Introduction

  • Course notes from the Data Vizualization in R course on DataCamp
  • I’m not going to take too many notes from the videos for this class.
    • In general, I will not be using the base R graphics library.
    • I much prefer ggplot and ggvis.
    • But I do think the videos are pretty good and I like the explaination of many of the plotting principles.

Whats Covered

  • A quick introduction to base R graphics
  • Different plot types
  • Adding details to plots
  • How much is too much
  • Advanced plot customization and beyond

Aditional Resources

   

A quick introduction to base R graphics

The world of data visualization

  • Our ability to interpret patterns is a key strength
  • Two basic types of data visualizations:
    • Exploratroy visualizations help us understand the data
    • Explanatory visualizations help us share our understanding with others
  • Exploratory data visualizations
    • keep as much detail as possible
    • practical limit of how much you can see and interpret
  • Explanatory data visualizations
    • Requires editorial decisions
    • highlight key features you want to emphasize
    • eliminate extraneous details
  • 4 graphics systems in R
    • Base graphics - Easiest to make a default chart. Its the focus of this course
    • Grid graphics - powerful set of modules for building other tools
    • Lattice graphics - general purpose system based on grid graphics
    • ggplot2 - implements the grammar of graphics and lets you build plot features in order and intuatively

– Creating an exploratory plot array

# Load MASS package
library(MASS)

# Plot whiteside data
plot(whiteside)

– Creating an explanatory scatterplot

# Plot Gas vs. Temp
plot(whiteside$Temp, whiteside$Gas,
  xlab = "Outside temperature",
  ylab = "Heating gas consumption")

– The plot() function is generic

# Apply the plot() function to Insul
plot(whiteside$Insul)

A preview of some more and less useful techniques

  • You can add points() and lines() to plots

  • You can control the point shape, color, line type and things like that

  • You can create a grid layout to compare multiple charts

  • Avoid pie charts. Use a bar chart instead

– Adding details to a plot using point shapes, color, and reference lines

# Load the MASS package
library(MASS)

head(Cars93)
##   Manufacturer   Model    Type Min.Price Price Max.Price MPG.city
## 1        Acura Integra   Small      12.9  15.9      18.8       25
## 2        Acura  Legend Midsize      29.2  33.9      38.7       18
## 3         Audi      90 Compact      25.9  29.1      32.3       20
## 4         Audi     100 Midsize      30.8  37.7      44.6       19
## 5          BMW    535i Midsize      23.7  30.0      36.2       22
## 6        Buick Century Midsize      14.2  15.7      17.3       22
##   MPG.highway            AirBags DriveTrain Cylinders EngineSize
## 1          31               None      Front         4        1.8
## 2          25 Driver & Passenger      Front         6        3.2
## 3          26        Driver only      Front         6        2.8
## 4          26 Driver & Passenger      Front         6        2.8
## 5          30        Driver only       Rear         4        3.5
## 6          31        Driver only      Front         4        2.2
##   Horsepower  RPM Rev.per.mile Man.trans.avail Fuel.tank.capacity
## 1        140 6300         2890             Yes               13.2
## 2        200 5500         2335             Yes               18.0
## 3        172 5500         2280             Yes               16.9
## 4        172 5500         2535             Yes               21.1
## 5        208 5700         2545             Yes               21.1
## 6        110 5200         2565              No               16.4
##   Passengers Length Wheelbase Width Turn.circle Rear.seat.room
## 1          5    177       102    68          37           26.5
## 2          5    195       115    71          38           30.0
## 3          5    180       102    67          37           28.0
## 4          6    193       106    70          37           31.0
## 5          4    186       109    69          39           27.0
## 6          6    189       105    69          41           28.0
##   Luggage.room Weight  Origin          Make
## 1           11   2705 non-USA Acura Integra
## 2           15   3560 non-USA  Acura Legend
## 3           14   3375 non-USA       Audi 90
## 4           17   3405 non-USA      Audi 100
## 5           13   3640 non-USA      BMW 535i
## 6           16   2880     USA Buick Century
# Plot Max.Price vs. Price as red triangles
plot(Cars93$Price, Cars93$Max.Price,
  pch = 17,
  col = 'red')

# Add Min.Price vs. Price as blue circles
points(Cars93$Price, Cars93$Min.Price,
  pch = 16,
  col = 'blue')

# Add an equality reference line with abline()
abline(a = 0, b = 1, lty = 2)

– Creating multiple plot arrays

# Load the robustbase package
library(robustbase)

# Set up the side-by-side plot array
par(mfrow = c(1,2))

# First plot: brain vs. body in its original form
plot(Animals2$body, Animals2$brain)

# Add the first title
title("Original representation")

# Second plot: log-log plot of brain vs. body
plot(Animals2$body, Animals2$brain, log = "xy")

# Add the second title
title("Log-log plot")

– Avoid pie charts

# Load the insuranceData package
library(insuranceData)

# Use the data() function to get the dataCar data frame
data(dataCar)
head(dataCar)
##   veh_value  exposure clm numclaims claimcst0 veh_body veh_age gender area
## 1      1.06 0.3039014   0         0         0    HBACK       3      F    C
## 2      1.03 0.6488706   0         0         0    HBACK       2      F    A
## 3      3.26 0.5694730   0         0         0      UTE       2      F    E
## 4      4.14 0.3175907   0         0         0    STNWG       2      F    D
## 5      0.72 0.6488706   0         0         0    HBACK       4      F    C
## 6      2.01 0.8542094   0         0         0    HDTOP       3      M    C
##   agecat            X_OBSTAT_
## 1      2 01101    0    0    0
## 2      4 01101    0    0    0
## 3      2 01101    0    0    0
## 4      2 01101    0    0    0
## 5      2 01101    0    0    0
## 6      4 01101    0    0    0
# Set up a side-by-side plot array
par(mfrow = c(1,2))

# Create a table of veh_body record counts and sort
tbl <- sort(table(dataCar$veh_body),
            decreasing = T)

tbl
## 
## SEDAN HBACK STNWG   UTE TRUCK HDTOP COUPE PANVN MIBUS MCARA CONVT   BUS 
## 22233 18915 16261  4586  1750  1579   780   752   717   127    81    48 
## RDSTR 
##    27
# Create the pie chart and give it a title
pie(tbl)
title("Pie chart")

# Create the barplot with perpendicular, half-sized labels
barplot(tbl, las = 2, cex.names = 0.5)

# Add a title
title("Bar chart")

   

Different plot types

Characterizing a single variable

– The hist() and truehist() functions

  • hist() is part of base R and its default option yields a histogram based on the number of times a record falls into each of the bins on which the histogram is based.
  • truehist() is from the MASS package and scales these counts to give an estimate of the probability density.
# Set up a side-by-side plot array
par(mfrow = c(1,2))

# Create a histogram of counts with hist()
hist(Cars93$Horsepower, main = "hist() plot")

# Create a normalized histogram with truehist()
truehist(Cars93$Horsepower, main = "truehist() plot")

– Density plots as smoothed histograms

# Create index16, pointing to 16-week chicks
head(ChickWeight)
##   weight Time Chick Diet
## 1     42    0     1    1
## 2     51    2     1    1
## 3     59    4     1    1
## 4     64    6     1    1
## 5     76    8     1    1
## 6     93   10     1    1
index16 <- which(ChickWeight$Time == 16)
index16
##  [1]   9  21  33  45  57  69  81  93 104 116 128 140 152 164 191 205 217
## [18] 229 241 253 265 277 289 301 313 325 337 349 361 373 385 397 409 421
## [35] 433 445 457 469 481 493 505 515 527 539 551 563 575
# Get the 16-week chick weights
weights <- ChickWeight$weight[index16]
weights
##  [1] 149 162 163 136 197 155 218 126  93 101 182 162  71 227 113 106  98
## [18] 275 131 145  72 197 169 144 184 187 143 170 221 151 235 287 198 135
## [35] 192 170 215 175 204 197 145 147 173 168 222 184 205
# Plot the normalized histogram
truehist(weights)

# Add the density curve to the histogram
lines(density(weights))

– Using the qqPlot() function to see many details in data

  • A practical limitation of both histograms and density estimates is that, if we want to know whether the Gaussian distribution assumption is reasonable for our data, it is difficult to tell.
  • The quantile-quantile plot, or QQ-plot, is a useful alternative:
    • we sort our data, plot it against a specially-designed x-axis based on our reference distribution (e.g., the Gaussian “bell curve”), and look to see whether the points lie approximately on a straight line.
    • In R, several QQ-plot implementations are available, but the most convenient one is the qqPlot() function in the car package.
# Load the car package to make qqPlot() available
library(car)

# Create index16, pointing to 16-week chicks
index16 <- which(ChickWeight$Time == 16)

# Get the 16-week chick weights
weights <- ChickWeight$weight[index16]

# Show the normal QQ-plot of the chick weights
qqPlot(weights)

# Show the normal QQ-plot of the Boston$tax data
qqPlot(Boston$tax)

Visualizing relations between two variables

– The sunflowerplot() function for repeated numerical data

# Set up a side-by-side plot array
par(mfrow = c(1,2))

# Create the standard scatterplot
plot(rad ~ zn, data = Boston)

# Add the title
title("Standard scatterplot")

# Create the sunflowerplot
sunflowerplot(rad ~ zn, data = Boston)

# Add the title
title("Sunflower plot")

– Useful options for the boxplot() function

# Create a variable-width boxplot with log y-axis & horizontal labels
boxplot(crim ~ rad, 
  data = Boston, 
  varwidth = T,
  log = "y",
  las = 1)

# Add a title
title("Crime rate vs. radial highway index")

– Using the mosaicplot() function

# Create a mosaic plot using the formula interface
mosaicplot(carb ~ cyl, 
  data = mtcars,
  color = T)

Showing more complex relations between variables

– Using the bagplot() function

  • The bag plot extends the box plot representation to two numerical variables, showing their relationship, both within two-dimensional “bags” corresponding to the “box” in the standard boxplot, and indicating outlying points outside these limits.
# Create a side-by-side boxplot summary
par(mfrow = c(1,2))
boxplot(Cars93$Min.Price, Cars93$Max.Price)

# Load aplpack to make the bagplot() function available
library(aplpack)

# Create a bagplot for the same two variables
bagplot(Cars93$Min.Price, Cars93$Max.Price,
  cex = 1.20)

# Add an equality reference line
abline(0,1, lty = 2)

– Plotting correlation matrices with the corrplot() function

# Load the corrplot library for the corrplot() function
library(corrplot)

# Extract the numerical variables from UScereal
str(UScereal)
## 'data.frame':    65 obs. of  11 variables:
##  $ mfr      : Factor w/ 6 levels "G","K","N","P",..: 3 2 2 1 2 1 6 4 5 1 ...
##  $ calories : num  212 212 100 147 110 ...
##  $ protein  : num  12.12 12.12 8 2.67 2 ...
##  $ fat      : num  3.03 3.03 0 2.67 0 ...
##  $ sodium   : num  394 788 280 240 125 ...
##  $ fibre    : num  30.3 27.3 28 2 1 ...
##  $ carbo    : num  15.2 21.2 16 14 11 ...
##  $ sugars   : num  18.2 15.2 0 13.3 14 ...
##  $ shelf    : int  3 3 3 1 2 3 1 3 2 1 ...
##  $ potassium: num  848.5 969.7 660 93.3 30 ...
##  $ vitamins : Factor w/ 3 levels "100%","enriched",..: 2 2 2 2 2 2 2 2 2 2 ...
col_numeric <- sapply(UScereal, is.numeric)

numericalVars <- UScereal[,col_numeric]

str(numericalVars)
## 'data.frame':    65 obs. of  9 variables:
##  $ calories : num  212 212 100 147 110 ...
##  $ protein  : num  12.12 12.12 8 2.67 2 ...
##  $ fat      : num  3.03 3.03 0 2.67 0 ...
##  $ sodium   : num  394 788 280 240 125 ...
##  $ fibre    : num  30.3 27.3 28 2 1 ...
##  $ carbo    : num  15.2 21.2 16 14 11 ...
##  $ sugars   : num  18.2 15.2 0 13.3 14 ...
##  $ shelf    : int  3 3 3 1 2 3 1 3 2 1 ...
##  $ potassium: num  848.5 969.7 660 93.3 30 ...
# Compute the correlation matrix for these variables
corrMat <- cor(numericalVars)
corrMat
##            calories   protein       fat    sodium     fibre       carbo
## calories  1.0000000 0.7060105 0.5901757 0.5286552 0.3882179  0.78872268
## protein   0.7060105 1.0000000 0.4112661 0.5727222 0.8096397  0.54709029
## fat       0.5901757 0.4112661 1.0000000 0.2595606 0.2260715  0.18285220
## sodium    0.5286552 0.5727222 0.2595606 1.0000000 0.4954831  0.42356172
## fibre     0.3882179 0.8096397 0.2260715 0.4954831 1.0000000  0.20307489
## carbo     0.7887227 0.5470903 0.1828522 0.4235617 0.2030749  1.00000000
## sugars    0.4952942 0.1848484 0.4156740 0.2112437 0.1489158 -0.04082599
## shelf     0.4263400 0.3963311 0.3256975 0.2341275 0.3578429  0.26045989
## potassium 0.4765955 0.8417540 0.3232754 0.5566426 0.9638662  0.24204848
##                sugars     shelf potassium
## calories   0.49529421 0.4263400 0.4765955
## protein    0.18484845 0.3963311 0.8417540
## fat        0.41567397 0.3256975 0.3232754
## sodium     0.21124365 0.2341275 0.5566426
## fibre      0.14891577 0.3578429 0.9638662
## carbo     -0.04082599 0.2604599 0.2420485
## sugars     1.00000000 0.2900511 0.2718335
## shelf      0.29005112 1.0000000 0.4262529
## potassium  0.27183347 0.4262529 1.0000000
# Generate the correlation ellipse plot
corrplot(corrMat, method = "ellipse")

– Building and plotting rpart() models

# Load the rpart library
library(rpart)

# Fit an rpart model to predict medv from all other Boston variables
tree_model <- rpart(medv ~ ., data = Boston)

# Plot the structure of this decision tree model
plot(tree_model)

# Add labels to this plot
text(tree_model, cex = .7)

   

Adding details to plots

The plot() function and its options

– Introduction to the par() function

# Assign the return value from the par() function to plot_pars
plot_pars <- par()

# Display the names of the par() function's list elements
names(plot_pars)
##  [1] "xlog"      "ylog"      "adj"       "ann"       "ask"      
##  [6] "bg"        "bty"       "cex"       "cex.axis"  "cex.lab"  
## [11] "cex.main"  "cex.sub"   "cin"       "col"       "col.axis" 
## [16] "col.lab"   "col.main"  "col.sub"   "cra"       "crt"      
## [21] "csi"       "cxy"       "din"       "err"       "family"   
## [26] "fg"        "fig"       "fin"       "font"      "font.axis"
## [31] "font.lab"  "font.main" "font.sub"  "lab"       "las"      
## [36] "lend"      "lheight"   "ljoin"     "lmitre"    "lty"      
## [41] "lwd"       "mai"       "mar"       "mex"       "mfcol"    
## [46] "mfg"       "mfrow"     "mgp"       "mkh"       "new"      
## [51] "oma"       "omd"       "omi"       "page"      "pch"      
## [56] "pin"       "plt"       "ps"        "pty"       "smo"      
## [61] "srt"       "tck"       "tcl"       "usr"       "xaxp"     
## [66] "xaxs"      "xaxt"      "xpd"       "yaxp"      "yaxs"     
## [71] "yaxt"      "ylbias"
# Display the number of par() function list elements
length(plot_pars)
## [1] 72

– Exploring the type option

# Set up a 2-by-2 plot array
par(mfrow = c(2,2))

# Plot the Animals2 brain weight data as points
head(Animals2)
##                            body brain
## Lesser short-tailed shrew 0.005  0.14
## Little brown bat          0.010  0.25
## Big brown bat             0.023  0.30
## Mouse                     0.023  0.40
## Musk shrew                0.048  0.33
## Star-nosed mole           0.060  1.00
plot(Animals2$brain, type = "p")

# Add the title
title("points")

# Plot the brain weights with lines
plot(Animals2$brain, type = "l")

# Add the title
title("lines")

# Plot the brain weights as lines overlaid with points
plot(Animals2$brain, type = "o")

# Add the title
title("overlaid")

# Plot the brain weights as steps
plot(Animals2$brain, type = "s")

# Add the title
title("steps")

– The surprising utility of the type “n” option

# Compute max_hp
max_hp <- max(Cars93$Horsepower, mtcars$hp)

# Compute max_mpg
max_mpg <- max(Cars93$MPG.city, Cars93$MPG.highway, mtcars$mpg)

# Create plot with type = "n"               
plot(Cars93$Horsepower, Cars93$MPG.city,
     type = "n", 
     xlim = c(0, max_hp),
     ylim = c(0, max_mpg), 
     xlab = "Horsepower",
     ylab = "Miles per gallon")

# Add open circles to plot
points(mtcars$hp, mtcars$mpg, pch = 1)

# Add solid squares to plot
points(Cars93$Horsepower, Cars93$MPG.city, pch = 15)

# Add open triangles to plot
points(Cars93$Horsepower, Cars93$MPG.highway, pch = 6)

Adding lines and points to plots

– The lines() function and line types

# Create the numerical vector x
x <- seq(0, 10, length = 200)

# Compute the Gaussian density for x with mean 2 and standard deviation 0.2
gauss1 <- dnorm(x, mean = 2, sd = 0.2)

# Compute the Gaussian density with mean 4 and standard deviation 0.5
gauss2 <- dnorm(x, mean = 4, sd = 0.5)

# Plot the first Gaussian density
plot(x, gauss1, 
  type = "l",
  ylab = "Gaussian probability density")

# Add lines for the second Gaussian density
lines(x, gauss2, lty = 2, lwd = 3)

– The points() function and point types

# Create an empty plot using type = "n"
plot(mtcars$hp, mtcars$mpg,
  type='n',
  xlab = "Horsepower",
  ylab = "Gas mileage")

# Add points with shapes determined by cylinder number
points(mtcars$hp, mtcars$mpg, pch = mtcars$cyl)

# Create a second empty plot
plot(mtcars$hp, mtcars$mpg, 
  type='n',
  xlab = "Horsepower",
  ylab = "Gas mileage")

# Add points with shapes as cylinder characters
points(mtcars$hp, mtcars$mpg, pch = as.character(mtcars$cyl))

– Adding trend lines from linear regression models

library(MASS)

# Build a linear regression model for the whiteside data
linear_model <- lm(Gas ~ Temp, data = whiteside)

# Create a Gas vs. Temp scatterplot from the whiteside data
plot(whiteside$Temp, whiteside$Gas)

# Use abline() to add the linear regression line
abline(linear_model, lty = 2)

Adding text to plots

– Using the text() function to label plot features

# Create MPG.city vs. Horsepower plot with solid squares
plot(Cars93$Horsepower, Cars93$MPG.city, pch = 15)

# Create index3, pointing to 3-cylinder cars
head(Cars93)
##   Manufacturer   Model    Type Min.Price Price Max.Price MPG.city
## 1        Acura Integra   Small      12.9  15.9      18.8       25
## 2        Acura  Legend Midsize      29.2  33.9      38.7       18
## 3         Audi      90 Compact      25.9  29.1      32.3       20
## 4         Audi     100 Midsize      30.8  37.7      44.6       19
## 5          BMW    535i Midsize      23.7  30.0      36.2       22
## 6        Buick Century Midsize      14.2  15.7      17.3       22
##   MPG.highway            AirBags DriveTrain Cylinders EngineSize
## 1          31               None      Front         4        1.8
## 2          25 Driver & Passenger      Front         6        3.2
## 3          26        Driver only      Front         6        2.8
## 4          26 Driver & Passenger      Front         6        2.8
## 5          30        Driver only       Rear         4        3.5
## 6          31        Driver only      Front         4        2.2
##   Horsepower  RPM Rev.per.mile Man.trans.avail Fuel.tank.capacity
## 1        140 6300         2890             Yes               13.2
## 2        200 5500         2335             Yes               18.0
## 3        172 5500         2280             Yes               16.9
## 4        172 5500         2535             Yes               21.1
## 5        208 5700         2545             Yes               21.1
## 6        110 5200         2565              No               16.4
##   Passengers Length Wheelbase Width Turn.circle Rear.seat.room
## 1          5    177       102    68          37           26.5
## 2          5    195       115    71          38           30.0
## 3          5    180       102    67          37           28.0
## 4          6    193       106    70          37           31.0
## 5          4    186       109    69          39           27.0
## 6          6    189       105    69          41           28.0
##   Luggage.room Weight  Origin          Make
## 1           11   2705 non-USA Acura Integra
## 2           15   3560 non-USA  Acura Legend
## 3           14   3375 non-USA       Audi 90
## 4           17   3405 non-USA      Audi 100
## 5           13   3640 non-USA      BMW 535i
## 6           16   2880     USA Buick Century
index3 <- which(Cars93$Cylinders == 3)
index3
## [1] 39 80 83
# Add text giving names of cars next to data points
text(x = Cars93$Horsepower[index3],
     y = Cars93$MPG.city[index3], 
     labels = Cars93$Make[index3], 
     adj = 0)

– Adjusting text position, size, and font

# Plot MPG.city vs. Horsepower as open circles
plot(Cars93$Horsepower, Cars93$MPG.city, pch = 1)

# Create index3, pointing to 3-cylinder cars
index3 <- which(Cars93$Cylinders == 3)

# Highlight 3-cylinder cars as solid circles
points(Cars93$Horsepower[index3], Cars93$MPG.city[index3], pch = 16)

# Add car names, offset from points, with larger bold text
text(
  Cars93$Horsepower[index3], 
  Cars93$MPG.city[index3], 
  Cars93$Make[index3], 
  adj = -0.2,
  cex = 1.2,
  font = 4)

– Rotating text with the srt argument

# Plot Gas vs. Temp as solid triangles
plot(whiteside$Temp, whiteside$Gas, pch=17)

# Create indexB, pointing to "Before" data
indexB <- which(whiteside$Insul == "Before")

# Create indexA, pointing to "After" data
indexA <- which(whiteside$Insul == "After")

# Add "Before" text in blue, rotated 30 degrees, 80% size
text(x = whiteside$Temp[indexB], y = whiteside$Gas[indexB],
     labels = "Before", col = 'blue', srt = 30, cex = .8)

# Add "After" text in red, rotated -20 degrees, 80% size
text(x = whiteside$Temp[indexA], y = whiteside$Gas[indexA],
     labels = "After", col = 'red', srt = -20, cex = .8)

Adding or modifying other plot details

– Using the legend() function

# Set up and label empty plot of Gas vs. Temp
plot(whiteside$Temp, whiteside$Gas,
     type = "n", 
     xlab = "Outside temperature",
     ylab = "Heating gas consumption")

# Create indexB, pointing to "Before" data
indexB <- which(whiteside$Insul == "Before")

# Create indexA, pointing to "After" data
indexA <- which(whiteside$Insul == "After")

# Add "Before" data as solid triangles
points(whiteside$Temp[indexB], whiteside$Gas[indexB], pch = 17)

# Add "After" data as open circles
points(whiteside$Temp[indexA], whiteside$Gas[indexA], pch = 1)

# Add legend that identifies points as "Before" and "After"
legend("topright", pch = c(17, 1), legend = c("Before", "After"))

– Adding custom axes with the axis() function

head(UScereal[,c("sugars", "shelf")],10)
##                              sugars shelf
## 100% Bran                 18.181818     3
## All-Bran                  15.151515     3
## All-Bran with Extra Fiber  0.000000     3
## Apple Cinnamon Cheerios   13.333333     1
## Apple Jacks               14.000000     2
## Basic 4                   10.666667     3
## Bran Chex                  8.955224     1
## Bran Flakes                7.462687     3
## Cap'n'Crunch              16.000000     2
## Cheerios                   0.800000     1
# Create a boxplot of sugars by shelf value, without axes
boxplot(sugars ~ shelf, data = UScereal, axes = F)

# Add a default y-axis to the left of the boxplot
axis(side = 2)

# Add an x-axis below the plot, labelled 1, 2, and 3
axis(side = 1, at = c(1,2,3))

# Add a second x-axis above the plot
axis(side = 3, at = c(1,2,3),
     labels = c("floor","middle","top"))

– Using the supsmu() function to add smooth trend curves

# Create a scatterplot of MPG.city vs. Horsepower
plot(Cars93$Horsepower, Cars93$MPG.city)

# Call supsmu() to generate a smooth trend curve, with default bass
trend1 <- supsmu(Cars93$Horsepower, Cars93$MPG.city)

# Add this trend curve to the plot
lines(trend1)

# Call supsmu() for a second trend curve, with bass = 10
trend2 <- supsmu(Cars93$Horsepower, Cars93$MPG.city, bass = 10)

# Add this trend curve as a heavy, dotted line
lines(trend2, lty = 3, lwd = 2)

   

How much is too much?

Managing visual complexity

– Too much is too much

# Compute the number of plots to be displayed
ncol(Cars93)^2
## [1] 729
# Plot the array of scatterplots
plot(Cars93)

– Deciding how many scatterplots is too many

# Construct the vector keep_vars
keep_vars <- c("calories", "protein", "fat",
               "fibre", "carbo", "sugars")

# Use keep_vars to extract the desired subset of UScereal
df <- UScereal[, keep_vars]
str(df)
## 'data.frame':    65 obs. of  6 variables:
##  $ calories: num  212 212 100 147 110 ...
##  $ protein : num  12.12 12.12 8 2.67 2 ...
##  $ fat     : num  3.03 3.03 0 2.67 0 ...
##  $ fibre   : num  30.3 27.3 28 2 1 ...
##  $ carbo   : num  15.2 21.2 16 14 11 ...
##  $ sugars  : num  18.2 15.2 0 13.3 14 ...
# Set up a two-by-two plot array
par(mfrow = c(2,2))

# Use matplot() to generate an array of two scatterplots
matplot(
  UScereal$calories, 
  UScereal[,c('protein', 'fat')], 
  xlab = "calories",
  ylab = "")


# Add a title
title("Two scatterplots")


# Use matplot() to generate an array of three scatterplots
matplot(
  UScereal$calories, 
  UScereal[,c('protein', 'fat', 'fibre')], 
  xlab = "calories",
  ylab = "")

# Add a title
title("Three scatterplots")

# Use matplot() to generate an array of four scatterplots
matplot(
  UScereal$calories, 
  UScereal[,c('protein', 'fat', 'fibre', 'carbo')], 
  xlab = "calories",
  ylab = "")

# Add a title
title("Four scatterplots")

# Use matplot() to generate an array of five scatterplots
matplot(
  UScereal$calories, 
  UScereal[,c('protein', 'fat', 'fibre', 'carbo','sugars')], 
  xlab = "calories",
  ylab = "")


# Add a title
title("Five scatterplots")

– How many words is too many?

library(wordcloud)

# Create mfr_table of manufacturer frequencies
mfr_table <- table(Cars93$Manufacturer)

# Create the default wordcloud from this table
wordcloud(
  words = names(mfr_table), 
  freq = as.numeric(mfr_table), 
  scale = c(2, 0.25))

# Change the minimum word frequency
wordcloud(
  words = names(mfr_table), 
  freq = as.numeric(mfr_table), 
  scale = c(2, 0.25),
  min.freq = 1)

# Create model_table of model frequencies
model_table <- table(Cars93$Model)

# Create the wordcloud of all model names with smaller scaling
wordcloud(
  words = names(model_table), 
  freq = as.numeric(model_table), 
  scale = c(.75, .25), 
  min.freq = 1)

Creating plot arrays with the mfrow parameter

– The Anscombe quartet

# Set up a two-by-two plot array
par(mfrow = c(2,2))

# Plot y1 vs. x1 
plot(anscombe$x1, anscombe$y1)

# Plot y2 vs. x2
plot(anscombe$x2, anscombe$y2)

# Plot y3 vs. x3
plot(anscombe$x3, anscombe$y3)

# Plot y4 vs. x4
plot(anscombe$x4, anscombe$y4)

– The utility of common scaling and individual titles

# Define common x and y limits for the four plots
xmin <- 4
xmax <- 19
ymin <- 3
ymax <- 13

# Set up a two-by-two plot array
par(mfrow = c(2,2))

# Plot y1 vs. x1 with common x and y limits, labels & title
plot(anscombe$x1, anscombe$y1,
     xlim = c(xmin, xmax),
     ylim = c(ymin, ymax),
     xlab = "x value", ylab = "y value",
     main = "First dataset")

# Do the same for the y2 vs. x2 plot
plot(anscombe$x2, anscombe$y2,
     xlim = c(xmin, xmax),
     ylim = c(ymin, ymax),
     xlab = "x value", ylab = "y value",
     main = "Second dataset")

# Do the same for the y3 vs. x3 plot
plot(anscombe$x3, anscombe$y3,
     xlim = c(xmin, xmax),
     ylim = c(ymin, ymax),
     xlab = "x value", ylab = "y value",
     main = "Third dataset")

# Do the same for the y4 vs. x4 plot
plot(anscombe$x4, anscombe$y4,
     xlim = c(xmin, xmax),
     ylim = c(ymin, ymax),
     xlab = "x value", ylab = "y value",
     main = "Fourth dataset")

– Using multiple plots to give multiple views of a dataset

# Set up a two-by-two plot array
par(mfrow = c(2,2))

# Plot the raw duration data
plot(geyser$duration, main = "Raw data")

# Plot the normalized histogram of the duration data
truehist(geyser$duration, main = "Histogram")

# Plot the density of the duration data
plot(density(geyser$duration), main = "Density")

# Construct the normal QQ-plot of the duration data
qqPlot(geyser$duration, main = "QQ-plot")

Creating plot arrays with the layout() function

– Constructing and displaying layout matrices

# Use the matrix function to create a matrix with three rows and two columns
layoutMatrix <- matrix(
  c(
    0, 1,
    2, 0,
    0, 3
  ), 
  byrow = T, 
  nrow = 3
)

# Call the layout() function to set up the plot array
layout(layoutMatrix)

# Show where the three plots will go 
layout.show(n = 3)

– Creating a triangular array of plots

# Set up the plot array
layout(layoutMatrix)

# Construct vectors indexB and indexA
indexB <- which(whiteside$Insul == "Before")
indexA <- which(whiteside$Insul == "After")

# Create plot 1 and add title
plot(whiteside$Temp[indexB], whiteside$Gas[indexB],
     ylim = c(0,8))
title("Before data only")

# Create plot 2 and add title
plot(whiteside$Temp, whiteside$Gas,
     ylim = c(0,8))
title("Complete dataset")

# Create plot 3 and add title
plot(whiteside$Temp[indexA], whiteside$Gas[indexA],
     ylim = c(0,8))
title("After data only")

– Creating arrays with different sized plots

# Create row1, row2, and layoutVector
row1 <- c(1,0,0)
row2 <- c(0,2,2)
layoutVector <- c(row1,row2, row2)

# Convert layoutVector into layoutMatrix
layoutMatrix <- matrix(layoutVector, byrow = T, nrow = 3)

# Set up the plot array
layout(layoutMatrix)

# Plot scatterplot
plot(Boston$rad, Boston$zn)

# Plot sunflower plot
sunflowerplot(Boston$rad, Boston$zn)

   

Advanced plot customization and beyond

Creating and saving more complex plots

– Some plot functions also return useful information

# Create a table of Cylinders frequencies
tbl <- table(Cars93$Cylinders)

# Generate a horizontal barplot of these frequencies
mids <- barplot(tbl, 
  horiz = T,
  col = "transparent",
  names.arg = "")

# Add names labels with text()
text(20, mids, names(tbl))

# Add count labels with text()
text(35, mids, as.numeric(tbl))

– Using the symbols() function to display relations between more than two variables

# Call symbols() to create the default bubbleplot
symbols(Cars93$Horsepower, Cars93$MPG.city,
        circles = sqrt(Cars93$Price))

# Repeat, with the inches argument specified
symbols(Cars93$Horsepower, Cars93$MPG.city,
        circles = sqrt(Cars93$Price),
        inches = 0.1)

– Saving plot results as files

# Call png() with the name of the file we want to create
png('bubbleplot.png')

# Re-create the plot from the last exercise
symbols(Cars93$Horsepower, Cars93$MPG.city,
        circles = sqrt(Cars93$Price),
        inches = 0.1)

# Save our file and return to our interactive session
dev.off()
## quartz_off_screen 
##                 2
# Verify that we have created the file
list.files(pattern = "png")
## [1] "bubbleplot.png"

Using color effectively

– Using color to enhance a bubbleplot

# Iliinsky and Steele color name vector
IScolors <- c("red", "green", "yellow", "blue",
              "black", "white", "pink", "cyan",
              "gray", "orange", "brown", "purple")

# Create the `cylinderLevel` variable
cylinderLevel <- as.numeric(Cars93$Cylinders)

# Create the colored bubbleplot
symbols(
  Cars93$Horsepower, Cars93$MPG.city, 
  circles = as.numeric(Cars93$Cylinders), 
  inches = 0.2, 
  bg = IScolors[cylinderLevel])

– Using color to enhance stacked barplots

# Create a table of Cylinders by Origin
tbl <- table(Cars93$Cylinders, Cars93$Origin)

# Create the default stacked barplot
barplot(tbl)

# Enhance this plot with color
barplot(tbl, col = IScolors)

Other graphics systems in R

– The tabplot package and grid graphics

# Load the insuranceData package
library(insuranceData)

# Use the data() function to load the dataCar data frame
data(dataCar)
head(dataCar)
##   veh_value  exposure clm numclaims claimcst0 veh_body veh_age gender area
## 1      1.06 0.3039014   0         0         0    HBACK       3      F    C
## 2      1.03 0.6488706   0         0         0    HBACK       2      F    A
## 3      3.26 0.5694730   0         0         0      UTE       2      F    E
## 4      4.14 0.3175907   0         0         0    STNWG       2      F    D
## 5      0.72 0.6488706   0         0         0    HBACK       4      F    C
## 6      2.01 0.8542094   0         0         0    HDTOP       3      M    C
##   agecat            X_OBSTAT_
## 1      2 01101    0    0    0
## 2      4 01101    0    0    0
## 3      2 01101    0    0    0
## 4      2 01101    0    0    0
## 5      2 01101    0    0    0
## 6      4 01101    0    0    0
# Load the tabplot package
suppressPackageStartupMessages(library(tabplot))

# Generate the default tableplot() display
tableplot(dataCar)

– A lattice graphics example

# Load the lattice package
library(lattice)

# Use xyplot() to construct the conditional scatterplot
xyplot(calories ~ sugars | shelf, data = UScereal)

– A ggplot2 graphics example

# Load the ggplot2 package
library(ggplot2)

# Create the basic plot (not displayed): basePlot
basePlot <- ggplot(Cars93, aes(x = Horsepower, y = MPG.city))

# Display the basic scatterplot
basePlot + 
  geom_point()

# Color the points by Cylinders value
basePlot + 
  geom_point(colour = IScolors[Cars93$Cylinders])

# Make the point sizes also vary with Cylinders value
basePlot + 
  geom_point(colour = IScolors[Cars93$Cylinders], 
             size = as.numeric(Cars93$Cylinders))