Created
March 27, 2014 02:18
-
-
Save smach/9798663 to your computer and use it in GitHub Desktop.
Sample R script for finding winners in a proportional election system
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Sample R script for finding winners in a proportional election system | |
# by Sharon Machlis | |
# This example assumes a spreadsheet with a list of candidates with column headers | |
# Municipality, Party, Place, Name, Variable | |
# and a spreadsheet with a list of results with column headers | |
# Municipality, Red, Blue, Green (Red, Blue, Green being sample political party names) | |
# See sample spreadsheet format at | |
# https://onedrive.live.com/redir?resid=7DDBA42BF10D288B!662&authkey=!AAFnW1H3wGiZgQU&ithint=file%2c.xlsx | |
# Read in data from spreadsheets: candidates list and election results | |
library("xlsx") | |
candidates <- read.xlsx("test.xlsx", sheetName = "candidates", stringsAsFactors=FALSE) | |
results <- read.xlsx("test.xlsx", sheetName = "results", stringsAsFactors=FALSE) | |
########## USING data.tables ############### | |
library(data.table) | |
# Create data tables dtcandidates and dtresults from the data frames we just made above | |
dtcandidates <- data.table(candidates) | |
dtresults <- data.table(results) | |
# setkey tells data.table which column variables we want to search or group by | |
setkey(dtcandidates, Municipality, Party, Place) | |
setkey(dtresults, Municipality) | |
# This function takes a municipality name and returns which candidates won seats | |
getwinners <- function(muni){ | |
numwinners <- dtresults[muni] # Gets the municipality's row from the results spreadsheet | |
numwinners$Municipality <- NULL # Deletes the Municipality column since we don't need that | |
# Find all the parties that had at least 1 winner | |
winningparties <- apply(numwinners, 2, function(x) x > 0) | |
parties <- subset(numwinners, select=winningparties) | |
# Get a vector of names of winning parties (just column names from parties) | |
partynames <- names(parties) | |
# Create an empty data frame to store info about each winning candidate | |
myresults <<- data.frame(Municipality=character(0), Party=character(0), Place=integer(0), Name=character(0), Variable=character(0)) | |
# This loop goes through each party that won seats and finds winning candidates for each party | |
for(p in partynames){ | |
# Extract number of seats won by the party: | |
themax <- as.numeric(subset(parties, select=p)) | |
# Find all the candidates from that party with a place less than or equal to number of winners | |
elected <- dtcandidates[J(muni, p, 1:themax)] | |
# Add those rows to the originally empty data frame we created above | |
myresults <<- rbind(myresults, elected) | |
} | |
return(myresults) | |
} | |
# Here, store all the municipalities you have results for in the dtresults data.table | |
cities <- dtresults$Municipality | |
# Run the getwinners function on each one of the cities | |
myresults_list <- lapply(cities, getwinners) | |
# Turn the list of results in myresults_list into a single data.table: | |
myresultsdt <- do.call(rbind, myresults_list) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment