Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import streamlit as st
 from PyPDF2 import PdfReader
 import pandas as pd
@@ -50,12 +49,12 @@ job = pd.Series(txt, name="Text")
 st.subheader("Candidate Profile 1", divider = "red")
 
 
-if 'upload_count_cand1' not in st.session_state:
-    st.session_state['upload_count_cand1'] = 0
+if 'upload_count' not in st.session_state:
+    st.session_state['upload_count'] = 0
 
-max_attempts_cand1 = 1
+max_attempts = 3
 
-if st.session_state['upload_count_cand1'] < max_attempts_cand1:
+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"
     )
@@ -84,7 +83,7 @@ for uploaded_file in uploaded_files:
         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 = "tv")
+        st.plotly_chart(fig, key = "figure 1")
         
        
             
@@ -102,7 +101,7 @@ for uploaded_file in uploaded_files:
         fig = 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(fig, key = "bar")
+        st.plotly_chart(fig, key = "figure 2")
         
 
         
@@ -111,81 +110,17 @@ for uploaded_file in uploaded_files:
             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_cand1}).")
+    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_cand1']} time(s).")
-
-
-
+        st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
 
 
-st.subheader ("Candidate Profile 2", divider = "green")
 
 
 
-if 'upload_count_cand2' not in st.session_state:
-    st.session_state['upload_count_cand2'] = 0
-
-max_attempts_cand2 = 3
-
-if st.session_state['upload_count_cand2'] < max_attempts_cand2:
-    uploaded_files = st.file_uploader(
-        "Upload your resume in .pdf format", 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')
-        
-        
-        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)
         
 
-        
-        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 = "iris")
-        
-       
-            
-        
-        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 = 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(fig, key = "radio")
-        
-
-        
-        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}")
-
-else:
-    st.warning(f"You have reached the maximum URL attempts ({max_attempts_cand2}).")
-    if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
-        st.info(f"Files uploaded {st.session_state['upload_count_cand2']} time(s).")
 
 # fix else: warning
 # fix, keys