2010 Cooperative research meeting of ISM, Japan
“Tutorials on statistical software R”
Dates: 25, 26 November 2010
(On 27 November, Japanese R user’s meeting will be held)
Place: Rooms D304 and D305
The Institute of Statistical Mathematics,
Tachikawa, Tokyo, Japan
Speakers:
Prof. Hadley Wickham (Rice University, USA)
Prof. Uwe Ligges (Technische Universitat Dortmund, Germany)
Program:
25 November (Thu) 10:30 - 17:00
10:30-12:00 Tutorial of ggplot2 (1) by Hadley Wickham
12:00-13:00 Lunch
13:00-14:00 Tutorial of ggplot2 (2) by Hadley Wickham
14:10-15:10 Prospects and Challenges for CRAN - with a glance on
64-bit Windows binaries by Uwe Ligges
15:10-15:30 Break
15:30-16:30 Tutorial of ggplot2 (3) by Hadley Wickham
16:30-17:00 Discussion
26 November (Fri) 10:30 - 17:00
10:30-12:00 My first R package (1) by Uwe Ligges
12:00-13:00 Lunch
13:00-14:00 My first R package (2) by Uwe Ligges
14:10-15:10 One future of interactive graphics in R by Hadley Wickham
15:10-15:30 Break
15:30-16:30 My first R package (3) by Uwe Ligges
16:30-17:00 Discussion
Note: Participants can use their laptop computers during tutorials.
Abstracts of talks:
“Tutorial of ggplot2” by Hadley Wickham
This tutorial is mainly based on my book: “ggplot2: Elegant Graphics for
Data Analysis” Springer, 2009.
(1) Introduction to ggplot2: How to create scatterplots, and how to add
extra variables with aesthetics (like colour, shape and size) or
facetting. Data: fuel economy of US cars.
(2) Graphics for large data: Histograms and bar charts for displaying
distributional summaries. Boxplots. Other techniques for overcoming
overplotting when drawing scatterplots of large datasets. Data:
prices and characteristics of 50,000 diamonds.
(3) Data manipulation and transformation: Group-wise summaries and
transformations to add extra information to your plots. How to
visualise time series. Data: trends in US baby names over the last
120 years.
“Prospects and Challenges for CRAN - with a glance on 64-bit
Windows binaries” by Uwe Ligges
R, a software package for statistical computing and graphics,
has evolved into the lingua franca of (computational) statistics. One of
the cornerstones of R's success is the decentralized and modularized way
of creating software using a multi-tiered development model. The R
Development Core Team provides the `base system', which delivers basic
statistical functionality, and many other developers contribute code in
the form of extensions in a standardized format via so-called packages.
In order to be accessible by a broader audience, packages are made
available via standardized source code repositories such as CRAN. To
support such a loosely coupled development model, repositories should be
able to verify that the provided packages meet certain formal quality
criteria and `work': both relative to the development of the base R
system as well as with other packages (interoperability). However,
established quality assurance systems and collaborative infrastructures
typically face several challenges, some of them discussed in this talk.
In addition, we will take a glance on 64-bit Windows binaries. 64-bit
Windows binaries for both R and packages are supported since R version
2.11.0 and as such available on CRAN and other package repositories.
“My first R package” by Uwe Ligges
After an introduction and general discussion regarding R packages, we
will focus on the installation and administration of packages in several
libraries. In order to develop a package, the tools for building, installing
and checking the package must be set up appropriately and the handling
of these tools will be discussed. The main part is the development of the
package: preparing functions and data, writing documentation, including C
code, looking at scoping issue and solving name clashes by introducing a
namespace, as well as the debugging. All these topics will be discussed.
"One future of interactive graphics in R" by Hadley Wickham
In this talk, I'll discuss the past, present and future of interactive
graphics, with a focus on our work developing the next generation
graphics canvas for R. Our initial experiments are very promising -
with the right C primitives, it's possible to write fast interactive
and dynamic graphics using pure R code.