Daniel Baker dnbaker

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

Integer Hash Function

Thomas Wang, Jan 1997

last update Mar 2007

	/*
	* :abstract: set the base in pSeq at index i in the read to the base in bSeq at index i in the read.
	* These 8-bit integers are the points in memory returned by bam_get_seq(p) and bam_get_seq(b), respectively.
	* :param: pSeq [uint8_t *]
	* :param: bSeq [uint8_t *]
	* :param: i [int/integral type]
	*/
	#define set_base(pSeq, bSeq, i) (pSeq)[(i)>>1] = ((bam_seqi(bSeq, i) << (((~i) & 1) << 2)) \| (((pSeq)[(i)>>1]) & (0xf0U >> (((~i) & 1) << 2))))
	/*
	* :abstract: set the base at index i in the read to "N".

	import pysam
	from itertools import chain

	def get_qchars(bampath):
	return set(chain.from_iterable(set(c.qual) for
	c in pysam.AlignmentFile(bampath)))

	#ifndef KMER2STR_H
	#define KMER2STR_H
	#include "stdint.h"


	#ifndef num2nuc
	# ifndef NUM2NUC_STR
	# define NUM2NUC_STR "ACGTN"
	# endif
	# define num2nuc(x) NUM2NUC_STR[(uint8_t)x]

	#ifndef FALL_THROUGH_IPOW_H
	#define FALL_THROUGH_IPOW_H
	#include "stdint.h"

	static inline int64_t ipow(int32_t base, uint8_t exp) {
	static const uint8_t highest_bit_set[] = {
	0, 1, 2, 2, 3, 3, 3, 3,
	4, 4, 4, 4, 4, 4, 4, 4,
	5, 5, 5, 5, 5, 5, 5, 5,
	5, 5, 5, 5, 5, 5, 5, 5,

	/* Assumes that both strings are of equal length.
	*
	*/

	int hd(char a, char b) {
	int ret = 0;
	while(a) ret += (a++ != *b++);
	return ret;
	}

	try:
	from cytoolz import frequencies
	except ImportError:
	from collections import Counter as frequencies
	# Works, but it's less than 3x as fast
	# A simple pure python counter is twice as fast as Counter anyhow....
	from itertools import chain

	def get_qchars_counts(bampath):
	'''

	#!/bin/bash

	# Script for installing tmux on systems where you don't have root access.
	# tmux will be installed in $HOME/local/bin.
	# It's assumed that wget and a C/C++ compiler are installed.

	# exit on error
	set -e

	TMUX_VERSION=1.8