Update app.py

app.py

@@ -1,36 +1,16 @@
-import streamlit as st
-from PyPDF2 import PdfReader
-import pandas as pd
-from sklearn.feature_extraction.text import TfidfVectorizer
-
-from sklearn.metrics.pairwise import cosine_similarity
-
 import streamlit as st
 from PyPDF2 import PdfReader
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from gliner import GLiNER
-
-
-import streamlit as st
-import pandas as pd
-from PyPDF2 import PdfReader
-from gliner import GLiNER
-
-import streamlit as st
-import pandas as pd
-from PyPDF2 import PdfReader
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
-import tempfile
-
 import plotly.express as px
+
 with st.sidebar:
     st.button("DEMO APP", type="primary")
    
 
-    expander = st.expander("**Important notes on the YouTube Comments Sentiment Analysis App**")
+    expander = st.expander("**Important notes on the AI Resume Analysis based on Keywords App**")
     expander.write('''
     
     
@@ -38,16 +18,13 @@ with st.sidebar:
     This app accepts files in .pdf formats.
     
     **How to Use**
-    Upload your file first. Then, click the 'Results' button.
+    Paste the job description first. Then, upload your resume to retrieve the results. You can upload up to 10 resumes in total.
     
     **Usage Limits**
-    You can request results up to 5 times. 
+    You can request results up to 10 times in total.
     
      **Subscription Management**
-    This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own Named Entity Recognition (NER) Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at [email protected]
-    
-    **Authorization**
-    For security purposes, your authorization access expires hourly. To restore access, click the "Request Authorization" button. 
+    This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own AI Resume Analysis based on Keywords Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at [email protected]
     
     **Customization**
     To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
@@ -63,19 +40,20 @@ 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
 
-max_attempts = 20
+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 1"
+        "Upload your resume in .pdf format", type="pdf", key="candidate 1"
     )
     if uploaded_files:
         st.session_state['upload_count'] += 1
@@ -85,37 +63,31 @@ if st.session_state['upload_count'] < max_attempts:
             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","organization", "date", "time", "role", "skills", "year"]
                 entities = model.predict_entities(text_data, labels)
                 df = pd.DataFrame(entities)
-                st.dataframe(entities)
-                st.dataframe(df)
+                
+                
                 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())
-                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")
+                
         
-                fig2 = 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'])
+                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):")
@@ -123,77 +95,15 @@ if st.session_state['upload_count'] < max_attempts:
                     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.")
+    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")
-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 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')
-                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)
-                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())
-                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")
-        
-                fig4 = 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(fig4, 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}). 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).")
+    
+