{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wed Apr 27 16:12:57 PDT 2016\r\n"
     ]
    }
   ],
   "source": [
    "!date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Software:\n",
      "\n",
      "    System Software Overview:\n",
      "\n",
      "      System Version: OS X 10.9.5 (13F34)\n",
      "      Kernel Version: Darwin 13.4.0\n",
      "      Boot Volume: Hummingbird\n",
      "      Boot Mode: Normal\n",
      "      Computer Name: hummingbird\n",
      "      User Name: Sam (Sam)\n",
      "      Secure Virtual Memory: Enabled\n",
      "      Time since boot: 9 days 6:19\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "system_profiler SPSoftwareDataType"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "      Model Name: Xserve\n",
      "      Model Identifier: Xserve3,1\n",
      "      Processor Name: Quad-Core Intel Xeon\n",
      "      Processor Speed: 2.26 GHz\n",
      "      Number of Processors: 2\n",
      "      Total Number of Cores: 8\n",
      "      L2 Cache (per Core): 256 KB\n",
      "      L3 Cache (per Processor): 8 MB\n",
      "      Memory: 24 GB\n",
      "      Processor Interconnect Speed: 5.86 GT/s\n",
      "      Boot ROM Version: XS31.0081.B06\n",
      "      SMC Version (system): 1.43f4\n",
      "      LOM Revision: 1.1.8\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "#Uses grep to exclude lines that display serial number and hardware UUID\n",
    "system_profiler SPHardwareDataType | grep -v [SH][ea]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "### Add to md5 checksums file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "real\t12m58.000s\n",
      "user\t1m44.985s\n",
      "sys\t0m28.281s\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "\n",
    "#For loop generates a md5 checksum has value for each file\n",
    "#and appends the output to the checksums.md5 file.\n",
    "time for file in /Volumes/owl_web/nightingales/O_lurida/20160223_gbs/160123_I132_FCH3YHMBBXX_L4_OYSzenG1AAD96FAAPEI-109_[12].fq.gz\n",
    "    do\n",
    "        md5 \"$file\" >> /Volumes/owl_web/nightingales/O_lurida/20160223_gbs/checksums.md5\n",
    "        done"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Calculate total number of reads generated by this project.\n",
    "\n",
    "###Calculate number of reads per file, append filename and corresponding number of reads to readme file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "160123_I132_FCH3YHMBBXX_L4_OYSzenG1AAD96FAAPEI-109_1.fq.gz\t364261046\n",
      "\n",
      "160123_I132_FCH3YHMBBXX_L4_OYSzenG1AAD96FAAPEI-109_2.fq.gz\t364261046\n",
      "\n",
      "728522092\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "real\t29m40.999s\n",
      "user\t18m34.488s\n",
      "sys\t1m58.738s\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "\n",
    "#Initializes variable.\n",
    "totalreads=0\n",
    "\n",
    "#For loop counts the lines in each file and divides them by four. This is performed because\n",
    "#Illumina sequencing files are composed of four lines per read.\n",
    "#A running total of the total number of reads is generated [totalreads=$((readcount+totalreads))]\n",
    "#and is printed after the for loop completes.\n",
    "\n",
    "#Format the output (printf) to print the filename, followed by a tab, followed by the readcount.\n",
    "#The command \"tee -a\" is used to both print the output to the screen and append the output to the readme.md file.\n",
    "time for file in /Volumes/owl_web/nightingales/O_lurida/20160223_gbs/160123_I132_FCH3YHMBBXX_L4_OYSzenG1AAD96FAAPEI-109_[12].fq.gz\n",
    "    do linecount=`gunzip -c \"$file\" | wc -l`\n",
    "    readcount=$((linecount/4))\n",
    "    totalreads=$((readcount+totalreads))\n",
    "    printf \"%s\\t%s\\n\\n\" \"${file##*/}\" \"$readcount\" | tee -a /Volumes/owl_web/nightingales/O_lurida/20160223_gbs/readme.md\n",
    "done\n",
    "echo $totalreads\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}