def calculate_distortion():
data_table = load_data_table(DATA_111_URL)
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
cluster_list_hierarchical = closest_pairs_and_clustering_algorithms.hierarchical_clustering(
singleton_list, 9)
cluster_list_kmeans = closest_pairs_and_clustering_algorithms.kmeans_clustering(
singleton_list, 9, 5)
distortion_hierarchical = closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_hierarchical, data_table)
distortion_kmeans = closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_kmeans, data_table)
print "distortion_hierarchical: ", distortion_hierarchical
print "distortion_kmeans: ", distortion_kmeans
def compare_distortion():
distortion_hierarchical_111 = []
distortion_kmeans_111 = []
distortion_hierarchical_290 = []
distortion_kmeans_290 = []
distortion_hierarchical_896 = []
distortion_kmeans_896 = []
data_table = load_data_table(DATA_111_URL)
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
for num in xrange(6, 21):
cluster_list_hierarchical = closest_pairs_and_clustering_algorithms.hierarchical_clustering(
singleton_list[:], num)
cluster_list_kmeans = closest_pairs_and_clustering_algorithms.kmeans_clustering(
singleton_list[:], num, 5)
distortion_hierarchical_111.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_hierarchical, data_table))
distortion_kmeans_111.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_kmeans, data_table))
print "distortion_hierarchical_111: ", distortion_hierarchical_111
print "distortion_kmeans_111: ", distortion_kmeans_111
data_table = load_data_table(DATA_290_URL)
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
for num in xrange(6, 21):
cluster_list_hierarchical = closest_pairs_and_clustering_algorithms.hierarchical_clustering(
singleton_list[:], num)
cluster_list_kmeans = closest_pairs_and_clustering_algorithms.kmeans_clustering(
singleton_list[:], num, 5)
distortion_hierarchical_290.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_hierarchical, data_table))
distortion_kmeans_290.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_kmeans, data_table))
print "distortion_hierarchical_290: ", distortion_hierarchical_290
print "distortion_kmeans_290: ", distortion_kmeans_290
data_table = load_data_table(DATA_896_URL)
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
for num in xrange(6, 21):
cluster_list_hierarchical = closest_pairs_and_clustering_algorithms.hierarchical_clustering(
singleton_list[:], num)
cluster_list_kmeans = closest_pairs_and_clustering_algorithms.kmeans_clustering(
singleton_list[:], num, 5)
distortion_hierarchical_896.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_hierarchical, data_table))
distortion_kmeans_896.append(
closest_pairs_and_clustering_algorithms.compute_distortion(
cluster_list_kmeans, data_table))
print "distortion_hierarchical_896: ", distortion_hierarchical_896
print "distortion_kmeans_896: ", distortion_kmeans_896
