Update app.py

app.py

@@ -1,6 +1,16 @@
 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 stop words if not already available
+nltk.download("stopwords")
+nltk.download("punkt")
+
+# Load English stop words
+stop_words = set(stopwords.words("english"))
 
 @st.cache_resource
 def load_model():
@@ -8,38 +18,80 @@ 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
+    
+    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
+                
+    return (match_count / total_keywords) * 100 if total_keywords > 0 else 0
+
 def keyword_match(job_desc, resume):
-    job_keywords = set(re.findall(r'\b\w+\b', job_desc.lower()))
-    resume_keywords = set(re.findall(r'\b\w+\b', resume.lower()))
+    job_keywords = set(re.findall(r'\b\w+\b', job_desc))
+    resume_keywords = set(re.findall(r'\b\w+\b', resume))
     common_keywords = job_keywords.intersection(resume_keywords)
-    match_ratio = len(common_keywords) / len(job_keywords) * 100
-    return match_ratio
+    return (len(common_keywords) / len(job_keywords)) * 100 if job_keywords else 0
 
-st.title("Enhanced Resume and Job Description Similarity Checker")
+st.title("Advanced Resume and Job Description Similarity Checker")
 
 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():
-        job_description_embedding = model.encode(job_description)
-        resume_embedding = model.encode(resume_text)
+        # 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)
         similarity_score = util.cos_sim(job_description_embedding, resume_embedding).item() * 100
-        keyword_score = keyword_match(job_description, resume_text)
+
+        # Calculate keyword-based similarity
+        keyword_score = keyword_match(processed_job_desc, processed_resume)
+
+        # Calculate synonym-based similarity
+        synonym_score = synonym_match(processed_job_desc, processed_resume)
         
-        # Combine scores (weighted or simple average)
-        overall_score = (similarity_score * 0.7) + (keyword_score * 0.3)
+        # Combine scores (adjusting weights as needed)
+        overall_score = (similarity_score * 0.5) + (keyword_score * 0.3) + (synonym_score * 0.2)
         
-        st.write(f"**Similarity Score:** {overall_score:.2f}%")
+        st.write(f"**Overall Similarity Score:** {overall_score:.2f}%")
         
-        # Adjusted feedback
-        if overall_score > 70:
-            st.success("Great match! Your resume aligns well with the job description.")
+        # Adjusted feedback 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.info("Good match! Your resume has relevant information, but it could be tailored a bit more.")
-        elif overall_score > 30:
-            st.warning("Partial match. Your resume shows some alignment, but consider emphasizing relevant skills and experiences.")
+            st.warning("Moderate match. Your resume has some relevant information, but consider emphasizing key skills.")
+        elif overall_score > 35:
+            st.error("Low match. Your resume does not align well. Consider revising to highlight key skills.")
         else:
-            st.error("Low match. Consider revising your resume to better reflect the job requirements.")
+            st.error("Very low match. Your resume is significantly different from the job description. Major revisions may be needed.")
     else:
         st.error("Please paste both the job description and your resume to proceed.")