dsparks

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

ANES <- read.csv("https://raw.github.com/dsparks/Test_image/master/2008%20ANES%20Thermometers.csv")
head(ANES)

# Multidimensional scaling of a rectangular thermometer rating matrix
thermometerFrame <- ANES[, -c(1:2)]

dsparks

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

# Example usage
x <- c(4,6,4,5,6,7)
y <- 1:6
plot(x, y, "o", pch=20)  # bezier() generates smoothed curves from these points
points(bezier(x, y), type="l", col="red")

dsparks

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

ANES <- read.csv("http://www.oberlin.edu/faculty/cdesante/assets/downloads/ANES.csv")
ANES <- ANES[ANES$year == 2008, -c(1, 11, 17)]  # Limit to just 2008 respondents,
head(ANES)  # remove some non-helpful variables

with(ANES, plot(jitter(pid7), jitter(ideo7)))

dsparks

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

searchTerms <- c("New York", "Los Angeles", "Chicago", "Houston", "Philadelphia",
                 "Phoenix", "San Antonio", "San Diego", "Dallas", "San Jose",
                 "Jacksonville", "Indianapolis", "Austin", "San Francisco", 
                 "Columbus", "Fort Worth", "Charlotte", "Detroit", "El Paso",
                 "Memphis")

dsparks

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?)

dsparks

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

# Generate some sample data:
myData <- data.frame(x = rnorm(500), y = rnorm(500))
# With a unit-circle hole in the center:
myData <- myData[sqrt(rowSums(myData^2)) > 1, ]
plot(myData)

dsparks

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

# Load most recent senate roll call data:
rollCall <- readKH("http://amypond.sscnet.ucla.edu/rollcall/static/S112.ord")

# Run wnominate on the roll call object
nDims <- 3

dsparks

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

ftseIndex <- EuStockMarkets[, 4]
plot(ftseIndex, col = "GRAY")

# Calculate 10-day rolling mean, quickly:
smoothIndex <- rollmean(x = ftseIndex,  # original series

dsparks

doInstall <- TRUE
toInstall <- c("XML")
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?)

dsparks

require("proxy")
library(proxy)


# kmeans++ center initialization algorithm
kMeansPP <- function(df, k, doPlot = TRUE){
  kCenters <- data.frame(matrix(NA, ncol = ncol(df), nrow = k))
  whichPoints <- rep(NA, k)
  whichPoints[1] <- sample(1:nrow(df), 1)
  kCenters[1, ] <- df[whichPoints[1], ]  # Initial center