nwstephens

# This code produces an error at startup

require(miniUI)
require(shiny)

ff <- function () 
{

  ui <- miniPage(
    gadgetTitleBar("Variable Profiler"), 

nwstephens

selectConn <- function() {
  ui <- miniPage(
    gadgetTitleBar("ODBC Connect"),
    miniContentPanel(
      selectInput('server', 'Server', c(
        'SQL Server',
        'Postgres'
      ), width='100%'),
      p(strong('Port')),
      verbatimTextOutput("selectedPort"),

nwstephens

# Turn on profvis in RStudio first and run this code second
# No preview panel appears and flamechart does not represent

library(profvis)

# Generate data
times <- 4e5
cols <- 150
data <- as.data.frame(x = matrix(rnorm(times * cols, mean = 5), ncol = cols))
data <- cbind(id = paste0("g", seq_len(times)), data)

nwstephens

############ RStudio Server Pro ##############

# Add group

sudo groupadd -g 800 guests
sudo groupadd -g 801 rstudio-superuser-admins
sudo groupadd -g 802 admins
sudo groupadd -g 803 rstudio
sudo groupadd -g 804 rstudio-admins

nwstephens

library(microbenchmark)

N <- 1000
X <- matrix(rnorm(N*10), nrow = N)
y <- rnorm(N)
write.csv(X, outfile <- tempfile())

microbenchmark(
  Compute = lm.fit(X, y),
  Write = write.csv(X, outfile),

nwstephens

require(readr)

### Generate large dataset on disk
numBlocks <- 10
blockSize <- 1000
x <- iris
ff <- tempfile()
for(i in 1:numBlocks){
  samp <- sample(1:nrow(x), blockSize, replace = T)
  write_csv(x[samp, ], ff, append = i > 1)

nwstephens

### Download Air On Time data ###

sudo rm -rd /tmp/flights
sudo mkdir /tmp/flights

for i in {1987..2008}
  do
    fnam=$i.csv.bz2
    sudo wget -O /tmp/flights/$fnam http://stat-computing.org/dataexpo/2009/$fnam
  done

nwstephens

### Compare SQLite to Spark
### June 5, 2016
### EC2 4 Core 16 Gb RAM

### Install ###

# Install
devtools::install_github("hadley/devtools")
devtools::install_github("hadley/dplyr")
devtools::install_github("rstudio/rspark", auth_token = "XXXXXXXXXX")

nwstephens

---
title: "Python and R with Feather"
output: html_notebook
---

```{r setup, include=FALSE}
library(feather)
library(ggplot2)
setwd('/home/nathan/sol-eng-sales/vignettes/notebooks/demos/5-feather')
```

nwstephens

# Test loading data into remote spark instance

library(rspark)

# Connect
sc3 <- spark_connect("spark://54.245.95.88:7077")
db3 <- src_spark(sc3)

# Load CSV
cat('Michael, 29\n', file='people.csv', append = FALSE)