ソーシャルグラフ分析
•
25 likes•2,519 views
This document provides an introduction to analyzing social graphs using graph databases. It discusses using Neo4j to store social graph data and analyze centrality and clustering coefficients. Sample code is shown for inserting nodes and relationships in Neo4j and traversing the graph. Analyzing a sample social network dataset found centrality values ranged from 1 to over 900, with a median of 10, and clustering coefficients ranged from 0 to 1. Visualization of the social graph and analysis results is also briefly discussed.
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) {
GraphDatabaseService graphDb = new
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally {
tx.finish();
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-51-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) {
GraphDatabaseService graphDb = new
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally {
tx.finish();
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-52-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) { ID: 1
GraphDatabaseService graphDb = new NAME: kimura
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally {
tx.finish();
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-53-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) { ID: 1
GraphDatabaseService graphDb = new NAME: kimura
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally {
tx.finish();
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-54-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) { ID: 1
GraphDatabaseService graphDb = new NAME: kimura
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally { ID: 2
tx.finish(); NAME: Kato
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-55-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) { ID: 1
GraphDatabaseService graphDb = new NAME: kimura
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
firstNode.setProperty("Name", "Kimura");
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally { ID: 2
tx.finish(); NAME: Kato
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-56-320.jpg)
![Insert vertices,
make relationship
public final class InputVertex {
public static void main(final String[] args) { ID: 1
GraphDatabaseService graphDb = new NAME: kimura
EmbeddedGraphDatabase("/tmp/neo4j");
Transaction tx = graphDb.beginTx();
try {
Node firstNode = graphDb.createNode();
ID: 3
firstNode.setProperty("Name", "Kimura"); Relation: Like
Node secondNode = graphDb.createNode();
secondNode.setProperty("Name", "Kato");
firstNode.createRelationshipTo(secondNode,
DynamicRelationshipType.withName("LIKE"));
tx.success();
} finally { ID: 2
tx.finish(); NAME: Kato
}
graphDb.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-57-320.jpg)
![Batch Insert
• Non thread safe, non transaction
• But very fast!
public final class Batch {
public static void main(final String[] args) {
BatchInserter inserter = new BatchInserterImpl("/tmp/neo4j",
BatchInserterImpl.loadProperties("/tmp/neo4j.props"));
Map<String, Object> prop = new HashMap<String, Object>();
prop.put("Name", "Kimura");
prop.put("Age", 21);
long node1 = inserter.createNode(prop);
prop.put("Name", "Kato");
prop.put("Age", 21);
long node2 = inserter.createNode(prop);
inserter.createRelationship(node1, node2,
DynamicRelationshipType.withName("LIKE"), null);
inserter.shutdown();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-58-320.jpg)
![Traversal sample
•
public static void main(final String[] args) {
GraphDatabaseService graphDB = new EmbeddedGraphDatabase(args[0]);
Node node = graphDB.getNodeById(1);
Traverser friends = node.traverse(
//
Order.DEPTH_FIRST, BREADTH_FIRST
//
StopEvaluator.END_OF_GRAPH, DEPTH_ONE
//
ReturnableEvaluator.ALL_BUT_START_NODE, ALL, isReturnableNode()
//
DynamicRelationshipType.withName("LIKE"),
//
Direction.OUTGOING); INCOMING, BOTH
for (Node nodeBuf : friends) {
TraversalPosition currentPosition = friends.currentPosition();
}
}](https://image.slidesharecdn.com/20110806mixikimuramodify-110806083355-phpapp01/85/-59-320.jpg)
ソーシャルグラフ分析
- 2. • ( ) • @kimuras • G(2007 ) • • •
- 3. Agenda • Introduction • The past work • Introduction to GraphDB • Introduction to Neo4j • Introduction to analysis sample
- 4. Introduction
- 5. Motivation for social graph analysis
- 6. mixi 30000000 ID 22500000 # of member id 15000000 7500000 0 2007 2008 2009 2010 2011 year
- 7. What is Social Graph?
- 15. Feed Back
- 16. Feed Back
- 17. Feed Back
- 18. Feed Back
- 19. Feed Back
- 20. Approach for SG analysis Feed Back
- 21. The past work
- 22. • •
- 23. Relational Databases Dump & Denormalization from_id to_id id name age Key value 1 2 1 Kimura 18 From:1 2,3 1 3 2 kato 45 From:2 3 2 3 3 ito 21 Prof:1 Kimura,18 Prof:2 Kato,45
- 24. Relational Databases Dump & reimplementation Denormalization from_id to_id id name age Key value 1 1 2 3 maintenance cost 1 2 Kimura kato 18 45 From:1 From:2 2,3 3 2 3 3 ito 21 Prof:1 Kimuras,18 Prof:2 Kato,45 scalability
- 26. What is graph
- 27. What is graph Vertex (node : )
- 28. What is graph Vertex (node : ) Edge ( )
- 29. What is graph Vertex (node : ) Undirected graph ( ) Edge ( )
- 30. What is graph Vertex (node : ) Edge ( )
- 31. What is graph Vertex (node : ) Edge ( )
- 32. What is graph Vertex (node : ) Edge ( )
- 33. What is graph Vertex (node : ) Directed graph ( ) Edge ( )
- 34. What is GraphDB Vertex (node : ) Edge ( )
- 35. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( )
- 36. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 NAME: ITO PROP: Female AGE: 21
- 37. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 NAME: ITO PROP: Female AGE: 21
- 38. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 NAME: ITO PROP: Female AGE: 21
- 39. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 ID: 3 NAME: ITO LABEL: Like PROP: Female Since: 2011/08/06 AGE: 21 OutGoing: 2
- 40. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 ID: 3 NAME: ITO LABEL: Like PROP: Female Since: 2011/08/06 AGE: 21 OutGoing: 2
- 41. What is GraphDB ID: 1 Vertex (node : ) NAME: kimura PROP: Male AGE: 18 Edge ( ) ID: 2 ID: 3 NAME: ITO LABEL: Like PROP: Female Since: 2011/08/06 AGE: 21 OutGoing: 2
- 42. The implementations for GraphDB http://en.wikipedia.org/wiki/GraphDB
- 44. GraphDB Neo4j • True ACID transactions • High availability • Scales to billions of nods and relationships • High speed querying through traversals Single instance(GPLv3) Multiple instance(AGPLv3) Embedded EmbeddedGraphDatabase HighlyAvailableGraphDatabase Standalone Neo4j Server Neo4j Server high availability mode http://neo4j.org/
- 45. Other my favorite features for Neo4j • RESTful APIs • Query Language(Cypher) • Full indexing – lucene • Implemented graph algorithm – A*, Dijkstra – High speed traverse • Gremlin supported – Like a query language http://www.tinkerpop.com/post/4633229547/tinkerpop-graph-stack
- 46. Introduction simple Neo4j usecase Single node Multi node Embedded Analyses system Analyses system Analyses system Analyses system Server
- 47. Introduction simple Neo4j usecase Single node Multi node Embedded Analyses system Analyses system Analyses system Analyses system Server
- 48. Introduction simple Neo4j usecase Single node Multi node Analyses system Embedded Analyses system Analyses system Analyses system Server
- 49. Introduction simple Neo4j usecase Single node Multi node Analyses system Embedded Analyses system Analyses system Analyses system Server
- 50. Introduction to simple embedded Neo4j • Insert Vertices & make Relationships • Single node & Embedded • Traversal sample
- 51. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { GraphDatabaseService graphDb = new EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { tx.finish(); } graphDb.shutdown(); } }
- 52. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { GraphDatabaseService graphDb = new EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { tx.finish(); } graphDb.shutdown(); } }
- 53. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { ID: 1 GraphDatabaseService graphDb = new NAME: kimura EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { tx.finish(); } graphDb.shutdown(); } }
- 54. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { ID: 1 GraphDatabaseService graphDb = new NAME: kimura EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { tx.finish(); } graphDb.shutdown(); } }
- 55. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { ID: 1 GraphDatabaseService graphDb = new NAME: kimura EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { ID: 2 tx.finish(); NAME: Kato } graphDb.shutdown(); } }
- 56. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { ID: 1 GraphDatabaseService graphDb = new NAME: kimura EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); firstNode.setProperty("Name", "Kimura"); Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { ID: 2 tx.finish(); NAME: Kato } graphDb.shutdown(); } }
- 57. Insert vertices, make relationship public final class InputVertex { public static void main(final String[] args) { ID: 1 GraphDatabaseService graphDb = new NAME: kimura EmbeddedGraphDatabase("/tmp/neo4j"); Transaction tx = graphDb.beginTx(); try { Node firstNode = graphDb.createNode(); ID: 3 firstNode.setProperty("Name", "Kimura"); Relation: Like Node secondNode = graphDb.createNode(); secondNode.setProperty("Name", "Kato"); firstNode.createRelationshipTo(secondNode, DynamicRelationshipType.withName("LIKE")); tx.success(); } finally { ID: 2 tx.finish(); NAME: Kato } graphDb.shutdown(); } }
- 58. Batch Insert • Non thread safe, non transaction • But very fast! public final class Batch { public static void main(final String[] args) { BatchInserter inserter = new BatchInserterImpl("/tmp/neo4j", BatchInserterImpl.loadProperties("/tmp/neo4j.props")); Map<String, Object> prop = new HashMap<String, Object>(); prop.put("Name", "Kimura"); prop.put("Age", 21); long node1 = inserter.createNode(prop); prop.put("Name", "Kato"); prop.put("Age", 21); long node2 = inserter.createNode(prop); inserter.createRelationship(node1, node2, DynamicRelationshipType.withName("LIKE"), null); inserter.shutdown(); } }
- 59. Traversal sample • public static void main(final String[] args) { GraphDatabaseService graphDB = new EmbeddedGraphDatabase(args[0]); Node node = graphDB.getNodeById(1); Traverser friends = node.traverse( // Order.DEPTH_FIRST, BREADTH_FIRST // StopEvaluator.END_OF_GRAPH, DEPTH_ONE // ReturnableEvaluator.ALL_BUT_START_NODE, ALL, isReturnableNode() // DynamicRelationshipType.withName("LIKE"), // Direction.OUTGOING); INCOMING, BOTH for (Node nodeBuf : friends) { TraversalPosition currentPosition = friends.currentPosition(); } }
- 60. Traversal sample Order.BREADTH_FIRST •
- 61. Traversal sample Order.BREADTH_FIRST •
- 62. Traversal sample Order.BREADTH_FIRST •
- 63. Traversal sample Order.BREADTH_FIRST •
- 64. Traversal sample Order.BREADTH_FIRST •
- 65. Traversal sample Order.BREADTH_FIRST •
- 66. Traversal sample Order.DEPTH_FIRST •
- 67. Traversal sample Order.DEPTH_FIRST •
- 68. Traversal sample Order.DEPTH_FIRST •
- 69. Traversal sample Order.DEPTH_FIRST •
- 70. Traversal sample Order.DEPTH_FIRST •
- 71. Traversal sample Order.DEPTH_FIRST •
- 72. Neoclipse sample http://wiki.neo4j.org/content/Neoclipse
- 73. experiment • mixi Neo4j • • Machine: 24 core CPU, Memory 65GB • Neo4j: BatchInsert, community, embedded • Data • 1500 6 513m17sec (about 8.6h)
- 74. Network Dataset • Stanford Large Network Dataset Collection • SNAP has a Wide variety of graph data! Social Networks Communication networks Citation networks Collaboration networks Web graphs Product co-purchasing networks Internet peer-to-peer networks Road networks Autonomous systems graphs Signed networks Wikipedia networks and metadata Memetracker and Twitter http://snap.stanford.edu/data/index.html
- 75. Introduction to Analysis Sample
- 76. Architecture Service Database Analysis Visualization (Social Graph)
- 77. Introduction Analyses Sample • Centrality ( ) • Clustering coefficient ( )
- 78. Centrality ( ) • = Pagerank
- 79. • • = Vertex ( )
- 80. • • = Vertex ( ) 1 1 1
- 81. • • = Vertex ( ) 2 1 1 2 1 2
- 82. • • = Vertex ( ) 2 1 1 2 1 2
- 83. • • = Vertex ( ) 2 1 1 4 2 1 2
- 84. • • = Vertex ( ) 2 1 1 4 2 1 2
- 85. mixi • 1000 • summary Min 1st Que. Median Mean 3rd Que. Max 1.00 3.00 10.00 25.69 30.00 903.00
- 86. • • ≒
- 87. • • ≒ =0/3=0
- 88. • • ≒ =0/3=0 =1/3
- 89. • • ≒ =0/3=0 =1/3 =2/3
- 90. • • ≒ =0/3=0 =1/3 =2/3 =3/3=1
- 91. • 1000 • summary Min 1st Que. Median Mean 3rd Que. Max 0.00 0.00 0.1157 0.2071 0.2667 1.000
- 94. • 25 0.08
- 95. • 14 0.17
- 96. • 10 0.68
- 97. • 4 1
- 99. • 2hop Social Graph • Edge • ( ) • Vertex • ( ) • Gephi http://gephi.org/
- 101. • Social Graph • • GraphDB • Neo4j • R • Visualization
- 102. Thanks!
Editor's Notes
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- &#x30FB;TC&#x3082;mysql&#x3082;&#x73FE;&#x5F79;&#x3060;&#x3057;&#x3001;&#x5927;&#x597D;&#x304D;\n
- &#x30FB;TC&#x3082;mysql&#x3082;&#x73FE;&#x5F79;&#x3060;&#x3057;&#x3001;&#x5927;&#x597D;&#x304D;\n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n
- \n