danielecook

from pyquery import PyQuery as pq
from icalendar import Calendar, Event
import datetime
from datetime import date, timedelta
from dateutil.relativedelta import *
from dateutil.parser import *
from pprint import pprint as pp

clubid = 722
url = "https://www.lafitness.com/Pages/ClassSchedulePrintVersion.aspx?clubid=%s" % clubid

danielecook

# I am trying to make R a little easier by adding a few helper functions. Most of these mimic functionality seen in Stata.

# This function attempts to mimic the order command in Stata; 
# Usage:
# df <- corder(df,<list of columns>)

# Order variables in a data frame.

corder <- function(df,...) {
  cols <-as.vector(eval(substitute((alist(...)))),mode="character")

danielecook

wget 'ftp://ftp.ncbi.nih.gov/pub/HomoloGene/current/homologene.data'
egrep "\t9606\t" homologene.data | sort | cut -f 1,3,4 > human.txt
egrep "\t6239\t" homologene.data | sort | cut -f 1,3,4 > celegans.txt
join -1 1 -2 1 -t $'\t' human.txt celegans.txt | cut -f 2,3,4,5 | sort | echo -e "Human_Entrez\tHuman_Symbol\tElegans_Entrez\tElegans_Symbol\n$(cat -)" > orthologs.txt
rm human.txt celegans.txt homologene.data

danielecook

#!/usr/bin/python
import re
from itertools import groupby as g
import subprocess
import sys
from collections import OrderedDict

def most_common(L):
  return max(g(sorted(L)), key=lambda(x, v):(len(list(v)),-L.index(x)))[0]

danielecook

# Special thanks for insights from flowingdata.com regarding this.

library(plotKML)
library(plyr)
library(dplyr)
library(fpc)

num_locations <- 5

# Usage: Place this script in the directory containing your runkeeper data. You can run from terminal using 'Rscript map_runkeeper.R', or

danielecook

function SRX_fetch_fastq() {
    sra_set=`esearch -db sra -query $1 | efetch -format docsum | xtract -element Run@acc`
    echo "Downloading Run $1:" 
    echo ${sra_set}
    echo "-------"
    for SRA in $sra_set; do
        echo "Downloading $SRA"
        fastq-dump $SRA
    done;
}

danielecook

library(stringr)
library(dplyr)
"""
# Generate concatenated worm_track data using the following
for folder in `ls -d *\/`; do
    for file in `ls $folder/worm*`; do
        cat $file | awk -v file=$file '{print file","$1}' >> worm_track_all.txt
    done;
done;
"""

danielecook

#!/bin/bash
wget 'http://hgdownload.soe.ucsc.edu/goldenPath/ce10/database/rmsk.txt.gz' -O LCR_rmsk.txt.gz
gunzip -kfc LCR_rmsk.txt.gz | grep 'Low_complexity' | cut -f 6,7,8 > LCR_ce10_rmsk.bed
rm LCR_rmsk.txt.gz


# Generate the set of regions complementary (e.g. NOT low complexity)
# Download c. elegans chromosome information
mysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e "select chrom, size from ce10.chromInfo"  > ce10.genome
bedtools complement -i LCR_ce10_rmsk.bed  -g ce10.genome | sort -k 1,1 -k2,2n > LCR_complement_ce10.bed

danielecook

import os, subprocess, uuid, re
import vcf.filters



class bcf(file):
    def __init__(self, file):
        # Start by storing basic information about the vcf/bcf
        self.file = file
        self.ops = []

danielecook

echo "Sync Profile Loaded"

export PS1="\w 🍔  "
alias refresh="source ~/.bash_profile"
alias git log=“git log --graph --pretty=format:'%Cred%h%Creset -%C(yellow)%d%Creset %s %Cgreen(%cr) %C(bold blue)<%an>%Creset' --abbrev-commit”

export PATH=/usr/local/bin:$PATH

# Get working directory of frontmost finder window.
cdf() {