Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,6 +1,16 @@
|
|
1 |
import streamlit as st
|
2 |
from sentence_transformers import SentenceTransformer, util
|
3 |
import re
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
5 |
@st.cache_resource
|
6 |
def load_model():
|
@@ -8,38 +18,80 @@ def load_model():
|
|
8 |
|
9 |
model = load_model()
|
10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
def keyword_match(job_desc, resume):
|
12 |
-
job_keywords = set(re.findall(r'\b\w+\b', job_desc
|
13 |
-
resume_keywords = set(re.findall(r'\b\w+\b', resume
|
14 |
common_keywords = job_keywords.intersection(resume_keywords)
|
15 |
-
|
16 |
-
return match_ratio
|
17 |
|
18 |
-
st.title("
|
19 |
|
20 |
job_description = st.text_area("Paste the job description here:", height=200)
|
21 |
resume_text = st.text_area("Paste your resume here:", height=200)
|
22 |
|
23 |
if st.button("Compare"):
|
24 |
if job_description.strip() and resume_text.strip():
|
25 |
-
|
26 |
-
|
|
|
|
|
|
|
|
|
|
|
27 |
similarity_score = util.cos_sim(job_description_embedding, resume_embedding).item() * 100
|
28 |
-
|
|
|
|
|
|
|
|
|
|
|
29 |
|
30 |
-
# Combine scores (
|
31 |
-
overall_score = (similarity_score * 0.
|
32 |
|
33 |
-
st.write(f"**Similarity Score:** {overall_score:.2f}%")
|
34 |
|
35 |
-
# Adjusted feedback
|
36 |
-
if overall_score >
|
37 |
-
st.success("
|
|
|
|
|
38 |
elif overall_score > 50:
|
39 |
-
st.
|
40 |
-
elif overall_score >
|
41 |
-
st.
|
42 |
else:
|
43 |
-
st.error("
|
44 |
else:
|
45 |
st.error("Please paste both the job description and your resume to proceed.")
|
|
|
1 |
import streamlit as st
|
2 |
from sentence_transformers import SentenceTransformer, util
|
3 |
import re
|
4 |
+
import nltk
|
5 |
+
from nltk.corpus import stopwords
|
6 |
+
from nltk.tokenize import word_tokenize
|
7 |
+
|
8 |
+
# Download stop words if not already available
|
9 |
+
nltk.download("stopwords")
|
10 |
+
nltk.download("punkt")
|
11 |
+
|
12 |
+
# Load English stop words
|
13 |
+
stop_words = set(stopwords.words("english"))
|
14 |
|
15 |
@st.cache_resource
|
16 |
def load_model():
|
|
|
18 |
|
19 |
model = load_model()
|
20 |
|
21 |
+
# Synonym dictionary for common terms
|
22 |
+
synonyms = {
|
23 |
+
"data analysis": {"data analytics", "data analyst"},
|
24 |
+
"machine learning": {"ml", "artificial intelligence", "ai"},
|
25 |
+
"programming": {"coding", "development", "software engineering"},
|
26 |
+
"statistical analysis": {"statistics", "statistical modeling"},
|
27 |
+
"visualization": {"data viz", "tableau", "visualizing data"}
|
28 |
+
}
|
29 |
+
|
30 |
+
def preprocess(text):
|
31 |
+
# Tokenize, remove stop words, and normalize text
|
32 |
+
words = word_tokenize(text.lower())
|
33 |
+
filtered_words = [word for word in words if word.isalnum() and word not in stop_words]
|
34 |
+
normalized_text = " ".join(filtered_words)
|
35 |
+
return normalized_text
|
36 |
+
|
37 |
+
def synonym_match(job_desc, resume):
|
38 |
+
match_count = 0
|
39 |
+
total_keywords = 0
|
40 |
+
|
41 |
+
for key, variants in synonyms.items():
|
42 |
+
job_contains = any(term in job_desc for term in variants) or key in job_desc
|
43 |
+
resume_contains = any(term in resume for term in variants) or key in resume
|
44 |
+
|
45 |
+
if job_contains:
|
46 |
+
total_keywords += 1
|
47 |
+
if resume_contains:
|
48 |
+
match_count += 1
|
49 |
+
|
50 |
+
return (match_count / total_keywords) * 100 if total_keywords > 0 else 0
|
51 |
+
|
52 |
def keyword_match(job_desc, resume):
|
53 |
+
job_keywords = set(re.findall(r'\b\w+\b', job_desc))
|
54 |
+
resume_keywords = set(re.findall(r'\b\w+\b', resume))
|
55 |
common_keywords = job_keywords.intersection(resume_keywords)
|
56 |
+
return (len(common_keywords) / len(job_keywords)) * 100 if job_keywords else 0
|
|
|
57 |
|
58 |
+
st.title("Advanced Resume and Job Description Similarity Checker")
|
59 |
|
60 |
job_description = st.text_area("Paste the job description here:", height=200)
|
61 |
resume_text = st.text_area("Paste your resume here:", height=200)
|
62 |
|
63 |
if st.button("Compare"):
|
64 |
if job_description.strip() and resume_text.strip():
|
65 |
+
# Preprocess text
|
66 |
+
processed_job_desc = preprocess(job_description)
|
67 |
+
processed_resume = preprocess(resume_text)
|
68 |
+
|
69 |
+
# Calculate embeddings-based similarity
|
70 |
+
job_description_embedding = model.encode(processed_job_desc)
|
71 |
+
resume_embedding = model.encode(processed_resume)
|
72 |
similarity_score = util.cos_sim(job_description_embedding, resume_embedding).item() * 100
|
73 |
+
|
74 |
+
# Calculate keyword-based similarity
|
75 |
+
keyword_score = keyword_match(processed_job_desc, processed_resume)
|
76 |
+
|
77 |
+
# Calculate synonym-based similarity
|
78 |
+
synonym_score = synonym_match(processed_job_desc, processed_resume)
|
79 |
|
80 |
+
# Combine scores (adjusting weights as needed)
|
81 |
+
overall_score = (similarity_score * 0.5) + (keyword_score * 0.3) + (synonym_score * 0.2)
|
82 |
|
83 |
+
st.write(f"**Overall Similarity Score:** {overall_score:.2f}%")
|
84 |
|
85 |
+
# Adjusted feedback based on combined score
|
86 |
+
if overall_score > 80:
|
87 |
+
st.success("Excellent match! Your resume closely aligns with the job description.")
|
88 |
+
elif overall_score > 65:
|
89 |
+
st.info("Strong match! Your resume aligns well, but a few minor tweaks could help.")
|
90 |
elif overall_score > 50:
|
91 |
+
st.warning("Moderate match. Your resume has some relevant information, but consider emphasizing key skills.")
|
92 |
+
elif overall_score > 35:
|
93 |
+
st.error("Low match. Your resume does not align well. Consider revising to highlight key skills.")
|
94 |
else:
|
95 |
+
st.error("Very low match. Your resume is significantly different from the job description. Major revisions may be needed.")
|
96 |
else:
|
97 |
st.error("Please paste both the job description and your resume to proceed.")
|