benmarwick

# starting with code from 
# https://gist.github.com/tomhopper/faa24797bb44addeba79?fbclid=IwAR3FFiHpUhTESqi_ylASZP5-zYD0lOrQyyHM2MSEvnVRCIykmjNREGTv4Uk

library(ggplot2)
library(grid)
library(dplyr)

#' Create some data to plot
n <- 100
df <- data.frame(DateTime =  seq(10, 20, length.out = 100),

benmarwick

library(tidyverse)
library(gh)

.token = ""  # get one from https://github.com/settings/tokens

# get all pkgs on GitHub mirror of CRAN
n <-  5000 # 16125 # https://github.com/cran
cran_repos <- gh("/users/:username/repos",
                 username = "cran",

benmarwick

#------------------------------------------------------
# Exploring the PCA published by Prentiss (1998) to understand the 
# usefulness of the Sullivan and Rozen debitage typology


# read in & tidy the data -----------------------------------------------
library(tidyverse)
# got these data from table 7 (p. 644) of https://www.jstor.org/stable/2694112
# OCR'd using https://tabula.technology/
prentiss <- readr::read_csv("tabula-Prentiss 1988.csv")

benmarwick

library("shiny")
library("EBImage") # >= 4.19.3
library(imager)

ui <- fluidPage(# Application title
  titlePanel("Image outline, chords, and landmarks"),
  

benmarwick

# https://arxiv.org/pdf/1809.09328.pdf & https://twitter.com/CT_Bergstrom/status/1035327464644333568
# they use Mathematica, boo! So let's make them with R

# starting with https://stackoverflow.com/q/33396168/1036500

library(ggplot2)


p <- ggplot() + 
  geom_point(data = anscombe,

benmarwick

# Summarising multiple metric attributes of artefacts

p1 <- read_excel("data/riumailuoi.xlsx", sheet = 'phase1')

summary_stats_table <- function(x) {
  x %>% 
    select(Mass, 
           Length,  
           Width,     
           Thickness,     

benmarwick

# list of lists
url <- "https://en.wikipedia.org/wiki/Lists_of_World_Heritage_Sites"

# Table of sites per country can be found at each of these pages
# probably the simplest entry point

# Africa
africa <- "https://en.wikipedia.org/wiki/List_of_World_Heritage_Sites_in_Africa"

# Americas

benmarwick

---
title: 'C14 analysis: Coastal vs Inland'
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

Import and clean the data:

benmarwick

library(tidyverse)
the_pages <- c(
  "https://en.wikipedia.org/wiki/Angela_McGowan",
  "https://en.wikipedia.org/wiki/Caroline_Bird_(archaeologist)",
  "https://en.wikipedia.org/wiki/Jo_McDonald",
  "https://en.wikipedia.org/wiki/Laurajane_Smith",
  "https://en.wikipedia.org/wiki/Louise_Zarmati",
  "https://en.wikipedia.org/wiki/Marcia-Anne_Dobres",
  "https://en.wikipedia.org/wiki/Sarah_Colley",

benmarwick

library(tidyverse)

base_url <- "http://academicjobs.wikia.com/wiki/Archaeology_Jobs_"

# starts at 2010-2011

years <- map_chr(2010:2019, ~str_glue('{.x}-{.x +1}'))
# though it seems to start at 2007-8: https://academicjobs.fandom.com/wiki/Archaeology_07-08

urls_for_each_year <- str_glue('{base_url}{years}')