def Repair(pop, s, i, x): # Checking if it is going beyond the boundary
Newlab = [] ##Store the labels in lab
Newcenter = []
new_center = []
new_pop = []
pbm_index_newpop = []
sil_score_newpop = []
C = []
pop = np.array(pop)
A = pop.max(axis=0) #Getting the maximum from the column
B = pop.min(axis=0) #Getting the minimum from the column
for j in range(0, len(s)):
if (s[j] < A[i]):
s[j] = A[i]
elif (s[j] > B[i]):
s[j] = B[i]
else:
s[j] = s[j]
print("Value of offspring for the {} is {} for axis{}\n".format(x, s, i))
center1 = s[0:4]
#print("Value of center 1 is\n", center1)
center2 = s[4:8]
#print("Value of center 2 is\n", center2)
center3 = s[8:12]
#print("Value of center 3 is\n", center3)
C.append(center1)
C.append(center2)
C.append(center3)
C = np.array(C)
print("Value of Initial Center\n", C)
data = genfromtxt('iris.csv',
delimiter=',',
skip_header=0,
usecols=range(0, 4)) ##Read the input data
actual_label = genfromtxt('iris.csv',
delimiter=',',
dtype=str,
skip_header=0,
usecols=(4))
u, lab = Kmeans_clu(3, data, C)
Newlab.insert(i, lab) #Store the labels in lab
Newcenter.insert(i, u)
features = len(data[0])
max_cluster = 3
cluster = 3
new_pbm = cal_pbm_index(cluster, data, u, lab)
pbm_index_newpop.insert(
i, new_pbm) #Store the second objective function(PBM Ind1ex)
s = silhouette_score(data, lab)
sil_score_newpop.insert(
i, s) #Store the first objective funvtion(Silhouette Score)
new_center = pop_create(max_cluster, features, cluster, u)
new_pop.insert(i, new_center)
RN = {}
for mm in range(
0, max_gen
): ## Initialize dictionary of size upto length maximum generation
CN[mm] = {}
RN[mm] = {}
for i in range(0, chromosome):
cluster = random.randint(
2, max_cluster
) ##Randomly selects cluster number from 2 to root(poplation)
K.insert(i, cluster) ##Store the number of clusters in clu
u, label = Kmeans_clu(cluster, data)
lab.insert(i, label) ##Store the labels in lab
center.insert(i, u)
new_pbm = cal_pbm_index(cluster, data, u, label)
pbm_index.insert(i,
new_pbm) ##Store the second objective function(PBM Index)
dn = calculate_dunn_index(data, label, cluster)
ini_dunn.insert(i, dn)
s = silhouette_score(data, label)
sil_score.insert(i,
s) ##Store the first objective funvtion(Silhouette Score)
new_center = pop_create(max_cluster, features, cluster, u)
population.insert(i, new_center) ##Store the populations in population
file.write("Initial Clusters : " + str(K) + '\n')
file.write("Initial PBM : " + str(pbm_index) + '\n')
file.write("Initial Sil score : " + str(sil_score) + '\n')
file.write("Initial Dunn : " + str(ini_dunn) + '\n')
index = ini_dunn.index(max(ini_dunn))