dsparks

rm(list = ls())
# from http://projecteuler.net/index.php?section=problems&id=42

Text <- readLines("http://projecteuler.net/project/words.txt")
TextString <- gsub("\"", "", unlist(strsplit(Text, "\",\"")))

TriangleNumbers <- cumsum(1:100)

StringLetters <- strsplit(TextString, "")
LetterRank <- rank(LETTERS)

dsparks

require(ggplot2)

Data <- data.frame(Group = sample(c(1, 2), 100, replace = T))
Data$Value <- rnorm(100, Data$Group * 2 - 6, 1)
Data$Group <- LETTERS[1:2][Data$Group]

Plot1 <- qplot(Value, data = Data, geom = "density", fill = Group, alpha = I(1/2))
Plot1 <- Plot1 + scale_fill_manual(values = c("#3E6995", "#953E3E"))
print(Plot1)

dsparks

require(cluster)

Polarizer <- function(group, data){

  if((mean(is.na(group)) > 0.99) | length(group) <= 1){
    Output <- c(NA, NA)
    } else {

  SameGroup <- try(as.matrix(daisy(data.frame(group))) == 0)
  diag(SameGroup) <- NA

dsparks

PaletteMaker <- function(pid = "GG"){
  pal <- colorRampPalette(c(gray(0), gray(1)))(5)
  if(pid == "GG") pal <- c("#69D2E7", "#A7DBD8", "#E0E4CC", "#F38630", "#FA6900")
  if(pid == "TP") pal <- rev(c("#ECD078", "#D95B43", "#C02942", "#542437", "#53777A"))
  if(pid == "cuek") pal <- c("#556270", "#4ECDC4", "#C7F464", "#FF6B6B", "#C44D58")
  if(pid == "OF") pal <- c("#00A0B0", "#6A4A3C", "#CC333F", "#EB6841", "#EDC951")
  if(pid == "SP") pal <- rev(c("#BCBDAC", "#CFBE27", "#F27435", "#F02475", "#3B2D38"))
  if(pid == "VM") pal <- c("#8C2318", "#5E8C6A", "#88A65E", "#BFB35A", "#F2C45A")
  if(pid == "MC") pal <- rev(c("#FAD089", "#FF9C5B", "#F5634A", "#ED303C", "#3B8183"))
  if(pid == "yab") pal <- c("#351330", "#424254", "#64908A", "#E8CAA4", "#CC2A41")

dsparks

# See: http://stats.stackexchange.com/questions/12148/looking-for-a-name-for-a-mean-influencing-statistic
# Somewhat personalized

sdfBeta <- function(numer, denom = 1){
  if(identical(1, denom)){denom <- rep(1, length(numer))}
  Bj <- sum(numer, na.rm = T) / sum(denom, na.rm = T)
  Bjni <- (sum(numer, na.rm = T) - numer) / (sum(denom, na.rm = T) - denom)
  StdError <- sd(Bjni, na.rm = T)
  Value <- (Bj - Bjni) / StdError
  names(Value) <- names(numer)

dsparks

# http://en.wikipedia.org/wiki/Logit#Definition

# Logit: From probability to normal
# Logistic (inverse logit): From normal to probability

Logit <- function(p){log(p / (1 - p))}
Logistic <- function(x){exp(x) / (1 + exp(x))}

dsparks

library(ggplot2)

x.centers <- c(-2, 1, 3)
x.ses <- c(1, 2, 1/2)
y.centers <- c(1/2, -2, 2)
y.ses <- c(1/4, 3/2, 1)

NN <- 5000#0
Sample1 <- cbind(rnorm(NN, x.centers[1], x.ses[1]), rnorm(NN, y.centers[1], y.ses[1]))
Sample2 <- cbind(rnorm(NN, x.centers[2], x.ses[2]), rnorm(NN, y.centers[2], y.ses[2]))

dsparks

Eddfinder <- function(v){
  v=floor(v)
  possibles=1:max(v)
  count=function(w){length(v[v>w])}
  which.max(lapply(possibles,count)<=possibles)
  }

Eddington <- function(value,name){
  temp=lapply(split(value,name),eddfinder)
  unlist(temp)

dsparks

doInstall <- TRUE  # Change to FALSE if you don't want packages installed.
toInstall <- c("foreign", "ggplot2", "reshape2", "plyr", "devtools")
if(doInstall){install.packages(toInstall, repos = "http://cran.r-project.org")}
lapply(toInstall, library, character.only = TRUE)

dsparks

library(ggplot2)
library(scales)

# Generate data
myData <- data.frame(x = rnorm(1000),
                     y = rnorm(1000))
myData$z <- with(myData, x * y)

# Make an untransformed plot
badVersion <- ggplot(myData,