No legend shows up using multiple geom_point and geom_line functions in 1 graph

Question

I'm struggling to learn the ins and outs of R, ggplot2, etc - being more used to being taught in an A to Z manner an entire (fixed) coding language (not used to open source - I learned to code when dinosaurs roamed the earth). So I have kluged together the following code to create one graph. Only ... I don't have the dupe legends problem -- I have no legend a'tall!

erc <- ggplot(usedcarval, aes(x = usedcarval$age))   +
  geom_line(aes(y = usedcarval$dealer), colour = "orange", size = .5) +
  geom_point(aes(y = usedcarval$dealer), 
             show.legend = TRUE, colour = "orange", size = 1) +
  geom_line(aes(y = usedcarval$pvtsell), colour = "green", size = .5) +
  geom_point(aes(y = usedcarval$pvtsell), colour = "green", size = 1) +
  geom_line(aes(y = usedcarval$tradein), colour = "blue", size = .5) +
  geom_point(aes(y = usedcarval$tradein), colour = "blue", size = 1) +
  geom_line(aes(y = as.integer(predvalt)), colour = "gray", size = 1) +
  geom_line(aes(y = as.integer(predvalp)), colour = "gray", size = 1) + 
  geom_line(aes(y = as.integer(predvald)), colour = "gray", size = 1) +
  labs(x = "Value of a Used Car as it Ages (Years)", y = "Dollars") +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(axis.text.x = element_text(angle = 60, vjust = .6)) 
erc 

I can't figure out how to put an image in this text since I have no link except to my dropbox...

I would appreciate any help. Sincerely, Stephanie

Answer 1

Ok, I felt like doing some ggplot, and it was an interesting task to contrast the way ggplot-beginners (I was one not so long ago) approach it compared to the way you need to do it to get things like legends.

Here is the code:

library(ggplot2)
library(gridExtra)
library(tidyr)

# fake up some data
n <- 100
dealer <- 12000 + rnorm(n,0,100)
age <- 10 + rnorm(n,3)
pvtsell <- 10000 + rnorm(n,0,300)
tradein <- 5000 + rnorm(n,0,100)
predvalt <- 6000 + rnorm(n,0,120)
predvalp <- 7000 + rnorm(n,0,100)
predvald <- 8000 + rnorm(n,0,100)
usedcarval <- data.frame(dealer=dealer,age=age,pvtsell=pvtsell,tradein=tradein,
                        predvalt=predvalt,predvalp=predvalp,predvald=predvald)

# The ggplot-naive way
erc <- ggplot(usedcarval, aes(x = usedcarval$age))   +
  geom_line(aes(y = usedcarval$dealer), colour = "orange", size = .5) +
  geom_point(aes(y = usedcarval$dealer), 
             show.legend = TRUE, colour = "orange", size = 1) +
  geom_line(aes(y = usedcarval$pvtsell), colour = "green", size = .5) +
  geom_point(aes(y = usedcarval$pvtsell), colour = "green", size = 1) +
  geom_line(aes(y = usedcarval$tradein), colour = "blue", size = .5) +
  geom_point(aes(y = usedcarval$tradein), colour = "blue", size = 1) +
  geom_line(aes(y = as.integer(predvalt)), colour = "gray", size = 1) +
  geom_line(aes(y = as.integer(predvalp)), colour = "gray", size = 1) + 
  geom_line(aes(y = as.integer(predvald)), colour = "gray", size = 1) +
  labs(x = "ggplot naive way - Value of a Used Car as it Ages (Years)", y = "Dollars") +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(axis.text.x = element_text(angle = 60, vjust = .6)) 

# The tidyverse way
#    ggplot needs long data, not wide data. 
#    Also we have two different sets of data for points and lines

gdf <- usedcarval %>% gather(series,value,-age)
pdf <- gdf %>% filter( series %in% c("dealer","pvtsell","tradein"))

# our color and size lookup tables
clrs = c("dealer"="orange","pvtsell"="green","tradein"="blue","predvalt"="gray","predvalp"="gray","predvald"="gray")
szes = c("dealer"=0.5,"pvtsell"=0.0,"tradein"=0.5,"predvalt"=1,"predvalp"=1,"predvald"=1)

trc <- ggplot(gdf,aes(x=age)) + geom_line(aes(y=value,color=series,size=series)) + 
  scale_color_manual(values=clrs) +
  scale_size_manual(values=szes) +
  geom_point(data=pdf,aes(x=age,y=value,color=series),size=1) + 
  labs(x = "tidyverse way - Value of a Used Car as it Ages (Years)", y = "Dollars") +
  theme_bw() +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(axis.text.x = element_text(angle = 60, vjust = .6)) 

grid.arrange(erc, trc, ncol=1)

Study it, espeically look at gdf , pdf and gather . You just can't get legends without using "long data".

If you want more information on the "tidyverse", start here: Hadley Wickham's tidyverse

Answer 2

If you are looking for a short example of how to take some series data that comes in wide format, convert it to long format (using gather ), and then plot it with a ggplot (with a legend), here is a nice short example I cooked up for someone recently:

library(ggplot2)
library(tidyr)

# womp up some fake news (uhh... data)
x <- seq(-pi,pi,by=0.25)
y <- sin(x)
yhat <- sin(x) + 0.4*rnorm(length(x))

# This is the data in wide form 
#      you will never get ggplot to make a legend for it
#     it simply hates wide data
df1 <- data.frame(x=x,y=y,yhat=yhat)

# So we use gather from tidyr to make it into long data
#      creates two new colums, throws y and yhat in them, and replicates x as needed
#       you have to look at the data frame to understand gather,
#       and read the docs a few times
df2 <- gather(df1,series,value,-x)   

# it is now in long form and we can plot it
ggplot(df2) + geom_line(aes(x,value,color=series))

So here is the plot: