John Downs munk

Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
Models and Issues in Data Stream Systems
Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
[Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

	import csv
	filename = '/full/path/tofile/'
	with open(filename, 'rb') as csvfile:
	reader = csv.reader(csvfile, delimiter=' ', quotechar='\|')
	result = [row for row in reader if 'N/A' in reader]
	print result

	import itertools as it
	import random

	def cards(n, t):
	nt = n*t
	images = range(nt)
	return [[j for j in images[i:i + t]] for i in range(0, n*t, t)]

	def edges(cards, link_count):
	ct = min(len(cards), link_count) # we can't have more edges than cards for prop4

	(ns interactive)

	(defn my-fancy-function
	[x y z]
	(* x y z))

	(comment
	(= 1 (my-fancy-function 1 1 1)) ; eval here, move to a test ns when you're done and want a regression suite
	)

	; HTTP Client for OpenHDS-REST

	(ns ohds.client
	(:require [clojure.edn :as edn]
	[clojure.tools.logging :as log]
	[org.httpkit.client :as http]
	[clojure.data.json :as json]
	[schema.core :as s])
	(:import (java.time LocalDateTime)))

	(ns framework
	(:require [reagent.core :as reagent]))
	(def isClient (not (nil? (try (.-document js/window)
	(catch js/Object e nil)))))

	(def rflush reagent/flush)

	(defn add-test-div [name]
	(let [doc js/document
	body (.-body js/document)

-#!/bin/bash
-set -eu
-shopt -s nullglob
-readonly base_dir=/var/lib/docker/registry
-readonly output_dir=$(mktemp -d -t trace-images-XXXX)
-readonly jq=/usr/bin/jq
-readonly repository_dir=$base_dir/repositories

	# Python 3.4

	import requests
	import bs4

	def get_stock_price(name):
	url = "https://www.google.com/finance"
	data = requests.get(url, params={'q': name})
	bs = bs4.BeautifulSoup(data.text)
	div_price = bs.find(attrs={"id": "price-panel"})

	import json
	import httplib
	import pymongo
	from time import sleep

	url = 'http://citibikenyc.com/stations/json'
	connection = pymongo.Connection()
	db = connection['citibike']
	collection = db['station_status']