def kmeansTest(k=2, n=20, verbose=False):
random.seed(0)
xMean = 3
xSD = 1
yMean = 5
ySD = 1
d1Samples = util.genDistribution(xMean, xSD, yMean, ySD, n, '1.')
d2Samples = util.genDistribution(xMean+3, xSD, yMean+1, ySD, n, '2.')
allSamples = d1Samples + d2Samples
print("before clustering")
util.plot_cluster([cluster.Cluster(allSamples)])
print("after clustering")
clusters = kmeans(allSamples, k, verbose)
util.plot_cluster(clusters, verbose)
print('Final result')
for c in clusters:
print('', c)
#### Implement the centroid updating function here!
def update(self, samples):
"""Replace the samples in the cluster by new samples
Return: how much the centroid has changed"""
return helper.update(self, samples)
def __str__(self):
names = []
for e in self.samples:
names.append(e.getName())
names.sort()
result = 'Cluster with centroid '\
+ str(self.centroid.getFeatures()) + ' contains:\n '
for e in names:
result = result + e + ', '
return result[:-2]
if __name__ == "__main__":
test_samples = util.genDistribution()
c = Cluster(test_samples)
print(c.centroid)
print("cluster center: ", c.centroid.features)
util.plot_cluster([c])
# now assign the cluster new samples, and move it
test_samples2 = util.genDistribution(1, 1, 1, 1, 30)
diff = c.update(test_samples2)
print("center moved: ", diff)
# plot_cluster expects an array of cluster...
util.plot_cluster([c])
all_cluster.append(cl.Cluster(tmp_data))
data += tmp_data
def onclick(event):
# Creating a new point and finding the k nearest neighbours
new = sample.Sample('', [event.xdata, event.ydata], '')
knn(new, data, K)
# draw the new point
data.append(new)
pylab.scatter([new.getFeatures()[0]], \
[new.getFeatures()[1]], \
label = new.getLabel(), \
marker = util.make_cmarkers()[LABELS.index(new.getLabel())], \
color = util.make_cmap()[LABELS.index(new.getLabel())])
pylab.draw()
# start plotting
fig = pylab.figure()
cid = fig.canvas.mpl_connect('button_press_event', onclick)
util.plot_cluster(all_cluster, centroid=False)
pylab.show()
# new_pt = sample.Sample('', [0.2, 0.3], '')
# knn(new_pt, data, K)
#
# data.append(new_pt)
# print("\nafter....")
# util.plotSamples(data)
# plt.show()
pass
"""
fill the array allSamples to hold the samples, each sample
takes two attributes of an iris instance
"""
for line in data:
content = line.strip().split(",")
d = sample.Sample('', [float(content[1]), float(content[3])])
allSamples.append(d)
# ---- end of your code --- #
verbose = False
k = 3
print("before clustering")
unclustered = [kmeans.Cluster(allSamples)]
util.plot_cluster(unclustered)
clusters = unclustered
print("after clustering")
# IMPLEMENTATION: apply k means to cluster the samples
# ---- start your code ---- #
pass
clusters = kmeans.kmeans(allSamples, 3, verbose)
# ---- end of your code --- #
util.plot_cluster(clusters, verbose)
""" bonus """
normalized_allSamples = allSamples
print("after normalizing")