###Jill Mesirov - Broad Institute
@broadinstitute
Broad has generated >150 TBPs in a year, how was this number calculated?
###Bas Burger - BT Global Commerce
def estimate_size_factor(counts): | |
#COUNTS = GENES (rows) x CELLS (columns) | |
genes = counts[:, 0] | |
#ONLY COUNTS WITHOUT HEADER NOR GENES | |
counts = numpy.array(counts[1:, 1:], dtype = int) | |
#DONT REMOVE INFITE VALUES AS IT CAUSES PROBLEMS | |
log_counts = numpy.log(counts) | |
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ |
"""Solve 'Towers of Hanoi'""" | |
import pylab as p; | |
import mpl_toolkits.mplot3d.axes3d as p3; | |
def solve(g,n): | |
X = [sum(g[0])] | |
Y = [sum(g[1])] | |
Z = [sum(g[2])] | |
moved = 0 |
from __future__ import with_statement | |
import matplotlib.pyplot as plt | |
plt.rc('xtick', labelsize='x-small') | |
import yaml | |
def convert(yaml_file): | |
"""Convert the data in a yaml file generated by count_barcodes.py to a | |
.dat file with space seperated sorted fractions of barcode distribution. | |
""" |
"""Randomly picks out some title / sequence / quality triples | |
from a given fastq file and writes them in to a new fastq file. | |
This is to generate rudimentary test data which doesn't take too long to run. | |
Usage: make_random_test_fastq.py <fastq_file> <target file size in MB> | |
""" | |
import os | |
import sys | |
from random import random |
log_entry = { | |
'date': '2011-03-31T00:00:00', | |
'machine': 'SN167', | |
'project': '0255_A81BF6ABXX', | |
'size': 277025390592L | |
} |
###Jill Mesirov - Broad Institute
@broadinstitute
Broad has generated >150 TBPs in a year, how was this number calculated?
###Bas Burger - BT Global Commerce