mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-09-10 04:00:35 +00:00
266 lines
9.1 KiB
Plaintext
266 lines
9.1 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"[](https://colab.research.google.com/github/Hawksight-AI/semantica/blob/main/cookbook/advanced/02_Advanced_Graph_Analytics.ipynb)\n",
|
|
"\n",
|
|
"# Advanced Graph Analytics\n",
|
|
"\n",
|
|
"## Overview\n",
|
|
"\n",
|
|
"This notebook demonstrates advanced graph analytics using GraphAnalyzer, CentralityCalculator, CommunityDetector, ConnectivityAnalyzer, GraphValidator, Deduplicator, and **GraphStore** for persistent storage.\n",
|
|
"\n",
|
|
"\n",
|
|
"**Documentation**: [API Reference](https://semantica.readthedocs.io/reference/kg/)\n",
|
|
"\n",
|
|
"### Learning Objectives\n",
|
|
"\n",
|
|
"- Use GraphAnalyzer for comprehensive graph analysis\n",
|
|
"- Use CentralityCalculator for advanced centrality measures\n",
|
|
"- Use CommunityDetector for community detection\n",
|
|
"- Use ConnectivityAnalyzer for connectivity analysis\n",
|
|
"- Use GraphValidator and Deduplicator for graph quality\n",
|
|
"- **Use GraphStore to persist graphs to Neo4j or FalkorDB**\n",
|
|
"\n",
|
|
"## Installation\n",
|
|
"\n",
|
|
"Install Semantica from PyPI:\n",
|
|
"\n",
|
|
"```bash\n",
|
|
"pip install semantica\n",
|
|
"# Or with all optional dependencies:\n",
|
|
"pip install semantica[all]\n",
|
|
"```\n",
|
|
"\n",
|
|
"---\n",
|
|
"\n",
|
|
"## Workflow: Graph Analysis → Centrality → Communities → Connectivity → Validation → Deduplication → **Persist to Graph Store**\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from semantica.kg import GraphBuilder, GraphAnalyzer, CentralityCalculator, CommunityDetector, ConnectivityAnalyzer, GraphValidator\n",
|
|
"from semantica.deduplication import DuplicateDetector, EntityMerger, MergeStrategy\n",
|
|
"\n",
|
|
"builder = GraphBuilder()\n",
|
|
"analyzer = GraphAnalyzer()\n",
|
|
"\n",
|
|
"entities = [\n",
|
|
" {\"id\": \"e1\", \"type\": \"Organization\", \"name\": \"Apple Inc.\", \"properties\": {}},\n",
|
|
" {\"id\": \"e2\", \"type\": \"Person\", \"name\": \"Tim Cook\", \"properties\": {}},\n",
|
|
" {\"id\": \"e3\", \"type\": \"Location\", \"name\": \"Cupertino\", \"properties\": {}}\n",
|
|
"]\n",
|
|
"\n",
|
|
"relationships = [\n",
|
|
" {\"source\": \"e2\", \"target\": \"e1\", \"type\": \"CEO_of\", \"properties\": {}},\n",
|
|
" {\"source\": \"e1\", \"target\": \"e3\", \"type\": \"located_in\", \"properties\": {}}\n",
|
|
"]\n",
|
|
"\n",
|
|
"kg = builder.build(entities, relationships)\n",
|
|
"\n",
|
|
"metrics = analyzer.compute_metrics(kg)\n",
|
|
"\n",
|
|
"print(f\"Graph metrics:\")\n",
|
|
"print(f\" Entities: {metrics.get('entity_count', 0)}\")\n",
|
|
"print(f\" Relationships: {metrics.get('relationship_count', 0)}\")\n",
|
|
"print(f\" Density: {metrics.get('density', 0):.3f}\")\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Step 2: Advanced Centrality Measures\n",
|
|
"\n",
|
|
"Calculate multiple centrality measures.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"centrality_calculator = CentralityCalculator()\n",
|
|
"\n",
|
|
"degree_centrality_result = centrality_calculator.calculate_degree_centrality(kg)\n",
|
|
"degree_centrality = degree_centrality_result.get('centrality', {})\n",
|
|
"betweenness_centrality_result = centrality_calculator.calculate_betweenness_centrality(kg)\n",
|
|
"betweenness_centrality = betweenness_centrality_result.get('centrality', {})\n",
|
|
"\n",
|
|
"print(f\"Degree centrality: {len(degree_centrality)} entities\")\n",
|
|
"print(f\"Betweenness centrality: {len(betweenness_centrality)} entities\")\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Step 3: Community Detection\n",
|
|
"\n",
|
|
"Detect communities in the graph.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"community_detector = CommunityDetector()\n",
|
|
"\n",
|
|
"communities = community_detector.detect_communities(kg)\n",
|
|
"\n",
|
|
"print(f\"Detected {len(communities)} communities\")\n",
|
|
"for i, community in enumerate(communities[:3], 1):\n",
|
|
" print(f\" Community {i}: {len(community)} entities\")\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Step 4: Connectivity Analysis\n",
|
|
"\n",
|
|
"Analyze graph connectivity.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"connectivity_analyzer = ConnectivityAnalyzer()\n",
|
|
"\n",
|
|
"connectivity = connectivity_analyzer.analyze_connectivity(kg)\n",
|
|
"\n",
|
|
"print(f\"Connectivity analysis:\")\n",
|
|
"print(f\" Is connected: {connectivity.get('is_connected', False)}\")\n",
|
|
"print(f\" Components: {len(connectivity.get('components', []))}\")\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Step 5: Graph Validation and Deduplication\n",
|
|
"\n",
|
|
"Validate and deduplicate the graph.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"graph_validator = GraphValidator()\n",
|
|
"\n",
|
|
"validation_result = graph_validator.validate(kg)\n",
|
|
"\n",
|
|
"print(f\"Graph validation: {validation_result.get('valid', False)}\")\n",
|
|
"print(f\"Issues found: {len(validation_result.get('issues', []))}\")\n",
|
|
"\n",
|
|
"# For deduplication, use semantica.deduplication module:\n",
|
|
"# from semantica.deduplication import DuplicateDetector, EntityMerger, MergeStrategy\n",
|
|
"# detector = DuplicateDetector(similarity_threshold=0.8)\n",
|
|
"# duplicate_groups = detector.detect_duplicate_groups(kg.get('entities', []))\n",
|
|
"# merger = EntityMerger()\n",
|
|
"# merge_operations = merger.merge_duplicates(kg.get('entities', []), strategy=MergeStrategy.KEEP_MOST_COMPLETE)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Step 6: Persist to Graph Store\n",
|
|
"\n",
|
|
"Store the analyzed graph in a persistent graph database using GraphStore.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from semantica.graph_store import GraphStore\n",
|
|
"\n",
|
|
"# Option 1: Neo4j (requires Neo4j server running)\n",
|
|
"graph_store = GraphStore(backend=\"neo4j\", uri=\"bolt://localhost:7687\", user=\"neo4j\", password=\"password\")\n",
|
|
"graph_store.connect()\n",
|
|
"\n",
|
|
"# Store entities as nodes and track node ID mapping\n",
|
|
"node_id_map = {}\n",
|
|
"for entity in entities:\n",
|
|
" node = graph_store.create_node(\n",
|
|
" labels=[entity[\"type\"]],\n",
|
|
" properties={\"name\": entity[\"name\"], \"original_id\": entity[\"id\"]}\n",
|
|
" )\n",
|
|
" node_id_map[entity[\"id\"]] = node.get(\"id\")\n",
|
|
" print(f\"Stored node: {entity['name']} (ID: {node.get('id')})\")\n",
|
|
"\n",
|
|
"# Store relationships using mapped node IDs\n",
|
|
"for rel in relationships:\n",
|
|
" source_id = node_id_map.get(rel[\"source\"])\n",
|
|
" target_id = node_id_map.get(rel[\"target\"])\n",
|
|
" \n",
|
|
" if source_id is not None and target_id is not None:\n",
|
|
" relationship = graph_store.create_relationship(\n",
|
|
" start_node_id=source_id,\n",
|
|
" end_node_id=target_id,\n",
|
|
" rel_type=rel[\"type\"],\n",
|
|
" properties=rel.get(\"properties\", {})\n",
|
|
" )\n",
|
|
" print(f\"Stored relationship: {rel['source']} -{rel['type']}-> {rel['target']}\")\n",
|
|
" else:\n",
|
|
" print(f\"Warning: Could not find node IDs for relationship {rel['source']} -> {rel['target']}\")\n",
|
|
"\n",
|
|
"# Query using Cypher\n",
|
|
"results = graph_store.execute_query(\"MATCH (n) RETURN n.name, labels(n) LIMIT 10\")\n",
|
|
"print(f\"\\nQuery results: {len(results.get('records', []))} nodes\")\n",
|
|
"\n",
|
|
"# Get statistics\n",
|
|
"stats = graph_store.get_stats()\n",
|
|
"print(f\"\\nGraph store statistics:\")\n",
|
|
"print(f\" Node count: {stats.get('node_count', 'N/A')}\")\n",
|
|
"print(f\" Relationship count: {stats.get('relationship_count', 'N/A')}\")\n",
|
|
"print(f\" Label counts: {stats.get('label_counts', {})}\")\n",
|
|
"\n",
|
|
"graph_store.close()\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Summary\n",
|
|
"\n",
|
|
"You've learned advanced graph analytics:\n",
|
|
"\n",
|
|
"- **GraphAnalyzer**: Comprehensive graph analysis and metrics\n",
|
|
"- **CentralityCalculator**: Multiple centrality measures\n",
|
|
"- **CommunityDetector**: Community detection\n",
|
|
"- **ConnectivityAnalyzer**: Connectivity analysis\n",
|
|
"- **GraphValidator**: Graph validation\n",
|
|
"- **Deduplicator**: Graph deduplication\n",
|
|
"- **GraphStore**: Persist graphs to Neo4j or FalkorDB\n",
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"language_info": {
|
|
"name": "python"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|