EvanTheB

#!/usr/bin/env python3

import sys
import os
import json
import subprocess
from itertools import tee, filterfalse

import markdown_link_extractor

EvanTheB

#!/usr/bin/env bash

set -euo pipefail
# set -x

rm likes

curl -sS -n -G -H 'Content-Type: application/json' https://intranet.gimr.garvan.org.au/rest/api/content/ --data-urlencode limit=500 --data-urlencode type=page --data-urlencode type=page > tmpdata

for i in $(seq 500); do

EvanTheB

##fileformat=VCFv4.2
##FILTER=<ID=PASS,Description="All filters passed">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
##reference=ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz
##contig=<ID=1,length=249250621,md5=1b22b98cdeb4a9304cb5d48026a85128>
##contig=<ID=2,length=243199373,md5=a0d9851da00400dec1098a9255ac712e>

EvanTheB

File is ~100 million lines, with ~30 categories in the first column. So sort type 1 should execute ~30 subprocesses.
Takes ~ 180 seconds, so subprocess overhead should be very minimal. 

Type 1, multiple sub-sorts:

$ time env time -v -o sort1.time awk -v cmd="sort -k2,2n" '$1 != prev {close(cmd); prev=$1} {print | cmd}' vcf.bed > vcf.sort1.bed  

real	2m57.867s
user	0m46.381s
sys	4m14.309s

EvanTheB

function autolike () {
    [].forEach.call(
        document.getElementById("likes-and-labels-container")
        .getElementsByClassName("like-button-text"),
        function (e) {
            console.error(e);
            if (e.innerText === "Like") {
                e.parentNode.click();
                // [].forEach.call(
                //     document.getElementsByClassName("like-button"), 

EvanTheB

#!/usr/bin/env bash
set -euo pipefail

CACHE_FILE="$HOME"/.cache/qstat.map

# a 1 minute timed cache
# does not actually handle failures properly. todo
if ! test -e $CACHE_FILE || (( $(find "$CACHE_FILE" -mmin +1 | wc -l) > 0)); then
    CACHE_FILE_TMP="$CACHE_FILE.$$.$RANDOM"
    trap 'rm '"$CACHE_FILE_TMP" EXIT

EvanTheB

import random
import collections

def num_cards():
    cures = [0] * 48 + [1] * 4
    random.shuffle(cures)
    def split(x, n):
        return [x[i:len(x):n] for i in range(n)]
    cures = [c + [2] for c in split(cures, 5)]
    [random.shuffle(c) for c in cures]

EvanTheB

#!/bin/bash
set -xeuo pipefail
IFS=$'\n\t'

# git clone https://github.com/cloudflare/zlib &
[ -d "zlib-1.2.8" ] || curl -L https://github.com/cloudflare/zlib/archive/v1.2.8.tar.gz | tar zx  &
# git clone https://github.com/ebiggers/libdeflate.git &
[ -d "libdeflate-1.0" ] || curl -L https://github.com/ebiggers/libdeflate/archive/v1.0.tar.gz | tar zx &
# git clone https://github.com/samtools/htslib.git &
[ -d "htslib-1.8" ] || curl -L https://github.com/samtools/htslib/releases/download/1.8/htslib-1.8.tar.bz2 | tar jx &

EvanTheB

task bwa_mem_tool {
  Int threads
  Int min_seed_length
  Int min_std_max_min

  command {
    echo ${threads} ${min_seed_length} ${sep=',' min_std_max_min+} > output.sam
  }
  output {
    File sam = "output.sam"

EvanTheB

#define TIMEIT(F, N, REPS) \
{\
    clock_t start = clock();\
    for (int i = 0; i < N; ++i)\
    {\
    }\
    clock_t diff_loop = clock() - start;\
    double results[REPS];\
    for (int i = 0; i < REPS; ++i)\
    {\