Resume-Screening/app.py at main · Udayan-Singh/Resume-Screening · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
import nltk
import pickle
import re
import streamlit as st
from sklearn.feature_extraction.text import TfidfVectorizer

tfidf = TfidfVectorizer(stop_words='english')

nltk.download('punkt')
nltk.download('stopwords')


clf = pickle.load(open('knn.pkl','rb'))
tfidf = pickle.load(open('tfidf.pkl','rb'))

# WEB APP
def cleanResume(txt):
    cleanText = re.sub(r'http\S+\s', ' ', txt)
    cleanText = re.sub(r'RT|cc', ' ', cleanText)
    cleanText = re.sub(r'#\S+\s', ' ', cleanText)
    cleanText = re.sub(r'@\S+', '  ', cleanText)
    cleanText = re.sub(r'[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', cleanText)
    cleanText = re.sub(r'[^\x00-\x7f]', ' ', cleanText)
    cleanText = re.sub(r'\s+', ' ', cleanText)
    return cleanText

def main():
    st.title("Resume Screening App")
    upload_file = st.file_uploader('Upload your resume',type=['txt','pdf'])

    if upload_file is not None:
        try:
            resume_bytes = upload_file.read()
            resume_text = resume_bytes.decode('utf-8')
        except UnicodeDecodeError:
            resume_text = resume_bytes.decode('latin-1')


        cleaned_resume = cleanResume(resume_text)
        tfidf_resume = tfidf.transform([cleaned_resume])
        prediction_id = clf.predict(tfidf_resume)[0]


        category_mapping = {
            15: "Java Developer",
            23: "Testing",
            8: "DevOps Engineer",
            20: "Python Developer",
            24: "Web Designing",
            12: "HR",
            13: "Hadoop",
            3: "Blockchain",
            10: "ETL Developer",
            18: "Operations Manager",
            6: "Data Science",
            22: "Sales",
            16: "Mechanical Engineer",
            1: "Arts",
            7: "Database",
            11: "Electrical Engineering",
            14: "Health and fitness",
            19: "PMO",
            4: "Business Analyst",
            9: "DotNet Developer",
            2: "Automation Testing",
            17: "Network Security Engineer",
            21: "SAP Developer",
            5: "Civil Engineer",
            0: "Advocate",
        }

        category_name = category_mapping.get(prediction_id, "Unknown")
        st.write("Predicted Category: ", category_name)


if __name__ == "__main__":
    main()