Monthly Archives: October 2013

A fresh look at Prelims’ degree distribution…is it really scale free?

As Statistical Methods pointed out in their comment on my post, the methodology I used when I proposed that the Prelims graph’s degree distribution was scale free is outdated and not conclusive. This afternoon I decided to take a fresh look at the data following the methodology of Clausset et. al using the Python Powerlaw library. After fitting the data and plotting the probability density function, I evaluated the goodness of fit of the power law distribution through comparisons to the fit of other distributions. The results indicated that a power law distribution may not be the best fit (although a better than an exponential distribution), and a better fit might be a stretched exponential distribution (p > .05). In the following figure you can see the actual data (blue line), a power law fit (red dotted line), a log normal fit (green dotted line), and a stretched exponential fit (blue dotted line). More about this in a couple of weeks.

loglikelihood

Leave a Comment

Filed under Uncategorized

sonnet 0.1.6

Over the last year, I have been focused on studying networks at the CulturePlex, and it has been a heck of a learning process. After reading over my older posts, I’ve begun to realize that it is time to start updating my methods as I learn more about programming and statistics. My next blog post (June 22) will describe the renovated and re-focused Preliminaries Project as it will be presented in San Juan, Puerto Rico.

As I mentioned in my last post, I have been working on a small Python library to simplify visualization for use with the up and coming Preliminaries interactive website. Surprisingly, after I published it on PyPi two weeks ago, quite a few people installed it. To my horror, version 0.1.0 had a bug, if it got you I apologize. Tonight I will be releasing version 0.1.6, in which I have added very basic support for Matplotlib. Of course there is a lot to do, and hopefully as the year goes on my releases and testing and docs will get better and better. For now it’s pretty minimal. Check out a full usage example here:

sonnet example ipython notebook

source is here

Leave a Comment

Filed under Uncategorized

Prelims Round 2

It’s a new school year and the Preliminaries Project is alive and well. After a having a great time and meeting some cool folks at DH2013, it’s time to move forward and think about plans for the future.

Later this month at the Sixteenth Century Society and Conference in San Juan, we will be presenting a new look at the Prelims data set called Networks of Culture: A Graph-Driven Approach to Understanding Publishing in the Spanish Golden Age. This will be a more expansive look at publication in the Spanish Empire from 1598-1643,

Also, we are in the process of building the official website for the Preliminaries Project. It will be based on Skeleton, a Django project template system we are currently developing at the CulturePlex Lab. The site will describe the Prelims with information about the methodology and lines of research associated with the project. It will also include an interactive feature that allows the user to interact with the Prelims data set using the JavaScript D3 library. The interactive feature will be based on the Sonnet Python library, a NetworkX based library that produces detailed node data and statistics in JSON format. Since about ten minutes ago, Sonnet is available through PyPi

Later this week I will publish several examples using Sonnet to produce custom D3 graphs. Until then…Python Rules!

Leave a Comment

Filed under Uncategorized