Update app.py

app.py

@@ -39,150 +39,128 @@ with st.sidebar:
     
 ''')
 
-st.subheader ("Candidate Profile 1", divider = "green")
 
-txt = st.text_area("Paste the job description and then press Ctrl + Enter", key = "text 1")
+st.subheader("Candidate Profile 1", divider = "green")
+             
+txt = st.text_area("Job description", key = "text 1")
 job = pd.Series(txt, name="Text")
 
 
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
 
-max_attempts = 3
+max_attempts = 2
 
 if st.session_state['upload_count'] < max_attempts:
     uploaded_files = st.file_uploader(
-        "Upload your resume", accept_multiple_files=True, type="pdf", key="candidate 1"
+        "Upload your resume in .pdf format", type="pdf", key="candidate 1"
     )
-
-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')
-        
-        
-        frames = [job, data]
-        result = pd.concat(frames)
-        
-
-        model = GLiNER.from_pretrained("urchade/gliner_base")
-        labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
-        entities = model.predict_entities(text_data, labels)
-        df = pd.DataFrame(entities)
-        
-
-        st.subheader("Profile of candidate 1")
-        fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
+    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')
+                frames = [job, data]
+                result = pd.concat(frames)
+                
+                
+                model = GLiNER.from_pretrained("urchade/gliner_base")
+                labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
+                entities = model.predict_entities(text_data, labels)
+                df = pd.DataFrame(entities)
+                
+                
+                fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
                 values='score', color='label')
-        fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
-        st.plotly_chart(fig1, 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)
-        
-
-        
-        st.subheader("Measuring similarity between keywords of candidate profile 1 and job description")
-        fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
+                fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
+                st.plotly_chart(fig1, 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)
+                
+        
+                fig2 = 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(fig2, key = "figure 2")
+                st.plotly_chart(fig2, key = "figure 2")
 
-        
-        for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
-            st.write(f"Similarity of job description with candidate profile 1. {i + 1}: {similarity_score:.4f}")
-            st.write("A score closer to 1 (0.80, 0.90) means higher similarity between candidate profile 1 and job description. A score closer to 0 (0.20, 0.30) means lower similarity between candidate profile 1 and job description.")
+                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 URL attempts ({max_attempts}).")
-    
+    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 ("Candidate Profile 2", divider = "green")
-
-
-
+    
+               
+st.subheader("Candidate Profile 2", divider = "green")
+             
+txt = st.text_area("Job description", key = "text 2")
+job = pd.Series(txt, name="Text")
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
-
-max_attempts = 3
-
+max_attempts = 2
 if st.session_state['upload_count'] < max_attempts:
     uploaded_files = st.file_uploader(
-        "Upload your resume in .pdf format", accept_multiple_files=True, type="pdf", key="candidate 2"
+        "Upload your resume in .pdf format", type="pdf", key="candidate 2"
     )
-
-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')
-        
-        
-        frames = [job, data]
-        result = pd.concat(frames)
-        
-
-        model = GLiNER.from_pretrained("urchade/gliner_base")
-        labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
-        entities = model.predict_entities(text_data, labels)
-        df = pd.DataFrame(entities)
-        
-
-        
-        fig3 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
+    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')
+                frames = [job, data]
+                result = pd.concat(frames)
+                
+                
+                model = GLiNER.from_pretrained("urchade/gliner_base")
+                labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
+                entities = model.predict_entities(text_data, labels)
+                df = pd.DataFrame(entities)
+                
+                
+                fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
                 values='score', color='label')
-        fig3.update_layout(margin = dict(t=50, l=25, r=25, b=25))
-        st.plotly_chart(fig3, key = "figure 3")
-       
-            
-        
-        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)
-        
-
-        
-        
-        fig4 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
-                        x=['Resume 2', 'Jon Description'],
-                        y=['Resume 2', 'Job Description'])
-        st.plotly_chart(fig4, key = "figure 4")
-
-        
-        for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
-            st.write(f"Similarity with Candidate Profile. A score closer to 1 means higher similarity. {i + 1}: {similarity_score:.4f}")
-
+                fig1.update_layout(margin = dict(t=50, l=25, r=25, b=25))
+                st.plotly_chart(fig1, key = "figure 3")
+                
+                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)
+                
+        
+                fig2 = 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(fig2, key = "figure 4")
+                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 URL attempts ({max_attempts}).")
-    
+    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).")
 
 
 
 
+