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)
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]))
#cluster_list = sequential_clustering(singleton_list, 15)
#print "Displaying", len(cluster_list), "sequential clusters"
cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 20)
print "Distortion of hierarchical clusters is ", str(compute_distortion(cluster_list, data_table))
print "Displaying", len(cluster_list), "hierarchical clusters"
#cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
#print "Distortion of k-means clusters is ", str(compute_distortion(cluster_list, data_table))
#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, True)
#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
for cluster in cluster_list:
distortion += cluster.cluster_error(data_table)
return distortion
data_table = load_data_table(DATA_896_URL)
#hierarchical_clustering
distortion_hc = []
for num_cluster in range(6, 21):
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 = pj3.hierarchical_clustering(singleton_list, num_cluster)
distortion_hc.append(compute_distortion(cluster_list, data_table))
print "Distortion of hierarchical clusters is ", str(compute_distortion(cluster_list, data_table))
print "Displaying", len(cluster_list), "hierarchical clusters"
#kmeans_clustering
distortion_kc = []
for num_cluster in range(6, 21):
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 = pj3.kmeans_clustering(singleton_list, num_cluster, 5)
distortion_kc.append(compute_distortion(cluster_list, data_table))
print "Distortion of k-means clusters is ", str(compute_distortion(cluster_list, data_table))
print "Displaying", len(cluster_list), "k-means clusters"
