andrie

# 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){

andrie

library(ggplot2)
dat <- read.csv("world records.csv", stringsAsFactors = FALSE)

# Clean and transform the data --------------------------------------------

track <- within(dat, {
  Time <- as.numeric(Time.in.hours)
  Date <- as.Date(Date, format = "%d-%b-%y")
  Speed <- Distance / Time
  logDistance <- log10(Distance)

andrie

# Install from github ----------------

# install.packages(c("chron", "ggplot2", "dplyr", "stringi"))
# devtools::install_github("trinker/wakefield")

# Create a sample data frame ---------
library(wakefield)
r_data_frame(
  n = 500,
  id, 

andrie

library(magrittr)
library(dplyr)
library(tidyr)
library(ggplot2)
set.seed(1)
dat <- r_data_frame(12,
                    name,
                    r_series(grade, 100, relate = "+1_6")
) 

andrie

library(parallel)
set.seed(1)
m <- 10000
n <- 2000
A <- matrix(runif (m*n),m,n)


setMKLthreads(1)
system.time(S <- svd (A,nu=0,nv=0))
# user  system elapsed 

andrie

library(doSNOW)
library(tcltk)

cl <- makeSOCKcluster(2)
registerDoSNOW(cl)

pb <- txtProgressBar(max=100, style=3)
progress <- function(n) setTxtProgressBar(pb, n)
opts <- list(progress=progress)
r <- foreach(i=1:100, .options.snow=opts) %dopar% {

andrie

### Connect to SQL Server using RODBC

library(RODBC)
library(magrittr)

# Connect to SQL Server using RODBC ------------------

sqlHost <- "DAA136209339.sys-sqlsvr.local"
sqlDatabase <- "RevoTestDB"
dsnString <- "driver={SQL Server};server=%s;database=%s;trusted_connection=true"

andrie

# Objective
#
# Fit a gamma distribution knowing that:
# - 20% fall below 15 days
# - 80% fall below 60 days
# Inspired by http://www.johndcook.com/blog/2010/01/31/parameters-from-percentiles/

x <- c(0.2, 0.8)
y <- c(15, 60)

andrie

library(repr)

# Change plot size to 4 x 3
options(repr.plot.width=4, repr.plot.height=3)
curve(sin(x), from = 0, to=2*pi, n = 100)

# Change plot size to 8 x 3
options(repr.plot.width=8, repr.plot.height=3)
curve(sin(x), from = 0, to=4*pi, n = 200)

andrie

# Generate data in the form of a sine wave
set.seed(1)
n <- 1e3
dat <- data.frame(
  x = 1:n,
  y = sin(seq(0, 5*pi, length.out = n)) + rnorm(n=n, mean = 0, sd=0.1)
)

approxData <- data.frame(