Here are a few of the R packages I’ve been developing on my own.
SciencesPo: A Tool Set for Analyzing Political Behavior Data
The SciencesPo project is an effort of bringing to R some of the most common statistics used by applied social scientists in the field of political behavior. Although the project is far from complete, several algorithms are quite mature, and covering many topics, from descriptive analysis to seat apportionment methods and distributions.
SoundexBR: Phonetic-Coding for Portuguese
The aim of SoundexBR is to provide a method for decoding names into phonetic codes, as pronounced in Portuguese. Like the original English soundex algorithm, here the goal is for homophones to be encoded to the same representation so that they can be matched despite minor differences in spelling; therefore facilitating a process of (probabilistic/deterministic) record linkage without a common identifier. The GitHub repository hosts a file with some quick examples.
The Genderize project is a stab to implement some sort of Bayesian classifier to help decision on the gender of a name where this information is missing. There are three categories: masculinity, femininity and “intersex” with the probability based on a huge amount of first names data from different sources and countries. Therefore, the user can set language and country parameter to refine calculations.
FPTP2AV: Simulate Election Outcomes for AV Given FPTP Votes
As the name indicates, the aim of this package is to simulate election outcomes for the Alternative Voting System (AV) given FPTP votes. The package only resides in the GitHub platform. A related paper discussing the two systems and some results can be found here.