add: links to ixi and gsp in readme

Author: nicholsn

README.md

@@ -26,6 +26,15 @@ example, you could select participants that are female between the ages
 of 20 to 30 with a Verbal IQ between 100 and 120.
 
 Demo: http://openneu.ro/metasearch/
+
+## Datasets and Licenses
+Please refer to and follow the data licenses and use agreements listed
+on the homepage of each of the datasets in the table below.
+
+|Project Link to License|
+|-----------------------|
+|[Brain Genomics Superstruct Project][gsp]|
+|[IXI – Information eXtraction from Images][ixi]| 
 
  [fcp-indi]: http://fcon_1000.projects.nitrc.org
  [extract]: https://github.com/OpenNeuroLab/metasearch/blob/master/crawler/extract/Extract.ipynb
@@ -34,5 +43,7 @@ Demo: http://openneu.ro/metasearch/
  [pcoord]: http://syntagmatic.github.io/parallel-coordinates
  [d3]: https://d3js.org/
  [slick]: https://github.com/mleibman/SlickGrid/wiki
+ [gsp]: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/25833
+ [ixi]: http://brain-development.org/ixi-dataset/
 
 

crawler/transform.ipynb

@@ -424,36 +424,20 @@
     "# Merge Datasets\n",
     "joined = unique.join(mri, how='outer')\n",
     "joined['MRI'] = joined.t1_url.apply(lambda x: 'no' if pd.isnull(x) else 'yes')\n",
-    "final = joined.reset_index()\n"
+    "final = joined.reset_index()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "ename": "ValueError",
-     "evalue": "Length mismatch: Expected axis has 16 elements, new values have 15 elements",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-13-ad36511dd7a3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     14\u001b[0m                  \u001b[0;34m'MRIs'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m                  \u001b[0;34m'session_count'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m                  'MRI']\n\u001b[0m\u001b[1;32m     17\u001b[0m \u001b[0mfinal\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../docs/data/phenotype_mri.csv'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/Users/nicholsn/miniconda/envs/metasearch/lib/python2.7/site-packages/pandas/core/generic.pyc\u001b[0m in \u001b[0;36m__setattr__\u001b[0;34m(self, name, value)\u001b[0m\n\u001b[1;32m   2755\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2756\u001b[0m             \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2757\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__setattr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2758\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mAttributeError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2759\u001b[0m             \u001b[0;32mpass\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32mpandas/src/properties.pyx\u001b[0m in \u001b[0;36mpandas.lib.AxisProperty.__set__ (pandas/lib.c:44336)\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;32m/Users/nicholsn/miniconda/envs/metasearch/lib/python2.7/site-packages/pandas/core/generic.pyc\u001b[0m in \u001b[0;36m_set_axis\u001b[0;34m(self, axis, labels)\u001b[0m\n\u001b[1;32m    446\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    447\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_set_axis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 448\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_axis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    449\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_clear_item_cache\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    450\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/Users/nicholsn/miniconda/envs/metasearch/lib/python2.7/site-packages/pandas/core/internals.pyc\u001b[0m in \u001b[0;36mset_axis\u001b[0;34m(self, axis, new_labels)\u001b[0m\n\u001b[1;32m   2779\u001b[0m             raise ValueError('Length mismatch: Expected axis has %d elements, '\n\u001b[1;32m   2780\u001b[0m                              \u001b[0;34m'new values have %d elements'\u001b[0m \u001b[0;34m%\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2781\u001b[0;31m                              (old_len, new_len))\n\u001b[0m\u001b[1;32m   2782\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2783\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maxes\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnew_labels\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mValueError\u001b[0m: Length mismatch: Expected axis has 16 elements, new values have 15 elements"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "final.columns = ['project',\n",
     "                 'session_id',\n",
-    "                 'participant_id'\n",
+    "                 'participant_id',\n",
     "                 'age',\n",
     "                 'diagnosis',\n",
     "                 'dsm_iv_tr',\n",