def template_clustering(sample_file_path, amount_clusters, initializer, show_animation = False):
sample = read_sample(sample_file_path);
observer = None;
if (show_animation is True):
observer = ema_observer();
initial_means, initial_covariance = ema_initializer(sample, amount_clusters).initialize(initializer);
ema_instance = ema(sample, amount_clusters, initial_means, initial_covariance, observer=observer);
ema_instance.process();
clusters = ema_instance.get_clusters();
covariances = ema_instance.get_covariances();
means = ema_instance.get_centers();
cluster_length = [ len(cluster) for cluster in clusters ];
print("Data '" + sample_file_path + "'");
print("Clusters: " + str(len(clusters)) + ", Length:" + str(cluster_length));
if (observer is True):
ema_visualizer.show_clusters(observer.get_evolution_clusters()[0], sample, observer.get_evolution_covariances()[0], observer.get_evolution_means()[0]);
ema_visualizer.show_clusters(clusters, sample, covariances, means);
if (show_animation is True):
ema_visualizer.animate_cluster_allocation(sample, observer);
def template_clustering(sample_file_path, amount_clusters, initializer, show_animation = False):
sample = read_sample(sample_file_path);
observer = None;
if (show_animation is True):
observer = ema_observer();
initial_means, initial_covariance = ema_initializer(sample, amount_clusters).initialize(initializer);
ema_instance = ema(sample, amount_clusters, initial_means, initial_covariance, observer=observer);
ema_instance.process();
clusters = ema_instance.get_clusters();
covariances = ema_instance.get_covariances();
means = ema_instance.get_centers();
cluster_length = [ len(cluster) for cluster in clusters ];
print("Data '" + sample_file_path + "'");
print("Clusters: " + str(len(clusters)) + ", Length:" + str(cluster_length));
if (observer is True):
ema_visualizer.show_clusters(observer.get_evolution_clusters()[0], sample, observer.get_evolution_covariances()[0], observer.get_evolution_means()[0]);
ema_visualizer.show_clusters(clusters, sample, covariances, means);
if (show_animation is True):
ema_visualizer.animate_cluster_allocation(sample, observer);
def templateDataClustering(self,
sample_path,
amount_clusters,
expected_clusters_sizes,
init_type=ema_init_type.KMEANS_INITIALIZATION):
testing_result = False
if (init_type != ema_init_type.KMEANS_INITIALIZATION):
attempts = 10
else:
attempts = 5
for _ in range(attempts):
sample = read_sample(sample_path)
means, variances = None, None
if (init_type is not ema_init_type.KMEANS_INITIALIZATION):
means, variances = ema_initializer(
sample, amount_clusters).initialize(init_type)
ema_instance = ema(sample, amount_clusters, means, variances)
ema_instance.process()
clusters = ema_instance.get_clusters()
centers = ema_instance.get_centers()
covariances = ema_instance.get_covariances()
probabilities = ema_instance.get_probabilities()
assert len(centers) == len(clusters)
assert len(covariances) == len(clusters)
assert len(probabilities) == len(clusters)
for cluster_probability in probabilities:
assert len(cluster_probability) == len(sample)
for index_point in range(len(sample)):
total_probability = 0.0
for cluster_probability in probabilities:
total_probability += cluster_probability[index_point]
assert abs(total_probability - 1.0) <= 0.00001
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
if (len(sample) != sum(obtained_cluster_sizes)):
continue
if (expected_clusters_sizes != None):
obtained_cluster_sizes.sort()
expected_clusters_sizes.sort()
if (obtained_cluster_sizes != expected_clusters_sizes):
continue
testing_result = True
break
assert testing_result == True
def templateDataClustering(self, sample_path,
amount_clusters,
expected_clusters_sizes,
init_type = ema_init_type.KMEANS_INITIALIZATION):
testing_result = False
attempts = 10
for _ in range(attempts):
sample = read_sample(sample_path)
means, variances = None, None
if init_type is not ema_init_type.KMEANS_INITIALIZATION:
means, variances = ema_initializer(sample, amount_clusters).initialize(init_type)
ema_instance = ema(sample, amount_clusters, means, variances)
ema_instance.process()
clusters = ema_instance.get_clusters()
centers = ema_instance.get_centers()
covariances = ema_instance.get_covariances()
probabilities = ema_instance.get_probabilities()
assert len(centers) == len(clusters)
assert len(covariances) == len(clusters)
assert len(probabilities) == len(clusters)
for cluster_probability in probabilities:
assert len(cluster_probability) == len(sample)
for index_point in range(len(sample)):
total_probability = 0.0
for cluster_probability in probabilities:
total_probability += cluster_probability[index_point]
assert abs(total_probability - 1.0) <= 0.00001
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
if len(sample) != sum(obtained_cluster_sizes):
continue
if expected_clusters_sizes is not None:
obtained_cluster_sizes.sort()
expected_clusters_sizes.sort()
if obtained_cluster_sizes != expected_clusters_sizes:
continue
testing_result = True
break
assert testing_result is True
def testVisualizerNoFailures(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3)
means, variances = ema_initializer(sample, 4).initialize(ema_init_type.RANDOM_INITIALIZATION)
observer_instance = ema_observer()
ema_instance = ema(sample, 4, means, variances, observer_instance)
ema_instance.process()
clusters = ema_instance.get_clusters()
means = ema_instance.get_centers()
covariances = ema_instance.get_covariances()
ema_visualizer.show_clusters(clusters, sample, covariances, means)
ema_visualizer.animate_cluster_allocation(sample, observer_instance)
def testObserver(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2)
means, variances = ema_initializer(sample, 3).initialize(ema_init_type.RANDOM_INITIALIZATION)
observer_instance = ema_observer()
ema_instance = ema(sample, 3, means, variances, observer_instance)
ema_instance.process()
observer_length = len(observer_instance)
assert observer_length > 0
assert observer_length == len(observer_instance.get_evolution_clusters())
assert observer_length == len(observer_instance.get_evolution_covariances())
assert observer_length == len(observer_instance.get_evolution_means())
assert observer_length == observer_instance.get_iterations()
def testVisualizerNoFailures(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3)
means, variances = ema_initializer(sample, 4).initialize(ema_init_type.RANDOM_INITIALIZATION)
observer_instance = ema_observer()
ema_instance = ema(sample, 4, means, variances, observer_instance)
ema_instance.process()
clusters = ema_instance.get_clusters()
means = ema_instance.get_centers()
covariances = ema_instance.get_covariances()
ema_visualizer.show_clusters(clusters, sample, covariances, means)
ema_visualizer.animate_cluster_allocation(sample, observer_instance)
def testObserver(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2)
means, variances = ema_initializer(sample, 3).initialize(ema_init_type.RANDOM_INITIALIZATION)
observer_instance = ema_observer()
ema_instance = ema(sample, 3, means, variances, observer_instance)
ema_instance.process()
observer_length = len(observer_instance)
assert observer_length > 0
assert observer_length == len(observer_instance.get_evolution_clusters())
assert observer_length == len(observer_instance.get_evolution_covariances())
assert observer_length == len(observer_instance.get_evolution_means())
assert observer_length == observer_instance.get_iterations()
