egafni

"""
import os
import urllib

url = 'http://pastebin.com/raw.php?i=6nBX6sdE'
fn = 'karyotype.txt'
if not os.path.exists(fn):
    print 'Downloading %s to local file: %s' % (url, fn)
    with open(fn, 'w') as k_file:
        f = urllib.urlopen(url)

egafni

def vcf_genotype_ordering_iter(ploidy, num_alt_alleles, suffix=None):
    """
    Generator version of :func:`geno_ordering`
    """
    for a in range(num_alt_alleles+1):
        if ploidy == 1:
            yield (a,) + suffix
        elif ploidy > 1:
            for alleles in vcf_genotype_ordering_iter(ploidy-1, a, (a,) + (suffix or tuple())):
                yield alleles

egafni

from more_itertools import peekable

def segment(itrbl, is_group):
    """
    Similar to itertools.groupby but allows you to directly compare elements pairwise with a function rather than only being able to use a key.
        
    >>> f = lambda x, y: y - x < 50
    >>> list(segment([1, 2, 100, 101, 500, 505, 510, 700], f))
    [[1, 2], [100, 101], [500, 505, 510], [700]]
    >>> list(segment[1], f)

egafni

import shelve
from contextlib import closing


def shelve_locals(filename, locals_):
    """
    Intended to be called as shelve_locals(filename, locals()) from a debug session
    and then loaded into another environment like an ipython notebook.

    ex:

egafni

#!/usr/bin/env python

import sys
import subprocess as sp

GIT = '/usr/local/bin/git'

for line in sp.check_output('%s branch' % GIT, shell=True).strip().split("\n"):
    if line.startswith('* '):
        branch = line[2:]

egafni

def beta_binom_credible_interval(k, n, credible_interval_size=0.95, a=1, b=1):
    """
    Returns the credible interval of the posterior of a beta binomial.  This is the Bayesian
    interpretation of the 95% confidence interval.
    
    a, b are alpha/beta parameters of a beta distribution.
    Default of a=1, b=1 is a uniform distribution over [0, 1]
    
    >>> np.round(beta_binom_credible_interval(1, 2), 2)
    array([0.09, 0.91])

egafni

def get_segment_ranges(arr):
    """
    Get a list of (start, stop) ranges for segments of repeating elements within an array
    
    >>> get_segment_ranges([0,1,0,0,0,1,1,1,0,1])
    [(0, 1), (1, 2), (2, 5), (5, 8), (8, 9), (9, 10)]
    >>> get_segment_ranges([])
    []
    >>> get_segment_ranges([1,1,2])
    [(0, 2), (2, 3)]

egafni

def percentile_mask(arr, lower=None, upper=None):
    """
    >>> arr = np.array([1,2,3,4])
    array([False,  True,  True, False])
    >>> percentile_mask(arr, 25)
    array([False,  True,  True,  True])
    >>> percentile_mask(arr, None, 25)
    array([ True, False, False, False])
    """
    if lower is not None:

egafni

def get_adjacent_cells(arr, selected_idxs):
    """
    >>> arr = np.ones((3,))
    >>> get_adjacent_cells(arr, {(1,)})
    {(0,), (1,), (2,)}
    >>> arr = np.ones((3,2))
    >>> get_adjacent_cells(arr, {(1,1)})
    {(0, 1), (1, 0), (1, 1), (2, 1)}
    >>> arr = np.ones((3,2,3))
    >>> {(0, 1, 0), (1, 0, 0), (1, 1, 0), (1, 1, 1), (2, 1, 0)}

egafni

def credible_coordinates(arr, min_percentile=.99):
    """
    Calculates a type of credible "interval" by a simple greedy approach of the most likely coordinates of a joint
    density.

    >>> X = np.array([.1,.1,.5,.3])
    >>> Y = np.array([.2,.8])
    >>> Z = np.array([.5,.5])
    >>> R = np.array([[[x*y*z for z in Z] for y in Y] for x in X ])