Update app.py

app.py

@@ -63,110 +63,83 @@ with st.sidebar:
 
 
 
-st.subheader("AI Resume Analysis based on keywords", divider="red")
-
-
+import streamlit as st
+import pandas as pd
+from pypdf import PdfReader
+from transformers import pipeline
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import plotly.express as px
 
-txt = st.text_area("Job description", key = "text 1")
+txt = st.text_area("Job description", key="text 1")
 job = pd.Series(txt, name="Text")
 st.dataframe(job)
 
-if 'uploaded_files' not in st.session_state:
-    st.session_state['url_count'] = 0
+if 'upload_count' not in st.session_state:
+    st.session_state['upload_count'] = 0
 
 max_attempts = 5
 
-uploaded_files = st.file_uploader(
-    "Choose a CSV file", accept_multiple_files=True, type = "pdf", key = "candidate 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("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)
+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_upload"
+    )
+
+    if uploaded_files:
+        st.session_state['upload_count'] += 1
+        all_resumes_text = []
+        for uploaded_file in uploaded_files:
+            pdf_reader = PdfReader(uploaded_file)
+            text_data = ""
+            for page in pdf_reader.pages:
+                text_data += page.extract_text()
+            all_resumes_text.append(text_data)
+            data = pd.Series(text_data, name='Text')
+            st.dataframe(data)
+
+            frames = [job, data]
+            result = pd.concat(frames)
+            st.dataframe(result)
+
+            model = pipeline("ner", model="xomad/gliner-model-merge-large-v1.0", aggregation_strategy="simple")
+            labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
+            entities = model(text_data, labels=labels)
+            df_entities = pd.DataFrame(entities)
+            st.subheader("Extracted Entities:")
+            st.dataframe(df_entities)
+
+            fig = px.treemap(df_entities, path=[px.Constant("all"), 'word', 'entity_group'],
+                             values='score', color='entity_group')
+            fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
+            st.plotly_chart(fig)
 
-        import plotly.express as px
-        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)
-
-
-
-        
-
-
-
-        
-            
-        
         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)
 
-        import plotly.express as px
-        st.subheader("A score closer to 1 means closer match")
-        
-        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'])
+        fig = px.imshow(cosine_sim_df, text_auto=True,
+                        labels=dict(x="Cosine similarity", y="Text", color="Productivity"),
+                        x=['Job Description'] + [f'Candidate {i+1}' for i in range(len(all_resumes_text))],
+                        y=['Job Description'] + [f'Candidate {i+1}' for i in range(len(all_resumes_text))])
         st.plotly_chart(fig)
 
         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}")
 
-    
-if 'uploaded_files' in st.session_state:
-    st.write(f"URL pasted {st.session_state['uploaded_files']} times.")
-
+else:
+    st.warning(f"Maximum upload attempts reached ({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).")
 
 
 
-st.divider()
-
-txt = st.text_area("Job description", key = "text 2")
-job = pd.Series(txt, name="Text")
-st.dataframe(job)
 
-uploaded_files = st.file_uploader(
-    "Choose a CSV file", accept_multiple_files=True, type = "pdf", key = "candidate 2"
-)
-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)
-