Update app.py

app.py

@@ -47,7 +47,7 @@ st.subheader("Job Description", divider="red")
 txt = st.text_area("Paste the job description and then press Ctrl + Enter", key="text 1")
 job = pd.Series(txt, name="Text")
 
-st.subheader("Applicant Profile 1", divider="green")
+st.subheader("Applicant Resume 1", divider="green")
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
 
@@ -86,11 +86,79 @@ else:
 
 
 
+st.subheader("Applicant Resume 2", divider="green")
+if 'upload_count' not in st.session_state:
+    st.session_state['upload_count'] = 0
 
+max_attempts = 3
+if st.session_state['upload_count'] < max_attempts:
+    uploaded_files = st.file_uploader("Upload Applicant's 2 resume", type="pdf", key="candidate 2")
+    if uploaded_files:
+        st.session_state['upload_count'] += 1
+        
+        pdf_reader = PdfReader(uploaded_files)
+        text_data = ""
+        for page in pdf_reader.pages:
+            text_data += page.extract_text()
+            st.text_area("Applicant's 2 resume", value = text_data, height = 300, key = "text 2")
+            data = pd.Series(text_data, name='Text')
+            frames = [job, data]
+            result = pd.concat(frames)
+            
+
+            vectorizer = TfidfVectorizer()
+            tfidf_matrix = vectorizer.fit_transform(result)
+            tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+            cosine_sim_matrix = cosine_similarity(tfidf_matrix)
+            cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
+
+            for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
+                with st.popover("See result"):
+                    st.write(f"Similarity of job description with Applicant's 2 resume based on keywords: {similarity_score:.2f}")
+                st.info(
+                    "A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's 2 resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's 2 resume and job description.")
+else:
+    st.warning(f"You have reached the maximum upload attempts ({max_attempts}).")
+    if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
+        st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
         
 
 
+st.subheader("Applicant Resume 3", divider="green")
+if 'upload_count' not in st.session_state:
+    st.session_state['upload_count'] = 0
 
+max_attempts = 3
+if st.session_state['upload_count'] < max_attempts:
+    uploaded_files = st.file_uploader("Upload Applicant's 3 resume", type="pdf", key="candidate 3")
+    if uploaded_files:
+        st.session_state['upload_count'] += 1
+        
+        pdf_reader = PdfReader(uploaded_files)
+        text_data = ""
+        for page in pdf_reader.pages:
+            text_data += page.extract_text()
+            st.text_area("Applicant's 3 resume", value = text_data, height = 300, key = "text 2")
+            data = pd.Series(text_data, name='Text')
+            frames = [job, data]
+            result = pd.concat(frames)
+            
+
+            vectorizer = TfidfVectorizer()
+            tfidf_matrix = vectorizer.fit_transform(result)
+            tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+            cosine_sim_matrix = cosine_similarity(tfidf_matrix)
+            cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
+
+            for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
+                with st.popover("See result"):
+                    st.write(f"Similarity of job description with Applicant's 3 resume based on keywords: {similarity_score:.2f}")
+                st.info(
+                    "A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's 3 resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's 3 resume and job description.")
+else:
+    st.warning(f"You have reached the maximum upload attempts ({max_attempts}).")
+    if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
+        st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")