def find_best_distance_epsilon(dbscan_xs_points_k_distance_method, threshold_majority):
num_points_dbscan_xs_data = len(dbscan_xs_points_k_distance_method)
dbscan_xs_points_k_distance_method_unique = array_sort(array_unique(dbscan_xs_points_k_distance_method))
accumulative_probabilities = array_matrix(list(accumulate_sum(array_matrix(list(collection_counter(dbscan_xs_points_k_distance_method).values())) / num_points_dbscan_xs_data)))
final_distance_epsilon = dbscan_xs_points_k_distance_method_unique[compute_arg_majority(accumulative_probabilities, threshold_majority)]
return final_distance_epsilon
def dbscan_final_clustering(xs_features_data, ys_labels_true, best_epsilon_value, num_closest_k_neighbors = 5):
ys_labels_predicted, clusters_centroids_indices, clusters_centroids_points, clusters_border_points, xs_features_data_inliers, xs_features_data_outliers = dbscan_clustering_method(xs_features_data, best_epsilon_value, num_closest_k_neighbors = num_closest_k_neighbors)
num_clusters_centroids = ( nan_max(ys_labels_predicted) + 1 )
plot_clusters_centroids_and_radii("DBSCAN", xs_features_data, ys_labels_predicted, clusters_centroids_points, num_clusters = num_clusters_centroids, epsilon = best_epsilon_value, damping = None, final_clustering = True)
if( num_clusters_centroids >= 2 ):
if( num_clusters_centroids <= 26 ):
plot_silhouette_analysis("DBSCAN", xs_features_data, ys_labels_predicted, clusters_centroids_points, num_clusters_centroids, epsilon = best_epsilon_value, damping = None, final_clustering = True)
dbscan_final_clustering_silhouette_score, dbscan_final_clustering_precision_score, dbscan_final_clustering_recall_score, dbscan_final_clustering_rand_index_score, dbscan_final_clustering_f1_score, dbscan_final_clustering_adjusted_rand_score, dbscan_final_clustering_confusion_matrix_rand_index = compute_clustering_performance_metrics("K-Means", xs_features_data, ys_labels_true, ys_labels_predicted, num_clusters_centroids, final_clustering = True)
plot_confusion_matrix_rand_index_clustering_heatmap("DBSCAN", dbscan_final_clustering_confusion_matrix_rand_index, num_clusters_centroids, epsilon = best_epsilon_value, damping = None, final_clustering = True)
xs_ids_examples = list(range(0, len(ys_labels_predicted)))
html_report_cluster_labels(array_matrix(xs_ids_examples), ys_labels_predicted, "dbscan.html")
return dbscan_final_clustering_silhouette_score, dbscan_final_clustering_precision_score, dbscan_final_clustering_recall_score, dbscan_final_clustering_rand_index_score, dbscan_final_clustering_f1_score, dbscan_final_clustering_adjusted_rand_score, dbscan_final_clustering_confusion_matrix_rand_index
def k_means_final_clustering(xs_features_data, ys_labels_true, num_clusters=4):
ys_labels_predicted, k_means_estimator_centroids, k_means_final_clustering_error = k_means_clustering_method(
xs_features_data, num_clusters=num_clusters, max_iterations=300)
plot_clusters_centroids_and_radii("K-Means",
xs_features_data,
ys_labels_predicted,
k_means_estimator_centroids,
num_clusters=num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
if (num_clusters >= 2):
if (num_clusters <= 26):
plot_silhouette_analysis("K-Means",
xs_features_data,
ys_labels_predicted,
k_means_estimator_centroids,
num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
k_means_final_clustering_silhouette_score, k_means_final_clustering_precision_score, k_means_final_clustering_recall_score, k_means_final_clustering_rand_index_score, k_means_final_clustering_f1_score, k_means_final_clustering_adjusted_rand_score, k_means_final_clustering_confusion_matrix_rand_index = compute_clustering_performance_metrics(
"K-Means",
xs_features_data,
ys_labels_true,
ys_labels_predicted,
num_clusters,
final_clustering=True)
plot_confusion_matrix_rand_index_clustering_heatmap(
"K-Means",
k_means_final_clustering_confusion_matrix_rand_index,
num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
xs_ids_examples = list(range(0, len(xs_features_data)))
html_report_cluster_labels(array_matrix(xs_ids_examples),
ys_labels_predicted, "k-means.html")
return k_means_final_clustering_error, k_means_final_clustering_silhouette_score, k_means_final_clustering_precision_score, k_means_final_clustering_recall_score, k_means_final_clustering_rand_index_score, k_means_final_clustering_f1_score, k_means_final_clustering_adjusted_rand_score, k_means_final_clustering_confusion_matrix_rand_index
def affinity_propagation_final_clustering(xs_features_data, ys_labels_true, best_damping_value = 0.5):
ys_labels_predicted, clusters_centroids_indices, clusters_centroids_points = affinity_propagation_clustering_method(xs_features_data, damping_value = best_damping_value, max_iterations = 300)
num_clusters_centroids = ( nan_max(ys_labels_predicted) + 1 )
if( num_clusters_centroids >= 2 ):
affinity_propagation_final_clustering_silhouette_score, affinity_propagation_final_clustering_precision_score, affinity_propagation_final_clustering_recall_score, affinity_propagation_final_clustering_rand_index_score, affinity_propagation_final_clustering_f1_score, affinity_propagation_final_clustering_adjusted_rand_score, affinity_propagation_final_clustering_confusion_matrix_rand_index = compute_clustering_performance_metrics("Affinity-Propagation", xs_features_data, ys_labels_true, ys_labels_predicted, num_clusters_centroids, final_clustering = True)
plot_confusion_matrix_rand_index_clustering_heatmap("Affinity-Propagation", affinity_propagation_final_clustering_confusion_matrix_rand_index, num_clusters_centroids, epsilon = None, damping = best_damping_value, final_clustering = True)
xs_ids_examples = list(range(0, len(ys_labels_predicted)))
html_report_cluster_labels(array_matrix(xs_ids_examples), ys_labels_predicted, "affinity-propagation.html")
return affinity_propagation_final_clustering_silhouette_score, affinity_propagation_final_clustering_precision_score, affinity_propagation_final_clustering_recall_score, affinity_propagation_final_clustering_rand_index_score, affinity_propagation_final_clustering_f1_score, affinity_propagation_final_clustering_adjusted_rand_score, affinity_propagation_final_clustering_confusion_matrix_rand_index
def dbscan_clustering_method(xs_features_data, current_epsilon, num_closest_k_neighbors = 5):
dbscan_clustering = dbscan(eps = current_epsilon, min_samples = num_closest_k_neighbors)
dbscan_clustering.fit(xs_features_data)
ys_labels_predicted = dbscan_clustering.labels_
clusters_centroids_indices = dbscan_clustering.core_sample_indices_
xs_features_data_inliers = xs_features_data[ys_labels_predicted != -1]
xs_features_data_outliers = xs_features_data[ys_labels_predicted == -1]
clusters_centroids_points = xs_features_data[clusters_centroids_indices, :]
clusters_border_points = array_matrix([list(point) for point in xs_features_data_inliers if point not in clusters_centroids_points])
return ys_labels_predicted, clusters_centroids_indices, clusters_centroids_points, clusters_border_points, xs_features_data_inliers, xs_features_data_outliers
k_means_xs_points_elbow_method, k_means_ys_points_elbow_method, best_num_clusters = plot_elbow_method("K-Means", k_means_squared_errors_sums_intertias, best_num_clusters, num_max_clusters = NUM_MAX_CLUSTERS)
error_k_means_final_clustering = k_means_final_clustering(normalized_data_xs_best_features_priori, ys_labels_true, num_clusters = best_num_clusters)
# ---- K-Means Clustering ----
# ---- DBScan Clustering ----
dbscan_num_centroids, dbscan_num_inliers, dbscan_num_outliers, dbscan_silhouette_scores, dbscan_precision_scores, dbscan_recall_scores, dbscan_rand_index_scores, dbscan_f1_scores, dbscan_adjusted_rand_scores = dbscan_pre_clustering(normalized_data_xs_best_features_priori, ys_labels_true, start_epsilon = START_EPSILON, end_epsilon = END_EPSILON, step_epsilon = STEP_EPSILON)
num_data_points_sorted_by_distance, k_neighbors_distances_epsilons = compute_distances_nearest_neighbors(normalized_data_xs_best_features_priori, num_closest_k_neighbors = NUM_K_NEAREST_NEIGHBORS)
dbscan_xs_points_k_distance_method = array_matrix( range( num_data_points_sorted_by_distance ) )
dbscan_ys_points_k_distance_method = k_neighbors_distances_epsilons
if(KNEED_LIB_IN_USE):
kneed_locator_k_distance = knee_locator(dbscan_xs_points_k_distance_method, dbscan_ys_points_k_distance_method, S = 1.0, curve = "convex", direction = "increasing")
best_distance_epsilon = dbscan_ys_points_k_distance_method[round(kneed_locator_k_distance.elbow, 0)]
else:
best_distance_epsilon = find_best_distance_epsilon(dbscan_ys_points_k_distance_method, THRESHOLD_MAJORITY)
print( "The best Distance ( ε (Epsilon Value) ), for DBScan, found:" )
def bisecting_k_means_clustering(xs_features_data,
examples_ids,
ys_labels_true,
final_max_num_clusters_and_iterations=2):
clusters_ids = [0]
clusters_data = [xs_features_data]
clusters_examples_ids = [examples_ids]
clusters_centroids_points = [0]
num_clusters = 1
tree_predictions_lists_with_offset = array_empty(
(len(xs_features_data), 0)).tolist()
tree_predictions_lists_without_offset = array_empty(
(len(xs_features_data), 0)).tolist()
ys_labels_predicted_with_offset = None
ys_labels_predicted_without_offset = None
current_iteration = 0
while (num_clusters < final_max_num_clusters_and_iterations):
cluster_index_with_more_examples = -1
num_max_examples_in_cluster = -1
for index_cluster in range(num_clusters):
num_examples_in_cluster = len(clusters_data[index_cluster])
if (num_examples_in_cluster > num_max_examples_in_cluster):
cluster_index_with_more_examples = index_cluster
num_max_examples_in_cluster = num_examples_in_cluster
cluster_id_to_be_divided = clusters_ids[
cluster_index_with_more_examples]
cluster_data_to_be_divided = clusters_data[
cluster_index_with_more_examples]
cluster_examples_ids_to_be_divided = clusters_examples_ids[
cluster_index_with_more_examples]
cluster_centroid_point_to_be_divided = clusters_centroids_points[
cluster_index_with_more_examples]
clusters_data.remove(cluster_data_to_be_divided)
clusters_examples_ids.remove(cluster_examples_ids_to_be_divided)
if (num_clusters == 1):
clusters_ids.pop(cluster_id_to_be_divided)
clusters_centroids_points.pop(0)
else:
cluster_centroid_point_index = 0
cluster_centroid_point_index_triggered = 0
for cluster_centroid_point in clusters_centroids_points:
if ((cluster_centroid_point_to_be_divided ==
cluster_centroid_point).all()):
cluster_centroid_point_index_triggered = cluster_centroid_point_index
cluster_centroid_point_index = (cluster_centroid_point_index +
1)
clusters_centroids_points.pop(
cluster_centroid_point_index_triggered)
if (num_clusters == 1):
two_sub_clusters_ids, two_sub_clusters_examples_ids, two_sub_clusters_data, two_sub_clusters_centroids, ys_labels_predicted_without_offset, ys_labels_predicted_with_offset, cluster_squared_error_sum_intertia = bissect_k_means_into_two_sub_clusters(
cluster_data_to_be_divided,
cluster_examples_ids_to_be_divided,
left_leaf_cluster_id_offset=0,
right_leaf_cluster_id_offset=0)
else:
two_sub_clusters_ids, two_sub_clusters_examples_ids, two_sub_clusters_data, two_sub_clusters_centroids, ys_labels_predicted_without_offset, ys_labels_predicted_with_offset, cluster_squared_error_sum_intertia = bissect_k_means_into_two_sub_clusters(
cluster_data_to_be_divided,
cluster_examples_ids_to_be_divided,
left_leaf_cluster_id_offset=cluster_id_to_be_divided,
right_leaf_cluster_id_offset=(num_clusters - 1))
ys_labels_predicted_with_offset_unique = array_sort(
array_unique_values(ys_labels_predicted_with_offset))
for sub_cluster_id in range(2):
clusters_ids.append(two_sub_clusters_ids[sub_cluster_id])
clusters_data.append(two_sub_clusters_data[sub_cluster_id])
clusters_examples_ids.append(
two_sub_clusters_examples_ids[sub_cluster_id])
clusters_centroids_points.append(
two_sub_clusters_centroids[sub_cluster_id])
for example_index in range(len(xs_features_data)):
if (example_index
in two_sub_clusters_examples_ids[sub_cluster_id]):
if (sub_cluster_id <
len(ys_labels_predicted_with_offset_unique)):
tree_predictions_lists_with_offset[
example_index].append(
ys_labels_predicted_with_offset_unique[
sub_cluster_id])
tree_predictions_lists_without_offset[
example_index].append(sub_cluster_id)
num_clusters = (num_clusters + 1)
current_iteration = (current_iteration + 1)
ys_final_labels_predicted = matrix_array_zeros(len(xs_features_data))
for example_index in range(len(xs_features_data)):
last_index = (len(tree_predictions_lists_with_offset[example_index]) -
1)
ys_final_labels_predicted[
example_index] = tree_predictions_lists_with_offset[example_index][
last_index]
clusters_centroids_points = array_matrix(clusters_centroids_points)
effective_num_clusters = len(
array_unique_values(ys_final_labels_predicted))
if (effective_num_clusters >= 2):
if (effective_num_clusters <= 26):
plot_clusters_centroids_and_radii("Bisecting-K-Means",
xs_features_data,
ys_final_labels_predicted,
clusters_centroids_points,
effective_num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
plot_silhouette_analysis("Bisecting-K-Means",
xs_features_data,
ys_final_labels_predicted,
clusters_centroids_points,
effective_num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
bisecting_k_means_final_clustering_silhouette_score, bisecting_k_means_final_clustering_precision_score, bisecting_k_means_final_clustering_recall_score, bisecting_k_means_final_clustering_rand_index_score, bisecting_k_means_final_clustering_f1_score, bisecting_k_means_final_clustering_adjusted_rand_score, bisecting_k_means_final_clustering_confusion_matrix_rand_index = compute_clustering_performance_metrics(
"Bisecting-K-Means",
xs_features_data,
ys_labels_true,
ys_final_labels_predicted,
effective_num_clusters,
final_clustering=True)
plot_confusion_matrix_rand_index_clustering_heatmap(
"Bisecting-K-Means",
bisecting_k_means_final_clustering_confusion_matrix_rand_index,
effective_num_clusters,
epsilon=None,
damping=None,
final_clustering=True)
xs_ids_examples = list(range(0, len(examples_ids)))
html_report_cluster_labels_hierarchical(
xs_ids_examples, tree_predictions_lists_without_offset,
"bisecting-k-means-hierarchical.html")
return clusters_ids, clusters_data, ys_final_labels_predicted, tree_predictions_lists_without_offset, num_clusters, effective_num_clusters