Skip to content

Instantly share code, notes, and snippets.

View druedin's full-sized avatar

druedin

6 followers · 0 following
View GitHub Profile
@druedin
druedin / gist:4141622
Created November 24, 2012 22:16
Wordscores and Wordfish Analysis
# #################################
# WORDSCORES AND WORDFISH ANALYSIS
# #################################
# setup
library(austin)
############################
# GETTING DOCUMENTS IN
############################
@druedin
druedin / gist:4141631
Created November 24, 2012 22:19
German Stopwords
die
und
der
in
zu
für
mit
ist
sich
den
@druedin
druedin / Let It Snow.R
Created December 15, 2012 20:23
Execute the code on http://www.statisticsblog.com/2012/12/let-it-snow/ directly
# Code by Matt Asher for statisticsblog.com
# Feel free to modify and redistribute
# How many flakes do you want to fall?
flakes = 100
# Width and height of your space
@druedin
druedin / Demo ajusCheck.R
Created December 15, 2012 21:28
Demonstrating ajusCheck
library(agrmt) # install from R-Forge
# Data:
V <- c(0,0,1,2,1.5,1.6)
# AJUS
ajus(V) # using default tolerance = 0.1
ajusPlot(V) # visual inspection
ajus(V, tolerance=0.2) # exploring
ajusCheck(V, t=seq(0.1,2,0.1)) # let's try them all
@druedin
druedin / missing.R
Last active December 11, 2015 08:39
Plot with missing values
miss <- !is.na(variable.name[country=="UK")
plot(which(miss), variable.name[country=="UK" & miss], col="red", type="b", lwd=2, axes=FALSE, xlim=c(1,16))
axis(2)
axis(1,at=c(1,6,11,16), labels=c("1995","2000","2005","2010"))
@druedin
druedin / as_pdf.R
Created February 3, 2013 11:48
Modified to run on Linux; original from Will Lowe http://conjugateprior.org/2013/01/no-more-ascii-art/
as_pdf <- function(x){
require(tools)
fname <- tempfile(pattern = "texview-", tmpdir = tempdir(),
fileext = ".tex")
header <- "\\documentclass{article}
\\usepackage[margin=10pt,font=small,labelformat=empty,
labelsep=none]{caption}
\\usepackage{dcolumn}
@druedin
druedin / ethnic-and-racial-studies.csl
Last active December 14, 2015 12:49
CSL for Ethnic and Racial Studies (ESR), second draft. Author instructions at: http://www.tandfonline.com/action/authorSubmission?journalCode=rers20&page=instructions
<?xml version="1.0" encoding="utf-8"?>
<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" page-range-format="chicago" demote-non-dropping-particle="sort-only">
<info>
<title>Ethnic and Racial Studies</title>
<id>http://www.zotero.org/styles/ethnic-and-racial-studies</id>
<link href="http://www.zotero.org/styles/ethnic-and-racial-studies" rel="self"/>
<link href="www.tandfonline.com/action/authorSubmission?journalCode=rers20&amp;page=instructions" rel="documentation"/>
<author>
<name>Didier Ruedin</name>
<email>didier.ruedin@wolfson.oxon.org</email>
@druedin
druedin / namav
Created June 15, 2013 20:34
Moving average handling NA
namav <- function(x,k=3){
x <- c(rep(NA, k),x,rep(NA,k)) # add NA on both sides
n <- length(x)
return(sapply((k+1):(n-k), function(i) sum(x[(i-k):(i+k)],na.rm=TRUE)/(2*k+1-sum(is.na(x[(i-k):(i+k)])))))
}
@druedin
druedin / gist:5842378
Last active December 18, 2015 20:48
Code for plot in http://druedin.com/2013/06/22/cronbachs-alpha-with-zero-inflated-data/
library(psych)
n <- 5000
x <- rnorm(n) # random values
r <- sapply(1:n, function(i) alpha(data.frame(x, c(x[1:i],rep.int(0,n-i))))$total$std.alpha)
plot(r, type="l", ylim=c(0,1), xlim=c(0,n), axes=FALSE, ylab="Alpha", xlab="Zero-Inflation (%)")
axis(2)
axis(1, at=seq(from=0,to=n,by=n/5), labels=seq(from=0,to=100,by=20))
@druedin
druedin / plzcanton.R
Last active November 20, 2020 21:19
Convert Swiss postcode (Postleitzahl, PLZ) to cantons. Essentially this is a database with information which postcodes are in which canton. For 16 postcodes, it is not possible to assign the canton unambiguously; I have assigned one of the cantons according to the largest municipality/hamlet involved -- usually ignoring hamlets. Source of underl…
plzcanton <- function(PLZ, format=1) {
# convert Swiss postcode to canton; v.0.4 (20 Nov 2020) didier.ruedin@unine.ch
# format 1 = numeric
# format 2 = string
# DATA: BFS canton numbers:
clabels <- c("ZH", "BE", "LU", "UR", "SZ", "OW", "NW", "GL", "ZG", "FR", "SO", "BS","BL", "SH", "AR", "AI", "SG", "GR", "AG", "TG", "TI", "VD", "VS", "NE", "GE", "JU")
# DATA: postcodes:
ZH <- c(8970, 8955, 8954, 8953, 8952, 8951, 8942, 8934, 8933, 8932, 8926, 8925, 8915, 8914, 8913, 8912, 8911, 8910, 8909, 8908, 8907, 8906, 8904, 8903, 8902, 8901, 8833, 8825, 8824, 8820, 8816, 8815, 8813, 8812, 8810, 8805, 8804, 8803, 8802, 8801, 8800, 8714, 8713, 8712, 8708, 8707, 8706, 8704, 8703, 8702, 8700, 8639, 8637, 8636, 8635, 8634, 8633, 8632, 8630, 8627, 8626, 8625, 8624, 8623, 8622, 8621, 8620, 8618, 8617, 8616, 8615, 8614, 8613, 8612, 8610, 8608, 8607, 8606, 8605, 8604, 8603, 8602, 8600, 8548, 8545, 8544, 8543, 8542, 8523, 8499, 8498, 8497, 8496, 8495, 8494, 8493, 8492, 8489, 8488, 8487, 8486, 8484, 8483, 8482, 8479