Tools

Statistics 4868/6610 Data Visualization

Prof. Eric A. Suess

1/20/2016

Introduction

Lets start visualizing data!

Software.

The more visualization tools you know how to use and take advantage of, the less likely you'll get stuck not knowing what to do with a dataset and the more likely you can make a graphic that matches your vision.

Introduction

Out-of-the-Box Visualization

  • Point-and-Click Software
  • MS Excel, Google Docs, Many Eyes, Tableau, SPSS, BlueskyStatistics, SAS

Programming

  • processing, processing.js, processing.py
  • python, matplotlib
  • R, trellis, ggplot2
  • SAS

Introduction

Illustration

  • Adobe Illustrator
  • Inkscape

Mapping

  • Google maps, Google earth, Google docs
  • yahoo maps and Microsoft maps
  • ARCGIS
  • Modest Maps, Ploymaps
  • tableau, R

Goal

To have an excellent example of a bubble plot, wordcloud, and a map posted online.

Try a software package to modify a graph using that software.

Graduate students make an animation using shiny.

Point-and-Click

We start by looking at various point-and-click packages.

MS Excel

Check out MS Excel 2016.

Very nice updates to the Chart Wizard.

Can make maps.

Google Docs and Sheets

Lots of great graphs you can make.

Can make maps.

Can make Bubble plots.

Automatically suggests plots.

Minitab and Minitab Express

Lots of standard graphs.

Can make a bubble plot.

IBM Many Eyes

Was a nice collaborative website. Could make a wordcloud.

Sorry Many Eyes has been closed.

Tableau and Tableau Public

What do you think about tableau?

VisualizeFree

Check out there website.

Interesting blog post

IBM SPSS

Very nice chart builder.

SPSS Visualization Designer

WatsonAnalytics

Aside: Check out the Automatic Statistician

SAS

Programming

Next we will discuss programming Tools.

Python

Python is a very flexible programming language that can be used to interact with data on the internet easily.

Check out

Processing

This is a programming language used for creating animated and interactive graphics.

Protovis

A graphical approach to visualization. Protovis development has ended. The developers are now working on D3.js.

The misoproject looks to be a next step.

R

R is an excellent programming environment for developing visualizations. The basic graphics are very configurable. There are many libraries that add additional graphics.

RStudio and shiny

  • RStuido has added a lot to making R more useful.

  • shiny is an add-on to R, produced by the developers of RStuido, that is useful for making visual animations with data.

Alternatively, check out

Mapping

Traditional mapping software now on the cloud.

Check out

Data

There is an R library Quandl Quandl R App

Get an account to access the data from within R.

Slide With R Code

# Example of labeling points
attach(mtcars)
plot(wt, mpg, main="Milage vs. Car Weight", 
    xlab="Weight", ylab="Mileage", pch=18, 
    col="blue")
text(wt, mpg, row.names(mtcars), cex=0.6, 
    pos=4, col="red")

plot of chunk unnamed-chunk-1

Combining Plots

# 4 figures arranged in 2 rows and 2 columns
attach(mtcars)
par(mfrow=c(2,2))
plot(wt,mpg, main="Scatterplot of wt vs. mpg")
plot(wt,disp, main="Scatterplot of wt 
     vs disp")
hist(wt, main="Histogram of wt")
boxplot(wt, main="Boxplot of wt")

plot of chunk unnamed-chunk-2

Try all of the code on this webpage from Quick R.

Lattice

graph_type description formula examples
barchart bar chart x ~ A or A ~ x
bwplot boxplot x ~ A or A ~ x
cloud 3D scatterplot z ~ x*y | A
contourplot 3D contour plot z ~ x*y
densityplot kernel density plot ~x | A*B
dotplot dotplot ~ x
histogram histogram ~ x

Lattice

graph_type description formula examples
levelplot 3D level plot z ~ y*x
parallel parallel coordinates plot data frame
splom scatterplot matrix data frame
stripplot strip plots A ~ x or x ~ A
xyplot scatterplot y ~ x | A
wireframe 3D wireframe graph z ~ y*x