dansondergaard

import sys
import textwrap

from itertools import dropwhile, takewhile
from collections import Counter


common_english_words = [
    'the', 'of', 'and', 'to', 'a', 'in', 'for', 'is', 'on', 'that', 'by',
    'this', 'with', 'i', 'you', 'it', 'not', 'or', 'be', 'are', 'from',

dansondergaard

amino_acid_masses = {
    'A': 71.0788,
    'R': 156.1875,
    'N': 114.1038,
    'D': 115.0886,
    'C': 103.1388,
    'E': 129.1155,
    'Q': 128.1307,
    'G': 57.0519,
    'H': 137.1411,

dansondergaard

from docker import Client

cli = Client()

imgs = cli.images(all=True)
conts = cli.containers(filters={'status': 'running'})

# Make a map from image id to the name (tag) of the image.
# If no name is set, just use the id.
img_map = {}

dansondergaard

function _jpu () {
        squeue -h | awk '{print $4}' | sort | uniq -c | sort -b -h -r
}

alias jpu=_jpu

dansondergaard

require('dplyr')
require('tidyr')
require('ggplot2')

# Read all cross-validation files and concatenate the dataframes.
tables = lapply(Sys.glob("cv_*.txt"), function (filename) {
  read.csv(filename, sep=" ", header=FALSE,
           col.names=c('File', 'Neighbors', 'Method', 'Accuracy'))
})

dansondergaard

#################
# notifications #
#################

function __record_cmd_begin -d "Record time when command started." -e fish_preexec
  set -g cmd_begin_time (eval date +"%s")
end

function __record_cmd_end -d "Record time when command ended." -e fish_postexec
  set -g cmd_end_time (eval date +"%s")

dansondergaard

#!/usr/bin/env python3

import sys
import os
import os.path
import argparse

import subprocess

DEVNULL = open(os.devnull, 'wb')

dansondergaard

import xml.etree.ElementTree as et
import base64
import array


def parse_file(filename_or_obj):
    tree = et.parse(filename_or_obj)
    for spectrum in tree.findall('.//spectrum'):
        mz_elm = spectrum.find('mzArrayBinary').find('data')
        intensity_elm = spectrum.find('intenArrayBinary').find('data')

dansondergaard

class symbol(object):
    _symbols = {}

    def __new__(cls, name):
        if name not in symbol._symbols:
            symbol._symbols[name] = object.__new__(cls, name)
        return symbol._symbols[name]

    def __init__(self, name):
        self.name = name

dansondergaard

def compute_error(partition):
    """Find the majority category of the partition. Count how big
       a part of the partition that the majority category is.
       Return the ratio of things that are *not* of the majority category."""
    categories = map(get_category, partition)
    majority = max(set(categories), key=categories.count)
    return 1 - (categories.count(majority) / float(len(partition)))

# This is what a typical partition looks like. The inner tuple may
# be very large (in the thousands) and the list of the length may