jmclawson

load_data <- function(){
  if (!file.exists("data/scorecard.rds")) {
    "https://ed-public-download.app.cloud.gov/downloads/College_Scorecard_Raw_Data_06102024.zip" |>
      download_once() |>
      utils::unzip(files = c("Most-Recent-Cohorts-Institution.csv", "CollegeScorecardDataDictionary.xlsx"), 
                   exdir = "data")
    
    scorecard <- readr::read_csv("data/Most-Recent-Cohorts-Institution.csv")
    
    dictionary <- "data/CollegeScorecardDataDictionary.xlsx" |> 

jmclawson

--- 
title: "Development Indicators by Continent"
author: "Gapminder Analytics Group"
format: dashboard
--- 

# Charts

```{r}
#| label: setup

jmclawson

---
title: "Understanding and using linear models in R"
subtitle: "A 10-slide guide to the dark side"
format: 
  revealjs:
    slide-number: true
    embed-resources: true
    warning: false
    message: false
    theme: dark

jmclawson

# helper function get_if_needed for downloading online documents exactly once: https://gist.github.com/jmclawson/65899e2de6bfee692b08141a98422240
source("https://gist.githubusercontent.com/jmclawson/65899e2de6bfee692b08141a98422240/raw/7c5590377332e427691f2331b69abd58be2141ec/get_if_needed.R")

get_micusp_metadata <- function(micusp_dir = "micusp"){
  get_if_needed("https://elicorpora.info/browse?mode=download&start=1&sort=dept&direction=desc",
                filename = "micusp_metadata.csv",
                destdir = micusp_dir)
  
  readr::read_csv("micusp/micusp_metadata.csv", show_col_types = FALSE) |> 
    janitor::clean_names()

jmclawson

# This process is adapted from https://sesync-ci.github.io/blog/transform-Alaska-Hawaii.html
# Here, it's offered as a function to simplify trial-and-error.

move_state <- function(
    df, # spatial dataframe
    choice, # value in "state" column
    rotation, # eg -39 * pi/180
    right, # amount to move eastward; use negative for left/west
    up# amount to move northward; use negative for down/south
  ){

jmclawson

collapse_rows <- function(df_g, col, lookleft = TRUE){
  col_num <- grep(deparse(substitute(col)), colnames(df_g$`_data`))
  
  collapse_style <- css(visibility = "hidden",
                        border_top = "0px")
  
  test_rows <- function(x) ifelse(is.na(x == lag(x)), FALSE, x == lag(x))
  
  if(col_num > 1 & lookleft) {
    col_left <- as.name(colnames(df_g$`_data`)[col_num - 1])

jmclawson

---
title: "Special cases of data importing in R"
---

The typical methods of importing data make it straightforward to import a single CSV file. But data will often be prepared in some other format. Some common scenarios include a folder of smaller CSV files or data prepared for use with SAS.

## Importing many CSV files

It is common to read in multiple CSV files and combine their data frames. Beyond a certain number, the process should be automated.

jmclawson

---
title: "Mapping with R"
output: 
  html_document:
    df_print: paged
    toc: true
    toc_float: true
date: "2023-06-30"
---

jmclawson

---
title: "Importing SAS data into R"
---

## Get the data

```{r}
# Just download it once
if(!file.exists("medical.sas7bdat")) {
    download.file("http://www.principlesofeconometrics.com/sas/medical.sas7bdat", 

jmclawson

library(wordcloud)
library(topicmodels)
library(plotly)

# Moves a table of texts through the necessary
# steps of preparation before building a topic
# model. The function applies these steps:
#  1. identifies text divisions by the `doc_id`
#     column
#  2. divides each of the texts into same-sized