Black Lives Matter. Please consider donating to Black Girls Code today.

geom_ribbon in ggplot2

How to make plots with geom_ribbon in ggplot2 and R.


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.

Line & Ribbon

library(plotly)

set.seed(1)
y <- sin(seq(1, 2*pi, length.out = 100))
x <- 1:100
plotdata <- data.frame(x=x, y=y, lower = (y+runif(100, -1, -0.5)), upper = (y+runif(100, 0.5, 1)))

p <- ggplot(plotdata) + geom_line(aes(y=y, x=x, colour = "sin"))+
    geom_ribbon(aes(ymin=lower, ymax=upper, x=x, fill = "band"), alpha = 0.3)+
    scale_colour_manual("",values="blue")+
    scale_fill_manual("",values="grey12")

fig <- ggplotly()

fig

Inspired by ggplot2 docs

Facets

library(plotly)

set.seed(1987)
pkgs <- c("ggplot2", "mgcv", "MASS")
invisible(lapply(pkgs, require, character.only = TRUE))

load(url('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic3.sav'))
titanic3 <- na.omit(titanic3[, -c(3,8:14)])
titanic3$class_sex <- apply(titanic3, 1,
                            function(x) paste(x[1], x[3], collapse = "_"))
titanic3$class_sex <- factor(titanic3$class_sex)
train <- titanic3[sample(row.names(titanic3),
                         size = round(nrow(titanic3) / 2)), ]
test <- titanic3[!(row.names(titanic3) %in% row.names(train)), ]

sim.data <- expand.grid(sex = c("male", "female"), sibsp = 0,
                        age = seq(1, 80), pclass = c("1st", "2nd", "3rd"))

glm.fit <- glm(survived ~ poly(age, 2) * sex * pclass + sibsp,
               "binomial", train)

inv.logit <- function(x) exp(x) / (1 + exp(x))
glm.pred <- predict(glm.fit, newdata = test, se.fit = TRUE)
pred <- data.frame(mean = inv.logit(glm.pred$fit),
                   lo = inv.logit(glm.pred$fit - 2 * glm.pred$se.fit),
                   hi = inv.logit(glm.pred$fit + 2 * glm.pred$se.fit),
                   survived = test$survived)
pred <- pred[order(pred$mean), ]
pred$id <- seq_along(pred$mean)
row.names(pred) <- NULL

pred <- predict(glm.fit, newdata = sim.data, se.fit = TRUE)
sim.data$mean <- inv.logit(pred$fit)
sim.data$lo <- inv.logit(pred$fit - 2 * pred$se.fit)
sim.data$hi <- inv.logit(pred$fit + 2 * pred$se.fit)

p <- ggplot(titanic3, aes(x = age, y = survived))
p <- p + geom_point()
p <- p + facet_grid(sex ~ pclass)
p <- p + geom_line(data = sim.data, aes(y = mean))
p <- p + geom_ribbon(data = sim.data, aes(y = mean, ymin = lo, ymax = hi),
                     alpha = .25)
p <- p + labs(x = "Passenger Age", y = "Probability of Survival")

fig <- ggplotly(p)

fig

Inspired by Zachary Jones

Facetwrap & Smooth

library(plotly)

set.seed(42)
n <- 100

df <- data.frame(location = rep(LETTERS[1:4], n),
                 score    = sample(45:80, 4*n, replace = TRUE))

df$fig    <- inv.logit(0.075 * df$score + rep(c(-4.5, -5, -6, -2.8), n))
df$pass <- sapply(df$fig, function(x){rbinom(1, 1, x)})

g <- glm(pass ~ location + score, data = df, family = 'binomial')

new.data <- expand.grid(score    = seq(46, 75, length = n), 
                        location = LETTERS[1:4])

preds <- predict(g, newdata = new.data, type = 'response',se = TRUE)
new.data$pred.full <- preds$fit

new.data$ymin <- new.data$pred.full - 2*preds$se.fit
new.data$ymax <- new.data$pred.full + 2*preds$se.fit

p <- ggplot(df,aes(x = score, y = pass)) +
    facet_wrap(~location) +
    geom_point(size=1) +
    geom_ribbon(data = new.data,aes(y = pred.full, ymin = ymin, ymax = ymax),alpha = 0.25) +
    geom_line(data = new.data,aes(y = pred.full),colour = "blue")

fig <- ggplotly(p)

fig

Inspired by Stack Overflow

Prediction Bands

library(plotly)

set.seed(42)
x <- rep(0:100,10)
y <- 15 + 2*rnorm(1010,10,4)*x + rnorm(1010,20,100)
id<-rep(1:10,each=101)

dtfr <- data.frame(x=x ,y=y, id=id)

library(nlme)

model.mx <- lme(y~x,random=~1+x|id,data=dtfr)

#create data.frame with new values for predictors
#more than one predictor is possible
new.dat <- data.frame(x=0:100)
#predict response
new.dat$pred <- predict(model.mx, newdata=new.dat,level=0)

#create design matrix
Designmat <- model.matrix(eval(eval(model.mx$call$fixed)[-2]), new.dat[-ncol(new.dat)])

#compute standard error for predictions
predvar <- diag(Designmat %*% model.mx$varFix %*% t(Designmat))
new.dat$SE <- sqrt(predvar) 
new.dat$SE2 <- sqrt(predvar+model.mx$sigma^2)

library(ggplot2) 
p <- ggplot(new.dat,aes(x=x,y=pred)) + 
geom_line() +
geom_ribbon(aes(ymin=pred-2*SE2,ymax=pred+2*SE2),alpha=0.2,fill="red") +
geom_ribbon(aes(ymin=pred-2*SE,ymax=pred+2*SE),alpha=0.2,fill="blue") +
geom_point(data=dtfr,aes(x=x,y=y), size=1) +
scale_y_continuous("y")

fig <- ggplotly(p)

fig

Inspired by Stack Overflow

Confidence Bands

library(plotly)

require(nlme)

set.seed(101)
mp <- data.frame(year=1990:2010)
N <- nrow(mp)

mp <-  within(mp,
         {
             wav <- rnorm(N)*cos(2*pi*year)+rnorm(N)*sin(2*pi*year)+5
             wow <- rnorm(N)*wav+rnorm(N)*wav^3
         })

m01 <- gls(wow~poly(wav,3), data=mp, correlation = corARMA(p=1))

fit <- predict(m01)

V <- vcov(m01)
X <- model.matrix(~poly(wav,3),data=mp)
se.fit <- sqrt(diag(X %*% V %*% t(X)))

predframe <- with(mp,data.frame(year,wav,
                                wow=fit,lwr=fit-1.96*se.fit,upr=fit+1.96*se.fit))

p <- ggplot(mp, aes(year, wow))+
    geom_point()+
    geom_line(data=predframe)+
    geom_ribbon(data=predframe,aes(ymin=lwr,ymax=upr),alpha=0.3)

fig <- ggplotly(p)

fig

Inspired by Stack overflow

Multiple Layers

library(plotly)

x=seq(1,10,length=100)
data=data.frame(x,dnorm(x,mean=6.5,sd=1))
names(data)=c('x','new.data')
x.ribbon=seq(1,10,length=20)
ribbon=data.frame(x.ribbon,
                  dnorm(x.ribbon,mean=5,sd=1)+.01,
                  dnorm(x.ribbon,mean=5,sd=1)-.01,
                  dnorm(x.ribbon,mean=5,sd=1))
names(ribbon)=c('x.ribbon','max','min','avg')

p <- ggplot()+geom_ribbon(data=ribbon,aes(ymin=min,ymax=max,x=x.ribbon,fill='lightgreen'))+
    geom_line(data=ribbon,aes(x=x.ribbon,y=avg,color='black'))+
    geom_line(data=data,aes(x=x,y=new.data,color='red'))+
    xlab('x')+ylab('density') + 
    scale_fill_identity() +
    scale_colour_manual(name = 'the colour', 
         values =c('black'='black','red'='red'))

fig <- ggplotly(p)

fig

Inspired by Stack Overflow

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)