Toronto Data Science Group - plots

toronto_datasci_plots.R

# Toronto Data Science Group Talk plots
# Myles Harrison
# http://www.everydayanalytics.ca/2014/02/toronto-data-science-group-talk.html

library(hexbin)
library(RColorBrewer)

# Create random data
x <- rnorm(5000, mean=1000)
y <- rnorm(5000, mean=2000)

# Scatterplot
plot(x, y, pch=16, col='black')
# Scatter with transparency
plot(x, y, pch=16, col=rgb(0,0,0,0.1))
# Smaller plotting symbols
plot(x, y, pch=16, col='black', cex=0.1)

# Simulate kernel density estimation with Euclidean distance to means
d <- sqrt((x-mean(x))^2 + (y-mean(y))^2)
# Select palette and normalize to fit in color range
palette(rainbow(32))
d <- d/max(d)*32+1
# Plot
plot(x, y, pch=16, col=d)

# Hexbinning
h <- hexbin(x,y)
plot(h)
# With color
plot(h, colramp=BTY)

# DISTRIBUTION
# Regular histogram
hist(x, breaks=125, col='red', xlab='x', main='Histogram of x')

# Boxplot
x2 <- rnorm(1000, mean=1000)
boxplot(x2)
# Add jitter
stripchart(x2,vertical=T,method="jitter",jitter=0.1,add=T, pch=16, 
           cex=0.1, col=rgb(0,0,0,0.5))

# Bubble chart demo
# Data from Flowing Data: http://flowingdata.com/2010/11/23/how-to-make-bubble-charts/

crime <- read.csv("http://datasets.flowingdata.com/crimeRatesByState2005.tsv", header=TRUE, sep="\t")
radius <- sqrt( crime$population/ pi )
plot(crime$murder, crime$burglary, col='red', pch=16, ylab='Burglary Rate', xlab='Murder Rate', xlim=c(0, 10), ylim=c(150, 1250))
symbols(crime$murder, crime$burglary, circles=radius, inches=0.35, fg="black", bg="red", xlab="Murder Rate", ylab="Burglary Rate", xlim=c(0, 10), ylim=c(150, 1250))

# Category-like colouring
palette(colorRampPalette(c("red", "green", "darkgreen"))(3))
c <- round(runif(50)*2)+1
symbols(crime$murder, crime$burglary, circles=radius, inches=0.35, fg="black", bg=c, xlab="Murder Rate", ylab="Burglary Rate", xlim=c(0, 10), ylim=c(150, 1250))
# Quantitive-like colouring
palette(colorRampPalette(c("lightblue", "yellow", "red"), interpolate='spline')(11))
c <- crime$population/max(crime$population)*10+1
symbols(crime$murder, crime$burglary, circles=radius, inches=0.35, fg="black", bg=c, xlab="Murder Rate", ylab="Burglary Rate", xlim=c(0, 10), ylim=c(150, 1250))