two function added for extracting names

nlu_job/name_extraction.py

@@ -0,0 +1,40 @@
+from django.conf import settings
+from django.utils import timezone
+from review.models import Review
+
+nlp = settings.MODEL
+STOP_WORDS = ['signature', 'care', 'emergency', 'er', 'center', 'nurse', 'dr', 'dr.', 'signaturecare']
+
+
+def extract_names_1st(location_id):
+    '''
+    Extract all names that presented in this month's all reviews
+    :param location_id: string -> ID of the  location which you want to collect reviews
+    :return: names: list -> A list of names that found in reviews
+    '''
+    reviews = Review.objects.filter(
+        location_id=location_id,
+        create_time__gte=timezone.now().replace(day=1, hour=0, minute=0, second=0, microsecond=0)
+    )\
+        .exclude(comment=None)
+    names = []
+    for r in reviews:
+        doc = nlp(r.comment)
+        for e in doc.ents:
+            names.append(e.text) if e.label_ in ['PERSON', 'ORG'] else None
+    return names
+
+
+def extract_names_2nd(names):
+    '''
+    2nd order names extraction.
+    removing all hand labeled stop words
+    :param names: List -> list of name.
+    :return: List -> list of name.
+    '''
+    new_names = []
+    for name in names:
+        for n in name.split():
+            if n.lower() not in STOP_WORDS and len(n) > 2:
+                new_names.append(n.lower())
+    return new_names