Create app.py

app.py

@@ -0,0 +1,164 @@
+import gradio as gr
+import networkx as nx
+import matplotlib.pyplot as plt
+import spacy
+import pandas as pd
+import numpy as np
+from pathlib import Path
+
+# Load SpaCy model
+nlp = spacy.load("en_core_web_sm")
+
+# Categories and their colors
+CATEGORIES = {
+    "Main Themes": "#004d99",
+    "Events": "#006400",
+    "People": "#8b4513",
+    "Laws/Policies": "#4b0082",
+    "Concepts": "#800000"
+}
+
+def load_historical_data():
+    """Load and process the Unit 5 text data."""
+    try:
+        with open("Unit5_OCR.txt", "r", encoding="utf-8") as f:
+            content = f.read()
+        return content
+    except FileNotFoundError:
+        return "Historical data file not found."
+
+def extract_entities(text):
+    """Extract named entities and important terms from text."""
+    doc = nlp(text)
+    entities = {}
+    
+    # Extract named entities
+    for ent in doc.ents:
+        if ent.label_ in ["PERSON", "EVENT", "DATE", "LAW", "ORG"]:
+            if ent.text not in entities:
+                entities[ent.text] = {
+                    "type": ent.label_,
+                    "count": 1,
+                    "context": []
+                }
+            else:
+                entities[ent.text]["count"] += 1
+    
+    return entities
+
+def find_related_terms(term, text, window_size=100):
+    """Find terms that appear near the search term."""
+    term = term.lower()
+    text = text.lower()
+    related = {}
+    
+    # Find all occurrences of the term
+    index = text.find(term)
+    while index != -1:
+        # Get surrounding context
+        start = max(0, index - window_size)
+        end = min(len(text), index + len(term) + window_size)
+        context = text[start:end]
+        
+        # Process context to find other entities
+        doc = nlp(context)
+        for ent in doc.ents:
+            if ent.text.lower() != term:
+                if ent.text not in related:
+                    related[ent.text] = {
+                        "type": ent.label_,
+                        "count": 1,
+                        "relevance": 1.0
+                    }
+                else:
+                    related[ent.text]["count"] += 1
+                    related[ent.text]["relevance"] += 0.5
+        
+        index = text.find(term, index + 1)
+    
+    return related
+
+def generate_context_map(term):
+    """Generate a network visualization for the given term."""
+    if not term.strip():
+        return None
+        
+    # Load historical data
+    content = load_historical_data()
+    if content == "Historical data file not found.":
+        return None
+    
+    # Create network graph
+    G = nx.Graph()
+    
+    # Find related terms
+    related_items = find_related_terms(term, content)
+    
+    # Add central node
+    G.add_node(term, category="Main Themes")
+    
+    # Add related nodes (limit to top 10 by relevance)
+    sorted_items = sorted(related_items.items(), 
+                         key=lambda x: x[1]["relevance"], 
+                         reverse=True)[:10]
+    
+    for item_name, item_data in sorted_items:
+        G.add_node(item_name, category=item_data["type"])
+        G.add_edge(term, item_name, 
+                  weight=item_data["relevance"],
+                  length=2.0/item_data["relevance"])
+    
+    # Create visualization
+    plt.figure(figsize=(12, 12))
+    plt.clf()
+    
+    # Set up the layout
+    pos = nx.spring_layout(G, k=1, iterations=50)
+    
+    # Draw nodes
+    for category, color in CATEGORIES.items():
+        nodes = [node for node, attr in G.nodes(data=True) 
+                if attr.get("category", "") == category]
+        nx.draw_networkx_nodes(G, pos, nodelist=nodes, 
+                             node_color=color, 
+                             node_size=2000)
+    
+    # Draw edges
+    nx.draw_networkx_edges(G, pos, edge_color='white', 
+                          width=1, alpha=0.5)
+    
+    # Add labels
+    labels = {node: node for node in G.nodes()}
+    nx.draw_networkx_labels(G, pos, labels, font_size=8, 
+                          font_color='white')
+    
+    # Set dark background
+    plt.gca().set_facecolor('#1a1a1a')
+    plt.gcf().set_facecolor('#1a1a1a')
+    
+    # Add title
+    plt.title(f"Historical Context Map for '{term}'", 
+              color='white', pad=20)
+    
+    return plt.gcf()
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=generate_context_map,
+    inputs=gr.Textbox(label="Enter a historical term from Unit 5",
+                     placeholder="e.g., Civil War, Abraham Lincoln, Reconstruction"),
+    outputs=gr.Plot(),
+    title="Historical Context Mapper",
+    description="This tool generates a network visualization showing the historical context and connections for terms from Unit 5 (1844-1877).",
+    theme="darkhuggingface",
+    examples=[
+        ["Civil War"],
+        ["Abraham Lincoln"],
+        ["Reconstruction"],
+        ["Manifest Destiny"],
+        ["Transcontinental Railroad"]
+    ]
+)
+
+if __name__ == "__main__":
+    iface.launch()