for x in data for y in data])/(len(data)**2)
sigma = np.sqrt(sigma2)
rho_exp = lambda x, y: 2-2*np.exp(-np.linalg.norm(x-y)/(2*sigma))
rho_gauss = lambda x, y: 2-2*np.exp(-np.linalg.norm(x-y)**2/(2*(sigma)**2))
G = eclust.kernel_matrix(data, rho)
#G = eclust.kernel_matrix(data, rho_gauss)
#G = eclust.kernel_matrix(data, rho_exp)
k = 3
r = []
r.append(wrapper.kmeans(k, data, run_times=5))
r.append(wrapper.gmm(k, data, run_times=5))
r.append(wrapper.spectral_clustering(k, data, G, run_times=5))
r.append(wrapper.spectral(k, data, G, run_times=5))
r.append(wrapper.kernel_kmeans(k, data, G, run_times=5, ini='random'))
#r.append(wrapper.kernel_kmeans(k, data, G, run_times=5, ini='k-means++'))
#r.append(wrapper.kernel_kmeans(k, data, G, run_times=5, ini='spectral'))
r.append(wrapper.kernel_kgroups(k,data,G,run_times=5, ini='random'))
#r.append(wrapper.kernel_kgroups(k,data,G,run_times=5, ini='k-means++'))
#r.append(wrapper.kernel_kgroups(k,data,G,run_times=5, ini='spectral'))
t = PrettyTable(['Algorithm', 'Accuracy', 'A-Rand'])
algos = ['kmeans', 'GMM', 'spectral clustering', 'spectral',
'kernel k-means', 'kernel k-groups']
for algo, zh in zip(algos, r):
t.add_row([algo,
metric.accuracy(z, zh),
r = []
for _ in range(num_experiments):
for dim in dimensions:
X, z = generate_data(dim)
G = eclust.kernel_matrix(X, lambda x, y: np.linalg.norm(x - y))
zh = wrapper.kmeans(k, X)
a = metric.accuracy(z, zh)
r.append(['k-means', dim, a])
zh = wrapper.gmm(k, X)
a = metric.accuracy(z, zh)
r.append(['gmm', dim, a])
zh = wrapper.spectral_clustering(k, X, G)
a = metric.accuracy(z, zh)
r.append(['spectral clustering', dim, a])
zh = wrapper.kernel_kmeans(k, X, G)
a = metric.accuracy(z, zh)
r.append(['kernel k-means', dim, a])
zh = wrapper.kernel_kgroups(k, X, G)
a = metric.accuracy(z, zh)
r.append(['kernel k-groups', dim, a])
df = pd.DataFrame(np.array(r), columns=['method', 'dimension', 'accuracy'])
df.to_csv(output, index=False)
delete_missing = np.where(data=='?')[0]
data = np.delete(data, delete_missing, axis=0)
data = np.array(data, dtype=float)
z = np.delete(z, delete_missing, axis=0)
# normalize data
data = (data - data.mean(axis=0))/data.std(axis=0)
G = eclust.kernel_matrix(data, rho)
#G = energy.eclust.kernel_matrix(data, rho_gauss)
#G = energy.eclust.kernel_matrix(data, rho_exp)
r = []
r.append(wrapper.kmeans(6, data, run_times=10))
r.append(wrapper.gmm(6, data, run_times=10))
r.append(wrapper.spectral_clustering(6, data, G, run_times=10))
r.append(wrapper.spectral(6, data, G, run_times=10))
#r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='random'))
r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='k-means++'))
#r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='spectral'))
#r.append(wrapper.kernel_kgroups(6,data,G,run_times=10, ini='random'))
r.append(wrapper.kernel_kgroups(6,data,G,run_times=10, ini='k-means++'))
#r.append(wrapper.kernel_kgroups(6,data,G,run_times=10, ini='spectral'))
t = PrettyTable(['Algorithm', 'Accuracy', 'A-Rand'])
algos = ['kmeans', 'GMM', 'spectral clustering', 'spectral',
'kernel k-means', 'kernel k-groups']
r = []
for _ in range(num_experiments):
for dim in dimensions:
X, z = generate_data(dim)
G = eclust.kernel_matrix(X, lambda x, y: np.linalg.norm(x-y))
zh = wrapper.kmeans(k, X)
a = metric.accuracy(z, zh)
r.append(['k-means', dim, a])
zh = wrapper.gmm(k, X)
a = metric.accuracy(z, zh)
r.append(['gmm', dim, a])
zh = wrapper.spectral_clustering(k, X, G)
a = metric.accuracy(z, zh)
r.append(['spectral clustering', dim, a])
zh = wrapper.kernel_kmeans(k, X, G)
a = metric.accuracy(z, zh)
r.append(['kernel k-means', dim, a])
zh = wrapper.kernel_kgroups(k, X, G)
a = metric.accuracy(z, zh)
r.append(['kernel k-groups', dim, a])
df = pd.DataFrame(np.array(r), columns=['method', 'dimension', 'accuracy'])
df.to_csv(output, index=False)
delete_missing = np.where(data == '?')[0]
data = np.delete(data, delete_missing, axis=0)
data = np.array(data, dtype=float)
z = np.delete(z, delete_missing, axis=0)
# normalize data
data = (data - data.mean(axis=0)) / data.std(axis=0)
G = eclust.kernel_matrix(data, rho)
#G = energy.eclust.kernel_matrix(data, rho_gauss)
#G = energy.eclust.kernel_matrix(data, rho_exp)
r = []
r.append(wrapper.kmeans(6, data, run_times=10))
r.append(wrapper.gmm(6, data, run_times=10))
r.append(wrapper.spectral_clustering(6, data, G, run_times=10))
r.append(wrapper.spectral(6, data, G, run_times=10))
#r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='random'))
r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='k-means++'))
#r.append(wrapper.kernel_kmeans(6, data, G, run_times=10, ini='spectral'))
#r.append(wrapper.kernel_kgroups(6,data,G,run_times=10, ini='random'))
r.append(wrapper.kernel_kgroups(6, data, G, run_times=10, ini='k-means++'))
#r.append(wrapper.kernel_kgroups(6,data,G,run_times=10, ini='spectral'))
t = PrettyTable(['Algorithm', 'Accuracy', 'A-Rand'])
algos = [
'kmeans', 'GMM', 'spectral clustering', 'spectral', 'kernel k-means',
'kernel k-groups'