Print

Print


*****  To join INSNA, visit http://www.insna.org  *****

<<<-------- aparna basu-------->>>

> I searched for the keyword 'Magnesium' on the Amazon site and found more
> than 50,000 titles, of which only 20 appear on the first page. I would
> like to draw a network from this data and would appreciate some help from
> anyone on this list who may have done this before.

To draw a network you have first to define it. Assume that the
50,000 titles are vertices, what are the links?

Some years ago I wrote a program in Python to get the network from
Amazon based on "Customers who bought" ...

http://vlado.fmf.uni-lj.si/vlado/podstat/AO/Amazon.zip
http://vlado.fmf.uni-lj.si/pub/networks/data/econ/amazon/amazon.htm

Since the program was interrupted several times I built in also
the 'restart from' option.
For small networks (some houndreds of vertices) I wrote, as an
'how to' illustration for students, a similar program in R.
The structure of Amazon's pages changed - some adaptations in both
programs are needed.

See also
http://mrvar.fdv.uni-lj.si/pub/mz/mz4.1/kejzar.pdf

Vlado
-- 
Vladimir Batagelj, University of Ljubljana, FMF, Department of Mathematics
  Jadranska 19, 1000 Ljubljana, Slovenia
http://vlado.fmf.uni-lj.si

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.