def run_example():
"""
Load a data table, compute a list of clusters and
plot a list of clusters
Set DESKTOP = True/False to use either matplotlib or simplegui
"""
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 = sequential_clustering(singleton_list, 15)
#print "Displaying", len(cluster_list), "sequential clusters"
#cluster_list = closest_pairs_and_clustering_algorithms.hierarchical_clustering(singleton_list, 9)
#print "Displaying", len(cluster_list), "hierarchical clusters"
cluster_list = closest_pairs_and_clustering_algorithms.kmeans_clustering(
singleton_list, 9, 5)
print "Displaying", len(cluster_list), "k-means clusters"
# draw the clusters using matplotlib or simplegui
if DESKTOP:
#alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, False)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list,
True) #add cluster centers
else:
alg_clusters_simplegui.PlotClusters(
data_table,
cluster_list) # use toggle in GUI to add cluster centers
def test_kmeans():
"""
Test for k-means clustering
kmeans_clustering should not mutate cluster_list, but make a new copy of each test anyways
"""
# load small data table
print
print "Testing kmeans_clustering on 24 county set"
data_24_table = load_data_table(DATA_24_URL)
kmeansdata_24 = [[15, 1, set([('34017', '36061'), ('06037',), ('06059',), ('36047',), ('36081',), ('06071', '08031'), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[15, 3, set([('34017', '36061'), ('06037', '06059'), ('06071',), ('36047',), ('36081',), ('08031',), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[15, 5, set([('34017', '36061'), ('06037', '06059'), ('06071',), ('36047',), ('36081',), ('08031',), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[10, 1, set([('34017', '36061'), ('06029', '06037', '06075'), ('11001', '24510', '34013', '34039', '51013', '51760', '51840', '54009'), ('06059',), ('36047',), ('36081',), ('06071', '08031', '41051', '41067'), ('36059',), ('36005',), ('01073', '55079')])],
[10, 3, set([('34013', '34017', '36061'), ('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('34039', '36047'), ('36081',), ('36059',), ('36005',), ('01073', '55079'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[10, 5, set([('34013', '34017', '36061'), ('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('34039', '36047'), ('36081',), ('36059',), ('36005',), ('01073', '55079'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[5, 1, set([('06029', '06037', '06075'), ('01073', '11001', '24510', '34013', '34017', '34039', '36047', '51013', '51760', '51840', '54009', '55079'), ('06059',), ('36005', '36059', '36061', '36081'), ('06071', '08031', '41051', '41067')])],
[5, 3, set([('06029', '06037', '06075'), ('11001', '24510', '34013', '34017', '34039', '36005', '36047', '36059', '36061', '36081', '51013'), ('08031', '41051', '41067'), ('06059', '06071'), ('01073', '51760', '51840', '54009', '55079')])],
[5, 5, set([('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('01073', '55079'), ('11001', '24510', '34013', '34017', '34039', '36005', '36047', '36059', '36061', '36081', '51013', '51760', '51840', '54009')])]]
suite = poc_simpletest.TestSuite()
for num_clusters, num_iterations, expected_county_tuple in kmeansdata_24:
# build initial list of clusters for each test since mutation is allowed
cluster_list = []
for idx in range(len(data_24_table)):
line = data_24_table[idx]
cluster_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
# compute student answer
student_clustering = student.kmeans_clustering(cluster_list, num_clusters, num_iterations)
student_county_tuple = set_of_county_tuples(student_clustering)
# Prepare test
error_message = "Testing kmeans_custering on 24 county table, num_clusters = " + str(num_clusters)
error_message += " num_iterations = " + str(num_iterations)
error_message += "\nStudent county tuples: " + str(student_county_tuple)
error_message += "\nExpected county tuples: " + str(expected_county_tuple)
suite.run_test(student_county_tuple == expected_county_tuple, True, error_message)
suite.report_results()
def test_kmeans():
"""
Test for k-means clustering
kmeans_clustering should not mutate cluster_list, but make a new copy of each test anyways
"""
# load small data table
print
print "Testing kmeans_clustering on 24 county set"
data_24_table = load_data_table(DATA_24_URL)
kmeansdata_24 = [[15, 1, set([('34017', '36061'), ('06037',), ('06059',), ('36047',), ('36081',), ('06071', '08031'), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[15, 3, set([('34017', '36061'), ('06037', '06059'), ('06071',), ('36047',), ('36081',), ('08031',), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[15, 5, set([('34017', '36061'), ('06037', '06059'), ('06071',), ('36047',), ('36081',), ('08031',), ('36059',), ('36005',), ('55079',), ('34013', '34039'), ('06075',), ('01073',), ('06029',), ('41051', '41067'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[10, 1, set([('34017', '36061'), ('06029', '06037', '06075'), ('11001', '24510', '34013', '34039', '51013', '51760', '51840', '54009'), ('06059',), ('36047',), ('36081',), ('06071', '08031', '41051', '41067'), ('36059',), ('36005',), ('01073', '55079')])],
[10, 3, set([('34013', '34017', '36061'), ('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('34039', '36047'), ('36081',), ('36059',), ('36005',), ('01073', '55079'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[10, 5, set([('34013', '34017', '36061'), ('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('34039', '36047'), ('36081',), ('36059',), ('36005',), ('01073', '55079'), ('11001', '24510', '51013', '51760', '51840', '54009')])],
[5, 1, set([('06029', '06037', '06075'), ('01073', '11001', '24510', '34013', '34017', '34039', '36047', '51013', '51760', '51840', '54009', '55079'), ('06059',), ('36005', '36059', '36061', '36081'), ('06071', '08031', '41051', '41067')])],
[5, 3, set([('06029', '06037', '06075'), ('11001', '24510', '34013', '34017', '34039', '36005', '36047', '36059', '36061', '36081', '51013'), ('08031', '41051', '41067'), ('06059', '06071'), ('01073', '51760', '51840', '54009', '55079')])],
[5, 5, set([('06029', '06037', '06075'), ('08031', '41051', '41067'), ('06059', '06071'), ('01073', '55079'), ('11001', '24510', '34013', '34017', '34039', '36005', '36047', '36059', '36061', '36081', '51013', '51760', '51840', '54009')])]]
suite = poc_simpletest.TestSuite()
for num_clusters, num_iterations, expected_county_tuple in kmeansdata_24:
# build initial list of clusters for each test since mutation is allowed
cluster_list = []
for idx in range(len(data_24_table)):
line = data_24_table[idx]
cluster_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
# compute student answer
student_clustering = student.kmeans_clustering(cluster_list, num_clusters, num_iterations)
student_county_tuple = set_of_county_tuples(student_clustering)
# Prepare test
error_message = "Testing kmeans_custering on 24 county table, num_clusters = " + str(num_clusters)
error_message += " num_iterations = " + str(num_iterations)
error_message += "\nStudent county tuples: " + str(student_county_tuple)
error_message += "\nExpected county tuples: " + str(expected_county_tuple)
suite.run_test(student_county_tuple == expected_county_tuple, True, error_message)
suite.report_results()
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