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(set([line[0]]), line[1], line[2], line[3],
line[4]))
#cluster_list = sequential_clustering(singleton_list, 15)
cluster_list = hierarchical_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"
# draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
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(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"
# 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(x):
"""
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, x, 5)
#print "Displaying", len(cluster_list), "k-means clusters"
return cluster_list
print sum(
map(lambda cluster: cluster.cluster_error(data_table), cluster_list))
# 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
pass
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 run_example():
"""
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(project_3.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 = hierarchical_clustering(singleton_list, 15)
#pprint(cluster_list)
#print("Displaying", len(cluster_list), "hierarchical clusters")
cluster_list = kmeans_clustering(singleton_list, 20, 20)
print("Displaying", len(cluster_list), "k-means clusters")
# draw the clusters using matplotlib
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)
#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]))
# ************** Here we have to choose the type of clustering we want to use for visualization ********************
#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"
if DESKTOP: # draw the clusters using matplotlib or simplegui
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_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"
distortion = sum([clstr.cluster_error(data_table) for clstr in cluster_list])
print "Distortion of clustering =", distortion
# draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
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_24_URL)
# data_table = gen_random_clusters(100)[0]
#singleton_list = []
#for line in data_table:
#singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
singleton_list = gen_random_clusters(100)
#cluster_list = sequential_clustering(singleton_list, 15)
#print "Displaying", len(cluster_list), "sequential clusters"
cluster_list = module3_project.hierarchical_clustering(singleton_list, 10)
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"
# draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
def visualize_data(cluster_input, data, method=None, display_centers=False):
"""
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)
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
if method == None:
cluster_list = sequential_clustering(singleton_list, cluster_input)
print("Displaying", len(cluster_list), "sequential clusters")
elif method == 'hierarchical_clustering':
cluster_list = clustering.hierarchical_clustering(singleton_list, cluster_input)
print("Displaying", len(cluster_list), "hierarchical clusters")
elif method == 'kmeans_clustering':
cluster_list = clustering.kmeans_clustering(singleton_list,
cluster_input[0],
cluster_input[1])
print("Displaying", len(cluster_list), "k-means clusters")
else:
print("ERROR: method entered into visualize_data not recognized")
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, display_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, 50)
print "Displaying", len(cluster_list), "hierarchical clusters"
#cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 20, 5)
#print "Displaying", len(cluster_list), "k-means clusters"
print 'Calculating distortion...'
print 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, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
def question_5_6():
"""
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 = hierarchical_clustering(singleton_list, 20)
print("Displaying", len(cluster_list), "hierarchical clusters")
# =============================================================================
# cluster_list = kmeans_clustering(singleton_list, 9, 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, False)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True) #add cluster centers
def q6(): data_table = viz.load_data_table(viz.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 = alg_project3.kmeans_clustering(singleton_list, 9, 5) alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
def q2(): data_table = viz.load_data_table(viz.DATA_3108_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 = alg_project3.hierarchical_clustering(singleton_list, 15) alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
def visualize(datafile, output, cluster_func):
data_table = load_data_table(datafile)
clusters = [alg_cluster.Cluster(set([x[0]]), x[1], x[2], x[3], x[4])
for x in data_table]
clusters = cluster_func(clusters)
print "Displaying", len(clusters), "clusters"
alg_clusters_matplotlib.plot_clusters(data_table, clusters, True, output)
return clusters
def q2():
data_table = viz.load_data_table(viz.DATA_3108_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 = alg_project3.hierarchical_clustering(singleton_list, 15)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
def q6():
data_table = viz.load_data_table(viz.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 = alg_project3.kmeans_clustering(singleton_list, 9, 5)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
def run_question_3():
data_table = pro3_viz.load_data_table(DATA_3108_URL)
data_table_cl = clusterize_data(data_table)
cluster_list = pro3.kmeans_clustering(data_table_cl, 15, 5)
print "Displaying", len(cluster_list), "k-means clusters"
# alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, False) # simple filled-in circles
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list,
True) # add cluster centers
def run_question_5():
data_table = pro3_viz.load_data_table(DATA_111_URL)
data_table_cl = clusterize_data(data_table)
cluster_list = pro3.hierarchical_clustering(data_table_cl, 9)
print "Displaying", len(cluster_list), "hierarchical clusters"
# alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, False) # simple filled-in circles
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list,
True) # add cluster centers
return cluster_list
def question5_plot():
"""
Generate the plot for question 5
"""
data_table = load_data_table(DATA_111_URL)
singleton_list = []
for line in data_table:
cluster = Cluster(set([line[0]]), line[1], line[2], line[3], line[4])
singleton_list.append(cluster)
cluster_list = hierarchical_clustering(singleton_list, 9)
plot_clusters(data_table, cluster_list, True)
def question6(URL, file_to_save, number_clusters=9, iterations=5, centers=False):
'''
:return:
'''
data_table, singleton_list = alg_project3_viz.run_example(URL)
cluster_list = kmeans_clustering(singleton_list, number_clusters, iterations)
print "Displaying", len(cluster_list), "k-means clusters"
if centers:
file = file_to_save[:-4] + 'with_centers' + '.png'
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, file, True)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, file_to_save, False)
def question2(URL, file_to_save, number_clusters=15, centers=False):
'''
:return:
'''
data_table, singleton_list = alg_project3_viz.run_example(URL)
cluster_list = hierarchical_clustering(singleton_list, number_clusters)
print "Displaying", len(cluster_list), "hierarchical clusters"
if centers:
file = file_to_save[:-4] + 'with_centers' + '.png'
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, file, centers)
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, file_to_save, centers)
def question3_plot():
"""
Generate the plot for question 3
"""
data_table = load_data_table(DATA_3108_URL)
singleton_list = []
for line in data_table:
cluster = Cluster(set([line[0]]), line[1], line[2], line[3], line[4])
singleton_list.append(cluster)
cluster_list = kmeans_clustering(singleton_list, 15, 5)
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)
#data_table = load_data_table(DATA_896_URL)
data_table = load_data_table(DATA_290_URL)
#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]))
original_dict = create_dictionary(data_table)
#original_list = []
#for line in data_table:
# original_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
#original_list = list(singleton_list)
#original_list = singleton_list[:]
#cluster_list = sequential_clustering(singleton_list, 15)
#print "Displaying", len(cluster_list), "sequential clusters"
print "About to display ...."
#cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 16)
#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"
# compute the distortion
if (True):
distortion = compute_distortion(cluster_list, data_table)
print distortion
# draw the clusters using matplotlib or simplegui
if (False):
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 Question5():
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 = module3_project.hierarchical_clustering(singleton_list, 9)
print "Displaying", len(cluster_list), "hierarchical clusters"
# draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
def run_question(number, data_set):
"""
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
"""
global DESKTOP
print "Loading data table ..."
data_table = load_data_table(data_set)
print "Data table loaded. Creating clusters ..."
singleton_list = []
# set correct number of clusters
if number in [2, 3]:
num_clusters = 15
elif number in [5, 6]:
num_clusters = 9
print "\nQuestion number: ", number
print "Number of clusters to be calculated: ", num_clusters
# parse data_table into cluster objects
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
print "\nCluster list created. Passing list to hierarchical_clustering ..."
# calculate clusters
if number == 0:
cluster_list = sequential_clustering(singleton_list, 15)
print "Displaying", len(cluster_list), "sequential clusters"
elif number in [2, 5]:
cluster_list = cpf.hierarchical_clustering(singleton_list,
num_clusters)
print "Displaying", len(cluster_list), "hierarchical clusters"
elif number in [3, 6]:
cluster_list = cpf.kmeans_clustering(singleton_list, num_clusters, 5)
print "Displaying", len(cluster_list), "k-means clusters"
else:
"Please pass a valid number to run_question. Valid options are 0, 2, 3, 5, or 6."
# 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 assignment_q2():
"""
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.hierarchical_clustering(singleton_list, 15)
print "Displaying", len(cluster_list), "hierarchical clusters"
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
def run_kmeans_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]))
def compute_distortion(cluster_list):
error = 0
for cluster in cluster_list:
error += cluster.cluster_error(data_table)
return error
error = []
for cluster_num in range(6, 21):
cluster_list = kmeans_clustering(singleton_list, cluster_num, 5)
error.append(compute_distortion(cluster_list))
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
return error
print("Displaying", len(cluster_list), "kmeans 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"
# 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 Question5():
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 = module3_project.hierarchical_clustering(singleton_list, 9)
print "Displaying", len(cluster_list), "hierarchical clusters"
# draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
def Q2_Q3_Q5_Q6_viz(data_file, clustering_algo, num_clusters, num_iterations, centers): '''Questions 2-6 Answer''' data_table = project.load_data_table(data_file) singleton_list = [] for line in data_table: singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4])) if clustering_algo == "h": cluster_list = project.hierarchical_clustering(singleton_list, num_clusters) print "Displaying", len(cluster_list), "hierarchical clusters" elif clustering_algo == "k": cluster_list = project.kmeans_clustering(singleton_list, num_clusters, num_iterations) print "Displaying", len(cluster_list), "kmeans clusters" else: print "Clustering method not recognized.\nPlease use 'h' for hierarchical_clustering\nor use 'k' for kmeans_clustering" return alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, centers) #False to remove cluster centers. True to include them
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"
# Question 2 answer: uncomment bottom two lines in block comment with
# data_table being equal to load_data_table(DATA_3108_URL)
# cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
# print "Displaying", len(cluster_list), "hierarchical clusters"
# Question 3 answer: uncomment bottom two lines in block comment with
# data_table being equal to load_data_table(DATA_3108_URL)
# cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 15, 5)
# print "Displaying", len(cluster_list), "k-means clusters"
# Question 5 answer: uncomment bottom two lines in block comment with
# data_table being equal to load_data_table(DATA_111_URL)
# cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
# print "Displaying", len(cluster_list), "hierarchical clusters"
# Question 6 answer: uncomment bottom two lines in block comment with
# data_table being equal to load_data_table(DATA_111_URL)
# cluster_list = alg_project3_solution.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, True)
else:
alg_clusters_simplegui.PlotClusters(
data_table,
cluster_list) # use toggle in GUI to add cluster centers
def run_example(data = 3108, algorithm = "sequential", display_centers = False):
"""
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
"""
if data == 3108:
data_url = DATA_3108_URL
if data == 896:
data_url = DATA_896_URL
if data == 290:
data_url = DATA_290_URL
if data == 111:
data_url = DATA_111_URL
data_table = load_data_table(data_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]))
if algorithm == "sequential":
cluster_list = sequential_clustering(singleton_list, 15)
print "Displaying", len(cluster_list), "sequential clusters"
if algorithm == "hierarchical":
cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
print "Displaying", len(cluster_list), "hierarchical clusters"
if algorithm == "k-means":
cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
print "Displaying", len(cluster_list), "k-means clusters"
# draw the clusters using matplotlib or simplegui
# display_centers = True adds cluster centers
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, display_centers)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list) # use toggle in GUI to add cluster centers
return
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_111_URL)
#data_table = load_data_table(DATA_290_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, 9)
#print "Displaying", len(cluster_list), "sequential clusters"
#start_time = time.clock()
cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 9)
#print "hierarchical:",compute_distortion(cluster_list)
#print "time taken for plot:"+ str(time.clock() - start_time)
print "Displaying", len(cluster_list), "hierarchical clusters"
#start_time = time.clock()
#cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, 9, 5)
#print "kmeans: ",compute_distortion(cluster_list)
#print "time taken for plot:"+ str(time.clock() - start_time)
#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
#print ""
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list) # use toggle in GUI to add cluster centers
def assignment_q6():
"""
Load a data table, compute a list of clusters and
plot a list of clusters
"""
data_table = load_data_table(DATA_111_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, 9, 5)
# q7
distortion = compute_distortion(cluster_list, data_table)
print "kmeans_clustering distortion:", distortion
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_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, 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"
# calculate cluster_error of hierarchical_clustering and kmeans_clustering
hc_error = compute_distortion(
alg_project3_solution.hierarchical_clustering(singleton_list, 9),
data_table)
kmc_error = compute_distortion(
alg_project3_solution.kmeans_clustering(singleton_list, 9, 5),
data_table)
print "cluster_error:\nhierarchical_clustring: ", hc_error, "\nkmeans_clustering: ", kmc_error
# 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
"""
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 = project3.hierarchical_clustering(singleton_list, 9)
#print "Displaying", len(cluster_list), "hierarchical clusters"
cluster_list = project3.kmeans_clustering(singleton_list, 9, 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 run_question(number, data_set):
"""
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
"""
global DESKTOP
print "Loading data table ..."
data_table = load_data_table(data_set)
print "Data table loaded. Creating clusters ..."
singleton_list = []
for line in data_table:
singleton_list.append(
alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3],
line[4]))
print "Cluster list created. Passing list to hierarchical_clustering ..."
if number == 0:
cluster_list = sequential_clustering(singleton_list, 15)
print "Displaying", len(cluster_list), "sequential clusters"
elif number in [2, 5]:
cluster_list = cpf.hierarchical_clustering(singleton_list, 9)
print "Displaying", len(cluster_list), "hierarchical clusters"
elif number in [3, 6]:
cluster_list = cpf.kmeans_clustering(singleton_list, 9, 5)
print "Displaying", len(cluster_list), "k-means clusters"
else:
"Please pass a valid number to run_question."
# 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 plot_Q6():
"""
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
"""
DIRECTORY = "http://commondatastorage.googleapis.com/codeskulptor-assets/"
DATA_111_URL = DIRECTORY + "data_clustering/unifiedCancerData_111.csv"
data_table = viz.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 = project.kmeans_clustering(singleton_list, 9, 5)
print "Displaying", len(cluster_list), "hierarchical clusters"
# draw the clusters using matplotlib
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, False)
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_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]))
# cluster_list = sequential_clustering(singleton_list, 15)
# print "Displaying", len(cluster_list), "sequential clusters"
# cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, 16)
# distortion = application3.compute_distortion(cluster_list, data_table)
# print "Displaying", len(cluster_list), "hierarchical clusters, distortion:", distortion
cluster_list = alg_project3_solution.kmeans_clustering(
singleton_list, 16, 5)
distortion = application3.compute_distortion(cluster_list, data_table)
print "Displaying", len(
cluster_list), "k-means clusters, distortion:", distortion
# 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
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 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('unifiedCancerData_111.csv')
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 'hierarchical error', app3_7.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 'k means error', app3_7.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, 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
import sys
sys.path.append('../../3_closest_pairs_&_clustering_algorithms')
import data.load_clusters as lc
import data.cluster as cl
import clustering as clr
import alg_clusters_matplotlib as cplot
data_table = lc.load_data_table(lc.DATA_896_URL) #DATA_3108_URL DATA_290_URL
singleton_list = []
for line in data_table:
singleton_list.append(cl.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
c = 7 # cluster count
cluster_list = clr.hierarchical_clustering(singleton_list, c)
cplot.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
"""
algo_used = 1 # 1: sequential clusters, 2: hierarchical clusters, 3: k-means clusters
data_urls = [DATA_3108_URL, DATA_896_URL, DATA_290_URL, DATA_111_URL]
source = 3 # pick which data source url
data_table = load_data_table(data_urls[source - 1])
def clustering(algo_used, num_clusters, num_iter = 5):
"""
Uses specified algorithm to cluster data
input: int for specified algorithm, data_table
output: cluster_list
"""
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
if algo_used == 1:
cluster_list = sequential_clustering(singleton_list, num_clusters)
print "Displaying", len(cluster_list), "sequential clusters"
elif algo_used == 2:
cluster_list = prj3.hierarchical_clustering(singleton_list, num_clusters)
print "Displaying", len(cluster_list), "hierarchical clusters"
elif algo_used == 3:
cluster_list = prj3.kmeans_clustering(singleton_list, num_clusters, num_iter)
print "Displaying", len(cluster_list), "k-means clusters"
return cluster_list
def gen_random_clusters(num_clusters):
"""
Creates a list of clusters where each cluster in this list corresponds to one randomly generated point in the 2 x 2 square
Input: number of clusters (int)
Output: list of random clusters that is num_clusters long (list)
"""
cluster_list = []
for cluster in xrange(num_clusters):
x = random.choice([1, -1]) * random.random()
y = random.choice([1, -1]) * random.random()
cluster_list.append(alg_cluster.Cluster(set([]), x, y, 1, 0))
return cluster_list
def question_one():
"""
Function for answering first question
"""
xvals = range(2, 200)
slow_yvals = []
fast_yvals = []
for num in xvals:
cluster_list = gen_random_clusters(num)
initial = time.time()
answer = prj3.slow_closest_pairs(cluster_list)
final = time.time()
slow_yvals.append(final - initial)
for num in xvals:
cluster_list = gen_random_clusters(num)
initial = time.time()
answer = prj3.fast_closest_pair(cluster_list)
final = time.time()
fast_yvals.append(final - initial)
slow_line = plt.plot(xvals, slow_yvals, color='r', label="Slow Closest Pair")
fast_line = plt.plot(xvals, fast_yvals, color='b', label="Fast Closest Pair")
plt.legend(loc=2)
plt.title("Efficiency of Slow and Fast Closest Pairs Algorithms")
plt.xlabel("Number of Clusters")
plt.ylabel("Run Times in Milliseconds")
plt.show()
def compute_distortion(cluster_list):
"""
Takes a list of clusters and uses cluster_error to compute its distortion.
input: list of clusters, original data table
output: cluster distortion int
"""
distortion = 0
for cluster in cluster_list:
distortion += cluster.cluster_error(data_table)
return distortion
def question_ten():
"""
Function for answering question 10
"""
xvals = xrange(6, 21)
kmeans_y = []
high_y = []
for clusters in xvals:
kmeans_y.append(compute_distortion(clustering(3, clusters)))
for clusters in xvals:
high_y.append(compute_distortion(clustering(2, clusters)))
kmeans_line = plt.plot(xvals, kmeans_y, color='r', label="K-Means Clustering")
high_line = plt.plot(xvals, high_y, color='b', label="Hierarchical Clustering")
plt.legend()
plt.title("Distortion Comparison Between Clustering Methods on 290 County Data Set")
plt.xlabel("Number of Output Clusters")
plt.ylabel("Distortion")
plt.show()
#question_one()
#question_ten()
# draw the clusters using matplotlib or simplegui
cluster_list = clustering(1, 5)
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, True)
else:
alg_clusters_simplegui.PlotClusters(data_table, cluster_list)
