def train(self, inputs):
# choose k random points as the initial mean
self.means = random.sample(inputs, self.k)
assignments = None
while True:
# find new assignments
new_assignments = map(self.classify, inputs)
# if no assignments have changed, we are done
if assignments == new_assignments:
return
# otherwise keep new assignments
assignments = new_assignments
# and compute new means based on the new assignement
for i in range(self.k):
# find all points assigned to cluster i
i_points = [p for p, a in zip(inputs, assignments) if a == i]
# make sure i_points is not empty so don't divide by 0
if i_points:
self.means[i] = vector_mean(i_points)
plt.plot(ks, errors)
plt.xticks(ks)
plt.xlabel("k")
plt.ylabel("total squared error")
plt.title("Total Error vs. # of Clusters")
plt.show()
# Bottom-up Hierarchical Clustering
base_cluster = bottom_up_cluster(inputs)
three_clusters = [get_values(cluster)
for cluster in generate_clusters(base_cluster, 3)]
for i, cluster, marker, color in zip([1, 2, 3],
three_clusters,
['D', 'o', '*'],
['r', 'g', 'b']):
xs, ys = zip(*cluster)
plt.scatter(xs, ys, color=color, marker=marker)
# put a number at the mean of the cluster
x, y = vector_mean(cluster)
plt.plot(x, y, marker='$' + str(i) + '$', color='black')
plt.title("User locations -- 3 Bottom-up Clusters, Min")
plt.xlabel("blocks east of city center")
plt.ylabel("blocks north of city center")
plt.show()