def squared_clustering_errors(inputs, k):
"""finds the total squared error from k-means clustering the inputs"""
clusterer = KMeans(k)
clusterer.train(inputs)
means = clusterer.means
assignments = map(clusterer.classify, inputs)
return sum(squared_distance(input, means[cluster])
for input, cluster in zip(inputs, assignments))
def classify(self, input):
"""return the index of the cluster closest to the input"""
return min(range(self.k),
key=lambda i: squared_distance(input, self.means[i]))