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
Question 3-1
Author: You-Hao Chang
"""
import helper
import AT_project_3 as pj3
import time
import matplotlib.pyplot as plt
running_time_scp = []
running_time_fcp = []
for num_clusters in range(2, 201):
cluster_list = helper.gen_random_clusters(num_clusters)
start_time = time.time()
pj3.slow_closest_pair(cluster_list)
running_time_scp.append(time.time() - start_time)
start_time = time.time()
pj3.fast_closest_pair(cluster_list)
running_time_fcp.append(time.time() - start_time)
#making comparison plots
fig, ax = plt.subplots()
x_vals = [idx for idx in range(2, 201)]
ax.plot(x_vals, running_time_scp, '-b', label = 'slow closest pair')
ax.plot(x_vals, running_time_fcp, '-r', label = 'fast closest pair')
ax.legend(loc = 'upper left')
ax.set_title('Timing results (in desktop Python)')
ax.set_xlabel('number of initial clusters')
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"
