def assignment_q3():
"""
Load a data table, compute a list of clusters and
plot a list of clusters
"""
data_table = load_data_table(DATA_3108_URL)
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster({line[0]}, line[1], line[2], line[3], line[4]))
cluster_list = project.kmeans_clustering(singleton_list, 15, 5)
print "Displaying", len(cluster_list), "k-means clusters"
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
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_3108_URL)
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster({line[0]}, line[1], line[2], line[3], line[4]))
# cluster_list = sequential_clustering(singleton_list, 50)
# print "Displaying", len(cluster_list), "sequential clusters"
# cluster_list = project.hierarchical_clustering(singleton_list, 15)
# print "Displaying", len(cluster_list), "hierarchical clusters"
cluster_list = project.kmeans_clustering(singleton_list, 15, 5)
print "Displaying", len(cluster_list), "k-means clusters"
# draw the clusters using matplotlib or simplegui
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
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 = 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:\t" + str(student_county_tuple)
error_message += "\nExpected county tuples:\t" + str(expected_county_tuple)
suite.run_test(student_county_tuple == expected_county_tuple, True, error_message)
suite.report_results()