benmarwick

# Adapted from https://stackoverflow.com/a/7267364/1036500 by Andrie de Vries

# This is it: theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))

library(ggplot2)

td <- expand.grid(
  hjust=c(0, 0.5, 1),
  vjust=c(0, 0.5, 1),
  angle=c(0, 45, 90),

benmarwick

library(usdanutrients)
library(tidyverse)

foods_simple <- 
	food %>% 
	separate(food, into = str_glue('V{1:11}'), sep = ",") %>% 
	distinct(V1) %>% 
	mutate(V1 = tolower(V1))  %>% 
	mutate(V1 = str_replace_all(V1, "[[:punct:]]", "")) %>% 
	rename(food = V1)

benmarwick

csv <-c('"Sample","Lab_Code","Age","One_sd"
"GM-C14-14","OxA-34804",12665,55
"GM-C14-16","OxA-34805",9240,40
"GM-C14-26","OxA-34806",2829,28')

c14_data <- read.csv(text = csv, header = TRUE)
names(c14_data)

# read in the filie

benmarwick

library(googlesheets)
library(readxl)
library(httr)

#-------------------------------------------------------------
# mapping police violence, https://mappingpoliceviolence.org/

# get google sheet info
mapping_police_violence <- gs_url("https://docs.google.com/spreadsheets/d/1dKmaV_JiWcG8XBoRgP8b4e9Eopkpgt7FL7nyspvzAsE/edit#gid=0")

benmarwick

library(chunked)
library(tidyverse)

# I want to look at the daily page views of Wikipedia articles
# before 2015... I can get zipped log files
# from here: https://dumps.wikimedia.org/other/pagecounts-ez/merged/2012/2012-12/
# I get bz file, unzip to get this: 

my_file <- 'pagecounts-2012-12-14/pagecounts-2012-12-14'

benmarwick

# function to do a dodged half-boxplot and jittered points next to each other
#
# data_in should be a data frame
# factor_col should be a bare column name (not a string)
#     although it will work if that column is factor or a character type
# numeric_col is the y axis continuous variable
# offset is the width of the boxplots and jittered point cloud
#
# the basic approach is to draw a boxplot without the tails
#   (e.g. only the interquartile range) and then use segments to add the

benmarwick

## GOAL:
## re-create a figure similar to Fig. 2 in Wilson et al. (2018), 
## Nature 554: 183-188. Available from:
## https://www.nature.com/articles/nature25479#s1
##
## combines a boxplot (or violin) with the raw data, by splitting each
## category location in two (box on left, raw data on right)


## call required packages

benmarwick

# we have downloaded the files from NASA Land Processes Distributed Active
# Archive Center (LP DAAC) at https://earthexplorer.usgs.gov/
# and unzipped the downloaded file
# which contains many zip files...

# read in the Zipped files
setwd("C:/Users/bmarwick/Downloads/030432578418876/DEM-ASTER-Korea")
library(fs)
zip_files <- dir_ls(regexp = "[.]zip$")

benmarwick

# data from http://reportcard.ospi.k12.wa.us/DataDownload.aspx
school_data <- readxl::read_excel("2_03_AIM-EOC-MSP-SBA Assessments School (with suppression - new format).xlsx")

# Level 4 is Advanced (exceeding state standard): http://www.k12.wa.us/assessment/StateTesting/FAQ.aspx

library(tidyverse)

# what does the data look like?
glimpse(school_data)

benmarwick

#------
# for tutorials see:
# - https://bigdataenthusiast.wordpress.com/tag/microsoft-cognitive-services-using-r/
# - https://westus.dev.cognitive.microsoft.com/docs/services/563879b61984550e40cbbe8d/operations/563879b61984550f30395236

# try facial analysis for sex and gender

# scrape each page for each year
img_srcs <-
map(odmp_urls,