parser.add_option('--KNN', dest='KNN', type="int", action='store', default=10)
parser.add_option('--normalize', dest='normalize', type="int", action='store', default=1)
(options, args) = parser.parse_args()
return options
if __name__ == '__main__':
# parse arguments
filename_wordsX = (sys.argv[1])
# read input
wordsX = IO.readPickledWords(filename_wordsX)
options = parseOptions()
# make graph
G = makeGraph(wordsX, options)
G = G.todense()
if options.normalize == 1:
G = toSymmetricStochastic(G, sym=(options.sym == 1), stochastic=(options.stochastic == 1), norm='l1')
elif options.normalize == 2:
G = toSymmetricStochastic(G, sym=(options.sym == 1), stochastic=(options.stochastic == 1), norm='l2')
msk = MSK(None, wordsX.words, wordsX.words)
# save the matrix.
# This is hacky, since we're trusting that G is generated with rows/columns that match the order of wordsX.words
msk.M = G
graphFilename = filename_wordsX.replace(".", "_WG.")
if options.KNN > 0:
graphFilename = graphFilename.replace(".", "_KNN"+str(options.KNN)+".")
IO.pickle(graphFilename, msk)
hammings = np.zeros(R)
for (i, noise) in enumerate(noise_levels):
for r in xrange(R):
np.random.seed(r)
# read files
wordsX, wordsY, seedsX, seedsY = mcca.readInput(options, filename_wordsX, filename_wordsY, filename_seedX, filename_seedY)
seed_length = len(seedsX.words)
pi = perm.randperm(xrange(len(wordsY.words)))
wordsY.permuteFirstWords(pi)
if options.K > 0:
GX = words_to_graph.makeGraph(wordsX, seedsX, options.graph_type, options.K)
GY = words_to_graph.makeGraph(wordsY, seedsY, options.graph_type, options.K)
GY = graphs.permute(GY, pi)
GX = graphs.toSymmetricStochastic(GX)
GY = graphs.toSymmetricStochastic(GY)
print 'Graph norms', norm(GX), norm(GY)
else:
GX = None
GY = None
print 'no graphs provided'
# add random noise to the features
if noise > 0:
if not options.pickled:
wordsX.features += noise * randn(wordsX.features.shape)
wordsY.features += noise * randn(wordsY.features.shape)
seedsX.features += noise * randn(seedsX.features.shape)
seedsY.features += noise * randn(seedsY.features.shape)
else:
wordsX.addReprNoise(noise)
