def template_clustering(file, map_size, radius, sync_order = 0.999, show_dyn = False, show_layer1 = False, show_layer2 = False, show_clusters = True):
# Read sample
sample = read_sample(file);
# Create network
network = syncsom(sample, map_size[0], map_size[1], radius);
# Run processing
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, show_dyn, sync_order);
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n");
# Show dynamic of the last layer.
if (show_dyn == True):
draw_dynamics(dyn_time, dyn_phase, x_title = "Time", y_title = "Phase", y_lim = [0, 3.14]);
if (show_clusters == True):
clusters = network.get_som_clusters();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, network.som_layer.weights);
visualizer.show();
# Show network stuff.
if (show_layer1 == True):
network.show_som_layer();
if (show_layer2 == True):
network.show_sync_layer();
if (show_clusters == True):
clusters = network.get_clusters();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.show();
def show_clusters(clusters, sample, covariances, means, figure = None, display = True):
"""!
@brief Draws clusters and in case of two-dimensional dataset draws their ellipses.
@param[in] clusters (list): Clusters that were allocated by the algorithm.
@param[in] sample (list): Dataset that were used for clustering.
@param[in] covariances (list): Covariances of the clusters.
@param[in] means (list): Means of the clusters.
@param[in] figure (figure): If 'None' then new is figure is creater, otherwise specified figure is used
for visualization.
@param[in] display (bool): If 'True' then figure will be shown by the method, otherwise it should be
shown manually using matplotlib function 'plt.show()'.
@return (figure) Figure where clusters were drawn.
"""
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
if figure is None:
figure = visualizer.show(display = False)
else:
visualizer.show(figure = figure, display = False)
if len(sample[0]) == 2:
ema_visualizer.__draw_ellipses(figure, visualizer, clusters, covariances, means)
if display is True:
plt.show()
return figure
def show_clusters(sample, clusters, representatives, **kwargs):
"""!
@brief Display BSAS clustering results.
@param[in] sample (list): Dataset that was used for clustering.
@param[in] clusters (array_like): Clusters that were allocated by the algorithm.
@param[in] representatives (array_like): Allocated representatives correspond to clusters.
@param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'figure', 'display', 'offset').
<b>Keyword Args:</b><br>
- figure (figure): If 'None' then new is figure is created, otherwise specified figure is used for visualization.
- display (bool): If 'True' then figure will be shown by the method, otherwise it should be shown manually using matplotlib function 'plt.show()'.
- offset (uint): Specify axes index on the figure where results should be drawn (only if argument 'figure' is specified).
@return (figure) Figure where clusters were drawn.
"""
figure = kwargs.get('figure', None)
display = kwargs.get('display', True)
offset = kwargs.get('offset', 0)
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample, canvas=offset)
for cluster_index in range(len(clusters)):
visualizer.append_cluster_attribute(offset, cluster_index, [representatives[cluster_index]], '*', 10)
return visualizer.show(figure=figure, display=display)
def testVisualizeHugeAmountClusters(self):
visualizer = cluster_visualizer();
data_clusters = [ [ [ random.random() ] ] for _ in range(0, 100) ];
visualizer.append_clusters(data_clusters);
visualizer.show();
def testVisualizeByDataOnly(self):
visualizer = cluster_visualizer();
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer.append_clusters([ sample ]);
visualizer.show();
def template_clustering(number_clusters, path, links):
sample = read_sample(path);
clusters_centroid_link = None;
clusters_single_link = None;
clusters_complete_link = None;
clusters_average_link = None;
visualizer = cluster_visualizer(len(links));
index_canvas = 0;
if (type_link.CENTROID_LINK in links):
agglomerative_centroid_link = agglomerative(sample, number_clusters, type_link.CENTROID_LINK);
(ticks, result) = timedcall(agglomerative_centroid_link.process);
clusters_centroid_link = agglomerative_centroid_link.get_clusters();
visualizer.append_clusters(clusters_centroid_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Centroid', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Centroid", "\tExecution time: ", ticks, "\n");
if (type_link.SINGLE_LINK in links):
agglomerative_simple_link = agglomerative(sample, number_clusters, type_link.SINGLE_LINK);
(ticks, result) = timedcall(agglomerative_simple_link.process);
clusters_single_link = agglomerative_simple_link.get_clusters();
visualizer.append_clusters(clusters_single_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Single', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Single", "\tExecution time: ", ticks, "\n");
if (type_link.COMPLETE_LINK in links):
agglomerative_complete_link = agglomerative(sample, number_clusters, type_link.COMPLETE_LINK);
(ticks, result) = timedcall(agglomerative_complete_link.process);
clusters_complete_link = agglomerative_complete_link.get_clusters();
visualizer.append_clusters(clusters_complete_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Complete', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Complete", "\tExecution time: ", ticks, "\n");
if (type_link.AVERAGE_LINK in links):
agglomerative_average_link = agglomerative(sample, number_clusters, type_link.AVERAGE_LINK);
(ticks, result) = timedcall(agglomerative_average_link.process);
clusters_average_link = agglomerative_average_link.get_clusters();
visualizer.append_clusters(clusters_average_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Average', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Average", "\tExecution time: ", ticks, "\n");
visualizer.show();
def testVisualizeOnExistedFigure(self):
figure = plt.figure();
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer = cluster_visualizer();
visualizer.append_clusters([ sample ]);
visualizer.show(figure);
def testVisualizeRectangeRepresentation3x5(self):
visualizer = cluster_visualizer(15, 5);
for i in range(15):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer.append_clusters([ sample ], None, i, markersize = 5);
visualizer.show();
def testVisualize2DAnd3DClusters(self):
sample_2d = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
sample_3d = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA);
visualizer = cluster_visualizer(2, 2);
visualizer.append_clusters([ sample_2d ], None, 0, markersize = 5);
visualizer.append_clusters([ sample_3d ], None, 1, markersize = 30);
visualizer.show();
def testVisualize1DClustersTwoCanvases(self):
sample_simple7 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE7);
sample_simple8 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE8);
# Two canvas visualization
visualizer = cluster_visualizer(2);
visualizer.append_clusters([ sample_simple7 ], None, 0, markersize = 30);
visualizer.append_clusters([ sample_simple8 ], None, 1, markersize = 30);
visualizer.show();
def testVisualize3DClustersTwoCanvases(self):
sample_tetra = read_sample(FCPS_SAMPLES.SAMPLE_TETRA);
sample_hepta = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA);
# Two canvas visualization
visualizer = cluster_visualizer(2);
visualizer.append_clusters([ sample_tetra ], None, 0, markersize = 30);
visualizer.append_clusters([ sample_hepta ], None, 1, markersize = 30);
visualizer.show();
def testVisualizeRectangeRepresentation2x2(self):
sample_simple1 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
sample_simple2 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2);
sample_simple3 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3);
visualizer = cluster_visualizer(3, 2);
visualizer.append_clusters([ sample_simple1 ], None, 0, markersize = 5);
visualizer.append_clusters([ sample_simple2 ], None, 1, markersize = 5);
visualizer.append_clusters([ sample_simple3 ], None, 2, markersize = 5);
visualizer.show();
def testVisualizeOnExistedFigureWithContentByDefault(self):
figure = plt.figure();
axis = figure.add_subplot(211);
axis.plot(range(0, 10, 1), range(0, 10, 1), marker = 'o', color = 'blue', ls = '');
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer = cluster_visualizer();
visualizer.append_clusters([ sample ]);
visualizer.show(figure);
def testVisualize2DClustersOneCanvas(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE4);
dbscan_instance = dbscan(sample, 0.7, 3, False);
dbscan_instance.process();
clusters = dbscan_instance.get_clusters();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample, markersize = 5);
visualizer.show();
def testVisualize3DClustersOneCanvas(self):
sample = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA);
dbscan_instance = dbscan(sample, 0.5, 3, False);
dbscan_instance.process();
clusters = dbscan_instance.get_clusters();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample, markersize = 30);
visualizer.show();
def display_fcps_clustering_results():
(simple4, simple4_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE4, 1, 0.999, show_dyn = False, show_conn = False, ccore_flag = True);
(simple_elongate, simple_elongate_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_ELONGATE, 0.5, 0.999, show_dyn = False, show_conn = False, ccore_flag = True);
(lsun, lsun_clusters) = template_clustering(FCPS_SAMPLES.SAMPLE_LSUN, 0.45, 0.9995, show_dyn = False, show_conn = False, ccore_flag = True, tolerance = 0.2);
visualizer = cluster_visualizer(1, 3);
visualizer.append_clusters(simple4_clusters, simple4, 0);
visualizer.append_clusters(simple_elongate_clusters, simple_elongate, 1);
visualizer.append_clusters(lsun_clusters, lsun, 2);
visualizer.show();
def template_kmeans_plusplus_initializer(path, amount, draw = True):
sample = read_sample(path);
centers = kmeans_plusplus_initializer(sample, amount).initialize();
if (draw is True):
visualizer = cluster_visualizer();
visualizer.append_cluster(sample);
visualizer.append_cluster(centers, marker = '*', markersize = 10);
visualizer.show();
return (sample, centers);
def show_clusters(data, clusters, noise=None):
"""!
@brief Display BANG clustering results.
@param[in] data (list): Dataset that was used for clustering.
@param[in] clusters (array_like): Clusters that were allocated by the algorithm.
@param[in] noise (array_like): Noise that were allocated by the algorithm.
"""
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, data)
visualizer.append_cluster(noise or [], data, marker='x')
visualizer.show()
def template_clustering(start_medoids, path, tolerance = 0.25, show = True):
sample = read_sample(path);
kmedoids_instance = kmedoids(sample, start_medoids, tolerance);
(ticks, result) = timedcall(kmedoids_instance.process);
clusters = kmedoids_instance.get_clusters();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
if (show is True):
visualizer = cluster_visualizer(1);
visualizer.append_clusters(clusters, sample, 0);
visualizer.show();
return (sample, clusters);
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = True):
sample = read_sample(path);
dbscan_instance = dbscan(sample, radius, neighb, ccore);
(ticks, result) = timedcall(dbscan_instance.process);
clusters = dbscan_instance.get_clusters();
noise = dbscan_instance.get_noise();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(noise, sample, marker = 'x');
visualizer.show();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
def template_clustering(start_centers, path, tolerance=0.25, ccore=True):
sample = read_sample(path)
kmeans_instance = kmeans(sample, start_centers, tolerance, ccore)
(ticks, result) = timedcall(kmeans_instance.process)
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(start_centers, marker="*", markersize=20)
visualizer.append_cluster(centers, marker="*", markersize=20)
visualizer.show()
def template_clustering(number_clusters, path, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.0, type_measurement = measurement_type.AVERAGE_INTER_CLUSTER_DISTANCE, entry_size_limit = 200, diameter_multiplier = 1.5, show_result = True):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, diameter_multiplier);
(ticks, result) = timedcall(birch_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = birch_instance.get_clusters();
if (show_result is True):
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.show();
return (sample, clusters);
def xmeans_clustering(
data: np.ndarray,
kmin: [int, None] = 1,
kmax: [int, None] = 20,
tolerance: float = 0.025,
criterion: enumerate = splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore: bool = True,
logger=Logger(name='clustering'),
visualize: bool = False) -> np.ndarray:
# Initial centers - KMeans algorithm
kmeans = KMeans(n_clusters=kmin)
kmeans.fit(data)
initial_centers = kmeans.cluster_centers_
# X-Means algorithm
xmeans_instance = xmeans(data=data,
initial_centers=initial_centers,
kmax=kmax,
tolerance=tolerance,
criterion=criterion,
ccore=ccore)
(ticks, _) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
criterion_string = "UNKNOWN"
if criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION:
criterion_string = "BAYESIAN INFORMATION CRITERION"
elif criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH:
criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH"
if logger is not None:
logger.debug(
"Initial centers: {},\n Execution time: {},\n Number of clusters: {},\n criterion: {}"
.format(initial_centers is not None, ticks, len(clusters),
criterion_string))
if visualize:
visualizer = cluster_visualizer()
visualizer.set_canvas_title(criterion_string)
visualizer.append_clusters(clusters, data)
visualizer.append_cluster(centers, None, marker='*')
visualizer.show()
return clusters
def find_optimal_amout_clusters(sample_path, kmin, kmax, algorithm):
sample = read_sample(sample_path)
search_instance = silhouette_ksearch(sample, kmin, kmax, algorithm=algorithm).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
print("Sample: '%s', Scores: '%s'" % (sample_path, str(scores)))
initial_centers = kmeans_plusplus_initializer(sample, amount).initialize()
kmeans_instance = kmeans(sample, initial_centers).process()
clusters = kmeans_instance.get_clusters()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
def show_feature_destibution(self, data=None):
visualizer = cluster_visualizer()
print("amount of nodes: ", self.__amount_nodes)
if (data is not None):
visualizer.append_cluster(data, marker='x')
for level in range(0, self.height):
level_nodes = self.get_level_nodes(level)
centers = [node.feature.get_centroid() for node in level_nodes]
visualizer.append_cluster(centers,
None,
markersize=(self.height - level + 1) * 5)
visualizer.show()
def testVisualizeClusterWithAttributes(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
cure_instance = cure(sample, 2, 5, 0.5, False);
cure_instance.process();
clusters = cure_instance.get_clusters();
representors = cure_instance.get_representors();
means = cure_instance.get_means();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
for cluster_index in range(len(clusters)):
visualizer.append_cluster_attribute(0, cluster_index, representors[cluster_index], '*', 10);
visualizer.append_cluster_attribute(0, cluster_index, [ means[cluster_index] ], 'o');
visualizer.show();
def find_optimal_amout_clusters(sample_path, kmin, kmax, algorithm):
sample = read_sample(sample_path)
search_instance = silhouette_ksearch(sample, kmin, kmax, algorithm=algorithm).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
print("Sample: '%s', Scores: '%s'" % (sample_path, str(scores)))
initial_centers = kmeans_plusplus_initializer(sample, amount).initialize()
kmeans_instance = kmeans(sample, initial_centers).process()
clusters = kmeans_instance.get_clusters()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
def testVisualizeClusterWithAttributes(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
cure_instance = cure(sample, 2, 5, 0.5, False);
cure_instance.process();
clusters = cure_instance.get_clusters();
representors = cure_instance.get_representors();
means = cure_instance.get_means();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
for cluster_index in range(len(clusters)):
visualizer.append_cluster_attribute(0, cluster_index, representors[cluster_index], '*', 10);
visualizer.append_cluster_attribute(0, cluster_index, [ means[cluster_index] ], 'o');
visualizer.show();
def show_clusters(sample,
clusters,
centers,
initial_centers=None,
**kwargs):
"""!
@brief Display K-Means clustering results.
@details Allocated figure by this method should be closed using `close()` method of this visualizer.
@param[in] sample (list): Dataset that was used for clustering.
@param[in] clusters (array_like): Clusters that were allocated by the algorithm.
@param[in] centers (array_like): Centers that were allocated by the algorithm.
@param[in] initial_centers (array_like): Initial centers that were used by the algorithm, if 'None' then initial centers are not displyed.
@param[in] **kwargs: Arbitrary keyword arguments (available arguments: 'figure', 'display', 'offset').
<b>Keyword Args:</b><br>
- figure (figure): If 'None' then new is figure is created, otherwise specified figure is used for visualization.
- display (bool): If 'True' then figure will be shown by the method, otherwise it should be shown manually using matplotlib function 'plt.show()'.
- offset (uint): Specify axes index on the figure where results should be drawn (only if argument 'figure' is specified).
@return (figure) Figure where clusters were drawn.
"""
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
offset = kwargs.get('offset', 0)
figure = kwargs.get('figure', None)
display = kwargs.get('display', True)
if figure is None:
figure = visualizer.show(display=False)
else:
visualizer.show(figure=figure, display=False)
kmeans_visualizer.__draw_centers(figure, offset, visualizer, centers,
initial_centers)
kmeans_visualizer.__draw_rays(figure, offset, visualizer, sample,
clusters, centers)
if display is True:
plt.show()
return figure
def optics_temp(self, point_list):
# data = np.array( point_list)
sample = point_list
start = time.time()
optics_instance = optics(sample, 0.5, 6, ccore=True)
optics_instance.process()
clusters = optics_instance.get_clusters()
end = time.time()
print("imte", end - start)
noise = optics_instance.get_noise()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker='x')
visualizer.show()
ordering = optics_instance.get_ordering()
analyser = ordering_analyser(ordering)
ordering_visualizer.show_ordering_diagram(analyser, amount_clusters)
def template_clustering(number_clusters, path, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.0, type_measurement = measurement_type.AVERAGE_INTER_CLUSTER_DISTANCE, entry_size_limit = 200, diameter_multiplier = 1.5, outlier_detector = 0, show_result = True):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, diameter_multiplier, outlier_detector);
(ticks, result) = timedcall(birch_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = birch_instance.get_clusters();
noise = birch_instance.get_noise();
if (show_result is True):
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(noise, sample, marker = 'x');
visualizer.show();
return (sample, clusters, noise);
def template_clustering(start_medoids, path, tolerance = 0.25, show = True):
sample = read_sample(path)
kmedoids_instance = kmedoids(sample, start_medoids, tolerance)
(ticks, result) = timedcall(kmedoids_instance.process)
clusters = kmedoids_instance.get_clusters()
medoids = kmedoids_instance.get_medoids()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if show is True:
visualizer = cluster_visualizer(1)
visualizer.append_clusters(clusters, sample, 0)
visualizer.append_cluster([sample[index] for index in start_medoids], marker='*', markersize=15)
visualizer.append_cluster(medoids, data=sample, marker='*', markersize=15)
visualizer.show()
return sample, clusters
def template_clustering(start_medoids, path, tolerance = 0.25, show = True):
sample = read_sample(path);
kmedoids_instance = kmedoids(sample, start_medoids, tolerance);
(ticks, result) = timedcall(kmedoids_instance.process);
clusters = kmedoids_instance.get_clusters();
medoids = kmedoids_instance.get_medoids();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
if (show is True):
visualizer = cluster_visualizer(1);
visualizer.append_clusters(clusters, sample, 0);
visualizer.append_cluster([ sample[index] for index in start_medoids ], marker = '*', markersize = 15);
visualizer.append_cluster(medoids, marker = '*', markersize = 15);
visualizer.show();
return (sample, clusters);
def template_clustering(start_medoids,
path,
tolerance=0.25,
show=True,
**kwargs):
ccore = kwargs.get('ccore', True)
data_type = kwargs.get('data_type', 'points')
original_data = read_sample(path)
sample = original_data
if data_type == 'distance_matrix':
sample = calculate_distance_matrix(sample)
metric = distance_metric(type_metric.EUCLIDEAN_SQUARE, data=sample)
kmedoids_instance = kmedoids(sample,
start_medoids,
tolerance,
metric=metric,
ccore=ccore,
data_type=data_type)
(ticks, result) = timedcall(kmedoids_instance.process)
clusters = kmedoids_instance.get_clusters()
print("Iterations:", kmedoids_instance.get_iterations())
print([len(cluster) for cluster in clusters])
print(clusters)
medoids = kmedoids_instance.get_medoids()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if show is True:
visualizer = cluster_visualizer(1)
visualizer.append_clusters(clusters, original_data, 0)
visualizer.append_cluster(
[original_data[index] for index in start_medoids],
marker='*',
markersize=15)
visualizer.append_cluster(medoids,
data=original_data,
marker='*',
markersize=15)
visualizer.show()
return original_data, clusters
def frame_generation(index_dynamic):
figure.clf()
if title is not None:
figure.suptitle(title, fontsize = 26, fontweight = 'bold')
ax1 = figure.add_subplot(121, projection='polar')
clusters = analyser.allocate_clusters(eps = tolerance, iteration = index_dynamic)
dynamic = analyser.output[index_dynamic]
visualizer = cluster_visualizer(size_row = 2)
visualizer.append_clusters(clusters, dataset)
artist1, = ax1.plot(dynamic, [1.0] * len(dynamic), marker='o', color='blue', ls='')
visualizer.show(figure, display = False)
artist2 = figure.gca()
return [ artist1, artist2 ]
def kmeans_plusplus_initializer_collection():
(sample1, centers1) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, 2, False);
(sample2, centers2) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, 3, False);
(sample3, centers3) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, 4, False);
(sample4, centers4) = template_kmeans_plusplus_initializer(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, 2, False);
visualizer = cluster_visualizer(4, 2);
visualizer.append_cluster(sample1, canvas = 0);
visualizer.append_cluster(centers1, canvas = 0, marker = '*', markersize = 10);
visualizer.append_cluster(sample2, canvas = 1);
visualizer.append_cluster(centers2, canvas = 1, marker = '*', markersize = 10);
visualizer.append_cluster(sample3, canvas = 2);
visualizer.append_cluster(centers3, canvas = 2, marker = '*', markersize = 10);
visualizer.append_cluster(sample4, canvas = 3);
visualizer.append_cluster(centers4, canvas = 3, marker = '*', markersize = 10);
visualizer.show();
def kmeans_plusplus_initializer_collection():
(sample1, centers1) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, 2, False)
(sample2, centers2) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, 3, False)
(sample3, centers3) = template_kmeans_plusplus_initializer(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, 4, False)
(sample4, centers4) = template_kmeans_plusplus_initializer(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, 2, False)
visualizer = cluster_visualizer(4, 2)
visualizer.append_cluster(sample1, canvas=0)
visualizer.append_cluster(centers1, canvas=0, marker='*', markersize=10)
visualizer.append_cluster(sample2, canvas=1)
visualizer.append_cluster(centers2, canvas=1, marker='*', markersize=10)
visualizer.append_cluster(sample3, canvas=2)
visualizer.append_cluster(centers3, canvas=2, marker='*', markersize=10)
visualizer.append_cluster(sample4, canvas=3)
visualizer.append_cluster(centers4, canvas=3, marker='*', markersize=10)
visualizer.show()
def template_clustering(radius,
neighb,
path,
invisible_axes=False,
ccore=True):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighb, ccore)
(ticks, result) = timedcall(dbscan_instance.process)
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker='x')
visualizer.show()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
def display_simple_dbscan_results():
(simple1, simple1_clusters, _) = template_clustering(0.4, 2, SIMPLE_SAMPLES.SAMPLE_SIMPLE1)
(simple2, simple2_clusters, _) = template_clustering(1, 2, SIMPLE_SAMPLES.SAMPLE_SIMPLE2)
(simple3, simple3_clusters, _) = template_clustering(0.7, 3, SIMPLE_SAMPLES.SAMPLE_SIMPLE3)
(simple4, simple4_clusters, _) = template_clustering(0.7, 3, SIMPLE_SAMPLES.SAMPLE_SIMPLE4)
(simple5, simple5_clusters, _) = template_clustering(0.7, 3, SIMPLE_SAMPLES.SAMPLE_SIMPLE5)
(simple6, simple6_clusters, _) = template_clustering(1, 2, SIMPLE_SAMPLES.SAMPLE_SIMPLE6)
(simple7, simple7_clusters, _) = template_clustering(1.0, 3, SIMPLE_SAMPLES.SAMPLE_SIMPLE7)
(simple8, simple8_clusters, _) = template_clustering(1.0, 3, SIMPLE_SAMPLES.SAMPLE_SIMPLE8)
visualizer = cluster_visualizer(8, 4)
visualizer.append_clusters(simple1_clusters, simple1, 0)
visualizer.append_clusters(simple2_clusters, simple2, 1)
visualizer.append_clusters(simple3_clusters, simple3, 2)
visualizer.append_clusters(simple4_clusters, simple4, 3)
visualizer.append_clusters(simple5_clusters, simple5, 4)
visualizer.append_clusters(simple6_clusters, simple6, 5)
visualizer.append_clusters(simple7_clusters, simple7, 6)
visualizer.append_clusters(simple8_clusters, simple8, 7)
visualizer.show()
def template_clustering(start_centers, path, tolerance = 0.025, criterion = splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore = False):
sample = read_sample(path)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion, ccore)
(ticks, _) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION): criterion_string = "BAYESIAN INFORMATION CRITERION";
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH): criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH";
print("Sample: ", ntpath.basename(path), "\nInitial centers: '", (start_centers is not None), "', Execution time: '", ticks, "', Number of clusters:", len(clusters), ",", criterion_string, "\n")
visualizer = cluster_visualizer()
visualizer.set_canvas_title(criterion_string)
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(centers, None, marker = '*')
visualizer.show()
def display_fcps_clustering_results():
(lsun, lsun_clusters) = template_clustering([10, 275, 385], FCPS_SAMPLES.SAMPLE_LSUN, 0.1, False);
(target, target_clusters) = template_clustering([10, 160, 310, 460, 560, 700], FCPS_SAMPLES.SAMPLE_TARGET, 0.1, False);
(two_diamonds, two_diamonds_clusters) = template_clustering([10, 650], FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, 0.1, False);
(wing_nut, wing_nut_clusters) = template_clustering([19, 823], FCPS_SAMPLES.SAMPLE_WING_NUT, 0.1, False);
(chainlink, chainlink_clusters) = template_clustering([30, 900], FCPS_SAMPLES.SAMPLE_CHAINLINK, 0.1, False);
(hepta, hepta_clusters) = template_clustering([0, 35, 86, 93, 125, 171, 194], FCPS_SAMPLES.SAMPLE_HEPTA, 0.1, False);
(tetra, tetra_clusters) = template_clustering([0, 131, 214, 265], FCPS_SAMPLES.SAMPLE_TETRA, 0.1, False);
(atom, atom_clusters) = template_clustering([0, 650], FCPS_SAMPLES.SAMPLE_ATOM, 0.1, False);
visualizer = cluster_visualizer(8, 4);
visualizer.append_clusters(lsun_clusters, lsun, 0);
visualizer.append_clusters(target_clusters, target, 1);
visualizer.append_clusters(two_diamonds_clusters, two_diamonds, 2);
visualizer.append_clusters(wing_nut_clusters, wing_nut, 3);
visualizer.append_clusters(chainlink_clusters, chainlink, 4);
visualizer.append_clusters(hepta_clusters, hepta, 5);
visualizer.append_clusters(tetra_clusters, tetra, 6);
visualizer.append_clusters(atom_clusters, atom, 7);
visualizer.show();
def display_fcps_clarans_results():
(lsun, lsun_clusters) = template_clustering(3, FCPS_SAMPLES.SAMPLE_LSUN, 10, 5);
(target, target_clusters) = template_clustering(6, FCPS_SAMPLES.SAMPLE_TARGET, 10, 5);
(two_diamonds, two_diamonds_clusters) = template_clustering(2, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, 2, 2);
(wing_nut, wing_nut_clusters) = template_clustering(2, FCPS_SAMPLES.SAMPLE_WING_NUT, 2, 2);
(chainlink, chainlink_clusters) = template_clustering(2, FCPS_SAMPLES.SAMPLE_CHAINLINK, 2, 2);
(hepta, hepta_clusters) = template_clustering(7, FCPS_SAMPLES.SAMPLE_HEPTA, 2, 2);
(tetra, tetra_clusters) = template_clustering(4, FCPS_SAMPLES.SAMPLE_TETRA, 2, 2);
(atom, atom_clusters) = template_clustering(2, FCPS_SAMPLES.SAMPLE_ATOM, 2, 2);
visualizer = cluster_visualizer(8, 4)
visualizer.append_clusters(lsun_clusters, lsun, 0)
visualizer.append_clusters(target_clusters, target, 1)
visualizer.append_clusters(two_diamonds_clusters, two_diamonds, 2)
visualizer.append_clusters(wing_nut_clusters, wing_nut, 3)
visualizer.append_clusters(chainlink_clusters, chainlink, 4)
visualizer.append_clusters(hepta_clusters, hepta, 5)
visualizer.append_clusters(tetra_clusters, tetra, 6)
visualizer.append_clusters(atom_clusters, atom, 7)
visualizer.show()
def display_fcps_clustering_results():
(lsun, lsun_clusters, _) = template_clustering(3, FCPS_SAMPLES.SAMPLE_LSUN, show_result = False);
(target, target_clusters, _) = template_clustering(6, FCPS_SAMPLES.SAMPLE_TARGET, show_result = False);
(two_diamonds, two_diamonds_clusters, _) = template_clustering(2, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, show_result = False);
(wing_nut, wing_nut_clusters, _) = template_clustering(2, FCPS_SAMPLES.SAMPLE_WING_NUT, show_result = False);
(chainlink, chainlink_clusters, _) = template_clustering(2, FCPS_SAMPLES.SAMPLE_CHAINLINK, show_result = False);
(hepta, hepta_clusters, _) = template_clustering(7, FCPS_SAMPLES.SAMPLE_HEPTA, show_result = False);
(tetra, tetra_clusters, _) = template_clustering(4, FCPS_SAMPLES.SAMPLE_TETRA, show_result = False);
(atom, atom_clusters, _) = template_clustering(2, FCPS_SAMPLES.SAMPLE_ATOM, show_result = False);
visualizer = cluster_visualizer(8, 4);
visualizer.append_clusters(lsun_clusters, lsun, 0);
visualizer.append_clusters(target_clusters, target, 1);
visualizer.append_clusters(two_diamonds_clusters, two_diamonds, 2);
visualizer.append_clusters(wing_nut_clusters, wing_nut, 3);
visualizer.append_clusters(chainlink_clusters, chainlink, 4);
visualizer.append_clusters(hepta_clusters, hepta, 5);
visualizer.append_clusters(tetra_clusters, tetra, 6);
visualizer.append_clusters(atom_clusters, atom, 7);
visualizer.show();
def frame_generation(index_iteration):
figure.clf()
figure.suptitle("Clustering genetic algorithm (iteration: " + str(index_iteration) + ")", fontsize=18, fontweight='bold')
visualizer = cluster_visualizer(4, 2, ["The best pop. on step #" + str(index_iteration), "The best population"])
local_minimum_clusters = ga_math.get_clusters_representation(observer.get_population_best()['chromosome'][index_iteration])
visualizer.append_clusters(local_minimum_clusters, data, 0)
global_minimum_clusters = ga_math.get_clusters_representation(observer.get_global_best()['chromosome'][index_iteration])
visualizer.append_clusters(global_minimum_clusters, data, 1)
ax1 = plt.subplot2grid((2, 2), (1, 0), colspan=2)
ga_visualizer.show_evolution(observer, 0, index_iteration + 1, ax1, False)
visualizer.show(figure, shift=0, display=False)
figure.subplots_adjust(top=0.85)
return [figure.gca()]
def display_fcps_clustering_results():
(lsun, lsun_clusters, _) = template_clustering(0.5, 3, FCPS_SAMPLES.SAMPLE_LSUN, False, True, False)
(target, target_clusters, _) = template_clustering(0.5, 2, FCPS_SAMPLES.SAMPLE_TARGET, False, True, False)
(two_diamonds, two_diamonds_clusters, _) = template_clustering(0.15, 7, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False)
(wing_nut, wing_nut_clusters, _) = template_clustering(0.25, 2, FCPS_SAMPLES.SAMPLE_WING_NUT, False, True, False)
(chainlink, chainlink_clusters, _) = template_clustering(0.5, 3, FCPS_SAMPLES.SAMPLE_CHAINLINK, False, True, False)
(hepta, hepta_clusters, _) = template_clustering(1, 3, FCPS_SAMPLES.SAMPLE_HEPTA, False, True, False)
(tetra, tetra_clusters, _) = template_clustering(0.4, 3, FCPS_SAMPLES.SAMPLE_TETRA, False, True, False)
(atom, atom_clusters, _) = template_clustering(15, 3, FCPS_SAMPLES.SAMPLE_ATOM, False, True, False)
visualizer = cluster_visualizer(8, 4)
visualizer.append_clusters(lsun_clusters, lsun, 0)
visualizer.append_clusters(target_clusters, target, 1)
visualizer.append_clusters(two_diamonds_clusters, two_diamonds, 2)
visualizer.append_clusters(wing_nut_clusters, wing_nut, 3)
visualizer.append_clusters(chainlink_clusters, chainlink, 4)
visualizer.append_clusters(hepta_clusters, hepta, 5)
visualizer.append_clusters(tetra_clusters, tetra, 6)
visualizer.append_clusters(atom_clusters, atom, 7)
visualizer.show()
def template_clustering(data_path, intervals, density_threshold, **kwargs):
print("Sample: '%s'." % os.path.basename(data_path))
data = read_sample(data_path)
clique_instance = clique(data, intervals, density_threshold)
clique_instance.process()
clusters = clique_instance.get_clusters()
noise = clique_instance.get_noise()
cells = clique_instance.get_cells()
print([len(cluster) for cluster in clusters])
clique_visualizer.show_grid(cells, data)
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, data)
visualizer.append_cluster(noise, data, marker='x')
visualizer.show()
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = True, show = True):
sample = read_sample(path);
dbscan_instance = dbscan(sample, radius, neighb, ccore);
(ticks, _) = timedcall(dbscan_instance.process);
clusters = dbscan_instance.get_clusters();
noise = dbscan_instance.get_noise();
print([len(cluster) for cluster in clusters]);
if (False):
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(noise, sample, marker = 'x');
visualizer.show();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
return (sample, clusters, noise);
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = True, show = True):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighb, ccore)
(ticks, _) = timedcall(dbscan_instance.process)
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
print([len(cluster) for cluster in clusters])
if show:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker = 'x')
visualizer.show()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
return sample, clusters, noise
def display_fcps_clustering_results():
(lsun, lsun_clusters) = template_clustering([10, 275, 385], FCPS_SAMPLES.SAMPLE_LSUN, 0.1, False)
(target, target_clusters) = template_clustering([10, 160, 310, 460, 560, 700], FCPS_SAMPLES.SAMPLE_TARGET, 0.1, False)
(two_diamonds, two_diamonds_clusters) = template_clustering([10, 650], FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, 0.1, False)
(wing_nut, wing_nut_clusters) = template_clustering([19, 823], FCPS_SAMPLES.SAMPLE_WING_NUT, 0.1, False)
(chainlink, chainlink_clusters) = template_clustering([30, 900], FCPS_SAMPLES.SAMPLE_CHAINLINK, 0.1, False)
(hepta, hepta_clusters) = template_clustering([0, 35, 86, 93, 125, 171, 194], FCPS_SAMPLES.SAMPLE_HEPTA, 0.1, False)
(tetra, tetra_clusters) = template_clustering([0, 131, 214, 265], FCPS_SAMPLES.SAMPLE_TETRA, 0.1, False)
(atom, atom_clusters) = template_clustering([0, 650], FCPS_SAMPLES.SAMPLE_ATOM, 0.1, False)
visualizer = cluster_visualizer(8, 4)
visualizer.append_clusters(lsun_clusters, lsun, 0)
visualizer.append_clusters(target_clusters, target, 1)
visualizer.append_clusters(two_diamonds_clusters, two_diamonds, 2)
visualizer.append_clusters(wing_nut_clusters, wing_nut, 3)
visualizer.append_clusters(chainlink_clusters, chainlink, 4)
visualizer.append_clusters(hepta_clusters, hepta, 5)
visualizer.append_clusters(tetra_clusters, tetra, 6)
visualizer.append_clusters(atom_clusters, atom, 7)
visualizer.show()
def initialize_kmedoids_model(
path_to_points="./lib/us_metros_scraped_geocoords.tsv"):
import numpy as np
from sklearn.cluster import KMeans
coords = []
labels = []
if isinstance(path_to_points, str):
for row in load_csv(path_to_points, delimiter="\t"):
try:
coords.append(
list(deg2dec((row["latitude"], row["longitude"]))))
labels.append(row["parent"])
except Exception as e:
print(e)
else:
coords = path_to_points
arr = np.array([c for c in coords if c and len(c) == 2])
print(f"Points: {len(arr)}")
k = 32
from pyclustering.cluster.kmedoids import kmedoids
# Load list of points for cluster analysis.
# Set random initial medoids.
initial_medoids = random.sample(range(0, len(arr)), k=k)
# Create instance of K-Medoids algorithm.
kmedoids_instance = kmedoids(arr, initial_medoids)
# Run cluster analysis and obtain results.
kmedoids_instance.process()
clusters = kmedoids_instance.get_clusters()
# Show allocated clusters.
print(clusters)
# return kmedoids_instance
# Display clusters.
from pyclustering.cluster import cluster_visualizer
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, arr)
visualizer.show()
def display_fcps_dependence_clustering_results():
(two_diamonds, two_diamonds_clusters_1, _) = template_clustering(0.15, 4, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_2, _) = template_clustering(0.15, 5, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_3, _) = template_clustering(0.15, 6, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_4, _) = template_clustering(0.15, 7, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_5, _) = template_clustering(0.10, 6, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_6, _) = template_clustering(0.12, 6, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_7, _) = template_clustering(0.15, 6, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
(two_diamonds, two_diamonds_clusters_8, _) = template_clustering(0.17, 6, FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS, False, True, False);
visualizer = cluster_visualizer(8, 4);
visualizer.append_clusters(two_diamonds_clusters_1, two_diamonds, 0);
visualizer.append_clusters(two_diamonds_clusters_2, two_diamonds, 1);
visualizer.append_clusters(two_diamonds_clusters_3, two_diamonds, 2);
visualizer.append_clusters(two_diamonds_clusters_4, two_diamonds, 3);
visualizer.append_clusters(two_diamonds_clusters_5, two_diamonds, 4);
visualizer.append_clusters(two_diamonds_clusters_6, two_diamonds, 5);
visualizer.append_clusters(two_diamonds_clusters_7, two_diamonds, 6);
visualizer.append_clusters(two_diamonds_clusters_8, two_diamonds, 7);
visualizer.show();
def testVisualizeClusterWithAttributesNumpy(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1,
return_type='numpy')
cure_instance = cure(sample, 2, 5, 0.5, False)
cure_instance.process()
clusters = cure_instance.get_clusters()
representors = cure_instance.get_representors()
means = cure_instance.get_means()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
for cluster_index in range(len(clusters)):
visualizer.append_cluster_attribute(
0, cluster_index, numpy.array(representors[cluster_index]),
'*', 10)
visualizer.append_cluster_attribute(
0, cluster_index, numpy.array([means[cluster_index]]), 'o')
visualizer.show()
def display_simple_clarans_results():
(simple1, simple1_clusters) = template_clustering(2, SIMPLE_SAMPLES.SAMPLE_SIMPLE1, 10, 3);
(simple2, simple2_clusters) = template_clustering(3, SIMPLE_SAMPLES.SAMPLE_SIMPLE2, 10, 3);
(simple3, simple3_clusters) = template_clustering(4, SIMPLE_SAMPLES.SAMPLE_SIMPLE3, 10, 3);
(simple4, simple4_clusters) = template_clustering(5, SIMPLE_SAMPLES.SAMPLE_SIMPLE4, 10, 4);
(simple5, simple5_clusters) = template_clustering(4, SIMPLE_SAMPLES.SAMPLE_SIMPLE5, 10, 5);
(simple6, simple6_clusters) = template_clustering(2, SIMPLE_SAMPLES.SAMPLE_SIMPLE6, 10, 3);
(simple7, simple7_clusters) = template_clustering(2, SIMPLE_SAMPLES.SAMPLE_SIMPLE7, 10, 3);
(simple8, simple8_clusters) = template_clustering(4, SIMPLE_SAMPLES.SAMPLE_SIMPLE8, 15, 5);
visualizer = cluster_visualizer(8, 4)
visualizer.append_clusters(simple1_clusters, simple1, 0)
visualizer.append_clusters(simple2_clusters, simple2, 1)
visualizer.append_clusters(simple3_clusters, simple3, 2)
visualizer.append_clusters(simple4_clusters, simple4, 3)
visualizer.append_clusters(simple5_clusters, simple5, 4)
visualizer.append_clusters(simple6_clusters, simple6, 5)
visualizer.append_clusters(simple7_clusters, simple7, 6)
visualizer.append_clusters(simple8_clusters, simple8, 7)
visualizer.show()
def template_clustering(path_sample, eps, minpts, amount_clusters = None, visualize = True):
sample = read_sample(path_sample);
optics_instance = optics(sample, eps, minpts, amount_clusters);
(ticks, _) = timedcall(optics_instance.process);
print("Sample: ", path_sample, "\t\tExecution time: ", ticks, "\n");
if (visualize is True):
clusters = optics_instance.get_clusters();
noise = optics_instance.get_noise();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(noise, sample, marker = 'x');
visualizer.show();
ordering = optics_instance.get_ordering();
analyser = ordering_analyser(ordering);
ordering_visualizer.show_ordering_diagram(analyser, amount_clusters);
def display_simple_clustering_results():
(simple1,
simple1_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE1,
visualize=False)
(simple2,
simple2_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE2,
visualize=False)
(simple3,
simple3_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE3,
visualize=False)
(simple4,
simple4_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE4,
visualize=False)
(simple5,
simple5_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE5,
visualize=False)
(simple6,
simple6_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE6,
visualize=False)
(simple7,
simple7_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE7,
visualize=False)
(simple8,
simple8_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE8,
visualize=False)
(simple9,
simple9_clusters) = template_clustering(SIMPLE_SAMPLES.SAMPLE_SIMPLE9,
visualize=False)
visualizer = cluster_visualizer(9, 3)
visualizer.append_clusters(simple1_clusters, simple1, 0, markersize=3)
visualizer.append_clusters(simple2_clusters, simple2, 1, markersize=3)
visualizer.append_clusters(simple3_clusters, simple3, 2, markersize=3)
visualizer.append_clusters(simple4_clusters, simple4, 3, markersize=3)
visualizer.append_clusters(simple5_clusters, simple5, 4, markersize=3)
visualizer.append_clusters(simple6_clusters, simple6, 5, markersize=6)
visualizer.append_clusters(simple7_clusters, simple7, 6, markersize=6)
visualizer.append_clusters(simple8_clusters, simple8, 7, markersize=6)
visualizer.append_clusters(simple9_clusters, simple9, 8, markersize=6)
visualizer.show()
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = False, show = True, tempos = tempos_dbscan):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighb, ccore)
(ticks, _) = timedcall(dbscan_instance.process)
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
print([len(cluster) for cluster in clusters])
if show:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker = 'x')
visualizer.show()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
tempos_dbscan.append(ticks)
return sample, clusters, noise
def testVisualize2DClustersThreeCanvases(self):
sample_simple1 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
sample_simple2 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2);
sample_simple3 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3);
dbscan_instance = dbscan(sample_simple1, 0.4, 2, False);
dbscan_instance.process();
clusters_sample1 = dbscan_instance.get_clusters();
dbscan_instance = dbscan(sample_simple2, 1, 2, False);
dbscan_instance.process();
clusters_sample2 = dbscan_instance.get_clusters();
dbscan_instance = dbscan(sample_simple3, 0.7, 3, False);
dbscan_instance.process();
clusters_sample3 = dbscan_instance.get_clusters();
visualizer = cluster_visualizer(3);
visualizer.append_clusters(clusters_sample1, sample_simple1, 0, markersize = 5);
visualizer.append_clusters(clusters_sample2, sample_simple2, 1, markersize = 5);
visualizer.append_clusters(clusters_sample3, sample_simple3, 2, markersize = 5);
visualizer.show();
def template_clustering(start_medoids,
sample,
tolerance=0.25,
show=True):
kmedoids_instance = kmedoids(sample, start_medoids, tolerance)
(ticks, result) = timedcall(kmedoids_instance.process)
clusters = kmedoids_instance.get_clusters()
medoids = kmedoids_instance.get_medoids()
print("Execution time: ", ticks, "\n")
if (show is True):
visualizer = cluster_visualizer(1)
visualizer.append_clusters(clusters, sample, 0)
visualizer.append_cluster(
[sample[index] for index in start_medoids],
marker='+',
markersize=15)
visualizer.append_cluster(medoids, marker='*', markersize=5)
visualizer.show()
return medoids
def show_feature_destibution(self, data = None):
"""!
@brief Shows feature distribution.
@details Only features in 1D, 2D, 3D space can be visualized.
@param[in] data (list): List of points that will be used for visualization, if it not specified than feature will be displayed only.
"""
visualizer = cluster_visualizer();
print("amount of nodes: ", self.__amount_nodes);
if (data is not None):
visualizer.append_cluster(data, marker = 'x');
for level in range(0, self.height):
level_nodes = self.get_level_nodes(level);
centers = [ node.feature.get_centroid() for node in level_nodes ];
visualizer.append_cluster(centers, None, markersize = (self.height - level + 1) * 5);
visualizer.show();
