# initialize means
numOfExperiments = 5 #number of random initial means experiments
for count in xrange(numOfExperiments):
if numOfExperiments == 1:
initialMeans[:] = np.loadtxt(os.path.join(os.path.dirname(__file__), fninitcentroids))
else:
initialMeans[:] = Utils.getInitialMeans(points, k)
print "Initial Means: \n%s" % initialMeans
print "Initial SSE: %s" % Utils.calcSSE(points, initialMeans)
means = np.zeros((k, len(points[0])))
means[:] = initialMeans
finalmeans, labels, SSE = km.run(points, means, numberOfClusters=k, threshold=d, maxiterations=i)
print "final means: %s" % finalmeans
if SSE < minSSE:
print '**New min SSE %s' % SSE
minSSE = SSE
minInitialMeans[:] = initialMeans
print 'Min initial means\n%s' % initialMeans
minMeans[:] = finalmeans
minLabels[:] = labels
print "min SSE: %s" % minSSE
print "min Initial means:\n %s" % minInitialMeans
print "min means:\n %s" % minMeans
#Plot.plotPoints(points, minLabels, title='final')
import pylab
from km.kmeans import KMeans
from util.utilities import *
if __name__ == '__main__':
# kmeans for 3 clusters
km = KMeans(showsubplots=False)
k,d,i = 3, 0.1, 10
data, centroids = Utils.generateTestDataAndCentroids(k, dimensions=2)
means, labels = km.run(data, numberOfClusters=k, threshold=d, maxiterations=i)
print "final means: \n%s" % means
#if not subplot:
Plot.plotPoints(data, labels, title='final means')
Plot.plotMeans(means)
pylab.show()
