour = "grey90", size = 1.5)

ggplotly(p)

Mixed shapes:

library(plotly)
library(ggplot2)

p <- ggplot(mtcars, aes(mpg, wt, shape = factor(cyl)))
p <-    
 p +
  geom_point(colour = "black", size = 4.5) +
  geom_point(colour = "pink", size = 4) +
  geom_point(aes(shape = factor(cyl)))

ggplotly(p)

Liner Regression

library(plotly)
library(ggplot2)

dat <- data.frame(cond = rep(c("A", "B"), each=10),
                  xvar = 1:20 + rnorm(20,sd=3),
                  yvar = 1:20 + rnorm(20,sd=3))

p <- ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +    # Use hollow circles
    geom_smooth(method=lm)   # Add linear regression line

ggplotly(p)

library(plotly)
library(ggplot2)

dat <- data.frame(cond = rep(c("A", "B"), each=10),
                  xvar = 1:20 + rnorm(20,sd=3),
                  yvar = 1:20 + rnorm(20,sd=3))

p <- ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +
    geom_smooth()

Without confidence boundary area:

library(plotly)
library(ggplot2)

dat <- data.frame(cond = rep(c("A", "B"), each=10),
                  xvar = 1:20 + rnorm(20,sd=3),
                  yvar = 1:20 + rnorm(20,sd=3))

p <- ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +    # Use hollow circles
    geom_smooth(method=lm,   # Add linear regression line
                se=FALSE)    # Don't add shaded confidence region

ggplotly(p)

Multiple regressions:

library(plotly)
library(ggplot2)

x <-  1:10
dd <- rbind(data.frame(x=x,fac="a", y=x+rnorm(10)),
            data.frame(x=2*x,fac="b", y=x+rnorm(10)))
coef <- lm(y~x:fac, data=dd)$coefficients
p <- qplot(data=dd, x=x, y=y, color=fac)+
    geom_abline(slope=coef["x:faca"], intercept=coef["(Intercept)"])+
    geom_abline(slope=coef["x:facb"], intercept=coef["(Intercept)"])

ggplotly(p)

Constrained slope

library(plotly)
library(ggplot2)

n <- 20

x1 <- rnorm(n); x2 <- rnorm(n)
y1 <- 2 * x1 + rnorm(n)
y2 <- 3 * x2 + (2 + rnorm(n))
A <- as.factor(rep(c(1, 2), each = n))
df <- data.frame(x = c(x1, x2), y = c(y1, y2), A = A)
fm <- lm(y ~ x + A, data = df)

p <- ggplot(data = cbind(df, pred = predict(fm)), aes(x = x, y = y, color = A))
p <- p + geom_point() + geom_line(aes(y = pred))

ggplotly(p)

Stat Summary

library(plotly)
library(ggplot2)

hist <- data.frame(date=Sys.Date() + 0:13, counts=1:14)
hist <- transform(hist, weekday=factor(weekdays(date), levels=c('Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday')))

p <- ggplot(hist, aes(x=weekday, y=counts, group=1)) +
    geom_point(stat='summary', fun.y=sum) +
    stat_summary(fun.y=sum, geom="line")

ggplotly(p)

Line order

library(plotly)
library(ggplot2)

dat <- data.frame(x = sample(1:10), y = sample(1:10), order = sample(1:10))
p <- ggplot(dat[order(dat$order),], aes(x, y)) + geom_point() + geom_text(aes(y = y + 0.25,label =      order)) +
     geom_path()

ggplotly(p)

Adding horizontal line

library(plotly)
library(ggplot2)

p <- ggplot(mtcars,aes(mpg,qsec))+geom_point() +
  geom_segment(aes(x=15,xend=20,y=18,yend=18))

ggplotly(p)

Adding points to line

library(plotly)
library(ggplot2)

df <- data.frame(time=as.factor(c(1,1,2,2,3,3,4,4,5,5)), 
               value=as.numeric(c(7, 8, 9, 10, 10, 11, 10.5, 11.4, 10.9, 11.6)), 
               side=as.factor(c("E","F","E","F","E","F","E","F","E","F")))


p <- ggplot(df, aes(time, value, group=side, colour=side)) + 
     geom_line(size=1)
p <- p + geom_point()

ggplotly(p)

What About Dash?

Dash for R is an open-source framework for building analytical applications, with no Javascript required, and it is tightly integrated with the Plotly graphing library.

Learn about how to install Dash for R at https://dashr.plot.ly/installation.

Everywhere in this page that you see fig, you can display the same figure in a Dash for R application by passing it to the figure argument of the Graph component from the built-in dashCoreComponents package like this:

library(plotly)

fig <- plot_ly() 
# fig <- fig %>% add_trace( ... )
# fig <- fig %>% layout( ... ) 

library(dash)
library(dashCoreComponents)
library(dashHtmlComponents)

app <- Dash$new()
app$layout(
    htmlDiv(
        list(
            dccGraph(figure=fig) 
        )
     )
)

app$run_server(debug=TRUE, dev_tools_hot_reload=FALSE)