|
@@ -1,21 +1,73 @@
|
|
|
import re
|
|
|
+from decimal import Decimal
|
|
|
from django.conf import settings
|
|
|
-
|
|
|
+from .models import Staff
|
|
|
+from nlu_job.nlu_utils import model_inference
|
|
|
|
|
|
nlp = settings.MODEL
|
|
|
|
|
|
+nlu_url = settings.NLU_SERVER_URI
|
|
|
+
|
|
|
+
|
|
|
+def get_all_names(text):
|
|
|
+ res = model_inference(text)
|
|
|
+ entities = res.get('entities')
|
|
|
+ names = {ent.get('value') for ent in entities if ent.get('entity') in ['PERSON', 'ORG']}
|
|
|
+ return names
|
|
|
+
|
|
|
+
|
|
|
+def all_staffs(location):
|
|
|
+ names = []
|
|
|
+ staffs = Staff.objects.filter(location=location)
|
|
|
+ for s in staffs:
|
|
|
+ names.extend(s.get_nick_names)
|
|
|
+ return set(names)
|
|
|
+
|
|
|
|
|
|
def clean_text(text):
|
|
|
# replace some letter in text for getting better performance
|
|
|
text = re.sub(r':\s*', ' ', text)
|
|
|
- text = re.sub(r'&', ',', text)
|
|
|
+ text = re.sub(r'&', ', ', text)
|
|
|
+ text = re.sub(r'/', ', ', text)
|
|
|
text = re.sub(r'\.*\n\.*', '.', text)
|
|
|
text = re.sub(r'[dD][rR](\.|\s*)*', 'Dr. ', text)
|
|
|
return text
|
|
|
|
|
|
|
|
|
-def extract_names(text):
|
|
|
- text = clean_text(text)
|
|
|
- doc = nlp(text)
|
|
|
- names = {ent.text for ent in doc.ents if ent.label_ in ['PERSON', 'ORG']}
|
|
|
- return list(names)
|
|
|
+def extract_names(review):
|
|
|
+ text = clean_text(review.comment)
|
|
|
+ # doc = nlp(text)
|
|
|
+ # names = {ent.text for ent in doc.ents if ent.label_ in ['PERSON', 'ORG']}
|
|
|
+
|
|
|
+ names = get_all_names(text)
|
|
|
+ cleaned_names = []
|
|
|
+ for name in names:
|
|
|
+ for n in name.split():
|
|
|
+ cleaned_names.append(n) if n.lower() in all_staffs(review.location) else None
|
|
|
+ return cleaned_names
|
|
|
+
|
|
|
+
|
|
|
+def add_point_to_staff_profile(review):
|
|
|
+ staffs = Staff.objects.filter(location=review.location)
|
|
|
+ names = extract_names(review)
|
|
|
+ point_unit = Decimal(1/len(names)) if not names == [] else 0
|
|
|
+
|
|
|
+ for name in names:
|
|
|
+ for staff in staffs:
|
|
|
+ if name.lower() in staff.get_nick_names:
|
|
|
+ staff.name_mentioned += 1
|
|
|
+ staff.total_units += point_unit
|
|
|
+ staff.save()
|
|
|
+
|
|
|
+
|
|
|
+def make_all_staffs_point_zero():
|
|
|
+ staffs = Staff.objects.all()
|
|
|
+ for s in staffs:
|
|
|
+ s.total_units = 0
|
|
|
+ s.name_mentioned = 0
|
|
|
+ s.save()
|
|
|
+
|
|
|
+
|
|
|
+def extract_names_from_reviews(reviews):
|
|
|
+ for review in reviews:
|
|
|
+ add_point_to_staff_profile(review)
|