Update app.py

app.py

@@ -43,6 +43,34 @@ for uploaded_file in uploaded_files:
         result = pd.concat(frames)
         st.dataframe(result)
 
+import re
+def preprocess_text(text):
+    text = text.lower()  # Lowercase text
+    text = re.sub(f"[{re.escape(string.punctuation)}]", "", text)  # Remove punctuation
+    text = " ".join(text.split())  # Remove extra spaces, tabs, and new lines
+   
+    return text
+
+result['Text']= result["Text"].map(preprocess_text)
+st.dataframe(result['Text'])
+
+vectorizer = TfidfVectorizer()
+tfidf_matrix = vectorizer.fit_transform(result['Text'])
+
+tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+st.subheader("TF-IDF Values:")
+st.dataframe(tfidf_df)
+
+cosine_sim_matrix = cosine_similarity(tfidf_matrix)
+cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
+st.subheader("Cosine Similarity Matrix:")
+st.dataframe(cosine_sim_df)
+
+        
+st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
+for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
+    st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
+
     
 st.divider()