hrbrmstr

# Load the raw training data and replace missing values with NA
training.data.raw <- read.csv('train.csv',header=T,na.strings=c(""))

# Output the number of missing values for each column
sapply(training.data.raw,function(x) sum(is.na(x)))

# Quick check for how many different values for each feature
sapply(training.data.raw, function(x) length(unique(x)))

# A visual way to check for missing data

hrbrmstr

library(stringi)
library(microbenchmark)
library(ggplot2)
library(readr)

ex <- "example.txt"
mb <- microbenchmark(readLines=readLines(ex),
                     read_lines=read_lines(ex),
                     stri_read_lines=stri_read_lines(ex))

hrbrmstr

library('httr')
library('jsonlite')

get_measures <- function(deviceid) {

  .h <- list(
    "Origin" = "http://anasim.iet.unipi.it",
    "Accept-Encoding" = "gzip, deflate",
    "Accept-Language" = "it-IT,it;q=0.8,en-US;q=0.6,en;q=0.4",
    "User-Agent" = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.103 Safari/537.36",

hrbrmstr

Livecoding D3 in RStudio

This is a proof-of-concept on how one can use RStudio to livecode D3 visualizations.

Usage

You will need to install a couple of packages before getting started

devtools::install_github("yihui/servr")

hrbrmstr

library(SmarterPoland)
library(riverplot)
library(RColorBrewer)
library(graphics)
library(reshape2)
library(plyr)
library(stringr)
library(countrycode)

# DOWNLOAD THE DATA

hrbrmstr

# see github repos & package documentation
# - http://github.com/apache/spark/tree/master/R
# - http://spark.apache.org/docs/latest/api/R/

# install the SparkR package
devtools::install_github("apache/spark", ref="master", subdir="R/pkg")

# load the SparkR & ggplot2 packages
library('SparkR')
library('ggplot2')

hrbrmstr

hrbrmstr

hrbrmstr

Data sources:
CDC data on vaccine coverage: http://www.cdc.gov/flu/professionals/vaccination/reporti1112/reporti/index.htm
CDC data on current influenza situation:  http://gis.cdc.gov/grasp/fluview/fluportaldashboard.html 
Historical flu data: http://www.cdc.gov/flu/weekly/pastreports.htm
Locations of hospitals in Boston: https://data.cityofboston.gov/Public-Health/Hospital-Locations/46f7-2snz
NetLogo, a simple agent based model: http://ccl.northwestern.edu/netlogo/ 
Nemsis, emergency medical services API (haven't used this one myself): http://www.nemsis.org/v3/downloads/v3Archive.html 
Written for R, but useful for epi basics in any language: cran.r-project.org/doc/contrib/Epicalc_Book.pdf
"Provides access to health statistics and information on hospital inpatient and emergency department utilization": http://hcupnet.ahrq.gov/
Healthcare Research and Quality data directory: http://www.ahrq.gov/data/dataresources.htm

hrbrmstr

doInstall <- TRUE
toInstall <- c("XML", "maps", "ggplot2", "sp")
if(doInstall){install.packages(toInstall, repos = "http://cran.us.r-project.org")}
lapply(toInstall, library, character.only = TRUE)

myURL <- "http://en.wikipedia.org/wiki/United_States_presidential_election,_2012"

allTables <- readHTMLTable(myURL)
str(allTables)  # Look at the allTables object to find the specific table we want
stateTable <- allTables[[14]]  # We want the 14th table in the list (maybe 13th?)