Update app.py

app.py

@@ -1,549 +1,68 @@
-import gradio as gr
-import plotly.graph_objects as go
-import networkx as nx
-import pandas as pd
-from collections import defaultdict
+# Basic Network Explorer - Updates
 
-# Entity type colors
-ENTITY_COLORS = {
-    'PERSON': '#00B894',      # Green
-    'LOCATION': '#A0E7E5',    # Light Cyan
-    'EVENT': '#4ECDC4',       # Teal
-    'ORGANIZATION': '#55A3FF', # Light Blue
-    'DATE': '#FF6B6B'         # Red
-}
+## Changes Made Based on Feedback
 
-# Relationship types for dropdown
-RELATIONSHIP_TYPES = [
-    'works_with',
-    'located_in',
-    'participated_in',
-    'member_of',
-    'occurred_at',
-    'employed_by',
-    'founded',
-    'attended',
-    'knows',
-    'related_to',
-    'collaborates_with',
-    'other'
-]
+### 1. ✅ Name Change
+- Changed from "Basic Networks Explorer" to **"Basic Network Explorer"** (singular)
+- Updated throughout code and documentation
 
-class NetworkGraphBuilder:
-    def __init__(self):
-        self.entities = []
-        self.relationships = []
-        
-    def add_entity(self, name, entity_type, record_id):
-        """Add an entity to the collection"""
-        if name.strip():
-            self.entities.append({
-                'name': name.strip(),
-                'type': entity_type,
-                'record_id': record_id
-            })
-    
-    def add_relationship(self, source, target, rel_type):
-        """Add a relationship between entities"""
-        if source and target and source != target:
-            self.relationships.append({
-                'source': source.strip(),
-                'target': target.strip(),
-                'type': rel_type
-            })
-    
-    def build_graph(self):
-        """Build NetworkX graph from entities and relationships"""
-        G = nx.Graph()
-        
-        # Add nodes with attributes
-        for entity in self.entities:
-            G.add_node(
-                entity['name'],
-                entity_type=entity['type'],
-                record_id=entity['record_id']
-            )
-        
-        # Add edges
-        for rel in self.relationships:
-            if rel['source'] in G.nodes and rel['target'] in G.nodes:
-                G.add_edge(
-                    rel['source'],
-                    rel['target'],
-                    relationship=rel['type']
-                )
-        
-        return G
-    
-    def create_plotly_graph(self, G, layout_type='spring'):
-        """Create interactive Plotly visualization"""
-        if len(G.nodes) == 0:
-            return None
-        
-        # Choose layout
-        if layout_type == 'spring':
-            pos = nx.spring_layout(G, k=2, iterations=50)
-        elif layout_type == 'circular':
-            pos = nx.circular_layout(G)
-        elif layout_type == 'kamada_kawai':
-            pos = nx.kamada_kawai_layout(G)
-        else:
-            pos = nx.shell_layout(G)
-        
-        # Create edge traces
-        edge_traces = []
-        edge_labels = []
-        
-        for edge in G.edges(data=True):
-            x0, y0 = pos[edge[0]]
-            x1, y1 = pos[edge[1]]
-            
-            # Edge line
-            edge_trace = go.Scatter(
-                x=[x0, x1, None],
-                y=[y0, y1, None],
-                mode='lines',
-                line=dict(width=2, color='#888'),
-                hoverinfo='none',
-                showlegend=False
-            )
-            edge_traces.append(edge_trace)
-            
-            # Edge label (relationship type)
-            rel_type = edge[2].get('relationship', '')
-            edge_label = go.Scatter(
-                x=[(x0 + x1) / 2],
-                y=[(y0 + y1) / 2],
-                mode='text',
-                text=[rel_type],
-                textfont=dict(size=10, color='#555'),
-                hoverinfo='text',
-                hovertext=f"{edge[0]} → {rel_type} → {edge[1]}",
-                showlegend=False
-            )
-            edge_labels.append(edge_label)
-        
-        # Create node traces (one per entity type for legend)
-        node_traces = {}
-        for node, data in G.nodes(data=True):
-            entity_type = data.get('entity_type', 'UNKNOWN')
-            
-            if entity_type not in node_traces:
-                node_traces[entity_type] = {
-                    'x': [],
-                    'y': [],
-                    'text': [],
-                    'hovertext': [],
-                    'degree': []
-                }
-            
-            x, y = pos[node]
-            node_traces[entity_type]['x'].append(x)
-            node_traces[entity_type]['y'].append(y)
-            node_traces[entity_type]['text'].append(node)
-            
-            # Create hover text with connections
-            connections = list(G.neighbors(node))
-            hover_info = f"<b>{node}</b><br>"
-            hover_info += f"Type: {entity_type}<br>"
-            hover_info += f"Connections: {len(connections)}<br>"
-            if connections:
-                hover_info += f"Connected to: {', '.join(connections[:5])}"
-                if len(connections) > 5:
-                    hover_info += f"... and {len(connections) - 5} more"
-            
-            node_traces[entity_type]['hovertext'].append(hover_info)
-            node_traces[entity_type]['degree'].append(G.degree(node))
-        
-        # Create Plotly traces for each entity type
-        data = edge_traces + edge_labels
-        
-        for entity_type, trace_data in node_traces.items():
-            # Calculate node sizes based on degree
-            max_degree = max(trace_data['degree']) if trace_data['degree'] else 1
-            sizes = [20 + (degree / max_degree) * 30 for degree in trace_data['degree']]
-            
-            node_trace = go.Scatter(
-                x=trace_data['x'],
-                y=trace_data['y'],
-                mode='markers+text',
-                marker=dict(
-                    size=sizes,
-                    color=ENTITY_COLORS.get(entity_type, '#CCCCCC'),
-                    line=dict(width=2, color='white')
-                ),
-                text=trace_data['text'],
-                textposition='top center',
-                textfont=dict(size=10, color='#333'),
-                hovertext=trace_data['hovertext'],
-                hoverinfo='text',
-                name=entity_type,
-                showlegend=True
-            )
-            data.append(node_trace)
-        
-        # Create figure
-        fig = go.Figure(
-            data=data,
-            layout=go.Layout(
-                title=dict(
-                    text='<b>Entity Network Graph</b><br><sub>Node size indicates number of connections</sub>',
-                    x=0.5,
-                    xanchor='center'
-                ),
-                showlegend=True,
-                hovermode='closest',
-                margin=dict(b=20, l=5, r=5, t=80),
-                xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
-                yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
-                plot_bgcolor='#fafafa',
-                height=700,
-                legend=dict(
-                    title=dict(text='<b>Entity Types</b>'),
-                    orientation='v',
-                    yanchor='top',
-                    y=1,
-                    xanchor='left',
-                    x=1.02
-                )
-            )
-        )
-        
-        return fig
+### 2. ✅ Footer Attribution Updated
+**Old:**
+- DiSc project at Oxford
 
-def collect_entities_from_records(*args):
-    """Collect all entities from the input fields"""
-    builder = NetworkGraphBuilder()
-    
-    # Each record has 5 entity fields (person, location, event, org, date)
-    num_records = 6
-    fields_per_record = 5
-    
-    for i in range(num_records):
-        record_id = i + 1
-        base_idx = i * fields_per_record
-        
-        # Extract entities for this record
-        person = args[base_idx] if base_idx < len(args) else ""
-        location = args[base_idx + 1] if base_idx + 1 < len(args) else ""
-        event = args[base_idx + 2] if base_idx + 2 < len(args) else ""
-        org = args[base_idx + 3] if base_idx + 3 < len(args) else ""
-        date = args[base_idx + 4] if base_idx + 4 < len(args) else ""
-        
-        if person:
-            builder.add_entity(person, 'PERSON', record_id)
-        if location:
-            builder.add_entity(location, 'LOCATION', record_id)
-        if event:
-            builder.add_entity(event, 'EVENT', record_id)
-        if org:
-            builder.add_entity(org, 'ORGANIZATION', record_id)
-        if date:
-            builder.add_entity(date, 'DATE', record_id)
-    
-    # Create list of all entity names for relationship dropdowns
-    entity_names = [e['name'] for e in builder.entities]
-    
-    # Create summary
-    summary = f"""
-    ### 📊 Entities Collected
-    - **Total entities:** {len(builder.entities)}
-    - **People:** {sum(1 for e in builder.entities if e['type'] == 'PERSON')}
-    - **Locations:** {sum(1 for e in builder.entities if e['type'] == 'LOCATION')}
-    - **Events:** {sum(1 for e in builder.entities if e['type'] == 'EVENT')}
-    - **Organizations:** {sum(1 for e in builder.entities if e['type'] == 'ORGANIZATION')}
-    - **Dates:** {sum(1 for e in builder.entities if e['type'] == 'DATE')}
-    
-    Now define relationships between these entities below.
-    """
-    
-    # Return summary and update dropdowns
-    return (
-        summary,
-        gr.update(visible=True),  # Show relationship section
-        gr.update(choices=entity_names, value=None),  # Update all relationship dropdowns
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None),
-        gr.update(choices=entity_names, value=None)
-    )
+**New:**
+- "This Basic Network Explorer tool was created as part of a Bodleian Libraries (University of Oxford) Sassoon Research Fellowship."
+- "The code for this tool was built with the aid of Claude Sonnet 4.5."
 
-def generate_network_graph(*args):
-    """Generate the network graph from all inputs"""
-    builder = NetworkGraphBuilder()
-    
-    # Collect entities (first 30 args: 6 records × 5 fields)
-    num_records = 6
-    fields_per_record = 5
-    
-    for i in range(num_records):
-        record_id = i + 1
-        base_idx = i * fields_per_record
-        
-        person = args[base_idx] if base_idx < len(args) else ""
-        location = args[base_idx + 1] if base_idx + 1 < len(args) else ""
-        event = args[base_idx + 2] if base_idx + 2 < len(args) else ""
-        org = args[base_idx + 3] if base_idx + 3 < len(args) else ""
-        date = args[base_idx + 4] if base_idx + 4 < len(args) else ""
-        
-        if person:
-            builder.add_entity(person, 'PERSON', record_id)
-        if location:
-            builder.add_entity(location, 'LOCATION', record_id)
-        if event:
-            builder.add_entity(event, 'EVENT', record_id)
-        if org:
-            builder.add_entity(org, 'ORGANIZATION', record_id)
-        if date:
-            builder.add_entity(date, 'DATE', record_id)
-    
-    # Collect relationships (next args: 5 relationships × 3 fields)
-    relationship_start = 30
-    num_relationships = 5
-    
-    for i in range(num_relationships):
-        base_idx = relationship_start + (i * 3)
-        source = args[base_idx] if base_idx < len(args) else None
-        target = args[base_idx + 1] if base_idx + 1 < len(args) else None
-        rel_type = args[base_idx + 2] if base_idx + 2 < len(args) else None
-        
-        if source and target:
-            builder.add_relationship(source, target, rel_type)
-    
-    # Get layout type (last arg)
-    layout_type = args[-1] if len(args) > relationship_start else 'spring'
-    
-    # Build graph
-    G = builder.build_graph()
-    
-    if len(G.nodes) == 0:
-        return None, "❌ No entities to display. Please add some entities first."
-    
-    if len(G.edges) == 0:
-        return None, "⚠️ No relationships defined. The graph will show isolated nodes."
-    
-    # Create visualization
-    fig = builder.create_plotly_graph(G, layout_type)
-    
-    # Create statistics
-    stats = f"""
-    ### 📈 Network Statistics
-    - **Nodes (Entities):** {G.number_of_nodes()}
-    - **Edges (Relationships):** {G.number_of_edges()}
-    - **Network Density:** {nx.density(G):.3f}
-    - **Average Connections per Node:** {sum(dict(G.degree()).values()) / G.number_of_nodes():.2f}
-    """
-    
-    if G.number_of_edges() > 0:
-        # Find most connected nodes
-        degrees = dict(G.degree())
-        top_nodes = sorted(degrees.items(), key=lambda x: x[1], reverse=True)[:3]
-        stats += "\n**Most Connected Entities:**\n"
-        for node, degree in top_nodes:
-            stats += f"- {node}: {degree} connections\n"
-    
-    return fig, stats
+### 3. ✅ Terminology Change
+- Changed "Collected Entities" to **"Identified Entities"**
+- Updated button text from "Collect Entities" to **"Identify Entities"**
+- Updated instructions accordingly
 
-def create_interface():
-    with gr.Blocks(title="Basic Networks Explorer", theme=gr.themes.Soft()) as demo:
-        gr.Markdown("""
-        # Basic Networks Explorer
-        
-        Build interactive social network graphs by entering entities extracted through Named Entity Recognition (NER).
-        This tool demonstrates how NER can be used to visualize relationships and connections in text data.
-        
-        ### How to use this tool:
-        1. **📝 Enter entities** in the records below (people, locations, events, organizations, dates)
-        2. **🔗 Click "Collect Entities"** to gather all your inputs
-        3. **🤝 Define relationships** between entities in the relationship builder
-        4. **🎨 Choose a layout style** and click "Generate Network Graph"
-        5. **👁️ Explore** the interactive visualization
-        6. **🔄 Refresh the page** to start over with new data
-        """)
-        
-        # Add tip box
-        gr.HTML("""
-        <div style="background-color: #fff3cd; border: 1px solid #ffeaa7; border-radius: 8px; padding: 12px; margin: 15px 0;">
-            <strong style="color: #856404;">💡 Top tip:</strong> This tool works best when you have already identified entities from text using NER. Try the NER Explorer Tool first to extract entities automatically!
-        </div>
-        """)
-        
-        # Entity input section
-        entity_inputs = []
-        
-        with gr.Accordion("📚 Step 1: Enter Entities from Your Records", open=True):
-            for i in range(6):
-                with gr.Group():
-                    gr.Markdown(f"### Record {i+1}")
-                    with gr.Row():
-                        person = gr.Textbox(label="👤 Person", placeholder="e.g., Albert Einstein")
-                        location = gr.Textbox(label="📍 Location", placeholder="e.g., Berlin")
-                        event = gr.Textbox(label="📅 Event", placeholder="e.g., Nobel Prize Ceremony")
-                    with gr.Row():
-                        org = gr.Textbox(label="🏢 Organization", placeholder="e.g., Princeton University")
-                        date = gr.Textbox(label="🗓️ Date", placeholder="e.g., 1921")
-                    
-                    entity_inputs.extend([person, location, event, org, date])
-        
-        collect_btn = gr.Button("🔍 Collect Entities", variant="primary", size="lg")
-        
-        entity_summary = gr.Markdown()
-        
-        # Relationship section (initially hidden)
-        with gr.Column(visible=False) as relationship_section:
-            with gr.Accordion("🤝 Step 2: Define Relationships Between Entities", open=True):
-                gr.Markdown("Select entities and specify how they're connected:")
-            
-                relationship_inputs = []
-                
-                for i in range(5):
-                    with gr.Row():
-                        source = gr.Dropdown(label=f"From Entity {i+1}", choices=[], interactive=True)
-                        rel_type = gr.Dropdown(
-                            label="Relationship Type",
-                            choices=RELATIONSHIP_TYPES,
-                            value="related_to",
-                            interactive=True
-                        )
-                        target = gr.Dropdown(label=f"To Entity {i+1}", choices=[], interactive=True)
-                    
-                    relationship_inputs.extend([source, rel_type, target])
-            
-            with gr.Accordion("🎨 Step 3: Customize and Generate", open=True):
-                layout_type = gr.Dropdown(
-                    label="Graph Layout",
-                    choices=['spring', 'circular', 'kamada_kawai', 'shell'],
-                    value='spring',
-                    info="Choose how nodes are arranged"
-                )
-                
-                generate_btn = gr.Button("🔍 Generate Network Graph", variant="primary", size="lg")
-        
-        # Output section
-        gr.HTML("<hr style='margin: 30px 0;'>")
-        
-        with gr.Row():
-            network_stats = gr.Markdown()
-        
-        with gr.Row():
-            network_plot = gr.Plot(label="Interactive Network Graph")
-        
-        # Examples
-        with gr.Column():
-            gr.Markdown("""
-            ### 💡 No example entities to test? No problem!
-            Simply click on one of the examples provided below, and the fields will be populated for you.
-            """, elem_id="examples-heading")
-        gr.Examples(
-            examples=[
-                [
-                    # Record 1
-                    "Winston Churchill", "London", "Battle of Britain", "Royal Air Force", "1940",
-                    # Record 2
-                    "Franklin D. Roosevelt", "Washington D.C.", "Pearl Harbor Attack", "United States Navy", "December 7, 1941",
-                    # Record 3
-                    "Dwight D. Eisenhower", "Normandy", "D-Day Invasion", "Allied Forces", "June 6, 1944",
-                    # Record 4
-                    "Winston Churchill", "Yalta", "Yalta Conference", "Allied Powers", "February 1945",
-                    # Record 5
-                    "Harry S. Truman", "Potsdam", "Potsdam Conference", "Allied Powers", "July 1945",
-                    # Record 6
-                    "Douglas MacArthur", "Tokyo Bay", "Japanese Surrender", "United States Military", "September 2, 1945"
-                ],
-                [
-                    # Record 1 - Pride and Prejudice
-                    "Elizabeth Bennet", "Longbourn", "First Ball", "", "1811",
-                    # Record 2
-                    "Mr. Darcy", "Pemberley", "First Ball", "", "1811",
-                    # Record 3
-                    "Jane Bennet", "Netherfield", "Dinner Party", "", "1811",
-                    # Record 4
-                    "Mr. Bingley", "Netherfield", "Dinner Party", "", "1811",
-                    # Record 5
-                    "Elizabeth Bennet", "Rosings Park", "Easter Visit", "", "1812",
-                    # Record 6
-                    "Mr. Darcy", "Rosings Park", "Easter Visit", "", "1812"
-                ]
-            ],
-            inputs=entity_inputs,
-            label="Examples"
-        )
-        
-        # Add custom CSS to match NER tool styling
-        gr.HTML("""
-        <style>
-            /* Make the Examples label text black */
-            .gradio-examples-label {
-                color: black !important;
-            }
-            h4.examples-label, .examples-label {
-                color: black !important;
-            }
-            #examples-heading + div label,
-            #examples-heading + div .label-text {
-                color: black !important;
-            }
-        </style>
-        """)
-        
-        # Wire up the interface
-        # Collect entities button
-        collect_btn.click(
-            fn=collect_entities_from_records,
-            inputs=entity_inputs,
-            outputs=[
-                entity_summary,
-                relationship_section
-            ] + relationship_inputs[::3] + relationship_inputs[2::3]  # Update source and target dropdowns
-        )
-        
-        # Generate graph button
-        all_inputs = entity_inputs + relationship_inputs + [layout_type]
-        generate_btn.click(
-            fn=generate_network_graph,
-            inputs=all_inputs,
-            outputs=[network_plot, network_stats]
-        )
-        
-        # Information footer
-        gr.HTML("""
-        <hr style="margin-top: 40px; margin-bottom: 20px;">
-        <div style="background-color: #f8f9fa; padding: 20px; border-radius: 8px; margin-top: 20px;">
-            <h4 style="margin-top: 0;">ℹ️ About This Tool</h4>
-            <p style="font-size: 14px; line-height: 1.8;">
-                This tool demonstrates how <strong>Named Entity Recognition (NER)</strong> can be combined with 
-                <strong>network analysis</strong> to visualize relationships in text data. In real-world applications,
-                entities would be automatically extracted from text using NER models, and relationships could be 
-                identified through co-occurrence analysis, dependency parsing, or machine learning.
-            </p>
-            <p style="font-size: 14px; line-height: 1.8; margin-bottom: 0;">
-                <strong>Built with:</strong> Gradio, NetworkX, and Plotly | 
-                <strong>Graph Layouts:</strong> Spring (force-directed), Circular, Kamada-Kawai, Shell
-            </p>
-        </div>
-        
-        <br> 
-        <hr style="margin-top: 40px; margin-bottom: 20px;">
-        <div style="background-color: #f8f9fa; padding: 20px; border-radius: 8px; margin-top: 20px; text-align: center;">
-            <p style="font-size: 14px; line-height: 1.8; margin: 0;">
-                This <strong>Basic Networks Explorer</strong> was created as part of a Bodleian Libraries Oxford Sassoon Research Fellowship.
-                </a>
-                funded research project:<br>
-                <em>Extracting Keywords from Crowdsourced Collections</em>.
-            </p><br><br> 
-            <p style="font-size: 14px; line-height: 1.8; margin: 0;">
-                The code for this tool was built with the aid of Claude Sonnet 4.5.
-            </p>
-        </div>
-        """)
-    
-    return demo
+### 4. ✅ Layout Restructured
+**Before:** Stacked vertically (busy at top)
 
-if __name__ == "__main__":
-    demo = create_interface()
-    demo.launch()
+**After:** Two-column layout
+- **Left Column:** Entity input records (Step 1)
+- **Right Column:** Relationship builder (Step 2) and customization (Step 3)
+
+This provides more breathing space and clearer visual organization.
+
+### 5. ✅ Bug Fix: Network Graph Generation
+**Issue:** Graph wasn't generating
+
+**Root Cause:** Incorrect argument order in relationship parsing
+- Expected: source, target, rel_type
+- Actual input: source, rel_type, target
+
+**Fix:** Corrected the argument extraction order to match the actual input order
+
+**Additional Improvement:** Graph now displays even without relationships (showing isolated nodes with a warning)
+
+### 6. ✅ British Examples with Auto-populated Relationships
+
+**Example 1: British WWII**
+- Winston Churchill, Clement Attlee, Field Marshal Montgomery, King George VI
+- Locations: London, North Africa, Yalta, Lüneburg Heath
+- Events: Battle of Britain, Battle of El Alamein, Yalta Conference, VE Day
+- **Relationships auto-populate:** works_with, participated_in connections
+
+**Example 2: Pride and Prejudice** (Already British)
+- Elizabeth Bennet, Mr Darcy, Jane Bennet, Mr Bingley
+- Locations: Longbourn, Pemberley, Rosings, Netherfield
+- Events: Meryton Assembly, Netherfield Ball, First Proposal
+- **Relationships auto-populate:** knows, located_in, participated_in connections
+
+### Additional Improvements
+- Simplified relationship dropdown labels (shortened from "From Entity 1" to just "From")
+- Better placeholder text in entity fields (British examples)
+- Graph now shows isolated nodes with warning if no relationships defined
+- More robust error handling
+
+## Files Updated
+1. `app.py` - Main application file with all changes
+2. `requirements.txt` - No changes needed
+3. `README.md` - Updated with new tool name
+
+## Ready for Deployment
+All files are updated and ready to upload to your Hugging Face Space: **Basic-Network-Explorer**