# ---- start your code ---- #
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")
def test_cluster_can_compare_with_mean(self):
c = kmeans.Cluster(p(1, 1))
self.assertTrue(c.same_mean(p(1, 1)))
self.assertFalse(c.same_mean(p(1, 2)))
def test_cluster_can_compute_mean_vector(self):
c = kmeans.Cluster(p(1, 1))
c.add(p(1, 1))
c.add(p(1.5, 2))
c.add(p(3, 4))
self.assertEquals(p(1.8, 2.3), c.mean_vector())
def test_point_can_be_added_to_cluster(self):
c = kmeans.Cluster(p(1, 1))
c.add(p(2, 2))
self.assertEquals(p(2, 2), c.points[0])