def CAclustering(self, constraints, final_n_of_clusters, clusters=None):
"""
Main hierarhical clustering loop
"""
self.l.log("Creating transitive ML closure...")
stevec = len(clusters)
for c in clusters:
print(clusters[c].clusterId, clusters[c].points)
for x in constraints:
if 'must-link' in x:
print("omejitev: ", x)
kluc1 = self.getClusterID(x['point'][0], clusters)
kluc2 = self.getClusterID(x['must-link'][0], clusters)
print(kluc1, " | ", kluc2, " | ", stevec, kluc1 == kluc2)
if kluc1 != kluc2:
tocke = []
tocke.append(clusters[kluc1].points)
tocke.append(clusters[kluc2].points)
clusters.pop(kluc1)
clusters.pop(kluc2)
nov = Cluster(stevec)
nov.update(kluc1, kluc2, 0, tocke) # TLE DEJ NOT
clusters.update({stevec: nov})
stevec += 1
m = stevec
self.l.log("Creating distance matrix....")
self.distances = {}
self.clusters = clusters
stevec = 0
for c in self.clusters:
print(self.clusters[c].points, self.clusters[c].clusterId)
for p in self.clusters[c].points:
stevec += 1
print(len(self.clusters), stevec)
z = [(clusters[a].clusterId, clusters[b].clusterId)
for a in self.clusters for b in self.clusters]
for l in z:
kljuc1 = str(l[0]) + " " + str(l[1])
kljuc2 = str(l[1]) + " " + str(l[0])
if l[0] != l[1]:
if kljuc1 in self.distances:
continue
elif kljuc2 in self.distances:
continue
else:
if self.linkage == "Ward":
c = []
u = []
v = []
for p in self.clusters[l[0]].points:
c.append(p.coords)
u.append(p.coords)
for r in self.clusters[l[1]].points:
c.append(r.coords)
v.append(r.coords)
centroid_uv = np.average(c, axis=0)
centroid_u = np.average(u, axis=0)
centroid_v = np.average(v, axis=0)
dist1 = 0
dist2 = 0
dist3 = 0
for point in c:
if self.distance_type == "Cosine":
dist1 += spatial.distance.cosine(
centroid_uv, point)**2
elif self.distance_type == "Euclidean":
dist1 += spatial.distance.euclidean(
centroid_uv, point)**2
for point in u:
if self.distance_type == "Cosine":
dist2 += spatial.distance.cosine(
centroid_u, point)**2
elif self.distance_type == "Euclidean":
dist2 += spatial.distance.euclidean(
centroid_u, point)**2
for point in v:
if self.distance_type == "Cosine":
dist3 += spatial.distance.cosine(
centroid_v, point)**2
elif self.distance_type == "Euclidean":
dist3 += spatial.distance.euclidean(
centroid_v, point)**2
dist = dist1 - dist2 - dist3
self.distances.update({kljuc1: dist})
elif self.linkage == "Average":
u = [(a, b) for a in self.clusters[l[0]].points
for b in self.clusters[l[1]].points]
dist = self.average_linkage(u)
self.distances.update({kljuc1: dist})
else:
print("Error creating distance matrix...")
exit(1)
self.l.log("Finding clusters...")
'''
s = sorted(self.distances.items(), key=lambda x: x[1])
for k, v in s:
print(k, v)
'''
print("st. omejitev: ", len(constraints))
# print("clustri: ", self.clusters.keys())
self.Z = np.array([])
# n = len(self.points) #na začetku je vsak primer svoj cluster
n = len(self.clusters)
idZ = 0
stop_clustering = False
while (n != final_n_of_clusters):
# print("### ",n," ###")
condition = True
# clusters_checked = []
while condition:
key = min(self.distances, key=self.distances.get)
kljuc = key
par = key.split(' ')
par = [int(i) for i in par]
dist = self.distances[kljuc]
# print(" ->",key, " ", self.check_cannot_link(constraints, self.clusters[par[0]].points, self.clusters[par[1]].points))
if self.check_cannot_link(constraints,
self.clusters[par[0]].points,
self.clusters[par[1]].points):
self.distances[kljuc] = sys.maxsize
if dist == sys.maxsize:
self.l.log(
"ABHC cannot find clusters under those constraints..."
)
return self.clusters
print(" Cannot link:", par)
else:
break
# print("--------------------")
# print(par[0], par[1])
# print(self.distances.keys())
self.distances.pop(kljuc, None)
self.izbrisi_razdalje(par[0])
self.izbrisi_razdalje(par[1])
# print(self.distances.keys())
tocke = []
tocke.append(self.clusters[par[0]].points)
tocke.append(self.clusters[par[1]].points)
# print("tocke: ", len(tocke))
novCluster = Cluster(m + idZ)
novCluster.update(par[0], par[1], dist, tocke)
novCluster.centroid = novCluster.calculateCentroid()
self.clusters.pop(par[0])
self.clusters.pop(par[1])
self.clusters.update({(m + idZ): novCluster})
# print("clustri:")
# print(self.clusters.keys())
# print("dodajam razdalje...")
# print("NOV:" ,m+idZ)
self.dodaj_razdalje(m + idZ)
print("par: ", par, "dist: ", '%.08f' % dist)
if idZ == 0:
self.Z = [par[0], par[1], dist, novCluster.n]
else:
newrow = [par[0], par[1], dist, novCluster.n]
self.Z = np.vstack([self.Z, newrow])
n = len(self.clusters)
idZ += 1
return self.clusters
def ABHclustering(self, constraints, final_n_of_clusters, clusters=None):
"""
Main hierarhical clustering loop
"""
self.l.log("Creating transitive ML closure...")
stevec = len(clusters)
for x in constraints:
if 'must-link' in x:
#print("omejitev: ", x)
kluc1 = self.getClusterID(x['point'][0], clusters)
kluc2 = self.getClusterID(x['must-link'][0], clusters)
#print(kluc1, " | " , kluc2," | ", stevec, kluc1 == kluc2)
if kluc1 != kluc2:
tocke = []
tocke.append(clusters[kluc1].points)
tocke.append(clusters[kluc2].points)
clusters.pop(kluc1)
clusters.pop(kluc2)
nov = Cluster(stevec)
nov.update(kluc1, kluc2, 0, tocke) #TLE DEJ NOT
clusters.update({stevec: nov})
stevec += 1
m = stevec
self.l.log("Creating distance matrix....")
self.distances = {}
self.clusters = clusters
stevec = 0
for c in self.clusters:
print(self.clusters[c].points, self.clusters[c].clusterId)
for p in self.clusters[c].points:
stevec += 1
print(len(self.clusters), stevec)
z = [(clusters[a].clusterId, clusters[b].clusterId)
for a in self.clusters for b in self.clusters]
for l in z:
kljuc1 = str(l[0]) + " " + str(l[1])
kljuc2 = str(l[1]) + " " + str(l[0])
if l[0] != l[1]:
if kljuc1 in self.distances:
continue
elif kljuc2 in self.distances:
continue
else:
if self.linkage == "Ward":
c = []
u = []
v = []
for p in self.clusters[l[0]].points:
c.append(p.coords)
u.append(p.coords)
for r in self.clusters[l[1]].points:
c.append(r.coords)
v.append(r.coords)
centroid_uv = np.average(c, axis=0)
centroid_u = np.average(u, axis=0)
centroid_v = np.average(v, axis=0)
dist1 = 0
dist2 = 0
dist3 = 0
for point in c:
if self.distance_type == "Cosine":
dist1 += spatial.distance.cosine(
centroid_uv, point)**2
elif self.distance_type == "Euclidean":
dist1 += spatial.distance.euclidean(
centroid_uv, point)**2
for point in u:
if self.distance_type == "Cosine":
dist2 += spatial.distance.cosine(
centroid_u, point)**2
elif self.distance_type == "Euclidean":
dist2 += spatial.distance.euclidean(
centroid_u, point)**2
for point in v:
if self.distance_type == "Cosine":
dist3 += spatial.distance.cosine(
centroid_v, point)**2
elif self.distance_type == "Euclidean":
dist3 += spatial.distance.euclidean(
centroid_v, point)**2
dist = dist1 - dist2 - dist3
self.distances.update({kljuc1: dist})
elif self.linkage == "Average":
u = [(a, b) for a in self.clusters[l[0]].points
for b in self.clusters[l[1]].points]
dist = self.average_linkage(u)
self.distances.update({kljuc1: dist})
else:
print("Error creating distance matrix...")
exit(1)
self.l.log("Finding clusters...")
'''
s = sorted(self.distances.items(), key=lambda x: x[1])
for k, v in s:
print(k, v)
'''
print("st. omejitev: ", len(constraints))
#print("clustri: ", self.clusters.keys())
self.Z = np.array([])
#n = len(self.points) #na začetku je vsak primer svoj cluster
n = len(self.clusters)
idZ = 0
stop_clustering = False
while (n != final_n_of_clusters):
#print("### ",n," ###")
condition = True
#clusters_checked = []
while condition:
"""
if len(clusters_checked) == len(self.clusters):
print("Ni mozno nadaljne zruzevanje, ostalo je ",len(self.clusters)," clustrov.")
break
dist, pair = self.closest_clusters(clusters_checked)
if(pair is None):
stop_clustering = True
break
par = list()
for el in pair:
par.append(el)
self.constraints = self.sort_constraints()
#ali ima katerakoli tocka iz obeh clustrov ML, jo zdruzi in ponovno poisci najblizja clustra
#ML_pair = self.check_must_link(constraints, self.clusters[par[0]].points)
if ML_pair == -1:
ML_pair = self.check_must_link(constraints, self.clusters[par[1]].points)
if ML_pair != -1:
par[0] = ML_pair[0]
par[1] = ML_pair[1]
condition = self.check_cannot_link(constraints, self.clusters[par[0]].points, self.clusters[par[1]].points)
if condition:
clusters_checked.append([par[0], par[1]])
dist = self.cluster_distance(par[0], par[1])
if stop_clustering:
break
#print("par: ", par, ", dist: ", round(dist,2), " ", len(self.clusters))
"""
key = min(self.distances, key=self.distances.get)
kljuc = key
par = key.split(' ')
par = [int(i) for i in par]
dist = self.distances[kljuc]
#print(" ->",key, " ", self.check_cannot_link(constraints, self.clusters[par[0]].points, self.clusters[par[1]].points))
if self.check_cannot_link(constraints,
self.clusters[par[0]].points,
self.clusters[par[1]].points):
self.distances[kljuc] = sys.maxsize
if dist == sys.maxsize:
self.l.log(
"ABHC cannot find clusters under those constraints..."
)
return self.clusters
print(" Cannot link:", par)
else:
break
# print("--------------------")
# print(par[0], par[1])
#print(self.distances.keys())
self.distances.pop(kljuc, None)
self.izbrisi_razdalje(par[0])
self.izbrisi_razdalje(par[1])
#print(self.distances.keys())
tocke = []
tocke.append(self.clusters[par[0]].points)
tocke.append(self.clusters[par[1]].points)
#print("tocke: ", len(tocke))
novCluster = Cluster(m + idZ)
novCluster.update(par[0], par[1], dist, tocke)
novCluster.centroid = novCluster.calculateCentroid()
self.clusters.pop(par[0])
self.clusters.pop(par[1])
self.clusters.update({(m + idZ): novCluster})
#print("clustri:")
#print(self.clusters.keys())
#print("dodajam razdalje...")
#print("NOV:" ,m+idZ)
self.dodaj_razdalje(m + idZ)
print("par: ", par, "dist: ", '%.08f' % dist)
if idZ == 0:
self.Z = [par[0], par[1], dist, novCluster.n]
else:
newrow = [par[0], par[1], dist, novCluster.n]
self.Z = np.vstack([self.Z, newrow])
n = len(self.clusters)
idZ += 1
#zapomni si primere, kateri so v drugi skupini kot v prejšni iteraciji.
self.diff = []
clusters_checked = set()
hm = 0
for cluster in self.clusters:
val = -1
for point in self.clusters[cluster].points:
hm += 1
if val < 0:
val = self.prev_dict[point.reference]
if val in clusters_checked:
self.diff.append(point.reference)
else:
if val != self.prev_dict[point.reference]:
self.diff.append(point.reference)
clusters_checked.add(val)
self.prev_dict = self.make_dict()
print(len(self.diff))
print(sorted(self.diff))
print("stevilo primerov: ", hm)
return self.clusters
def randomClusters(self, max_clusters):
for i in range(0, max_clusters):
cluster = Cluster()
cluster.centroid = self.randomPoint()
self.clusters.append(cluster)
def hierarhicalClustering(self, clusters=None):
"""
Main hierarhical clustering loop
"""
distanca = 0
self.l.log("Building distance matrix...")
n = len(self.points) #na začetku je vsak primer svoj cluster
data = []
for c in self.clusters:
p = [point.coords for point in self.clusters[c].points]
data.append(p[0])
df = pd.DataFrame(data, columns=np.array([a for a in self.attributes]))
n_df = (df.values)
self.d_matrix = np.zeros(((df.values).shape[0], (df.values).shape[0]))
for i in range((df.values).shape[0]):
for j in range((df.values).shape[0]):
kljuc1 = str(i) + ' ' + str(j)
kljuc2 = str(j) + ' ' + str(i)
if i != j:
if kljuc1 in self.distances:
continue
elif kljuc2 in self.distances:
continue
else:
if self.linkage == "Ward":
l = []
l.append(n_df[i])
l.append(n_df[j])
centroid = np.average(l, axis=0)
dist = 0
if self.distance_type == "Cosine":
dist += spatial.distance.cosine(
centroid, n_df[i])**2
dist += spatial.distance.cosine(
centroid, n_df[j])**2
elif self.distance_type == "Euclidean":
dist += spatial.distance.euclidean(
centroid, n_df[i])**2
dist += spatial.distance.euclidean(
centroid, n_df[i])**2
self.distances.update({kljuc1: dist})
elif self.linkage == "Average":
if self.distance_type == "Cosine":
dist = spatial.distance.cosine(
n_df[i], n_df[j])
elif self.distance_type == "Euclidean":
dist = spatial.distance.euclidean(
n_df[i], n_df[j])
self.distances.update({kljuc1: dist})
else:
print("Error creating distance matrix...")
exit(1)
idZ = 0
m = len(self.points)
self.l.log("Finding clusters...")
while n > 1:
"""
dist, pair = self.closest_clusters()
par = list()
for el in pair:
par.append(el)
dist = np.amin(self.d_matrix)
result = np.where(self.d_matrix == dist)
par = list()
for el in result[0]:
par.append(el)
print("--",par)
"""
key = min(self.distances, key=self.distances.get)
par = key.split(' ')
par = [int(i) for i in par]
dist = self.distances[key]
#print("--------------------")
#print(par[0], par[1])
self.distances.pop(key, None)
self.izbrisi_razdalje(par[0])
self.izbrisi_razdalje(par[1])
#print("5 238" in self.distances)
tocke = []
tocke.append(self.clusters[par[0]].points)
tocke.append(self.clusters[par[1]].points)
#print("tocke: ", len(tocke))
novCluster = Cluster(m + idZ)
novCluster.update(par[0], par[1], dist, tocke)
novCluster.centroid = novCluster.calculateCentroid()
self.clusters.pop(par[0])
self.clusters.pop(par[1])
self.clusters.update({(m + idZ): novCluster})
#print("dodajam razdalje...")
self.dodaj_razdalje(m + idZ)
"""
novCluster = Cluster(par[0])
novCluster.update(par[0], par[1], dist, tocke)
novCluster.centroid = novCluster.calculateCentroid()
self.clusters.pop(par[0])
self.clusters.pop(par[1])
self.clusters.update({(par[0]): novCluster})
#TODO: preracunaj razdalje v matriki razdalj
"""
if idZ == 0:
self.Z = [par[0], par[1], dist, novCluster.n]
else:
newrow = [par[0], par[1], dist, novCluster.n]
self.Z = np.vstack([self.Z, newrow])
n = len(self.clusters)
#self.vseSilhuete.update({idZ: self.metodaSilhuet()})
print("par: ", par, ", dist: ", '%.08f' % dist)
#print(idZ, n, m+idZ)
idZ += 1
self.l.log("Dendrogram created...")
#vrnil naj bi matriko Z, in rezultate metod, ki nam povejo koliko clustrov je
#print("Optimalno stevilo clustrov po metodi silhuet: ", len(self.points)-1-max(self.vseSilhuete.items(), key=operator.itemgetter(1))[0])
return self.clusters
parser = argparse.ArgumentParser()
parser.add_argument('k', metavar='k', type=int,
help='The number of clusters to be used')
args = parser.parse_args()
k = args.k
clusters = []
plants = file_reader.readFile()
centroids = random.sample(plants, k)
# Inicia os clusters com centroids randômicos
for i in range(0, k):
cluster = Cluster(i)
cluster.centroid = centroids[i]
clusters.append(cluster)
isConverging = False
iterationsLimit = 1000
currentIteration = 0
while (currentIteration < iterationsLimit and not isConverging):
for cluster in clusters:
cluster.plants = []
for plant in plants:
# O primeiro elemento representa o cluster mais próxima e o segundo
# representa a distância até o centróide do mesmo
closestCluster = [0, 99999999]