#Loading data points from multiple files, for SSE error in whole dataset
#files = glob.glob(os.path.join(os.path.dirname(__file__), multiplefilepath + '*zscore.dat'))
#files.sort()
#
#points = np.loadtxt(files[9])
#
#cfiles = glob.glob(os.path.join(os.path.dirname(__file__), multiplefilepath + '*_initialcentroids*'))
#cfiles.sort()
#fninitcentroids = cfiles[9]
# run kmeans
km = KMeans(showsubplots=False)
initialMeans = np.zeros((k, len(points[0])))
minSSE = sys.maxint
minInitialMeans = np.zeros((k, len(points[0])))
minMeans = np.zeros((k, len(points[0])))
minLabels = np.zeros(len(points), dtype=int)
# initialize means
numOfExperiments = 5 #number of random initial means experiments
for count in xrange(numOfExperiments):
if numOfExperiments == 1:
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()
