brendano

#!/usr/bin/env python2.6
""" 
Input is Excel-style CSV.  Either stdin or filename.
Output is honest-to-goodness tsv: no quoting or any \\n\\r\\t.
"""

from __future__ import print_function
import csv, sys

warning_count=0

liebke

;; significance testing with randomization

(use '(incanter core stats datasets charts))
(def data (to-matrix (get-dataset :plant-growth)))

;; Break the first column of the data into groups based on 
;; treatment type (second column) using the group-by function.
(def groups (group-by data 1 :cols 0))

(t-test (first groups) :y (second groups))

liebke

(use '(incanter core processing))

;; simple interactive Processing example taken from processingjs.org website:
;; http://processingjs.org/source/basic-example/processingjs_basic-example.html

;; set up variable references to use in the sketch object
(let [radius (ref 50.0)
      X (ref nil)
      Y (ref nil)

jlowin

library(ggplot2)

#extract reference data
mapcounties <- map_data("county")
mapstates <- map_data("state")

#merge data with ggplot county coordinates
mapcounties$county <- with(mapcounties , paste(region, subregion, sep = ","))
mergedata <- merge(mapcounties, unemp_data, by.x = "county", by.y = "counties")
mergedata <- mergedata[order(mergedata$order),]

hadley

How to write a reproducible example.

You are most likely to get good help with your R problem if you provide a reproducible example. A reproducible example allows someone else to recreate your problem by just copying and pasting R code.

There are four things you need to include to make your example reproducible: required packages, data, code, and a description of your R environment.

• Packages should be loaded at the top of the script, so it's easy to see which ones the example needs.

• The easiest way to include data in an email is to use dput() to generate

mxcl

This script has been moved.

hadley

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") {

hadley

data <- iris

d <- dist(scale(iris[, 1:4]))
h <- hclust(d, "ward")

data$ORDER <- order(h$order)
data$HEIGHT <- 0
data$LEVEL <- 0
data$POINTS <- 1

mblondel

# Mathieu Blondel, October 2010
# License: BSD 3 clause

import numpy as np
from numpy import linalg

def linear_kernel(x1, x2):
    return np.dot(x1, x2)

def polynomial_kernel(x, y, p=3):

drewconway

require(RCurl)
require(XML)

google.counts<-function(s){
    search.url<-paste("http://www.google.com/search?q=",gsub(" ","+",s),sep="")
    search.html<-getURL(search.url)
    parse.search<-htmlTreeParse(search.html,useInternalNodes = TRUE)
    search.nodes<-getNodeSet(parse.search,"//div[@id='resultStats']")
    search.value<-strsplit(xmlValue(search.nodes[[1]])," ",fixed=TRUE)[[1]][2]
    return(as.numeric(gsub(",","",search.value,fixed=TRUE)))