feat: integrate real data - app working with embeddings

app.py

@@ -14,10 +14,9 @@ from pathlib import Path
 sys.path.append(str(Path(__file__).parent))
 
 from config import *
-from data.mock_data import (
-    get_candidate_data,
-    get_company_matches,
-    get_network_graph_data
+from data.data_loader import (
+    load_embeddings,
+    find_top_matches
 )
 from utils.display import (
     display_candidate_profile,
@@ -124,14 +123,6 @@ def render_header():
     
     st.markdown(f'<h1 class="main-title">{APP_TITLE}</h1>', unsafe_allow_html=True)
     st.markdown(f'<p class="sub-title">{APP_SUBTITLE}</p>', unsafe_allow_html=True)
-    
-    # Demo mode indicator
-    if DEMO_MODE:
-        st.info(
-            "🎭 **Demo Mode Active** - Displaying hardcoded sample data. "
-            "This will be replaced with real matching when embeddings are loaded.",
-            icon="ℹ️"
-        )
 
 
 def render_sidebar():
@@ -170,7 +161,7 @@ def render_sidebar():
         st.markdown("### 👀 View Mode")
         view_mode = st.radio(
             "Select view:",
-            ["📊 Overview", "📝 Detailed Cards", "📈 Table View"],
+            ["📊 Overview", "🔍 Detailed Cards", "📈 Table View"],
             help="Choose how to display company matches"
         )
         
@@ -207,14 +198,48 @@ def render_sidebar():
         return top_k, min_score, view_mode
 
 
-def render_network_section(candidate_id: int, top_k: int):
+def get_network_graph_data(candidate_id, matches):
+    """Generate network graph data from matches."""
+    nodes = []
+    edges = []
+    
+    # Add candidate node
+    nodes.append({
+        'id': f'C{candidate_id}',
+        'label': f'Candidate #{candidate_id}',
+        'color': '#4ade80',
+        'shape': 'dot',
+        'size': 30
+    })
+    
+    # Add company nodes and edges
+    for comp_id, score, comp_data in matches:
+        nodes.append({
+            'id': f'COMP{comp_id}',
+            'label': comp_data.get('name', f'Company {comp_id}')[:30],
+            'color': '#ff6b6b',
+            'shape': 'box',
+            'size': 20
+        })
+        
+        edges.append({
+            'from': f'C{candidate_id}',
+            'to': f'COMP{comp_id}',
+            'value': float(score) * 10,
+            'title': f'{score:.3f}'
+        })
+    
+    return {'nodes': nodes, 'edges': edges}
+
+
+def render_network_section(candidate_id: int, matches):
     """Render interactive network visualization section."""
     
     st.markdown('<div class="section-header">🕸️ Network Visualization</div>', unsafe_allow_html=True)
     
     with st.spinner("Generating interactive network graph..."):
         # Get graph data
-        graph_data = get_network_graph_data(candidate_id, top_k)
+        graph_data = get_network_graph_data(candidate_id, matches)
         
         # Create HTML graph
         html_content = create_network_graph(
@@ -252,7 +277,7 @@ def render_matches_section(matches, view_mode: str):
         # Table view
         display_match_table(matches)
         
-    elif view_mode == "📝 Detailed Cards":
+    elif view_mode == "🔍 Detailed Cards":
         # Card view - detailed
         for rank, (comp_id, score, comp_data) in enumerate(matches, 1):
             display_company_card(comp_data, score, rank)
@@ -277,12 +302,35 @@ def main():
     # Main content area
     st.markdown("---")
     
+    # Load embeddings (cache in session state)
+    if 'embeddings_loaded' not in st.session_state:
+        with st.spinner("🔄 Loading embeddings and data..."):
+            cand_emb, comp_emb, cand_df, comp_df = load_embeddings()
+            st.session_state.embeddings_loaded = True
+            st.session_state.candidate_embeddings = cand_emb
+            st.session_state.company_embeddings = comp_emb
+            st.session_state.candidates_df = cand_df
+            st.session_state.companies_df = comp_df
+            st.success("✅ Data loaded successfully!")
+    
     # Load candidate data
     candidate_id = DEMO_CANDIDATE_ID
-    candidate = get_candidate_data(candidate_id)
+    candidate = st.session_state.candidates_df.iloc[candidate_id]
     
     # Load company matches
-    matches = get_company_matches(candidate_id, top_k)
+    matches_list = find_top_matches(
+        candidate_id,
+        st.session_state.candidate_embeddings,
+        st.session_state.company_embeddings,
+        st.session_state.companies_df,
+        top_k
+    )
+    
+    # Format matches for display
+    matches = [
+        (m['company_id'], m['score'], st.session_state.companies_df.iloc[m['company_id']])
+        for m in matches_list
+    ]
     
     # Filter by minimum score
     matches = [(cid, score, cdata) for cid, score, cdata in matches if score >= min_score]
@@ -309,17 +357,10 @@ def main():
     st.markdown("---")
     
     # Network visualization (full width)
-    render_network_section(candidate_id, len(matches))
+    render_network_section(candidate_id, matches)
     
     st.markdown("---")
     
-    # Footer with instructions
-    st.success(
-        "✅ **MVP Demo Ready!** This interface shows the core functionality. "
-        "Next step: Replace mock data with real embeddings for dynamic matching.",
-        icon="🎉"
-    )
-    
     # Technical info expander
     with st.expander("🔧 Technical Details", expanded=False):
         st.markdown(f"""
@@ -328,20 +369,16 @@ def main():
             - Similarity Metric: Cosine Similarity
             - Top K Matches: {top_k}
             - Minimum Score: {min_score:.0%}
-            - Demo Mode: {'✅ Enabled' if DEMO_MODE else '❌ Disabled'}
-            
-            **Data Sources:**
-            - Candidates: 9,544 profiles
-            - Companies: 180,000 entities
-            - Job Postings: 700 (bridge data)
+            - Candidates Loaded: {len(st.session_state.candidates_df):,}
+            - Companies Loaded: {len(st.session_state.companies_df):,}
             
             **Algorithm:**
-            1. Text representation of candidates/companies
-            2. Sentence transformer embeddings (384D)
-            3. Cosine similarity calculation
-            4. Top-K ranking
+            1. Load pre-computed embeddings (.npy files)
+            2. Calculate cosine similarity
+            3. Rank companies by similarity score
+            4. Return top-K matches
         """)
 
 
 if __name__ == "__main__":
-    main()
+    main()

data/data_loader.py

@@ -0,0 +1,43 @@
+import numpy as np
+import pickle
+from sklearn.metrics.pairwise import cosine_similarity
+
+def load_embeddings():
+    """Load pre-computed embeddings and metadata."""
+    
+    # Load embeddings
+    candidate_embeddings = np.load('data/processed/candidate_embeddings.npy')
+    company_embeddings = np.load('data/processed/company_embeddings.npy')
+    
+    # Load metadata
+    with open('data/processed/candidates_processed.pkl', 'rb') as f:
+        candidates_df = pickle.load(f)
+    
+    with open('data/processed/companies_processed.pkl', 'rb') as f:
+        companies_df = pickle.load(f)
+    
+    return candidate_embeddings, company_embeddings, candidates_df, companies_df
+
+def find_top_matches(candidate_idx, candidate_embeddings, company_embeddings, companies_df, top_k=10):
+    """Find top K company matches for a candidate."""
+    
+    # Get candidate embedding
+    candidate_vec = candidate_embeddings[candidate_idx].reshape(1, -1)
+    
+    # Calculate similarities
+    similarities = cosine_similarity(candidate_vec, company_embeddings)[0]
+    
+    # Get top K indices
+    top_indices = np.argsort(similarities)[::-1][:top_k]
+    
+    # Build results
+    matches = []
+    for idx in top_indices:
+        matches.append({
+            'company_id': idx,
+            'company_name': companies_df.iloc[idx].get('name', f'Company {idx}'),
+            'job_title': companies_df.iloc[idx].get('title', 'N/A'),
+            'score': float(similarities[idx])
+        })
+    
+    return matches

utils/display.py

@@ -5,107 +5,94 @@ Contains formatted display components for candidates and companies.
 
 import streamlit as st
 import pandas as pd
+import ast
 from typing import Dict, Any, List, Tuple
 
 
-def display_candidate_profile(candidate: Dict[str, Any]):
+def display_candidate_profile(candidate):
     """
     Display comprehensive candidate profile in Streamlit.
     
     Args:
-        candidate: Dictionary with candidate data
+        candidate: Pandas Series with candidate data
     """
     
     st.markdown("### 👤 Candidate Profile")
     st.markdown("---")
     
-    # Basic Info
-    col1, col2 = st.columns([2, 1])
-    
-    with col1:
-        st.markdown(f"**Name:** {candidate.get('name', 'N/A')}")
-        st.markdown(f"**Desired Position:** {candidate.get('job_position_name', 'N/A')}")
-        
-    with col2:
-        st.metric("Match Score", f"{candidate.get('matched_score', 0):.2%}")
-    
     # Career Objective
     with st.expander("🎯 Career Objective", expanded=True):
         st.write(candidate.get('career_objective', 'Not provided'))
     
     # Skills
     with st.expander("💻 Skills & Expertise", expanded=True):
-        skills = candidate.get('skills', [])
-        if skills:
-            # Display as tags
-            skills_html = " ".join([f'<span style="background-color: #0066CC; color: white; padding: 5px 10px; border-radius: 15px; margin: 3px; display: inline-block;">{skill}</span>' for skill in skills[:15]])
-            st.markdown(skills_html, unsafe_allow_html=True)
-        else:
-            st.write("No skills listed")
+        try:
+            skills = ast.literal_eval(candidate.get('skills', '[]'))
+            if skills:
+                # Display as tags
+                skills_html = " ".join([f'<span style="background-color: #0066CC; color: white; padding: 5px 10px; border-radius: 15px; margin: 3px; display: inline-block;">{skill}</span>' for skill in skills[:15]])
+                st.markdown(skills_html, unsafe_allow_html=True)
+            else:
+                st.write("No skills listed")
+        except:
+            st.write(candidate.get('skills', 'No skills listed'))
     
     # Education
     with st.expander("🎓 Education"):
-        edu_data = {
-            'Institution': candidate.get('educational_institution_name', []),
-            'Degree': candidate.get('degree_names', []),
-            'Major': candidate.get('major_field_of_studies', []),
-            'Year': candidate.get('passing_years', []),
-            'GPA': candidate.get('educational_results', [])
-        }
-        
-        if any(edu_data.values()):
-            df_edu = pd.DataFrame(edu_data)
-            st.dataframe(df_edu, use_container_width=True, hide_index=True)
-        else:
+        try:
+            institutions = ast.literal_eval(candidate.get('educational_institution_name', '[]'))
+            degrees = ast.literal_eval(candidate.get('degree_names', '[]'))
+            majors = ast.literal_eval(candidate.get('major_field_of_studies', '[]'))
+            years = ast.literal_eval(candidate.get('passing_years', '[]'))
+            
+            if institutions and any(institutions):
+                for i in range(len(institutions)):
+                    degree = degrees[i] if i < len(degrees) else 'N/A'
+                    major = majors[i] if i < len(majors) else 'N/A'
+                    year = years[i] if i < len(years) else 'N/A'
+                    
+                    st.write(f"**{degree}** in {major}")
+                    st.write(f"📍 {institutions[i]}")
+                    st.write(f"📅 {year}")
+                    if i < len(institutions) - 1:
+                        st.write("---")
+            else:
+                st.write("No education information provided")
+        except:
             st.write("No education information provided")
     
     # Work Experience
     with st.expander("💼 Work Experience"):
-        exp_data = {
-            'Company': candidate.get('professional_company_names', []),
-            'Position': candidate.get('positions', []),
-            'Location': candidate.get('locations', []),
-            'Start': candidate.get('start_dates', []),
-            'End': candidate.get('end_dates', [])
-        }
-        
-        if any(exp_data.values()):
-            df_exp = pd.DataFrame(exp_data)
-            st.dataframe(df_exp, use_container_width=True, hide_index=True)
+        try:
+            companies = ast.literal_eval(candidate.get('professional_company_names', '[]'))
+            positions = ast.literal_eval(candidate.get('positions', '[]'))
+            starts = ast.literal_eval(candidate.get('start_dates', '[]'))
+            ends = ast.literal_eval(candidate.get('end_dates', '[]'))
             
-            # Show responsibilities
-            responsibilities = candidate.get('responsibilities', '')
-            if responsibilities:
-                st.markdown("**Key Responsibilities:**")
-                st.text(responsibilities)
-        else:
+            if companies and any(companies):
+                for i in range(len(companies)):
+                    position = positions[i] if i < len(positions) else 'N/A'
+                    start = starts[i] if i < len(starts) else 'N/A'
+                    end = ends[i] if i < len(ends) else 'N/A'
+                    
+                    st.write(f"**{position}** at {companies[i]}")
+                    st.write(f"📅 {start} - {end}")
+                    if i < len(companies) - 1:
+                        st.write("---")
+                
+                # Show responsibilities
+                responsibilities = candidate.get('responsibilities', '')
+                if responsibilities:
+                    st.markdown("**Key Responsibilities:**")
+                    st.text(responsibilities)
+            else:
+                st.write("No work experience listed")
+        except:
             st.write("No work experience listed")
-    
-    # Languages
-    with st.expander("🌍 Languages"):
-        languages = candidate.get('languages', [])
-        proficiency = candidate.get('proficiency_levels', [])
-        
-        if languages:
-            for lang, prof in zip(languages, proficiency):
-                st.write(f"• **{lang}** - {prof}")
-        else:
-            st.write("No languages listed")
-    
-    # Certifications
-    with st.expander("🏅 Certifications"):
-        providers = candidate.get('certification_providers', [])
-        skills = candidate.get('certification_skills', [])
-        
-        if providers:
-            for provider, skill in zip(providers, skills):
-                st.write(f"• **{skill}** by {provider}")
-        else:
-            st.write("No certifications listed")
 
 
 def display_company_card(
-    company_data: Dict[str, Any],
+    company_data,
     similarity_score: float,
     rank: int
 ):
@@ -113,7 +100,7 @@ def display_company_card(
     Display company information as a card.
     
     Args:
-        company_data: Dictionary with company data
+        company_data: Pandas Series with company data
         similarity_score: Match score
         rank: Ranking position
     """
@@ -152,44 +139,19 @@ def display_company_card(
             )
         
         # Company details
-        col1, col2, col3 = st.columns(3)
-        
-        with col1:
-            st.markdown(f"**📍 Location**")
-            location = f"{company_data.get('city', '')}, {company_data.get('state', '')}, {company_data.get('country', '')}"
-            st.write(location)
-        
-        with col2:
-            st.markdown(f"**👥 Size**")
-            st.write(company_data.get('employee_count', 'N/A'))
-        
-        with col3:
-            st.markdown(f"**🏭 Industry**")
-            industries = company_data.get('industries_list', 'N/A')
-            st.write(industries.split(',')[0] if ',' in str(industries) else industries)
+        st.markdown(f"**Company ID:** {company_data.name}")
         
         # Description
-        description = company_data.get('description', 'No description available')
+        description = company_data.get('description', company_data.get('text', 'No description available'))
+        if len(str(description)) > 200:
+            description = str(description)[:200] + "..."
         st.markdown(f"**About:** {description}")
         
-        # Required skills
-        required_skills = company_data.get('required_skills', '')
-        if required_skills:
-            st.markdown("**🔧 Required Skills:**")
-            skills_list = [s.strip() for s in str(required_skills).split('|')[:8]]
-            skills_html = " ".join([f'<span style="background-color: #CC0000; color: white; padding: 5px 10px; border-radius: 15px; margin: 3px; display: inline-block; font-size: 12px;">{skill}</span>' for skill in skills_list])
-            st.markdown(skills_html, unsafe_allow_html=True)
-        
-        # Job postings
-        job_titles = company_data.get('posted_job_titles', '')
-        if job_titles:
-            st.markdown(f"**💼 Open Positions:** {job_titles}")
-        
         st.markdown("---")
 
 
 def display_match_table(
-    matches: List[Tuple[int, float, Dict[str, Any]]],
+    matches: List[Tuple[int, float, Any]],
     show_top_n: int = 10
 ):
     """
@@ -207,21 +169,11 @@ def display_match_table(
     table_data = []
     
     for rank, (comp_id, score, comp_data) in enumerate(matches[:show_top_n], 1):
-        # Get key skills (first 3)
-        skills = comp_data.get('required_skills', 'N/A')
-        if skills and skills != 'N/A':
-            skills_list = [s.strip() for s in str(skills).split('|')[:3]]
-            skills_display = ', '.join(skills_list)
-        else:
-            skills_display = 'N/A'
-        
         table_data.append({
             'Rank': f"#{rank}",
-            'Company': comp_data.get('name', 'N/A'),
+            'Company ID': comp_id,
             'Score': f"{score:.1%}",
-            'Location': f"{comp_data.get('city', 'N/A')}, {comp_data.get('state', 'N/A')}",
-            'Top Skills': skills_display,
-            'Employees': comp_data.get('employee_count', 'N/A')
+            'Match Quality': '🔥 Excellent' if score >= 0.7 else '✨ Very Good' if score >= 0.6 else '👍 Good' if score >= 0.5 else '⭐ Fair'
         })
     
     # Display as dataframe
@@ -235,10 +187,8 @@ def display_match_table(
         column_config={
             "Rank": st.column_config.TextColumn(width="small"),
             "Score": st.column_config.TextColumn(width="small"),
-            "Company": st.column_config.TextColumn(width="medium"),
-            "Location": st.column_config.TextColumn(width="medium"),
-            "Top Skills": st.column_config.TextColumn(width="large"),
-            "Employees": st.column_config.TextColumn(width="small")
+            "Company ID": st.column_config.TextColumn(width="medium"),
+            "Match Quality": st.column_config.TextColumn(width="medium")
         }
     )
     
@@ -246,8 +196,8 @@ def display_match_table(
 
 
 def display_stats_overview(
-    candidate_data: Dict[str, Any],
-    matches: List[Tuple[int, float, Dict[str, Any]]]
+    candidate_data,
+    matches: List[Tuple[int, float, Any]]
 ):
     """
     Display overview statistics about the matching results.
@@ -292,4 +242,4 @@ def display_stats_overview(
             help="Highest similarity score"
         )
     
-    st.markdown("---")
+    st.markdown("---")

utils/display_old.py

@@ -0,0 +1,295 @@
+"""
+Display utilities for HRHUB Streamlit UI.
+Contains formatted display components for candidates and companies.
+"""
+
+import streamlit as st
+import pandas as pd
+from typing import Dict, Any, List, Tuple
+
+
+def display_candidate_profile(candidate: Dict[str, Any]):
+    """
+    Display comprehensive candidate profile in Streamlit.
+    
+    Args:
+        candidate: Dictionary with candidate data
+    """
+    
+    st.markdown("### 👤 Candidate Profile")
+    st.markdown("---")
+    
+    # Basic Info
+    col1, col2 = st.columns([2, 1])
+    
+    with col1:
+        st.markdown(f"**Name:** {candidate.get('name', 'N/A')}")
+        st.markdown(f"**Desired Position:** {candidate.get('job_position_name', 'N/A')}")
+        
+    with col2:
+        st.metric("Match Score", f"{candidate.get('matched_score', 0):.2%}")
+    
+    # Career Objective
+    with st.expander("🎯 Career Objective", expanded=True):
+        st.write(candidate.get('career_objective', 'Not provided'))
+    
+    # Skills
+    with st.expander("💻 Skills & Expertise", expanded=True):
+        skills = candidate.get('skills', [])
+        if skills:
+            # Display as tags
+            skills_html = " ".join([f'<span style="background-color: #0066CC; color: white; padding: 5px 10px; border-radius: 15px; margin: 3px; display: inline-block;">{skill}</span>' for skill in skills[:15]])
+            st.markdown(skills_html, unsafe_allow_html=True)
+        else:
+            st.write("No skills listed")
+    
+    # Education
+    with st.expander("🎓 Education"):
+        edu_data = {
+            'Institution': candidate.get('educational_institution_name', []),
+            'Degree': candidate.get('degree_names', []),
+            'Major': candidate.get('major_field_of_studies', []),
+            'Year': candidate.get('passing_years', []),
+            'GPA': candidate.get('educational_results', [])
+        }
+        
+        if any(edu_data.values()):
+            df_edu = pd.DataFrame(edu_data)
+            st.dataframe(df_edu, use_container_width=True, hide_index=True)
+        else:
+            st.write("No education information provided")
+    
+    # Work Experience
+    with st.expander("💼 Work Experience"):
+        exp_data = {
+            'Company': candidate.get('professional_company_names', []),
+            'Position': candidate.get('positions', []),
+            'Location': candidate.get('locations', []),
+            'Start': candidate.get('start_dates', []),
+            'End': candidate.get('end_dates', [])
+        }
+        
+        if any(exp_data.values()):
+            df_exp = pd.DataFrame(exp_data)
+            st.dataframe(df_exp, use_container_width=True, hide_index=True)
+            
+            # Show responsibilities
+            responsibilities = candidate.get('responsibilities', '')
+            if responsibilities:
+                st.markdown("**Key Responsibilities:**")
+                st.text(responsibilities)
+        else:
+            st.write("No work experience listed")
+    
+    # Languages
+    with st.expander("🌍 Languages"):
+        languages = candidate.get('languages', [])
+        proficiency = candidate.get('proficiency_levels', [])
+        
+        if languages:
+            for lang, prof in zip(languages, proficiency):
+                st.write(f"• **{lang}** - {prof}")
+        else:
+            st.write("No languages listed")
+    
+    # Certifications
+    with st.expander("🏅 Certifications"):
+        providers = candidate.get('certification_providers', [])
+        skills = candidate.get('certification_skills', [])
+        
+        if providers:
+            for provider, skill in zip(providers, skills):
+                st.write(f"• **{skill}** by {provider}")
+        else:
+            st.write("No certifications listed")
+
+
+def display_company_card(
+    company_data: Dict[str, Any],
+    similarity_score: float,
+    rank: int
+):
+    """
+    Display company information as a card.
+    
+    Args:
+        company_data: Dictionary with company data
+        similarity_score: Match score
+        rank: Ranking position
+    """
+    
+    with st.container():
+        # Header with rank and score
+        col1, col2, col3 = st.columns([1, 4, 2])
+        
+        with col1:
+            st.markdown(f"### #{rank}")
+        
+        with col2:
+            st.markdown(f"### 🏢 {company_data.get('name', 'Unknown Company')}")
+        
+        with col3:
+            # Color-coded score
+            if similarity_score >= 0.7:
+                color = "#00FF00"  # Green
+                label = "Excellent"
+            elif similarity_score >= 0.6:
+                color = "#FFD700"  # Gold
+                label = "Very Good"
+            elif similarity_score >= 0.5:
+                color = "#FFA500"  # Orange
+                label = "Good"
+            else:
+                color = "#FF6347"  # Red
+                label = "Fair"
+            
+            st.markdown(
+                f'<div style="text-align: center; padding: 10px; background-color: {color}20; border: 2px solid {color}; border-radius: 10px;">'
+                f'<span style="font-size: 24px; font-weight: bold; color: {color};">{similarity_score:.1%}</span><br>'
+                f'<span style="font-size: 12px;">{label} Match</span>'
+                f'</div>',
+                unsafe_allow_html=True
+            )
+        
+        # Company details
+        col1, col2, col3 = st.columns(3)
+        
+        with col1:
+            st.markdown(f"**📍 Location**")
+            location = f"{company_data.get('city', '')}, {company_data.get('state', '')}, {company_data.get('country', '')}"
+            st.write(location)
+        
+        with col2:
+            st.markdown(f"**👥 Size**")
+            st.write(company_data.get('employee_count', 'N/A'))
+        
+        with col3:
+            st.markdown(f"**🏭 Industry**")
+            industries = company_data.get('industries_list', 'N/A')
+            st.write(industries.split(',')[0] if ',' in str(industries) else industries)
+        
+        # Description
+        description = company_data.get('description', 'No description available')
+        st.markdown(f"**About:** {description}")
+        
+        # Required skills
+        required_skills = company_data.get('required_skills', '')
+        if required_skills:
+            st.markdown("**🔧 Required Skills:**")
+            skills_list = [s.strip() for s in str(required_skills).split('|')[:8]]
+            skills_html = " ".join([f'<span style="background-color: #CC0000; color: white; padding: 5px 10px; border-radius: 15px; margin: 3px; display: inline-block; font-size: 12px;">{skill}</span>' for skill in skills_list])
+            st.markdown(skills_html, unsafe_allow_html=True)
+        
+        # Job postings
+        job_titles = company_data.get('posted_job_titles', '')
+        if job_titles:
+            st.markdown(f"**💼 Open Positions:** {job_titles}")
+        
+        st.markdown("---")
+
+
+def display_match_table(
+    matches: List[Tuple[int, float, Dict[str, Any]]],
+    show_top_n: int = 10
+):
+    """
+    Display match results as a formatted table.
+    
+    Args:
+        matches: List of (company_id, score, company_data) tuples
+        show_top_n: Number of matches to display
+    """
+    
+    st.markdown(f"### 🎯 Top {show_top_n} Company Matches")
+    st.markdown("---")
+    
+    # Prepare data for table
+    table_data = []
+    
+    for rank, (comp_id, score, comp_data) in enumerate(matches[:show_top_n], 1):
+        # Get key skills (first 3)
+        skills = comp_data.get('required_skills', 'N/A')
+        if skills and skills != 'N/A':
+            skills_list = [s.strip() for s in str(skills).split('|')[:3]]
+            skills_display = ', '.join(skills_list)
+        else:
+            skills_display = 'N/A'
+        
+        table_data.append({
+            'Rank': f"#{rank}",
+            'Company': comp_data.get('name', 'N/A'),
+            'Score': f"{score:.1%}",
+            'Location': f"{comp_data.get('city', 'N/A')}, {comp_data.get('state', 'N/A')}",
+            'Top Skills': skills_display,
+            'Employees': comp_data.get('employee_count', 'N/A')
+        })
+    
+    # Display as dataframe
+    df = pd.DataFrame(table_data)
+    
+    # Style the dataframe
+    st.dataframe(
+        df,
+        width='stretch',
+        hide_index=True,
+        column_config={
+            "Rank": st.column_config.TextColumn(width="small"),
+            "Score": st.column_config.TextColumn(width="small"),
+            "Company": st.column_config.TextColumn(width="medium"),
+            "Location": st.column_config.TextColumn(width="medium"),
+            "Top Skills": st.column_config.TextColumn(width="large"),
+            "Employees": st.column_config.TextColumn(width="small")
+        }
+    )
+    
+    st.info("💡 **Tip:** Scores above 0.6 indicate strong alignment between candidate skills and company requirements!")
+
+
+def display_stats_overview(
+    candidate_data: Dict[str, Any],
+    matches: List[Tuple[int, float, Dict[str, Any]]]
+):
+    """
+    Display overview statistics about the matching results.
+    
+    Args:
+        candidate_data: Candidate information
+        matches: List of matches
+    """
+    
+    st.markdown("### 📊 Matching Overview")
+    
+    col1, col2, col3, col4 = st.columns(4)
+    
+    with col1:
+        st.metric(
+            "Total Matches",
+            len(matches),
+            help="Number of companies analyzed"
+        )
+    
+    with col2:
+        avg_score = sum(score for _, score, _ in matches) / len(matches) if matches else 0
+        st.metric(
+            "Average Score",
+            f"{avg_score:.1%}",
+            help="Average similarity score"
+        )
+    
+    with col3:
+        excellent = sum(1 for _, score, _ in matches if score >= 0.7)
+        st.metric(
+            "Excellent Matches",
+            excellent,
+            help="Matches with score ≥ 70%"
+        )
+    
+    with col4:
+        best_score = max((score for _, score, _ in matches), default=0)
+        st.metric(
+            "Best Match",
+            f"{best_score:.1%}",
+            help="Highest similarity score"
+        )
+    
+    st.markdown("---")