[Mypyspace-developer] SF.net SVN: mypyspace:[342] graphRDF/branches/songsAsNodes

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

Revision: 342
          http://mypyspace.svn.sourceforge.net/mypyspace/?rev=342&view=rev
Author:   gearmonkey
Date:     2009-05-05 17:14:14 +0000 (Tue, 05 May 2009)

Log Message:
-----------
got an edge dump but in the process discovered a flaw in my string splitting algorithm that needs fixing and such.  error has been labeled but not fixed (maybe we need trak for mypyspace...)

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

Added Paths:
-----------
    graphRDF/branches/songsAsNodes/complexSongGraphEdgeDump.txt.zip

Added: graphRDF/branches/songsAsNodes/complexSongGraphEdgeDump.txt.zip
===================================================================
(Binary files differ)


Property changes on: graphRDF/branches/songsAsNodes/complexSongGraphEdgeDump.txt.zip
___________________________________________________________________
Added: svn:mime-type
   + application/octet-stream

Modified: graphRDF/branches/songsAsNodes/graphRDF.py
===================================================================
--- graphRDF/branches/songsAsNodes/graphRDF.py	2009-05-03 15:24:42 UTC (rev 341)
+++ graphRDF/branches/songsAsNodes/graphRDF.py	2009-05-05 17:14:14 UTC (rev 342)
@@ -320,11 +320,71 @@
 					idx += 1 
 			debug("added " + str(idx-oldidx) + " edges\n--------")
 		print "should have added all the edges now.  Have a look:\n" + str(self.S)
+		
+	def dumpEdgeList(self, filename, graphToPrint=None, prefix=''):
+		"""Writes out (text) the edgelist of the selected 
+		graph (G by default) as tab delimited pairs
+		
+		source0\ttarget0
+		source1\ttarget1
+		...
+		sourceN\ttargetN
+		
+		If the graph selected is G, each node is represented
+		as it's myspace artist ID.  If the selected graph 
+		is S the nodes will be printed as filenames (or more 
+		strictly, the path beyond the common <prefix>, which is 
+		nominally just the filename but not always if there 
+		is a directory structure of some kind.)
+		
+		WARNING: If the filename given for output already 
+		exists it will be overwritten without any further 
+		notice, be aware..."""
+		if graphToPrint==None or graphToPrint == 'G':
+			graphToPrint = self.G
+			dumpReducedGraph = True
+			print "Dumping the artist as node edge list."
+		elif graphToPrint == 'S':
+			graphToPrint = self.S
+			dumpReducedGraph = False
+			print "Dumping the song as node edge list.\nFile path prefix has been set to: " + prefix
+		else:
+			print "the graph specified does not exist.  please specifit either 'G' for artist-centric graph or 'S' for song-centric graph."
+			return
+		try:
+			fH = open(filename, 'w')
+		except Exception, err:
+			print("dumpEdgeList had trouble opening the file named " + filename + " for writing.  Sort it out and try again...")
+			print str(err)
+			return
+	
+		try:		
+			print "The edge list from this graph has these properties:"
+			print graphToPrint
+			print "will be dumped to " + filename
+		except Exception, err:
+			print("dumpEdgeList was unable to access the graph you requested.  Sort it out and try again...")
+			print str(err)
+			return
 			
 		
+		for edge in graphToPrint.es:
+			if dumpReducedGraph:
+				sourceText = str(graphToPrint.vs[edge.source]['uid'])
+				targetText = str(graphToPrint.vs[edge.target]['uid'])
+			else:
+				sourceText = str(graphToPrint.vs[edge.source]['track'].lstrip(prefix))
+				targetText = str(graphToPrint.vs[edge.target]['track'].lstrip(prefix))
+			fH.write(sourceText + '\t' + targetText + '\n')
+			fH.flush()
+			
+		return
 		
 		
 		
+		
+		
+		
 	
 	def getGenreAssortativity(self):
 		'''get the assortivaty coeff for the igraph G - based on Newman 2002 "Mixing Patterns in Networks"
@@ -375,13 +435,16 @@
 def main(argv=None):
 	plot = False
 	includeEnds = False
+	base = None
+	expanded = None
 	folder = "person_seed_134901208"
 	media = ''
+	
 	if argv is None:
 		argv = sys.argv
 	try:
 		try:
-			opts, args = getopt.getopt(argv[1:], "hf:m:o:vb:e:p", ["help", "folder=", "media=", "output=", "baseGraph=","expandedGraph=". "plot"])
+			opts, args = getopt.getopt(argv[1:], "hf:m:o:vb:e:p", ["help", "folder=", "media=", "output=", "baseGraph=","expandedGraph=", "plot"])
 		except getopt.error, msg:
 			raise Usage(msg)
 		
@@ -397,6 +460,8 @@
 				output = value
 			if option in ("-f", "--folder"):
 				folder = value
+			if option in ("-m", "--media"):
+				media = value
 			if option in ("-p", "--plot"):
 				plot = True
 			if option in ("-b", "--baseGraph"):
@@ -406,7 +471,9 @@
 				
 		logging.basicConfig(**loggingConfig)
 		
-		G = graph('')
+		baseGraph = igraph.Graph(folder, media)
+		if base != None:
+			G
 		G.populate()
 		
 				


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