def elbow_analysis(sample_file_path, kmin, kmax, **kwargs):
initializer = kwargs.get('initializer', kmeans_plusplus_initializer)
sample = read_sample(sample_file_path)
elbow_instance = elbow(sample, kmin, kmax, initializer=initializer)
elbow_instance.process()
amount_clusters = elbow_instance.get_amount()
wce = elbow_instance.get_wce()
centers = kmeans_plusplus_initializer(sample, amount_clusters).initialize()
kmeans_instance = kmeans(sample, centers)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
print("Sample '%s': Obtained amount of clusters: '%d'." % (sample_file_path, amount_clusters))
figure = plt.figure(1)
ax = figure.add_subplot(111)
ax.plot(range(kmin, kmax), wce, color='b', marker='.')
ax.plot(amount_clusters, wce[amount_clusters - kmin], color='r', marker='.', markersize=10)
ax.annotate("Elbow", (amount_clusters + 0.1, wce[amount_clusters - kmin] + 5))
ax.grid(True)
plt.ylabel("WCE")
plt.xlabel("K")
plt.show()
kmeans_visualizer.show_clusters(sample, clusters, centers)
def elbow_analysis(sample_file_path, kmin, kmax, **kwargs):
initializer = kwargs.get('initializer', kmeans_plusplus_initializer)
sample = read_sample(sample_file_path)
elbow_instance = elbow(sample, kmin, kmax, initializer=initializer)
elbow_instance.process()
amount_clusters = elbow_instance.get_amount()
wce = elbow_instance.get_wce()
centers = kmeans_plusplus_initializer(sample, amount_clusters).initialize()
kmeans_instance = kmeans(sample, centers)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
print("Sample '%s': Obtained amount of clusters: '%d'." %
(sample_file_path, amount_clusters))
figure = plt.figure(1)
ax = figure.add_subplot(111)
ax.plot(range(kmin, kmax), wce, color='b', marker='.')
ax.plot(amount_clusters,
wce[amount_clusters - kmin],
color='r',
marker='.',
markersize=10)
ax.annotate("Elbow",
(amount_clusters + 0.1, wce[amount_clusters - kmin] + 5))
ax.grid(True)
plt.ylabel("WCE")
plt.xlabel("K")
plt.show()
kmeans_visualizer.show_clusters(sample, clusters, centers)
def template_clustering(start_centers, path, tolerance=0.25, ccore=False):
sample = read_sample(path)
dimension = len(sample[0])
metric = distance_metric(type_metric.MANHATTAN)
observer = kmeans_observer()
kmeans_instance = kmeans(sample,
start_centers,
tolerance,
ccore,
observer=observer,
metric=metric)
(ticks, _) = 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_multidim()
visualizer.append_clusters(clusters, sample)
visualizer.show()
if dimension > 3:
kmeans_visualizer.show_clusters(sample, clusters, centers,
start_centers)
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def templateShowClusteringResultNoFailure(filename, initial_centers, ccore_flag):
sample = read_sample(filename)
kmeans_instance = kmeans(sample, initial_centers, 0.025, ccore_flag)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
kmeans_visualizer.show_clusters(sample, clusters, centers, initial_centers)
def templateShowClusteringResultNoFailure(filename, initial_centers, ccore_flag):
sample = read_sample(filename);
kmeans_instance = kmeans(sample, initial_centers, 0.025, ccore_flag);
kmeans_instance.process();
clusters = kmeans_instance.get_clusters();
centers = kmeans_instance.get_centers();
kmeans_visualizer.show_clusters(sample, clusters, centers, initial_centers);
def template_clustering(start_centers, path, tolerance=0.25, ccore=True):
sample = read_sample(path)
observer = kmeans_observer()
kmeans_instance = kmeans(sample,
start_centers,
tolerance,
ccore,
observer=observer)
(ticks, _) = timedcall(kmeans_instance.process)
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
kmeans_visualizer.show_clusters(sample, clusters, centers, start_centers)
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def run_elbow(data):
# create instance of Elbow method using K value from 1 to 10.
kmin, kmax = 1, 10
elbow_instance = elbow(data, kmin, kmax)
# process input data and obtain results of analysis
elbow_instance.process()
amount_clusters = elbow_instance.get_amount()
# perform cluster analysis using K-Means algorithm
centers = kmeans_plusplus_initializer(
data, amount_clusters,
amount_candidates=kmeans_plusplus_initializer.FARTHEST_CENTER_CANDIDATE).initialize()
kmeans_instance = kmeans(data, centers)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
kmeans_visualizer.show_clusters(data, clusters, centers)
def get_cluster_custom(sample, visualize=False, class_num=3):
metric = distance_metric(type_metric.USER_DEFINED, func=user_function)
# create K-Means algorithm with specific distance metric
initial_centers = kmeans_plusplus_initializer(sample,
class_num).initialize()
kmeans_instance = kmeans(sample, initial_centers, metric=metric)
# run cluster analysis and obtain results
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
cls_encoded = []
for cls_idx in clusters:
cls_encoded.append(sample[cls_idx])
final_centers = kmeans_instance.get_centers()
for i in range(len(final_centers)):
final_centers[i] = np.round(np.array(final_centers[i]))
loss = kmeans_instance.get_total_wce()
# Visualize obtained results
if visualize:
kmeans_visualizer.show_clusters(sample, clusters, final_centers)
return cls_encoded, final_centers, loss
def template_clustering(start_centers, path, tolerance = 0.25, ccore = False):
sample = read_sample(path)
dimension = len(sample[0])
metric = distance_metric(type_metric.MANHATTAN)
observer = kmeans_observer()
kmeans_instance = kmeans(sample, start_centers, tolerance, ccore, observer=observer, metric=metric)
(ticks, _) = 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_multidim()
visualizer.append_clusters(clusters, sample)
visualizer.show()
if dimension > 3:
kmeans_visualizer.show_clusters(sample, clusters, centers, start_centers)
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def elbow_kmeans_optimizer(X, k=None, kmin=1, kmax=5, visualize=True):
"""k-means clustering with or without automatically determined cluster numbers.
Reference: https://pyclustering.github.io/docs/0.8.2/html/d3/d70/classpyclustering_1_1cluster_1_1elbow_1_1elbow.html
# Arguments:
X (numpy array-like): Input data matrix.
kmin: Minimum number of clusters to consider. Defaults to 1.
kmax: Maximum number of clusters to consider. Defaults to 5.
visualize: Whether to perform k-means visualization or not.
# Returns:
numpy arraylike: Clusters.
numpy arraylike: Cluster centers.
"""
from pyclustering.utils import read_sample
from pyclustering.samples.definitions import SIMPLE_SAMPLES
from pyclustering.cluster.kmeans import kmeans
from pyclustering.cluster.center_initializer import kmeans_plusplus_initializer, random_center_initializer
from pyclustering.core.wrapper import ccore_library
from pyclustering.cluster.elbow import elbow
from pyclustering.cluster.kmeans import kmeans_visualizer
import pyclustering.core.elbow_wrapper as wrapper
if k is not None:
amount_clusters = k
else:
elbow_instance = elbow(X, kmin, kmax)
elbow_instance.process()
amount_clusters = elbow_instance.get_amount()
wce = elbow_instance.get_wce()
centers = kmeans_plusplus_initializer(X, amount_clusters).initialize()
kmeans_instance = kmeans(X, centers)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
kmeans_visualizer.show_clusters(X, clusters, centers)
return clusters, centers
# Load list of points for cluster analysis. sample = read_sample(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS) # Prepare initial centers using K-Means++ method. initial_centers = kmeans_plusplus_initializer(sample, 2).initialize() # Create instance of K-Means algorithm with prepared centers. kmeans_instance = kmeans(sample, initial_centers) # Run cluster analysis and obtain results. kmeans_instance.process() clusters = kmeans_instance.get_clusters() final_centers = kmeans_instance.get_centers() # Visualize obtained results kmeans_visualizer.show_clusters(sample, clusters, final_centers) from pyclustering.cluster.kmedoids import kmedoids from pyclustering.cluster import cluster_visualizer from pyclustering.utils import read_sample from pyclustering.samples.definitions import FCPS_SAMPLES # Load list of points for cluster analysis. sample = read_sample(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS) # Set random initial medoids. initial_medoids = [1, 500] # Create instance of K-Medoids algorithm. kmedoids_instance = kmedoids(sample, initial_medoids) # Run cluster analysis and obtain results.
# In[53]:
data_1 = list(data_1)
initial_centers = kmeans_plusplus_initializer(data_1, 10).initialize()
# Create instance of K-Means algorithm with prepared centers.
kmeans_instance = kmeans(data_1, initial_centers)
# Run cluster analysis and obtain results.
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
final_centers = kmeans_instance.get_centers()
# Visualize obtained results
# visualizer = cluster_visualizer_multidim()
kmeans_visualizer.show_clusters(data_1, clusters, final_centers)
# visualizer.append_clusters(clusters, data_1)
# visualizer.show()
# In[58]:
# 5 initialisations
for m in range(5):
initial_centers = kmeans_plusplus_initializer(data_1, 10).initialize()
# Create instance of K-Means algorithm with prepared centers.
kmeans_instance = kmeans(data_1, initial_centers)
# Run cluster analysis and obtain results.
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
samples = np.array(list(zip(ws, hs)))
for _ in range(1):
sample = samples[
np.random.choice(samples.shape[0], 20000, replace=False), :]
metric = distance_metric(type_metric.USER_DEFINED, func=iou_distance_wh)
initial_centers = kmeans_plusplus_initializer(sample, 9).initialize()
# Create instance of K-Means algorithm with prepared centers.
kmeans_instance = kmeans(sample, initial_centers, metric=metric)
# Run cluster analysis and obtain results.
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
final_centers = np.array(kmeans_instance.get_centers())
# Visualize obtained results
kmeans_visualizer.show_clusters(sample,
clusters,
final_centers,
display=False)
sccs = np.round(final_centers[np.argsort(np.prod(final_centers,
axis=1))]).astype(np.int)
print(sccs)
# [[ 9 13]
# [ 25 17]
# [ 16 31]
# [ 47 29]
# [ 32 51]
# [ 83 48]
# [ 61 91]
# [131 99]
# [210 189]]
plt.savefig('results/visdrone_anchors.png')
plt.scatter(reduced_data[i, 0],
reduced_data[i, 1],
c=col[int(model_train_label[i])],
marker='.')
gt_centers = []
for i in range(10):
tmp = []
tmp.append(arr_x[i] / arr_cnt[i])
tmp.append(arr_y[i] / arr_cnt[i])
gt_centers.append(tmp)
plt.title('sample data')
plt.show()
kmeans_visualizer.show_clusters(inp, gt_clusters, gt_centers)
# Visualize clustering results
visualizer = cluster_visualizer_multidim()
visualizer.append_clusters(gt_clusters, inp, marker='o')
# visualizer.append_cluster(noise, inp, marker='x')
# visualizer.set_canvas_title('original clustering : the ground truth')
visualizer.show()
# Prepare initial centers using K-Means++ method.
initial_centers = kmeans_plusplus_initializer(inp, 10).initialize()
# Create instance of K-Means algorithm with prepared centers.
kmeans_instance = kmeans(inp, initial_centers)
# Run cluster analysis and obtain results.
