jmclawson

library(foreign)
mytest.alldata <- list()
mytest.csvfile <- c()
mytest.dtafile <- c()
mytest.filelist <- list.files(path="data",pattern="*sav",recursive=FALSE,full.names=T)
for (number in 1:length(mytest.filelist)) {
  mytest.alldata[[number]] <- read.spss(mytest.filelist[number],to.data.frame = TRUE)
  mytest.csvfile[number] <- gsub("data/|.sav","",mytest.filelist[number])
  mytest.csvfile[number] <- paste(mytest.csvfile[number],".csv",sep="")
  mytest.dtafile[number] <- gsub("csv","dta",mytest.csvfile[number])

jmclawson

library(NLP) 
library(openNLP)

# credit due to http://stackoverflow.com/questions/30995232/how-to-use-opennlp-to-get-pos-tags-in-r
## SET "data.dir" to a directory containing text files. It's not designed for nested directories.
data.dir <- "data/texts/"

## SET "saveas.file" to the destination directory. Resulting files have an "n" prepended to the file name, but it may be useful to save to a separate directory.
saveas.file <- "data/texts-n/"

jmclawson

library(tidyverse)
library(tidytext)
library(reshape2)
library(wordVectors)

##### Modeling a Corpus #####

# This process for preparing and modeling the corpus is adapted from Women Writers Project's template_word2vec.Rmd
# These adaptations should allow for for preservation of modeling settings to aid in replicability.
# After training the model, recall its setting parameters by exploring the object's attributes.

jmclawson

base_beg <- "https://en.wikipedia.org/wiki/Category:"
base_end <- "th-century_novels"

get_cat_pages <- function(){
 categories <<- data.frame(century=c(),
                         nation=c(),
                         url=c(),
                         stringsAsFactors = FALSE)
 for (century in centuries){
  cat_url <- paste0(base_beg,century,base_end)

jmclawson

library(stylo)
library(ggplot2)
library(dendextend)

# Load with this line: devtools::source_gist("79cd732fb9e6a4f1dd14f1caaac4ee2d")
# Use df <- stylo() to save frequency results
# Then use stylo2gg(df) to visualize principal components
# Use stylo2gg(df, viz="hc") to show hierarchical clusters without rerunning stylo

stylo2gg <- function(df,

jmclawson

Black theme for ggplot2

This is an additional theme for ggplot2 that generates an inverse black and white color scheme.

Example

ggplot(mtcars, aes(wt, mpg)) + geom_point()
# Add theme_black()
ggplot(mtcars, aes(wt, mpg)) + geom_point(color = "white") + theme_black()

jmclawson

remotes::install_github("kjhealy/covdata")
library(covdata)
library(dplyr)
library(ggplot2)
library(ggrepel)
library(tidyr)

covus_wide <- covus %>% 
  select(date, state, measure, count) %>% 
  pivot_wider(id_cols = c(date, state), 

jmclawson

\newrobustcmd*{\mkcomprangezero}{%
  \begingroup
  \@ifstar
    {\blx@range@aux\blx@comprange@ii}
    {\blx@range@aux\blx@comprange@i}}
\def\blx@comprange@i[#1][#2]#3{%
  \let\blx@tempa\@empty
  \protected\def\blx@range@out@value{\appto\blx@tempa}%
  \def\blx@range@out@item@process{#2}%
  \let\blx@range@out@delim\blx@range@out@value

jmclawson

# To prepare it for use in documentation, import a .bib file, strip Bibdesk's extra fields and additions, and enclose each entry with code compatible with Latex's {listings} package.

library(dplyr)
library(stringr)
library(readr)

# 0. Set relative file path for the bibfile
# setwd()

# 1. read the bib file as a vector of lines

jmclawson

\usepackage{listings}
\usepackage{xcolor}

\let\oldaddbibresource\addbibresource
\renewcommand{\addbibresource}[1]{%
  \oldaddbibresource{#1}%
  \expandafter\newcommand\csname thebibfile\endcsname{#1}%
}

% \makeatletter