Update app.py

app.py

@@ -39,11 +39,11 @@ with st.sidebar:
     
 ''')
 
-st.subheader ("Candidate Profile 1", 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("Candidate Profile 1", divider="red")
+txt = st.text_area("Paste the job description and then press Ctrl + Enter", key="text 1")
+job = pd.Series(txt, name="Text")
 
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
@@ -54,68 +54,59 @@ 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"
     )
-
-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", divider = "green")
-        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)
-       
-            
-        
-        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", divider = "green")
-        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)
-
-        
-        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.info("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.")
-
+    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 = pipeline("ner", model="urchade/gliner_base", aggregation_strategy="simple")
+            labels = ["person", "country", "organization", "date", "time", "role", "skills", "year"]
+            entities = model(text_data, labels=labels)
+            df = pd.DataFrame(entities)
+
+            st.subheader("Profile of candidate 1", divider="green")
+            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", divider="green")
+            fig2 = px.imshow(cosine_sim_df, text_auto=True,
+                            labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
+                            x=['Resume 1', 'Job Description'],
+                            y=['Resume 1', 'Job Description'])
+            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.info("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.")
 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).")
     
-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 1", divider = "red")
 
 
 
+st.subheader("Candidate Profile 2", divider="red")
+txt = st.text_area("Paste the job description and then press Ctrl + Enter", key="text 1")
+job = pd.Series(txt, name="Text")
 
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
@@ -124,69 +115,50 @@ max_attempts = 3
 
 if st.session_state['upload_count'] < max_attempts:
     uploaded_files = st.file_uploader(
-        "Upload your resume", accept_multiple_files=True, type="pdf", key="candidate 2"
+        "Upload your resume", accept_multiple_files=True, 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")
-        fig3 = 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)
-       
-            
-        
-        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")
-        fig4 = 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(fig4)
-
-        
-        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.info("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.")
-
+    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 = pipeline("ner", model="urchade/gliner_base", aggregation_strategy="simple")
+            labels = ["person", "country", "organization", "date", "time", "role", "skills", "year"]
+            entities = model(text_data, labels=labels)
+            df = pd.DataFrame(entities)
+
+            st.subheader("Profile of candidate 1", divider="green")
+            fig3 = 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)
+
+            st.subheader("Measuring similarity between keywords of candidate profile 1 and job description", divider="green")
+            fig4 = px.imshow(cosine_sim_df, text_auto=True,
+                            labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
+                            x=['Resume 1', 'Job Description'],
+                            y=['Resume 1', 'Job Description'])
+            st.plotly_chart(fig4, key = "Figure 4")
+
+            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.info("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.")
 else:
-    st.warning(f"You have reached the maximum URL 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.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).")