def energy1D(X, z):
"""Energy clustering in 1 dimension. No need to run multiple times since
this is exact.
"""
zh, cost = energy1d.two_clusters1D(X)
return metric.accuracy(z, zh)
def energy1D(X, z):
"""Energy clustering in 1 dimension. No need to run multiple times since
this is exact.
"""
zh, cost = energy1d.two_clusters1D(X)
return metric.accuracy(z, zh)
def kmeans(k, X, z, run_times=10, init='k-means++'):
"""run_times is the number of times the algorithm is gonna run.
init = {'k-means++', 'random'}
"""
km = KMeans(k, n_init=run_times, init=init)
km.fit(X)
zh = km.labels_
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def kmeans(k, X, z, run_times=10, init='k-means++'):
"""run_times is the number of times the algorithm is gonna run.
init = {'k-means++', 'random'}
"""
km = KMeans(k, n_init=run_times, init=init)
km.fit(X)
zh = km.labels_
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def spectral(k, X, G, z, run_times=10):
"""Spectral clustering from sklearn library.
run_times is the number of times the algorithm is gonna run with different
initializations.
"""
sc = SpectralClustering(k, affinity='precomputed', n_init=run_times)
zh = sc.fit_predict(G)
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def spectral(k, X, G, z, run_times=10):
"""Spectral clustering from sklearn library.
run_times is the number of times the algorithm is gonna run with different
initializations.
"""
sc = SpectralClustering(k, affinity='precomputed', n_init=run_times)
zh = sc.fit_predict(G)
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def gmm(k, X, z, run_times=10, init='kmeans'):
"""GMM from sklearn library. init = {'kmeans', 'random'}, run_times
is the number of times the algorithm is gonna run with different
initializations.
"""
gm = GMM(k, n_init=run_times, init_params=init)
gm.fit(X)
zh = gm.predict(X)
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def gmm(k, X, z, run_times=10, init='kmeans'):
"""GMM from sklearn library. init = {'kmeans', 'random'}, run_times
is the number of times the algorithm is gonna run with different
initializations.
"""
gm = GMM(k, n_init=run_times, init_params=init)
gm.fit(X)
zh = gm.predict(X)
a = metric.accuracy(z, zh)
v = metric.variation_information(z, zh)
return a, v
def energy_hartigan(k, X, G, z, run_times=10, init="spectral"):
"""Run few times and pick the best objective function value."""
best_score = -np.inf
for rt in range(run_times):
Z0 = initialize(init, k, G, X)
zh = eclust.energy_hartigan(k, G, Z0, max_iter=300)
Zh = eclust.ztoZ(zh)
score = eclust.objective(Zh, G)
if score > best_score:
best_score = score
best_z = zh
a = metric.accuracy(z, best_z)
v = metric.variation_information(z, best_z)
return a, v
def energy_hartigan(k, X, G, z, run_times=10, init="spectral"):
"""Run few times and pick the best objective function value."""
best_score = -np.inf
for rt in range(run_times):
Z0 = initialize(init, k, G, X)
zh = eclust.energy_hartigan(k, G, Z0, max_iter=300)
Zh = eclust.ztoZ(zh)
score = eclust.objective(Zh, G)
if score > best_score:
best_score = score
best_z = zh
a = metric.accuracy(z, best_z)
v = metric.variation_information(z, best_z)
return a, v
def energy_spectral(k, X, G, z, run_times=10, init="random"):
"""Run few times and pick the best objective function value.
Choose the initializatio for k-means, which can be k-means++ or random.
"""
best_score = -np.inf
for rt in range(run_times):
zh = initialization.topeigen(k, G, run_times=run_times, init="random")
Zh = eclust.ztoZ(zh)
score = eclust.objective(Zh, G)
if score > best_score:
best_score = score
best_z = zh
a = metric.accuracy(z, best_z)
v = metric.variation_information(z, best_z)
return a, v
def energy_spectral(k, X, G, z, run_times=10, init="random"):
"""Run few times and pick the best objective function value.
Choose the initializatio for k-means, which can be k-means++ or random.
"""
best_score = -np.inf
for rt in range(run_times):
zh = initialization.topeigen(k, G, run_times=run_times, init="random")
Zh = eclust.ztoZ(zh)
score = eclust.objective(Zh, G)
if score > best_score:
best_score = score
best_z = zh
a = metric.accuracy(z, best_z)
v = metric.variation_information(z, best_z)
return a, v
n0 = 500
n1 = 500
data_class0 = data[np.where(labels == 0)]
data_class1 = data[np.where(labels == 1)]
idx0 = np.random.choice(range(len(data_class0)), n0, replace=True)
idx1 = np.random.choice(range(len(data_class1)), n1, replace=True)
data, labels = shuffle_data([data_class0[idx0], data_class1[idx1]])
#data = (data - data.mean(axis=0))/data.std(axis=0)
rho = lambda x, y: np.power(np.linalg.norm(x - y), 1)
#rho = lambda x, y: 2-2*np.exp(-np.power(np.linalg.norm(x-y),1)/(2*1**2))
G = eclust.kernel_matrix(data, rho)
labels_hat = run_clustering.kmeans(2, data)
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
print
labels_hat = run_clustering.gmm(2, data)
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
print
labels_hat = run_clustering.energy_hartigan(2,
data,
G,
run_times=5,
init="gmm")
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
n0 = 500
n1 = 500
data_class0 = data[np.where(labels==0)]
data_class1 = data[np.where(labels==1)]
idx0 = np.random.choice(range(len(data_class0)), n0, replace=True)
idx1 = np.random.choice(range(len(data_class1)), n1, replace=True)
data, labels = shuffle_data([data_class0[idx0], data_class1[idx1]])
#data = (data - data.mean(axis=0))/data.std(axis=0)
rho = lambda x, y: np.power(np.linalg.norm(x-y), 1)
#rho = lambda x, y: 2-2*np.exp(-np.power(np.linalg.norm(x-y),1)/(2*1**2))
G = eclust.kernel_matrix(data, rho)
labels_hat = run_clustering.kmeans(2, data)
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
print
labels_hat = run_clustering.gmm(2, data)
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
print
labels_hat = run_clustering.energy_hartigan(2, data, G, run_times=5,
init="gmm")
print accuracy(labels, labels_hat)
print type_errors(labels, labels_hat)
print