Update app.py

app.py

@@ -40,11 +40,11 @@ with st.sidebar:
 ''')
 
 
-st.subheader("Candidate Profile 1", divider = "green")
+
              
 txt = st.text_area("Job description", key = "text 1")
 job = pd.Series(txt, name="Text")
-
+st.dataframe(job)
 
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
@@ -53,552 +53,67 @@ max_attempts = 2
 
 if st.session_state['upload_count'] < max_attempts:
     uploaded_files = st.file_uploader(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 1"
+        "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')
-                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)
-                
-        
-                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.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})")
 
-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")
-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(
-        "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)
-                
-                
-                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 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)
-                
+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)
         
-                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 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 3", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 3")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 3"
-    )
-    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'],
+        frames = [job, data]
+        result = pd.concat(frames)
+        st.dataframe(result)
+
+        model = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0")
+        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)
+
+        import plotly.express as px
+        fig = 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 5")
-                
-                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.update_layout(margin = dict(t=50, l=25, r=25, b=25))
+        st.plotly_chart(fig)
+       
+            
         
-                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 6")
-                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})")
-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 4", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 4")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 4"
-    )
-    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 7")
-                
-                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)
-                
+        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)
         
-                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 8")
-                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})")
-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).")
-    
-               
-
-
+        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("Candidate Profile 5", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 5")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 5"
-    )
-    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 9")
-                
-                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)
-                
+        import plotly.express as px
+        st.subheader("A score closer to 1 means closer match")
         
-                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 10")
-                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})")
-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).")
-    
-               
+        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("Candidate Profile 6", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 6")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 6"
-    )
-    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 11")
-                
-                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 12")
-                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})")
-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("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}")
 
-st.subheader("Candidate Profile 7", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 7")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 7"
-    )
-    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 13")
-                
-                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 14")
-                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})")
-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 URL attempts ({max_attempts}).")
     
-
-
-st.subheader("Candidate Profile 8", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 8")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 8"
-    )
-    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 16")
-                
-                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 18")
-                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})")
 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 9", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 9")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 9"
-    )
-    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 17")
-                
-                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 18")
-                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})")
-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 10", divider = "green")
-             
-txt = st.text_area("Job description", key = "text 10")
-job = pd.Series(txt, name="Text")
-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(
-        "Upload your resume in .pdf format", type="pdf", key="candidate 10"
-    )
-    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 19")
                 
-                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 20")
-                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})")
-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).")
-