# Clustering Evaluation Imports
from functools import partial
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs as sk_make_blobs
from yellowbrick.cluster import InterclusterDistance
# Helpers for easy dataset creation
N_SAMPLES = 1000
N_FEATURES = 12
SHUFFLE = True
# Make blobs partial
make_blobs = partial(sk_make_blobs,
n_samples=N_SAMPLES,
n_features=N_FEATURES,
shuffle=SHUFFLE)
if __name__ == '__main__':
# Make 8 blobs dataset
X, y = make_blobs(centers=12)
# Instantiate the clustering model and visualizer
# Instantiate the clustering model and visualizer
visualizer = InterclusterDistance(KMeans(9))
visualizer.fit(X) # Fit the training data to the visualizer
visualizer.poof(outpath="images/icdm.png") # Draw/show/poof the data
# Clustering Evaluation Imports
from functools import partial
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs as sk_make_blobs
from yellowbrick.cluster import InterclusterDistance
# Helpers for easy dataset creation
N_SAMPLES = 1000
N_FEATURES = 12
SHUFFLE = True
# Make blobs partial
make_blobs = partial(sk_make_blobs, n_samples=N_SAMPLES, n_features=N_FEATURES, shuffle=SHUFFLE)
if __name__ == '__main__':
# Make 8 blobs dataset
X, y = make_blobs(centers=12)
# Instantiate the clustering model and visualizer
# Instantiate the clustering model and visualizer
visualizer = InterclusterDistance(KMeans(9))
visualizer.fit(X) # Fit the training data to the visualizer
visualizer.poof(outpath="images/icdm.png") # Draw/show/poof the data
def cluster_metrics(i_patches, a_patches, g_patches, city_names, K, save_path,
g_indices):
# intra-cluster distances: ssd of samples to the nearest cluster centre
sum_of_squared_distances = []
silhouette_scores = []
calinski_harabasz_scores = []
davies_bouldin_scores = []
k_mean_list = []
for k in K:
model, k_means, A = get_kmeans144_result(a_patches, k)
k_mean_list.append(k_means)
sum_of_squared_distances.append(k_means.inertia_)
labels = k_means.labels_
score = metrics.silhouette_score(A, labels, metric='euclidean')
silhouette_scores.append(score)
score = metrics.calinski_harabasz_score(A, labels)
calinski_harabasz_scores.append(score)
score = metrics.davies_bouldin_score(A, labels)
davies_bouldin_scores.append(score)
mydict = dict_cluster(i_patches, a_patches, g_patches, city_names,
k_means)
save_path_k = '{}_{}'.format(save_path, k)
gt_ratio = gt_metric(mydict, save_path_k)
plot_figure(K, sum_of_squared_distances, save_path,
'sum_of_squared_distances')
plot_figure(K, silhouette_scores, save_path, 'silhouette_scores')
plot_figure(K, calinski_harabasz_scores, save_path,
'calinski_harabasz_scores')
plot_figure(K, davies_bouldin_scores, save_path, 'davies_bouldin_score')
ssd_best_index = sum_of_squared_distances.index(
max(sum_of_squared_distances))
sil_best_index = silhouette_scores.index(max(silhouette_scores))
ch_best_index = calinski_harabasz_scores.index(
max(calinski_harabasz_scores))
db_best_index = davies_bouldin_scores.index(max(davies_bouldin_scores))
#gtr_best_index = gt_ratio.index(max(gt_ratio))
all_indices = [
ssd_best_index, sil_best_index, ch_best_index, db_best_index
] #, gtr_best_index] #, axis=None)
best_k = np.array(K)[np.unique(all_indices)]
for ind in range(len(K)): #best_k:
# Visualize output clusters of K means in 2D
k_means = k_mean_list[ind]
visualizer = InterclusterDistance(k_means)
visualizer.fit(A) # Fit the data to the visualizer
#visualizer.show() # Finalize and render the figure
visualizer.show(
outpath='{}_{}_InterclusterDistance.png'.format(save_path, ind))
visualizer.poof()
# Visualize through TSNE
A_embedded = TSNE().fit_transform(A)
plt.figure()
palette = sns.color_palette("bright", 2)
y_ = np.asarray(g_indices)
y = y_.astype(np.float32)
sns.scatterplot(A_embedded[:, 0],
A_embedded[:, 1],
hue=y,
legend='full',
palette=palette)
plt.savefig('{}_tsne.png'.format(save_path))
return
