Update app.py

app.py

@@ -34,36 +34,16 @@ uploaded_files = st.file_uploader(
 )
 
 
-all_resumes_text = []  # Store the text content of each PDF
 for uploaded_file in uploaded_files:
     pdf_reader = PdfReader(uploaded_file)
     text_data = ""
     for page in pdf_reader.pages:
         text_data += page.extract_text()
-        all_resumes_text.append(text_data)
+        st.write(text_data)
+        
         
 
-    if all_resumes_text:
-        all_documents = [job_description_series.iloc[0]] + all_resumes_text
-
-        vectorizer = TfidfVectorizer()
-        tfidf_matrix = vectorizer.fit_transform(all_documents)
-
-        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)
-
-        # Display similarity scores between the job description and each resume
-        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()
 
@@ -76,7 +56,7 @@ uploaded_files = st.file_uploader(
 )
 
 
-all_resumes_text = []  # Store the text content of each PDF
+
 
 
 for uploaded_file in uploaded_files:
@@ -84,29 +64,10 @@ for uploaded_file in uploaded_files:
     text_data = ""
     for page in pdf_reader.pages:
         text_data += page.extract_text()
-        all_resumes_text.append(text_data)
+        st.write(text_data)
         
 
-    if all_resumes_text:
-        all_documents = [job_description_series.iloc[0]] + all_resumes_text
-
-        vectorizer = TfidfVectorizer()
-        tfidf_matrix = vectorizer.fit_transform(all_documents)
-
-        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)
-
-        # Display similarity scores between the job description and each resume
-        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}")
-
+