sxv

import sys, random

# board is defined as list of 19 land tiles: Forest (4), Sheep (4), Wheat (4), Brick (3), Rocks (3), Desert (1)
def new_board(board=''):
  available = list('ffffsssswwwwbbbrrrd')
  for i in range(19):
    random.shuffle(available)
    board += available.pop()
  return board

sxv

import sys

rows = []

for line in open('gene_names.csv'):
  a,b,c = line.replace('\n','').split(',')
  rows.append([a,c])

for file in sys.argv[1:]:
  for i, line in enumerate(open(file)):

sxv

# usage:
#   python 3reads.py /batch/dir1/ /batch/dir2/        # run all steps on two batches
#   python 3reads.py -2 -3 -loadAndKeep /batch/dir    # run steps 2 and 3 and use STAR --loadAndKeep
#   python 3reads.py /batch/dir1 /batch/dir2/ -13     # run steps 1 and 3 on two batches
import sys, os

base_dir = '/home/sxv/code/s7s/'
MAKE_FASTQ = '%s/make_fastq.sh' % base_dir
ALIGN = '%s/align_smart-3seq.sh' % base_dir
MAKE_EXPRESSION_TABLE = '%s/make_expression_table.R' % base_dir

sxv

gawk '//{x=tolower($0); gsub(/[aeiou]/,"",x); a[x]++; b[x]=$0;}END{for(i in a){ if(a[i]==1){print i, b[i]} }}' /usr/share/dict/words

sxv

import sys

opts = {
  'window': 100000,
  'intrachrom': False
}
args = sys.argv[1:]
for a, arg in enumerate(args):
  if arg.startswith('-'):
    if arg.startswith('-w') or arg.startswith('--window'):

sxv

# define input cases via master_key.txt
# for each run, align fastq -> bam
#   if GATK specified, run GATK, variant calling, and annovar
# run matricizer2 on tab output
# todo: add R clustering scripts

## usage
# python rnarunner.py --input-dir /path/to/fastqs
## NOTES: input-dir must contain master_key.txt, input fastq.gz files, matricizer2.py, UCSC_GENE_NAME3.txt

sxv

# define input cases via master_key.txt
# for each run, align fastq -> bam
#   if GATK specified, run GATK, variant calling, and annovar
# run matricizer2 on tab output
# todo: add R clustering scripts

## usage
# python rnarunner.py --input-dir /path/to/fastqs
## NOTES: input-dir must contain master_key.txt, input fastq.gz files, matricizer2.py, UCSC_GENE_NAME3.txt

sxv

<canvas id="canvas"></canvas>
<script src="https://d3js.org/d3.v3.min.js"></script>
<script>
var num = 2000;
var canvas = document.getElementById("canvas");
var width = canvas.width = window.innerWidth;
var height = canvas.height = window.innerHeight;
var ctx = canvas.getContext("2d");
var particles = d3.range(num).map(function(i) {
  return [Math.round(width*Math.random()), Math.round(height*Math.random()), 2];

sxv

import sys
from glob import glob

if (len(sys.argv)<=1): match = '*n0*'
else: match = sys.argv[1]
file = glob(match)[0]

counts = {}
with open(file) as f:
  print f.readline()

sxv

#!/usr/bin/env bash

for f in *.vcf; do \
  gawk 'BEGIN{FS="\t"; OFS="\t"; }                        # separator=tab
        /CHROM/{
          ## for(i=0; i<NF; i++){ if($i=="FORMAT"){ samples=(NF-i) } }   # todo
          if($(NF-2)~/FORMAT/){
            samples=2;                                          # two samples?
            if($(NF)~/[nN]$/ || $(NF)~/normal$/){ swap=1 }    # is order t/n?
          }