[Mypyspace-developer] SF.net SVN: mypyspace:[343] graphRDF/branches/songsAsNodes

[<gea...@us...>]

Revision: 343
          http://mypyspace.svn.sourceforge.net/mypyspace/?rev=343&view=rev
Author:   gearmonkey
Date:     2009-05-09 07:10:32 +0000 (Sat, 09 May 2009)

Log Message:
-----------
added a script to help repair any graphs made (principally mine) before I sorted out the bug in graphRDF that was fixed in the previous revision.

Modified Paths:
--------------
    graphRDF/branches/songsAsNodes/graphRDF.py
    graphRDF/branches/songsAsNodes/hplot.py

Added Paths:
-----------
    graphRDF/branches/songsAsNodes/repairSongGraph.py

Modified: graphRDF/branches/songsAsNodes/graphRDF.py
===================================================================
--- graphRDF/branches/songsAsNodes/graphRDF.py	2009-05-05 17:14:14 UTC (rev 342)
+++ graphRDF/branches/songsAsNodes/graphRDF.py	2009-05-09 07:10:32 UTC (rev 343)
@@ -14,6 +14,7 @@
 import getopt
 import ftplib
 import mopy
+import re
 from logging import log, error, warning, info, debug
 import logging
 from numpy import *
@@ -24,6 +25,7 @@
 this package interfaces w/ myrdfspace.com to analyze and plot graphs of myspace artists
 
 by kurt Jacobson 29/10/2007 (c) 
+highly modified by Ben Fields on and around 15/04/2009
 
 dependencies:
 - igraph (http://cneurocvs.rmki.kfki.hu/igraph/)
@@ -69,10 +71,14 @@
 def string2List(listAsString):
 	"""A little helper function that takes in a string that was made by printing a list and breaks it up into a list of it composite parts.
 	      returns the list. 
-	      could do with some error checking, but seems to work with the track attribute and ought to work with the genres as well."""
-	items = listAsString.split("', '")
-	items[0] = items[0].lstrip("['")
+	      could do with some error checking, but seems to work with the track attribute and ought to work with the genres as well. 
+	Now handles both kinds of quote via the glory of regular expressions."""
+	sep = re.compile('[\'\"], [\'\"]')
+	items = sep.split(listAsString)
+	items[0] = items[0].lstrip("['")#could do this with a regEx also, but, eh...
+	items[0] = items[0].lstrip("[\"")
 	items[-1] = items[-1].rstrip("']")
+	items[-1] = items[-1].rstrip("\"]")
 	return items
 	
 	

Modified: graphRDF/branches/songsAsNodes/hplot.py
===================================================================
--- graphRDF/branches/songsAsNodes/hplot.py	2009-05-05 17:14:14 UTC (rev 342)
+++ graphRDF/branches/songsAsNodes/hplot.py	2009-05-09 07:10:32 UTC (rev 343)
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # encoding: utf-8
 """
-untitled.py
+hplot.py
 
 Created by Kurt Jacobson on 2008-11-11.
 Copyright (c) 2008 C4DM - Queen Mary U of London. All rights reserved.

Added: graphRDF/branches/songsAsNodes/repairSongGraph.py
===================================================================
--- graphRDF/branches/songsAsNodes/repairSongGraph.py	                        (rev 0)
+++ graphRDF/branches/songsAsNodes/repairSongGraph.py	2009-05-09 07:10:32 UTC (rev 343)
@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+# encoding: utf-8
+"""
+repairSongGraph.py
+
+A script to clean up the song graph without rebuilding the whole thing to deal with the poor string parsing in the original implementation
+
+"""
+
+import sys
+import os
+from graphRDF import *
+
+Usage = """usage: repairSongGraph [original Artist graphmlz] [orignal Song graphmlz] [destination Song graphmlz]\n"""
+
+def main(argv=None):
+	vertIdxsToDelete = []
+	uidsAffected = []
+	vertIdxsAdded = []
+	idx = 0
+	
+	if argv is None:
+		argv = sys.argv
+	if not len(argv) == 4:
+		print Usage
+		return 104
+	
+	
+	fixMe = graph('person_seed_134901208')
+	print "Loading original Artist graph from " + argv[1]
+	try:
+		fixMe.G = igraph.Graph.Load(argv[1], format='graphmlz')
+	except Exception, err:
+		print Usage + "encountered problems loading the original Artist graphmlz file."
+		return 105
+	fixMe.isPopulated = True
+	print "Loading orginal Song graph from " + argv[2]
+	try:
+		fixMe.S = igraph.Graph.Load(argv[2], format='graphmlz')
+	except Exception, err:
+		print Usage + "encountered problems loading the original Song graphmlz file."
+		return 106
+	print "will write out correceted graph to " + argv[3]
+	print "scrubbing Song Graph..."
+
+	
+	idx = len(fixMe.S.vs) - 1	
+	for vert in fixMe.S.vs:
+		tracks = string2List(vert['track'])
+		if len(tracks) > 1:
+			print "Removing corrupt vertex from artist with uid " + vert['uid'] + " and breaking it into " + str(len(tracks)) + " correct vertices."
+			vertIdxsToDelete.append(vert.index)
+			uidsAffected.append(vert['uid'])
+			fixMe.S.add_vertices(len(tracks))
+			for track in tracks:
+				idx +=1
+				fixMe.S.vs[idx]['track'] = track
+				fixMe.S.vs[idx]['uid'] = vert['uid']
+				vertIdxsAdded.append(idx)
+	print "found " + str(len(vertIdxsToDelete)) + " vertices to delete.\nAdding " + str(len(vertIdxsAdded)) + " repaired vertices."
+	
+	addedVertSeq = igraph.VertexSeq(fixMe.S, vertIdxsAdded)	
+	toDeleteVertSeq = igraph.VertexSeq(fixMe.S, vertIdxsToDelete)
+	artistVertsOfInterest = fixMe.G.vs.select(uid_in=uidsAffected)
+	sourcesDealtWith = []
+	targetsDealtWith = []
+	idx = len(fixMe.S.es) - 1
+	print "dealing with " + str(len(artistVertsOfInterest)) + "nodes in total"
+	for i,vert in enumerate(artistVertsOfInterest):
+		for index, edgeIdx in enumerate(fixMe.G.adjacent(vert.index, 'all')):
+			edge = fixMe.G.es[edgeIdx]
+			sources = fixMe.S.vs.select(uid=fixMe.G.vs[edge.source]['uid'])
+			targets = fixMe.S.vs.select(uid=fixMe.G.vs[edge.target]['uid'])
+			#print "Expanding edge " + str(edgeIdx) + " to " + str(len(sources) * len(targets)) + " edges."
+			oldidx = idx
+			for source in sources:
+				if not source.index in sourcesDealtWith:
+					sourcesDealtWith.append(source.index)
+					for target in targets:
+						if not target.index in targetsDealtWith:
+							targetsDealtWith.append(target.index)
+							fixMe.S.add_edges((source.index,target.index))
+							idx += 1
+							fixMe.S.es[idx]['audioWeight'] = -1
+				
+			#print "added " + str(idx-oldidx) + " edges\n--------"
+		print str(len(artistVertsOfInterest) - i - 1) + " nodes left to deal with"	
+	print "should have added all the edges now.  Have a look:\n" + str(fixMe.S) + "\nRemoving old corrupt nodes and saving. Saving expanding graph in outputfile dumpedgraph.mlz in case something goes wrong."
+	fixMe.S.write("dumpedgraph.mlz", format="graphmlz")
+	
+	cleanGraph = fixMe.S.delete_vertices(vertIdxsToDelete)
+	
+	print "overwriting " + argv[3] + " with corrected graph."
+	
+	cleanGraph.write(argv[3],format="graphmlz")
+	
+	return 0
+		
+	
+
+
+if __name__ == '__main__':
+	main()
+


Property changes on: graphRDF/branches/songsAsNodes/repairSongGraph.py
___________________________________________________________________
Added: svn:executable
   + *


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.