add target and strat_name matchers

UW-xDD · Dec 17, 2016 · 2a914d9 · 2a914d9
1 parent ea84b2f
commit 2a914d9
Showing 1 changed file with 40 additions and 7 deletions.
diff --git a/notebooks/1_candidate_generation.ipynb b/notebooks/1_candidate_generation.ipynb
@@ -9,15 +9,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
    "source": [
     "%load_ext autoreload\n",
     "%autoreload 2\n",
     "\n",
+    "import os\n",
+    "os.environ['SNORKELDB']=\"postgres://jhusson@localhost:5432/snorkel_strom\"\n",
+    "\n",
     "from snorkel import SnorkelSession\n",
     "session = SnorkelSession()"
    ]
@@ -74,7 +86,7 @@
    "source": [
     "from snorkel.models import candidate_subclass\n",
     "\n",
-    "Spouse = candidate_subclass('Spouse', ['person1', 'person2'])"
+    "strom = candidate_subclass('strom', ['strom', 'strat_name'])"
    ]
   },
   {
@@ -123,9 +135,30 @@
    },
    "outputs": [],
    "source": [
-    "from snorkel.matchers import PersonMatcher\n",
+    "from snorkel.matchers import RegexMatchSpan\n",
+    "\n",
+    "strom_matcher = RegexMatchSpan(rgx=\"stromatol|thrombol\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "from snorkel.matchers import DictionaryMatch\n",
+    "import urllib\n",
+    "import json\n",
+    "\n",
+    "request = urllib.urlopen('https://macrostrat.org/api/v2/defs/strat_names?all')\n",
+    "data = json.loads(request.read())\n",
+    "\n",
+    "strat_dict = { r['strat_name_long'] for r in data['success']['data'] }\n",
+    "\n",
     "\n",
-    "person_matcher = PersonMatcher(longest_match_only=True)"
+    "strat_matcher=DictionaryMatch(d=strat_dict,ignore_case=False,longest_match_only=True)"
    ]
   },
   {
@@ -704,7 +737,7 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python [default]",
+   "display_name": "Python 2",
    "language": "python",
    "name": "python2"
   },
@@ -718,7 +751,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "version": "2.7.11"
   }
  },
  "nbformat": 4,