mdouze

import numpy as np
import faiss



def search_knn(xq, xb, k, distance_type=faiss.METRIC_L2): 
    """ wrapper around the faiss knn functions without index """
    nq, d = xq.shape
    nb, d2 = xb.shape
    assert d == d2

j-martens

# Run Simon Urbanek's benchmark v2.5

cat("R version\n")
cat("=========\n")
print(R.version)

if(exists("Revo.version")) {
  cat("Revo version")
  cat("============")
  print(Revo.version)

dannguyen

Iowa Liquor Sales dataset via Socrata/data.iowa.gov

(preliminary exploration)

The state of Iowa has released an 800MB+ dataset of more than 3 million rows showing weekly liquor sales, broken down by liquor category, vendor, and product name, e.g. STRAIGHT BOURBON WHISKIES, Jim Beam Brands, Maker's Mark

This dataset contains the spirits purchase information of Iowa Class “E” liquor licensees by product and date of purchase from January 1, 2014 to current. The dataset can be used to analyze total spirits sales in Iowa of individual products at the store level.

You can view the dataset via Socrata

hadley

recode <- function(df, ..., match = c("first", "last")) {
  match <- match.arg(match)

  cases <- lapply(list(...), as.case)
  if (identical(match, "last")) cases <- rev(cases)

  n <- nrow(df)
  out <- rep(NA, length(n)) # logical will be upcast as needed

  # Simple loop-y implementation

kylebgorman

# autoloess.R: compute loess metaparameters automatically
# Kyle Gorman <gormanky@ohsu.edu>

aicc.loess <- function(fit) {
    # compute AIC_C for a LOESS fit, from:
    # 
    # Hurvich, C.M., Simonoff, J.S., and Tsai, C. L. 1998. Smoothing 
    # parameter selection in nonparametric regression using an improved 
    # Akaike Information Criterion. Journal of the Royal Statistical 
    # Society B 60: 271–293.

mike-lawrence

library(MASS)
library(lme4)

generate_data = function(
	n # number of units
	, k # number of trials within each condition within each unit
	, noise # measurement noise variance
	, I # population intercept
	, vI # across-units variance of intercepts
	, A # population A effect

bds

library(ggplot2)

sparkLinePlot <- function(df, plot.file) {

  highest <- subset(df, outcomes == max(outcomes))
  lowest <- subset(df, outcomes == min(outcomes))

  p <- ggplot(df, aes(x=date, y=outcomes)) +
       geom_line() +
       opts(panel.border = theme_rect(linetype = 0),