Spaces:
Runtime error
Runtime error
abhibisht89
commited on
Commit
•
e5e34f2
1
Parent(s):
1f96c50
create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import spacy
|
2 |
+
import gradio as gr
|
3 |
+
from spacy.pipeline import EntityRuler
|
4 |
+
from spacy import displacy
|
5 |
+
import jsonlines
|
6 |
+
nlp = spacy.load('en_core_web_sm')
|
7 |
+
|
8 |
+
# Create list with entity labels from jsonl file
|
9 |
+
with jsonlines.open("skill_patterns.jsonl") as f:
|
10 |
+
created_entities = [line['label'].upper() for line in f.iter()]
|
11 |
+
|
12 |
+
def extract_text_from_word(txt):
|
13 |
+
'''Opens en reads in a .doc or .docx file from path'''
|
14 |
+
return txt.replace('\n', ' ').replace('\t', ' ').lower()
|
15 |
+
|
16 |
+
def add_newruler_to_pipeline(skill_pattern_path):
|
17 |
+
'''Reads in all created patterns from a JSONL file and adds it to the pipeline after PARSER and before NER'''
|
18 |
+
|
19 |
+
# new_ruler = EntityRuler(nlp).from_disk(skill_pattern_path)
|
20 |
+
ruler=nlp.add_pipe("entity_ruler",after='parser')
|
21 |
+
ruler.from_disk(skill_pattern_path) # loads patterns only
|
22 |
+
|
23 |
+
def create_skill_set(doc):
|
24 |
+
'''Create a set of the extracted skill entities of a doc'''
|
25 |
+
|
26 |
+
return set([ent.label_.upper()[6:] for ent in doc.ents if 'skill' in ent.label_.lower()])
|
27 |
+
|
28 |
+
def create_skillset_dict(resume_names, resume_texts):
|
29 |
+
'''Create a dictionary containing a set of the extracted skills. Name is key, matching skillset is value'''
|
30 |
+
skillsets = [create_skill_set(resume_text) for resume_text in resume_texts]
|
31 |
+
return dict(zip(resume_names, skillsets))
|
32 |
+
|
33 |
+
def match_skills(vacature_set, cv_set, resume_name):
|
34 |
+
'''Get intersection of resume skills and job offer skills and return match percentage'''
|
35 |
+
|
36 |
+
if len(vacature_set) < 1:
|
37 |
+
print('could not extract skills from job offer text')
|
38 |
+
else:
|
39 |
+
pct_match = round(len(vacature_set.intersection(cv_set[resume_name])) / len(vacature_set) * 100, 0)
|
40 |
+
print(resume_name + " has a {}% skill match on this job offer".format(pct_match))
|
41 |
+
print('Required skills: {} '.format(vacature_set))
|
42 |
+
print('Matched skills: {} \n'.format(vacature_set.intersection(skillset_dict[resume_name])))
|
43 |
+
|
44 |
+
return (resume_name, pct_match)
|
45 |
+
|
46 |
+
add_newruler_to_pipeline("skill_patterns.jsonl")
|
47 |
+
|
48 |
+
def match(CV,JD):
|
49 |
+
resume_texts=[]
|
50 |
+
resume_texts.append(nlp(CV))
|
51 |
+
resume_names=['ABHI']
|
52 |
+
skillset_dict = create_skillset_dict(resume_names, resume_texts)
|
53 |
+
jd_skillset = create_skill_set(nlp(JD))
|
54 |
+
match_pairs = [match_skills(jd_skillset, skillset_dict, name) for name in skillset_dict.keys()]
|
55 |
+
return match_pairs
|
56 |
+
|
57 |
+
exp=["Who is steve jobs?","What is coldplay?","What is a turing test?","What is the most interesting thing about our universe?","What are the most beautiful places on earth?"]
|
58 |
+
|
59 |
+
desc="This is a semantic search engine powered by SentenceTransformers (Nils_Reimers) with a retrieval and reranking system on Wikipedia corous. This will return the top 5 results. So Quest on with Transformers."
|
60 |
+
|
61 |
+
inp1=gr.inputs.Textbox(lines=10, placeholder=None, default="", label="CV")
|
62 |
+
inp2=gr.inputs.Textbox(lines=10, placeholder=None, default="", label="JD")
|
63 |
+
|
64 |
+
out=gr.outputs.Textbox(type="auto",label="search results")
|
65 |
+
|
66 |
+
iface = gr.Interface(fn=match, inputs=[inp1,inp2], outputs=[out],examples=[exp],article=desc,title="Neural Search Engine",theme="huggingface",layout='vertical')
|
67 |
+
iface.launch()
|