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_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, 16)
#print "Displaying", len(cluster_list), "hierarchical clusters"
#cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 16, 5)
#print "Displaying", len(cluster_list), "k-means clusters"
kmeans = []
for clusters_number in xrange(6, 21):
cluster_list = alg_project3_solution.kmeans_clustering(
singleton_list, clusters_number, 5)
kmeans.append([
clusters_number, 0.0 +
alg_project3_solution.compute_distortion(cluster_list, data_table)
])
#cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 20)
#hierarchical = [[20, alg_project3_solution.compute_distortion(cluster_list, data_table)]]
hierarchical = []
for clusters_number in xrange(20, 5, -1):
cluster_list = alg_project3_solution.hierarchical_clustering(
singleton_list, clusters_number)
hierarchical.append([
clusters_number, 0.0 +
alg_project3_solution.compute_distortion(cluster_list, data_table)
])
hierarchical.reverse()
#print hierarchical[10], kmeans[10]
simpleplot.plot_lines(
"Distortion of the clusterings produced by hierarchical and k-means metods on 896 county data set",
800, 600, "Number of clusters n [6 .. 20]", "Distortion",
[hierarchical, kmeans], False,
["Hierarchical clustering", "k-means clustering with 5 iterations"])
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 = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
#print "Displaying", len(cluster_list), "hierarchical clusters"
cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
print "Displaying", len(cluster_list), "k-means clusters"
print "Distortion", alg_project3_solution.compute_distortion(cluster_list, data_table)
# 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 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_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, 16)
#print "Displaying", len(cluster_list), "hierarchical clusters"
#cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 16, 5)
#print "Displaying", len(cluster_list), "k-means clusters"
kmeans = []
for clusters_number in xrange(6, 21):
cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, clusters_number, 5)
kmeans.append([clusters_number, 0.0 + alg_project3_solution.compute_distortion(cluster_list, data_table)])
#cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 20)
#hierarchical = [[20, alg_project3_solution.compute_distortion(cluster_list, data_table)]]
hierarchical = []
for clusters_number in xrange(20, 5, -1):
cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, clusters_number)
hierarchical.append([clusters_number, 0.0 + alg_project3_solution.compute_distortion(cluster_list, data_table)])
hierarchical.reverse()
#print hierarchical[10], kmeans[10]
simpleplot.plot_lines("Distortion of the clusterings produced by hierarchical and k-means metods on 896 county data set",
800, 600, "Number of clusters n [6 .. 20]", "Distortion",
[hierarchical, kmeans], False,
["Hierarchical clustering", "k-means clustering with 5 iterations"])
def compute_kmeans_distortions(cluster_list):
""" list -> list
Takes a list of cluster objects and iteratively clusters the data further,
while calculating the distortion at each iteration. Returns a list of
distortion values.
"""
distortions = []
for iteration in range(6, 21):
new_list = sol.kmeans_clustering(cluster_list, iteration, 5)
distortions.append(sol.compute_distortion(new_list, data_table))
return distortions
def compute_hier_distortions(cluster_list):
""" list -> list
Takes a list of cluster objects and returns the list of distortions as that
list is further clustered from 20 down to 5 clusters.
"""
distortions = []
for iteration in range(20, 5, -1):
new_list = sol.hierarchical_clustering(cluster_list, iteration)
cluster_list = new_list
distortions.append(sol.compute_distortion(new_list, data_table))
distortions.reverse()
return distortions
"""
Assignment 3 Question 7 Answer
"""
import alg_project3_viz as viz
import alg_project3_solution as sol
import alg_cluster
data_table = viz.load_data_table(viz.DATA_111_URL)
hier_data_list = sol.make_data_list(data_table)
kmeans_data_list = sol.make_data_list(data_table)
hier_cluster_list = sol.hierarchical_clustering(hier_data_list, 9)
kmeans_cluster_list = sol.kmeans_clustering(kmeans_data_list, 9, 5)
print("hierarchical:", sol.compute_distortion(hier_cluster_list, data_table))
print("kmeans:", sol.compute_distortion(kmeans_cluster_list, data_table))
# Hierarchical: 175163886915.8305 or 1.752 x 10^11 with four significant figures
# K-means: 271254226924.20047 or 2.712 x 10^11
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_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"
# question 5
# cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
# print "Displaying", len(cluster_list), "hierarchical clusters"
# question 6
# cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
# print "Displaying", len(cluster_list), "k-means clusters"
# question 7
# cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
# kmeans_result = alg_project3_solution.compute_distortion(cluster_list, data_table)
# print("Displaying", kmeans_result, "kmeans_result")
# cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
# hierarchical_result = alg_project3_solution.compute_distortion(cluster_list, data_table)
# print("Displaying", hierarchical_result, "hierarchical_result")
# question 10
kmeans_res = []
for clusters_number in range(6, 21):
cluster_list = alg_project3_solution.kmeans_clustering(
singleton_list, clusters_number, 5)
kmeans_res.append([
clusters_number,
alg_project3_solution.compute_distortion(cluster_list, data_table)
])
hier_res = []
for clusters_number in range(20, 5, -1):
cluster_list = alg_project3_solution.hierarchical_clustering(
singleton_list, clusters_number)
hier_res.append([
clusters_number,
alg_project3_solution.compute_distortion(cluster_list, data_table)
])
hier_res.reverse()
# 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
create_separate_plots(kmeans_res, hier_res)
else:
alg_clusters_simplegui.PlotClusters(
data_table,
cluster_list) # use toggle in GUI to add cluster centers
