benmarwick

# ipak function: install and load multiple R packages.
# check to see if packages are installed. Install them if they are not, then load them into the R session.

ipak <- function(pkg){
    new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
    if (length(new.pkg)) 
        install.packages(new.pkg, dependencies = TRUE)
    sapply(pkg, require, character.only = TRUE)
}

benmarwick

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

benmarwick

## Correlation matrix with p-values. See http://goo.gl/nahmV for documentation of this function
cor.prob <- function (X, dfr = nrow(X) - 2) {
  R <- cor(X, use="pairwise.complete.obs")
  above <- row(R) < col(R)
  r2 <- R[above]^2
  Fstat <- r2 * dfr/(1 - r2)
  R[above] <- 1 - pf(Fstat, 1, dfr)
  R[row(R) == col(R)] <- NA
  R
}

benmarwick

# Load Data
grainData <- read.csv('grainSize.csv', check.names=F, na.strings='--' )

# Calculate Derived Sample Values
grainData[['Phi Diameter']] <- -log2( grainData[['Grain Diameter']] )
totalWeight <- sum( grainData[['Sample Weight']] )
grainData[["Percent Retained"]] <- grainData[['Sample Weight']] / totalWeight
grainData[["Cumulative Percent"]] <- cumsum( grainData[["Percent Retained"]] )
grainData[['Percent Finer']] <- 1 - grainData[['Cumulative Percent']]

benmarwick

require(stringr)
require(RCurl)
require(ggplot2)
gsqAPI = function(key,query,gid=0){ return( read.csv( paste( sep="",'http://spreadsheets.google.com/tq?', 'tqx=out:csv','&tq=', curlEscape(query), '&key=', key, '&gid=', gid) ) ) }

trim <- function (x) sub('@','',x)

twCounts=function(df){
	print("Counting @'d users")
    to.count=data.frame(table(df$to))

benmarwick

# @author: Michael J Bommarito II
# @date: Feb 20, 2011
# @email: michael.bommarito@gmail.com
# @packages: gridExtra, ggplot2

library(gridExtra)
library(ggplot2)

setwd('/data/workspace/blog/cn220/')

benmarwick

ks.default <- function(rows) seq(2, max(3, rows %/% 4))

many_kmeans <- function(x, ks = ks.default(nrow(x)), ...) {
  ldply(seq_along(ks), function(i) {
    cl <- kmeans(x, centers = ks[i], ...)
    data.frame(obs = seq_len(nrow(x)), i = i, k = ks[i], cluster = cl$cluster)
  })
}

all_hclust <- function(x, ks = ks.default(nrow(x)), point.dist = "euclidean", cluster.dist = "ward") {

benmarwick

ks.default <- function(rows) seq(2, max(3, rows %/% 4))

many_kmeans <- function(x, ks = ks.default(nrow(x)), ...) {
  ldply(seq_along(ks), function(i) {
    cl <- kmeans(x, centers = ks[i], ...)
    data.frame(obs = seq_len(nrow(x)), i = i, k = ks[i], cluster = cl$cluster)
  })
}

all_hclust <- function(x, ks = ks.default(nrow(x)), point.dist = "euclidean", cluster.dist = "ward") {

benmarwick

library(sqldf)

sqldf("SELECT
        day
        , avg(temp) as avg_temp
      FROM beaver2
      GROUP BY
        day;")

#   day avg_temp

benmarwick

read.tps = function(data) {
  # Reads the .tps file format produced by TPSDIG 
  # (http://life.bio.sunysb.edu/morph/ into a single data frame
  # USAGE: R> read.tps("filename.tps")
  a = readLines(data) # so we can do some searching and indexing
  LM = grep("LM", a) # find the line numbers for LM
  ID.ind = grep("ID", a) # find the line numbers for ID
  # and the ID values, SCALE values, and image names
  ID = gsub("(ID=)(.*)", "\\2", grep("ID", a, value=T)) 
  SCALE = gsub("(SCALE=)(.*)", "\\2", grep("SCALE", a, value=T))