Update app.py

app.py

@@ -84,15 +84,6 @@ for i in range(1, 51):  # Looping for 2 applicants
             tfidf_matrix = vectorizer.fit_transform(result)
             cosine_sim_matrix = cosine_similarity(tfidf_matrix)
 
-            
-            
-            cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
-            fig = px.imshow(cosine_sim_df, text_auto=True,
-                            labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
-                            x=['Resume', 'Jon Description'],
-                            y=['Resume', 'Job Description'])
-            st.plotly_chart(fig)
-
 
             
             for j, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
@@ -113,7 +104,7 @@ for i in range(1, 51):  # Looping for 2 applicants
 
 st.divider()
 
-st.subheader("Visualise", divider="blue")
+st.subheader("Visualise Applicant's Profile", divider="blue")
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
 
@@ -142,9 +133,6 @@ if st.session_state['upload_count'] < max_attempts:
                 fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
                 st.plotly_chart(fig)
  
-             
-
-                
 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:
@@ -152,7 +140,46 @@ else:
 
 
 
-        
+st.divider()
+st.subheader("Visualise Similarity", divider="blue")
+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 resume", type="pdf")
+    if uploaded_files:
+        st.session_state['upload_count'] += 1
+
+        with st.spinner("Wait for it...", show_time=True):
+            time.sleep(2)
+            pdf_reader = PdfReader(uploaded_files)
+            text_data = ""
+            for page in pdf_reader.pages:
+                text_data += page.extract_text()
+            
+                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)
+
+            
+                fig = px.imshow(cosine_sim_df, text_auto=True,
+                            labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
+                            x=['Resume 1', 'Jon Description'],
+                            y=['Resume 1', 'Job Description'])
+                st.plotly_chart(fig, key="figure 2")
+
+ 
+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).")