Update app.py

app.py

@@ -51,8 +51,8 @@ if 'applicant_data' not in st.session_state:
 
 max_attempts = 20
 
-for i in range(1, 11):  # Looping for 2 applicants
-    st.subheader(f"Applicant Resume {i}", divider="green")
+for i in range(1, 51):  # Looping for 2 applicants
+    st.subheader(f"Applicant {i} Resume", divider="green")
     applicant_key = f"applicant_{i}"
     upload_key = f"candidate_{i}"
 
@@ -83,9 +83,9 @@ for i in range(1, 11):  # Looping for 2 applicants
             tfidf_matrix = vectorizer.fit_transform(result)
             cosine_sim_matrix = cosine_similarity(tfidf_matrix)
 
-            st.subheader(f"Similarity Analysis for Applicant {i}")
+            
             for j, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
-                with st.popover("See result"):
+                with st.popover(f"See Result for Applicant {i}"):
                     st.write(f"Similarity between Applicant's resume and job description based on keywords: {similarity_score:.2f}")
                     st.info(
                         f"A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's {i} resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's {i} resume and job description.")
@@ -100,6 +100,63 @@ for i in range(1, 11):  # Looping for 2 applicants
       
 
 
+st.divider()
+
+st.subheader("Visualise", 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
+        
+        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)
+            model = GLiNER.from_pretrained("urchade/gliner_base")
+            labels = ["person", "country", "organization", "role", "skills"]
+            entities = model.predict_entities(text_data, labels)
+            df = pd.DataFrame(entities)
+
+            tab1, tab2, tab3 = st.tabs(["Applicant's Profile", "Similarity"])
+            with tab1:
+                fig = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
+                             values='score', color='label')
+                fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
+                st.plotly_chart(fig, key="figure 1")
+
+                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)
+
+            with tab2:
+                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, key="figure 2")
+
+        
+                
+            
+            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 1 resume based on keywords: {similarity_score:.2f}")
+                st.info(
+                    "A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's 1 resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's 1 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).")