Machine Learning/Kaggle Social Network Contest - Revision history

Jjhale: /* Status */

2010-11-23T02:55:05Z

Status

← Older revision		Revision as of 19:55, 22 November 2010
Line 17:		Line 17:
	\| 11/24		\| 11/24
	\| [[/load data\| Load data]]		\| [[/load data\| Load data]]
			\|-
			!\|Describe network
			\| started
			\| 11/24
			\| [[/Network Description\| Network Description]]
	\|-		\|-
	!\|Choose problem representation		!\|Choose problem representation

2010-11-20T10:48:36Z

@@ Line 1: / Line 1: @@
 == Status ==
 {| border="1" cellspacing="0" cellpadding="2"
@@ Line 47: / Line 38: @@
 | [[/what to do with all the money | Prize Plan]]
 |}
 == Key Contest Info ==
@@ Line 63: / Line 63: @@
 Don’t despair if your first couple of solutions score low, this is an explorative process.
-== Brainstorming on Process ==
+== Our Working Data Dumps ==
 * Adjacency list based from the training data:
     http://dl.dropbox.com/u/14895843/social-network-kaggle/adj_list.out.csv
@@ Line 103: / Line 83: @@
           Additionally, note that only the first 32.7k rows have 'followees'
-== Possible Features ==
+== Useful Links ==
-*nodeid
+* [[http://arxiv.org/abs/1011.4071 | Supervised Random Walks: Predicting and Recommending Links in Social Networks]]
-*nodetofollowid
+* Matrix Digraph Algs: http://www.personal.kent.edu/~rmuhamma/Algorithms/MyAlgorithms/GraphAlgor/graphIntro.htm
-*median path length
+* "Strongly Connected Components": http://www.personal.kent.edu/~rmuhamma/Algorithms/MyAlgorithms/GraphAlgor/strongComponent.htm
-*shortest distance from nodeid to nodetofollowid
+* http://en.wikipedia.org/wiki/Graph_theory#Graph-theoretic_data_structures
-*inbound edges
+* http://en.wikipedia.org/wiki/Glossary_of_graph_theory
-*outbound edges
+* [[http://books.google.com/books?id=Ww3_bKcz6kgC&lpg=PA67&ots=aFSGYEjA_g&dq=calculate%20degree%20in%20%22directed%20graph%22%20OR%20digraph&pg=PP7#v=onepage&q&f=false | Another Google Book on Social Network Analysis]]

2010-11-20T05:33:18Z

Working Data Dumps

← Older revision		Revision as of 22:33, 19 November 2010
Line 93:		Line 93:
	First column: inbound vertex		First column: inbound vertex
	Remaining columns: list of vertices which point to it		Remaining columns: list of vertices which point to it
	Note: This is useful if interested in following the edges backwards quickly. This is useful to load as a hashtable keyed on inbound vertex returning the list.		Note: This is useful if interested in following the edges backwards quickly.
			This is useful to load as a hashtable keyed on inbound vertex returning the list.
	* Degree Features for all Nodes:		* Degree Features for all Nodes:
	http://dl.dropbox.com/u/14895843/social-network-kaggle/node_degree_features.csv		http://dl.dropbox.com/u/14895843/social-network-kaggle/node_degree_features.csv

2010-11-20T04:14:50Z

Status

2010-11-20T04:14:25Z

← Older revision		Revision as of 21:14, 19 November 2010
Line 93:		Line 93:
	Second column: Outbound Degree (count of the number of outbound edges from node)		Second column: Outbound Degree (count of the number of outbound edges from node)
	Third column: Inbound Degree (count of the number of inbound edges to node)		Third column: Inbound Degree (count of the number of inbound edges to node)
			Note: You can think of these as number of followees and followers (respectively).
			Additionally, note that only the first 32.7k rows have 'followees'

	== Possible Features ==		== Possible Features ==

2010-11-20T04:04:39Z

Working Data Dumps

← Older revision		Revision as of 21:04, 19 November 2010
Line 88:		Line 88:
	Remaining columns: list of vertices which point to it		Remaining columns: list of vertices which point to it
	Note: This is useful if interested in following the edges backwards quickly. This is useful to load as a hashtable keyed on inbound vertex returning the list.		Note: This is useful if interested in following the edges backwards quickly. This is useful to load as a hashtable keyed on inbound vertex returning the list.
	* Degree Features for all Nodes::		* Degree Features for all Nodes:
	http://dl.dropbox.com/u/14895843/social-network-kaggle/node_degree_features.csv		http://dl.dropbox.com/u/14895843/social-network-kaggle/node_degree_features.csv
	First column: Node Id		First column: Node Id

2010-11-20T04:04:20Z

Working Data Dumps

← Older revision		Revision as of 21:04, 19 November 2010
Line 88:		Line 88:
	Remaining columns: list of vertices which point to it		Remaining columns: list of vertices which point to it
	Note: This is useful if interested in following the edges backwards quickly. This is useful to load as a hashtable keyed on inbound vertex returning the list.		Note: This is useful if interested in following the edges backwards quickly. This is useful to load as a hashtable keyed on inbound vertex returning the list.
			* Degree Features for all Nodes::
			http://dl.dropbox.com/u/14895843/social-network-kaggle/node_degree_features.csv
			First column: Node Id
			Second column: Outbound Degree (count of the number of outbound edges from node)
			Third column: Inbound Degree (count of the number of inbound edges to node)

	== Possible Features ==		== Possible Features ==

2010-11-19T07:46:10Z

Status

← Older revision		Revision as of 00:46, 19 November 2010
Line 18:		Line 18:
	!\|Load data		!\|Load data
	\| started		\| started
	\| -		\| 11/24
	\| [[/load data\| Load data]]		\| [[/load data\| Load data]]
	\|-		\|-
	!\|Choose problem representation		!\|Choose problem representation
	\| started		\| started
	\| -		\| 11/24
	\| [[/Problem Representation\| Problem Representation]]		\| [[/Problem Representation\| Problem Representation]]
	\|-		\|-
Line 33:		Line 33:
	!\|fit to model		!\|fit to model
	\| 0%		\| 0%
	\| ~~11/24~~		\|
	\| [[/model \| Model]]		\| [[/model \| Model]]
	\|-		\|-
	!\|Win competition		!\|Win competition
	\| 0%		\| 0%
	\| ~~11/24~~		\|
	\| [[/what to do with all the money \| Prize Plan]]		\| [[/what to do with all the money \| Prize Plan]]
	\|}		\|}

2010-11-19T05:41:02Z

Status

← Older revision		Revision as of 22:41, 18 November 2010
Line 17:		Line 17:
	\|-		\|-
	!\|Load data		!\|Load data
	\| ~~100%~~		\| started
	\| -		\| -
	\| [[/load data\| Load data]]		\| [[/load data\| Load data]]
	\|-		\|-
	!\|Choose problem representation		!\|Choose problem representation
	\| 5%		\| started
	\| -		\| -
	\| [[/Problem Representation\| Problem Representation]]		\| [[/Problem Representation\| Problem Representation]]

2010-11-19T03:54:21Z

Official Data Downloads: adding status section - to track progress and provide direction

@@ Line 7: / Line 7: @@
 * Official Test Data File: http://dl.dropbox.com/u/14895843/social-network-kaggle/social_test.txt
 * Official Sample Submission File: http://dl.dropbox.com/u/14895843/social-network-kaggle/sample_submission.csv
 == Key Contest Info ==