def test_clustering(data_set, method):
'''
Test the distortion of a data_set under clustering method.
Input: a tuple (data_table, cluster_list) and a clustering algorithm
Output: a list of distortion values
'''
# number of clusters to form
num_cluster_list = np.arange(6, 21, 1)
# init list to store distortion
distortion_list = []
# Loop over cluster sizes list
for num_cluster in num_cluster_list:
# make a copy of the cluster_list
cluster_list = [cluster.copy() for cluster in data_set[1]]
if method == 'K-Means':
# perfrom kmeans
cluster_list = project.kmeans_clustering(cluster_list, num_cluster,
10)
else:
# perform hier clustering
project.hierarchical_clustering(cluster_list, num_cluster)
# calculate and save distortion
distortion_list.append(
compute_distortion_data_set(data_set[0], cluster_list))
return distortion_list
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 cluster_data():
'''
Load a data table, compute a list of clusters and
Output: a tuple of two list of clusters (hierarchical, kmeans)
'''
DIRECTORY = "http://commondatastorage.googleapis.com/codeskulptor-assets/"
DATA_111_URL = DIRECTORY + "data_clustering/unifiedCancerData_111.csv"
DATA_290_URL = DIRECTORY + "data_clustering/unifiedCancerData_290.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]))
singleton_list_copy = [cluster.copy() for cluster in singleton_list]
return (project.hierarchical_clustering(singleton_list, 9),
project.kmeans_clustering(singleton_list_copy, 9, 5))
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]))
def compute_distortion(cluster_list):
distortion = 0
for clus in cluster_list:
error = clus.cluster_error(data_table)
distortion += error
return distortion
hierarchical_distortion = []
kmeans_distortion = []
# cluster_list = sequential_clustering(singleton_list, 15)
# print "Displaying", len(cluster_list), "sequential clusters"
for num_final_clusters in range(6, 21):
hierarchical_cluster_list = alg_project3_solution.hierarchical_clustering(singleton_list, num_final_clusters)
print "Displaying", len(hierarchical_cluster_list), "hierarchical clusters"
hierarchical_distortion.append(compute_distortion(hierarchical_cluster_list))
kmeans_cluster_list = alg_project3_solution.kmeans_clustering(singleton_list, num_final_clusters, 5)
print "Displaying", len(kmeans_cluster_list), "k-means clusters"
kmeans_distortion.append(compute_distortion(kmeans_cluster_list))
plt.plot(range(6, 21), hierarchical_distortion, 'g', lw = 2, label = "hierarchical distortion")
plt.plot(range(6, 21), kmeans_distortion, 'r', lw = 2, label = "kmeans distortion")
plt.legend(loc = 'upper left')
plt.xlabel('Number of final clusters')
plt.xlabel('Number of final clusters')
plt.ylabel('Distortion')
plt.title('Comparison of distortion between two clustering methods \n based on 111 county data set')
plt.grid()
plt.savefig('Comparison of distortion (111)')
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)
