def DBSCAN(data, clusters, dataNr = 0):
D = distance.squareform(distance.pdist(data))
S = 1 - (D / np.max(D))
db = cluster.DBSCAN().fit(S, eps=0.95, min_samples=10)
core_samples = db.core_sample_indices_
labels = db.labels_
x = np.linspace(min([x[0] for x in data]), max([x[0] for x in data]))
y = np.linspace(min([y[1] for y in data]), max([y[1] for y in data]))
colors = cycle('bgrcmy')
for k, col in zip(set(labels), colors):
if k == -1:
col = 'k'
markersize = 6
class_members = [index[0] for index in np.argwhere(labels == k)]
cluster_core_samples = [index for index in core_samples
if labels[index] == k]
for index in class_members:
x = data[index]
if index in core_samples and k != -1:
markersize = 14
else:
markersize = 6
pl.plot(x[0], x[1], 'o', markerfacecolor = col,
markeredgecolor = 'k', markersize = markersize)
draw.setImgTitle('DBSCAN_test' + str(dataNr))
draw.showImage()
def ECMC(data, clusters, dataNr = 0):
clusters = ECMCThrToClusters(data, clusters)
x = np.linspace(min([x[0] for x in data]), max([x[0] for x in data]))
y = np.linspace(min([y[1] for y in data]), max([y[1] for y in data]))
colors = 'bgrcmyk'
sign = 'o*.x+'
for c in range(len(clusters)):
#circ = pl.Circle((clusters[c].centre[0], clusters[c].centre[1]), radius = clusters[c].radius, facecolor = "none")
#ax = pl.gca()
#ax.add_patch(circ)
for m in clusters[c].members:
pl.plot(m[0], m[1], sign[c/len(colors)], markerfacecolor = colors[c%len(colors)], markersize = 3)
draw.setImgTitle('ECMC_test' + str(dataNr))
draw.showImage()
sys.exit('Usage: python spectral.py dataset k')
## Data preprocessing
data = parse_tab(sys.argv[1])
k = int(sys.argv[2])
classes = [example[-1] for example in data]
examples = data_to_na(data)
distances = euclidean_distances(examples, examples)
# Apply gaussian kernel as suggested in the documentation:
gamma = 0.5 # == 1 / num_features (heuristic)
similarity_matrix = numpy.exp(-distances * gamma)
## Clustering
sc = SpectralClustering(k=k, random_state=0)
sc.fit(similarity_matrix)
labels = sc.labels_
## Performance evaluation
ari = adjusted_rand_score(labels, classes)
homogeneity, completeness, v_measure = homogeneity_completeness_v_measure(labels, classes)
print('ARI: {0}'.format(ari))
print('Homogeneity: {0}'.format(homogeneity))
print('Completeness: {0}'.format(completeness))
print('V-measure: {0}'.format(v_measure))
addToResult('Spectral', ari, homogeneity, completeness, v_measure)
draw.scatter(examples, labels)
print(os.path.splitext(os.path.basename(sys.argv[1]))[0])
draw.setImgTitle('spectral_' + os.path.splitext(os.path.basename(sys.argv[1]))[0])
draw.showImage()
import drawing as draw
draw.savedImages = {}
if len(sys.argv) < 3:
sys.exit('Usage: python kmeans.py dataset k')
## Data preprocessing
data = parse_tab(sys.argv[1])
k = int(sys.argv[2])
classes = [example[-1] for example in data]
examples = data_to_na(data)
## Clustering
kmeans = KMeans(k=k, random_state=0)
kmeans.fit(examples)
codebook = kmeans.cluster_centers_
labels = kmeans.predict(examples)
## Performance evaluation
ari = adjusted_rand_score(labels, classes)
homogeneity, completeness, v_measure = homogeneity_completeness_v_measure(labels, classes)
print('ARI: {0}'.format(ari))
print('Homogeneity: {0}'.format(homogeneity))
print('Completeness: {0}'.format(completeness))
print('V-measure: {0}'.format(v_measure))
addToResult('k-means', ari, homogeneity, completeness, v_measure)
draw.scatter(examples, labels)
print(os.path.splitext(os.path.basename(sys.argv[1]))[0])
draw.setImgTitle('kmeans_' + os.path.splitext(os.path.basename(sys.argv[1]))[0])
draw.showImage()
