Collecting scandates from XNAT.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import sys, string\n",
    "sys.path.append('/home/grg/git/xnat-monitor/')\n",
    "from bbrc import xnat\n",
    "from lxml import etree\n",
    "\n",
    "central = xnat.connect_xnat('/home/grg/.xnat_bsc.cfg')\n",
    "ns = {'xnat':\"http://nrg.wustl.edu/xnat\"}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject</th>\n",
       "      <th>scandate</th>\n",
       "      <th>xnatdate</th>\n",
       "      <th>has_bvec</th>\n",
       "      <th>project</th>\n",
       "      <th>accession_number</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10019</td>\n",
       "      <td>2017-02-15</td>\n",
       "      <td>20170331</td>\n",
       "      <td>False</td>\n",
       "      <td>ALFA_PLUS</td>\n",
       "      <td>040510150217019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10044</td>\n",
       "      <td>2017-06-27</td>\n",
       "      <td>20170627</td>\n",
       "      <td>False</td>\n",
       "      <td>ALFA_PLUS</td>\n",
       "      <td>040510270617044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10065</td>\n",
       "      <td>2016-10-21</td>\n",
       "      <td>20170330</td>\n",
       "      <td>False</td>\n",
       "      <td>ALFA_OPCIONAL</td>\n",
       "      <td>030410211016065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>10070</td>\n",
       "      <td>2017-06-13</td>\n",
       "      <td>20170621</td>\n",
       "      <td>False</td>\n",
       "      <td>ALFA_PLUS</td>\n",
       "      <td>040510130617070</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10137</td>\n",
       "      <td>2017-06-07</td>\n",
       "      <td>20180117</td>\n",
       "      <td>False</td>\n",
       "      <td>ALFA_PLUS</td>\n",
       "      <td>040510070617137</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject    scandate  xnatdate  has_bvec        project accession_number\n",
       "0    10019  2017-02-15  20170331     False      ALFA_PLUS  040510150217019\n",
       "1    10044  2017-06-27  20170627     False      ALFA_PLUS  040510270617044\n",
       "2    10065  2016-10-21  20170330     False  ALFA_OPCIONAL  030410211016065\n",
       "3    10070  2017-06-13  20170621     False      ALFA_PLUS  040510130617070\n",
       "4    10137  2017-06-07  20180117     False      ALFA_PLUS  040510070617137"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "subjects = [string.atoi(e) for e in open('/tmp/amyloid_subjects.txt').read().split('\\n') if e != '']\n",
    "# list of subjects with correct bvec/bval (but who failed the denoising step in my initial attempt\n",
    "bvec_correct =  [10162, 10515, 10627, 10649, 10711, 10949, 11262, 11514, 11745, 12279, 12741, 12991, 13035, 13105, 13107, 13193, 13259,\n",
    "                 21136, 21138, 44008, 44301, 44396, 55854, 66008, 66027, 66100, 66162, 66301, 77012, 77164]\n",
    "\n",
    "res = []\n",
    "for subject in subjects:\n",
    "    # Looks for a matching scan in ALFA_PLUS first, then ALFA_OPCIONAL\n",
    "    project = 'ALFA_PLUS'\n",
    "    e = xnat.subject_experiments(central, 'ALFA_PLUS', str(subject))\n",
    "    if len(e) == 0:\n",
    "        project = 'ALFA_OPCIONAL'\n",
    "        e = xnat.subject_experiments(central, 'ALFA_OPCIONAL', str(subject))\n",
    "        \n",
    "    doc = etree.fromstring(e[0].get())\n",
    "    ans = doc.findall('.//xnat:date', ns)\n",
    "    scandate = ans[0].text # date of acquisition\n",
    "    ans = doc.findall('.//xnat:prearchivePath', ns)\n",
    "    xnatdate = ans[0].text.split('/')[-2].split('_')[0] # date of upload to xnat\n",
    "    ans = doc.findall('.//xnat:dcmAccessionNumber', ns)\n",
    "    accnum = ans[0].text\n",
    "    res.append((subject, scandate, xnatdate, subject in bvec_correct, project, accnum))\n",
    "\n",
    "# saving results in an Excel table and display the first lines\n",
    "import pandas as pd\n",
    "df = pd.DataFrame(res, columns=['subject', 'scandate', 'xnatdate', 'has_bvec', 'project', 'accession_number'])\n",
    "df.to_excel('/tmp/bvec_bval_dates.xls')\n",
    "df.head()"
   ]
  }
 ],
 "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": "2.7.11+"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}