Update app.py

app.py

@@ -1,16 +1,6 @@
 import streamlit as st
 from sentence_transformers import SentenceTransformer, util
 import re
-import nltk
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize
-
-# Download NLTK data files
-nltk.download("stopwords")
-nltk.download("punkt")
-
-# Load English stop words
-stop_words = set(stopwords.words("english"))
 
 @st.cache_resource
 def load_model():
@@ -18,87 +8,39 @@ def load_model():
 
 model = load_model()
 
-# Synonym dictionary for common terms
-synonyms = {
-    "data analysis": {"data analytics", "data analyst"},
-    "machine learning": {"ml", "artificial intelligence", "ai"},
-    "programming": {"coding", "development", "software engineering"},
-    "statistical analysis": {"statistics", "statistical modeling"},
-    "visualization": {"data viz", "tableau", "visualizing data"}
-}
-
-def preprocess(text):
-    # Tokenize, remove stop words, and normalize text
-    words = word_tokenize(text.lower())
-    filtered_words = [word for word in words if word.isalnum() and word not in stop_words]
-    normalized_text = " ".join(filtered_words)
-    return normalized_text
-
-def synonym_match(job_desc, resume):
-    match_count = 0
-    total_keywords = 0
-    matched_keywords = set()
-    missing_keywords = set()
-    
-    for key, variants in synonyms.items():
-        job_contains = any(term in job_desc for term in variants) or key in job_desc
-        resume_contains = any(term in resume for term in variants) or key in resume
-        
-        if job_contains:
-            total_keywords += 1
-            if resume_contains:
-                match_count += 1
-                matched_keywords.add(key)
-            else:
-                missing_keywords.add(key)
-                
-    return (match_count / total_keywords) * 100 if total_keywords > 0 else 0, list(matched_keywords)[:5], list(missing_keywords)[:5]
-
 def keyword_match(job_desc, resume):
-    job_keywords = set(re.findall(r'\b\w+\b', job_desc))
-    resume_keywords = set(re.findall(r'\b\w+\b', resume))
+    job_keywords = set(re.findall(r'\b\w+\b', job_desc.lower()))
+    resume_keywords = set(re.findall(r'\b\w+\b', resume.lower()))
     common_keywords = job_keywords.intersection(resume_keywords)
-    return (len(common_keywords) / len(job_keywords)) * 100 if job_keywords else 0, list(common_keywords)[:5]
+    return len(common_keywords) / len(job_keywords) * 100 if job_keywords else 0
 
-st.title("Resume and Job Description Similarity Checker")
+st.title("Enhanced Resume and Job Description Similarity Checker")
 
-job_description = st.text_area("Paste any job description here:", height=200)
+job_description = st.text_area("Paste the job description here:", height=200)
 resume_text = st.text_area("Paste your resume here:", height=200)
 
 if st.button("Compare"):
     if job_description.strip() and resume_text.strip():
-        # Preprocess text
-        processed_job_desc = preprocess(job_description)
-        processed_resume = preprocess(resume_text)
-
         # Calculate embeddings-based similarity
-        job_description_embedding = model.encode(processed_job_desc)
-        resume_embedding = model.encode(processed_resume)
+        job_description_embedding = model.encode(job_description)
+        resume_embedding = model.encode(resume_text)
         similarity_score = util.cos_sim(job_description_embedding, resume_embedding).item() * 100
 
-        # Calculate keyword-based similarity and matched keywords
-        keyword_score, matched_keywords = keyword_match(processed_job_desc, processed_resume)
-
-        # Calculate synonym-based similarity and missing skills
-        synonym_score, synonym_matches, synonym_misses = synonym_match(processed_job_desc, processed_resume)
+        # Calculate keyword-based similarity
+        keyword_score = keyword_match(job_description, resume_text)
         
-        # Combine scores (adjusting weights as needed)
-        overall_score = (similarity_score * 0.5) + (keyword_score * 0.3) + (synonym_score * 0.2)
+        # Combine scores (you could adjust the weights as needed)
+        overall_score = (similarity_score * 0.6) + (keyword_score * 0.4)
         
-        # Display the overall similarity score
-        st.write(f"**Overall Similarity Score:** {overall_score:.2f}%")
+        st.write(f"**Similarity Score:** {overall_score:.2f}%")
         
-        # Display matched keywords and missing skills
-        st.write("**Matched Keywords:**", ", ".join(matched_keywords + synonym_matches)[:5])
-        st.write("**Missing Skills to Consider Adding:**", ", ".join(synonym_misses)[:5])
-
-        # Adjusted feedback based on combined score
+        # Adjusted grading scale based on combined score
         if overall_score > 80:
             st.success("Excellent match! Your resume closely aligns with the job description.")
         elif overall_score > 65:
             st.info("Strong match! Your resume aligns well, but a few minor tweaks could help.")
         elif overall_score > 50:
-            st.warning("Moderate match. Your resume has some relevant information, but consider emphasizing key skills.")
+            st.warning("Moderate match. Your resume has some relevant information, but consider emphasizing relevant skills.")
         elif overall_score > 35:
             st.error("Low match. Your resume does not align well. Consider revising to highlight key skills.")
         else: