Update app.py

app.py

@@ -129,6 +129,70 @@ 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("Candidate profile 2", divider = "green")
+txt = st.text_area("Job description", key = "text 2")
+job = pd.Series(txt, name="Text")
+st.dataframe(job)
+
+if 'upload_count' not in st.session_state:
+    st.session_state['upload_count'] = 0
+
+max_attempts = 2
+
+if st.session_state['upload_count'] < max_attempts:
+    uploaded_files = st.file_uploader(
+        "Choose a PDF file", accept_multiple_files=True, type="pdf", key="candidate_upload"
+    )
+    if uploaded_files:
+        st.session_state['upload_count'] += 1
+        for uploaded_file in uploaded_files:
+            pdf_reader = PdfReader(uploaded_file)
+            text_data = ""
+            for page in pdf_reader.pages:
+                text_data += page.extract_text()
+                data = pd.Series(text_data, name = 'Text')
+                st.dataframe(data)
+                frames = [job, data]
+                result = pd.concat(frames)
+                st.dataframe(result)
+                model = GLiNER.from_pretrained("urchade/gliner_base")
+                labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
+                entities = model.predict_entities(text_data, labels)
+                df = pd.DataFrame(entities)
+                st.dataframe(entities)
+                st.dataframe(df)
+                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 = "fig1")
+                vectorizer = TfidfVectorizer()
+                tfidf_matrix = vectorizer.fit_transform(result)
+                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("A score closer to 1 means closer match")
+        
+                fig = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Cosine similarity", y="Text", color="Productivity"),
+                        x=['text1', 'Jon Description'],
+                        y=['text1', 'Job Description'])
+                st.plotly_chart(fig)
+
+                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}")
+
+else:
+    st.warning(f"You have reached the maximum upload attempts ({max_attempts}). Please refresh to upload more files.")
+
+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).")