[Mypyspace-developer] SF.net SVN: mypyspace:[349] graphRDF/branches/songsAsNodes/loadWeights.py

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

Revision: 349
          http://mypyspace.svn.sourceforge.net/mypyspace/?rev=349&view=rev
Author:   gearmonkey
Date:     2009-05-26 21:15:29 +0000 (Tue, 26 May 2009)

Log Message:
-----------
added the weight loader.

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

Added: graphRDF/branches/songsAsNodes/loadWeights.py
===================================================================
--- graphRDF/branches/songsAsNodes/loadWeights.py	                        (rev 0)
+++ graphRDF/branches/songsAsNodes/loadWeights.py	2009-05-26 21:15:29 UTC (rev 349)
@@ -0,0 +1,109 @@
+#!/usr/bin/env python
+# encoding: utf-8
+"""
+loadWeights.py
+
+reads in the tab delimited list from arg1 and a graph from arg2.  
+For each line in arg1 checks that there are 3 values.  
+Takes the first two values as the edge specification and the third as the the audioWeight.  
+If the third value isn't present writes the edge to a text file named in arg3.
+Saves the updated graph in graphmlz formated file named in arg4.
+
+all args are required.
+
+Created by Benjamin Fields on 2009-05-17.
+Copyright (c) 2009 Goldsmiths University of London. All rights reserved.
+"""
+
+import sys
+import os
+import igraph
+import rightDict
+#import graphRDF
+
+Usage = """Usage:\nloadWeights.py weightfile.txt inGraph.mlz edgesLeft.txt outGraph.mlz\n\t\tFor more help read the source."""
+
+def createVerticesAttributeValueDict(workingGraph, attribute):
+	"""creates a rightDict of the values in a graph of a given attribute and the node it came from to enable looser string matching (will return a substring match as true).  May not work well if the values are non unique.
+	returns dictionary"""
+	attrValueDict = rightDict.rightDict()
+	for vert in workingGraph.vs:
+		attrValueDict[vert[attribute]] = vert.index
+	return attrValueDict
+
+def main(argv=None):
+	#if the graph has a different prefix than 
+	prefix = "http://myrdfspace.com/media_seed_134901208/"
+	
+	if argv is None:
+		argv = sys.argv
+	if len(argv) != 5:
+		print Usage
+		return 1
+	
+	try:
+		infileHandle = open(argv[1], 'r')
+		outfileHandle = open(argv[3], 'w')
+		typoOutHandle = open('typos.txt', 'w')
+	except Exception, err:
+		print >> sys.stderr, sys.argv[0].split("/")[-1] + ": " + str(err)
+		print >> sys.stderr, "\t" + Usage
+		return 2
+	print "loading graph into memory..."
+	try:
+		putWeightsInHere = igraph.Graph.Load('complexSongGraph.mlz', format='graphmlz')
+		print "again..."
+		putWeightsInHere = igraph.Graph.Load('complexSongGraph.mlz', format='graphmlz')
+	except RuntimeWarning:
+		print "Trying a second time..."
+		putWeightsInHere = igraph.Graph.Load('complexSongGraph.mlz', format='graphmlz')
+	except Exception, err:
+		print >> sys.stderr, sys.argv[0].split("/")[-1] + ": " + str(err)
+		print >> sys.stderr, "\t" + Usage
+		return 3
+		
+		
+	missed = 0
+	typos = 0
+	foundWeight = 0
+	print "processing..."
+	indexdict = createVerticesAttributeValueDict(putWeightsInHere, 'track')
+	for idx, line in enumerate(infileHandle):
+		
+		if idx%1000 == 0:
+			print str(idx) + " lines of " + argv[1] + " have been processed."
+		
+		try:
+			sourceV , targetV, Weight = line.strip().split('\t')
+		except ValueError:
+			outfileHandle.write(str(idx) + " : Missing Weight : " + line)
+			outfileHandle.flush()
+			missed += 1
+			continue
+		try:
+			srcIDX = indexdict[sourceV]
+			trgtIDX = indexdict[targetV]
+		
+			igraph.EdgeSeq(putWeightsInHere, [srcIDX, trgtIDX])[0]['audioWeight'] = float(Weight)
+		except Exception, err:
+			typoOutHandle.write(str(idx) + " : typo : " + line)
+			typoOutHandle.flush()
+			typos += 1
+			print >> sys.stderr, str(err) + "\n" + str(typos) + " typos found."
+			continue
+		
+		foundWeight += 1
+	
+	print "changed the weight of " + str(foundWeight) + " edges."
+	print "found " + str(missed) + " lines without weight."
+	print "Saving updated graph to " + str(argv[4])
+	
+	putWeightsInHere.write(argv[4], format='graphmlz')
+	infileHandle.close()
+	outfileHandle.close()
+	typoOutHandle.close()
+
+
+if __name__ == '__main__':
+	sys.exit(main())
+


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


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