revodavid

pbirthdaysim <- function(n, nsims=100000, feb29=TRUE) {
 ## Using nsims simulations, estimate the probability
 ## that a room of n people includes a shared birthday
 
 bdays <- 1:366 
 ## Feb 29 represented as day 366
 ## We'll sample other days 4 times as often
 ## compared to day 366
 probs <- c(rep(4,365),1)
 

revodavid

library(doAzureParallel)

# generate a credentials json file "cluster", then...

registerDoAzureParallel(cluster)

# Run 5 million option pricing simulations 
closingPrices <- foreach(i = 1:50, .combine='c') %dopar% {
  replicate(100000, getClosingPrice())
}

revodavid

findMyId <- function() {
  # Requires https://github.com/ROpenSciLabs/miner
  # dig a hole one block deep and stand in it to be found
  # returns the IDs of players standing in a hole
  ids <- getPlayerIds()
  holehiders <- NULL
  for (id in ids) {
    pos <- getPlayerPos(id, tile=TRUE)
    surround <- getBlocks(pos[1]-1,pos[2],pos[3]-1, pos[1]+1, pos[2], pos[3]+1)[,1,]
    inhole <- all(c(surround[1,2],surround[2,1],surround[2,3], surround[3,2])!=0)

revodavid

# Scrapes CRAN archives to determine the number of packages per release

# Create a list of pages to scrape, including both archive and current
extract_url <- function() {
    url <- list(
    archive = "https://cran-archive.r-project.org/bin/windows/contrib/",
    active = "https://cran.r-project.org/bin/windows/contrib/"
  )

    get_urls <- function(url) {

revodavid

## Credit: http://www.computerworld.com/article/2893271/business-intelligence/5-data-visualizations-in-5-minutes-each-in-5-lines-or-less-of-r.html
library(checkpoint)
checkpoint("2016-08-22")

## Correlation plot
file <- "https://github.com/smach/NICAR15data/raw/master/testscores.csv"
testdata <- read.csv(file, stringsAsFactors = FALSE)
library(ggvis)
ggvis(testdata, ~ pctpoor, ~ score) %>%
  layer_points(size := input_slider(10, 310, label = "Point size"), opacity := input_slider(0, 1, label = "Point opacity")) %>%

revodavid

## Plot Atlanta area unemployment
## Credit: http://www.computerworld.com/article/2893271/business-intelligence/5-data-visualizations-in-5-minutes-each-in-5-lines-or-less-of-r.html
library(checkpoint)
checkpoint("2016-08-22")

library(quantmod)
getSymbols("ATLA013URN", src = "FRED")
names(ATLA013URN) = "rate"
library(dygraphs)
dygraph(ATLA013URN, main = "Atlanta area unemployment")

revodavid

## Plot last 6 months of ANTM share price
## Credit: http://www.computerworld.com/article/2893271/business-intelligence/5-data-visualizations-in-5-minutes-each-in-5-lines-or-less-of-r.html
library(checkpoint)
checkpoint("2016-08-22")

library(quantmod)
getSymbols("ANTM", auto.assign=TRUE)
barChart(ANTM, subset = 'last 6 months')

revodavid

## Plot all Starbucks locations using OpenStreetMap
## Credit: http://www.computerworld.com/article/2893271/business-intelligence/5-data-visualizations-in-5-minutes-each-in-5-lines-or-less-of-r.html
library(checkpoint)
checkpoint("2016-08-22")

file <- "https://opendata.socrata.com/api/views/ddym-zvjk/rows.csv"
starbucks <- read.csv(file)
library(leaflet); library(magrittr)
leaflet() %>% addTiles() %>% setView(-84.3847, 33.7613, zoom = 16) %>% 
  addMarkers(data = starbucks, lat = ~ Latitude, lng = ~ Longitude, popup = starbucks$Name)

revodavid

set.seed(1)
N <- 2000
P <- 0.01
rare_success <- sample(c(TRUE, FALSE), N, replace=TRUE, prob=c(P, 1-P))
guess_not <- rep(0, N)
plot(roc(rare_success, guess_not), print.auc=TRUE)
## 
## Call:
## roc.default(response = rare_success, predictor = guess_not)
## 

revodavid

library(pROC)
plot(roc(test_set$bad_widget, glm_response_scores, direction="<"),
     col="yellow", lwd=3, main="The turtle finds its way")
## 
## Call:
## roc.default(response = test_set$bad_widget, predictor = glm_response_scores,     direction = "<")
## 
## Data: glm_response_scores in 59 controls (test_set$bad_widget FALSE) < 66 cases (test_set$bad_widget TRUE).
## Area under the curve: 0.9037
glm_simple_roc <- simple_roc(test_set$bad_widget=="TRUE", glm_link_scores)