HarlanH

library(plyr)
library(rMaps)

venues <- structure(list(name = c("pivotal", "aol", "columbia"), lat = c(40.7403372, 
                    40.7308948, 40.8074358), lon = c(-73.9951462, -73.9917096, -73.9625858 )), 
                    .Names = c("name", "lat", "lon"), row.names = c(NA, -3L), class = "data.frame")

times_square <- c(40.7577, -73.9857)

map <- Leaflet$new()

HarlanH

using VennEuler

# 1		364	23.30%	SAS only
# 10	350	22.41%	Python only
# 11	70	4.48%	Python and SAS
# 100	490	31.37%	R only
# 101	68	4.35%	R and SAS
# 110	200	12.80%	R and Python
# 111	20	1.28%	R, Python and SAS

HarlanH

df.by.rows <- function(df, fn, agg.type=numeric, .progress=NULL) 
{
  # A simplified and more-efficient version of aaply for data frames. Iterates over rows of the df, applies the
  # fn to each single-row slice, and aggregates the **scalar** results.
  #
  # Args:
  #    df - data frame to split
  #    fn - function to apply to each row
  #    agg.type - a constructor, one of numeric, character
  #    .progress - set to "text" to get a progress bar

HarlanH

# NOTE: requires ImageMagick to be installed and in the PATH! Should work on most Linux and Mac systems.

library(ggplot2)

d <- data.frame(x=rep(1:10,10), y=rnorm(100, 1:10))

files <- character()

for (i in 1:10)
{

HarlanH

# demonstration of monotonic smoothing with 2-D integral IVs
# Harlan Harris
# harlan@harris.name

library(ggplot2)
library(locfit)
library(monoProc)

df <-
structure(list(counts = c(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 

HarlanH

If you see the bug, keep your damn mouth shut!

Example #1
Show data.
I've written pointless code. 
traceback() shows where the problem lies, but not when or why
Explain "call stack" made of "frames", noting that many things that don't 
syntactically look like function calls in R actually are.
Error doesn't seem to happen all the time, so adding browser() calls 
might not be very helpful.

HarlanH

# solution via Hadley Wickham and others at: 
# http://www.mail-archive.com/r-help@stat.math.ethz.ch/msg85203.html

qq <- list(data.frame(c1=c('a', 'b', 'c')), data.frame(c1=c('a','d','e')), data.frame(c1=c('a','f','g')))

fold <- function(x, fun) {
        if (length(x) == 1) return(fun(x))
        
        accumulator <- fun(x[[1]], x[[2]])
        if (length(x) == 2) return(accumulator)

HarlanH

# Demo of techniques to visualize the predictions made by a categorization model.

library(ROCR)
library(ggplot2)

load(url('http://dl.dropbox.com/u/7644953/classifier-visualization.Rdata'))

pred.df$actual.bin <- ifelse(pred.df$actual == 'yes', 1, 0)
pred.df <- pred.df[order(pred.df$predicted, decreasing=TRUE), ]

HarlanH

# Data Science DC Titles Visualization

# Here's how this will work. In a main loop, a parameterized visualization function
# is called every N seconds. Each function gets the source spreadsheet fresh, and 
# generates a visual.

# aspects of this code borrowed from Drew Conway:
# https://raw.github.com/drewconway/ZIA/master/R/better_word_cloud/better_word_cloud.R

library(plyr)

HarlanH

library(XML)
library(RCurl)

# USAGE: ldply(c('9780387962406', '9780387961406', '0387981403'), function(x) ISBNdb(x, 'apikey'))

ISBNdb <- function(isbn, access_key, 
                   isbn.api='http://isbndb.com/api/books.xml?access_key=%s&index1=isbn&value1=%s') {
  isbn <- as.character(isbn)