def fitnessFunction(individual, algorithm, n_labels, ground_truth, m1, m2, m3):
w1 = individual[0]
w2 = individual[1]
# w3 = individual[2]
w3 = 0
corr = mf.calculateCorrelationMatrix(m1, m2, m3, w1, w2, w3)
if algorithm == 'complete':
agglomerative = AgglomerativeClustering(affinity='precomputed', n_clusters=n_labels, linkage='complete').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'average':
agglomerative = AgglomerativeClustering(affinity='precomputed', n_clusters=n_labels, linkage='average').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'kmedoids':
_, clusters = km.kMedoids(corr, n_labels, 100)
labels = km.sortLabels(clusters)
#fitness = metrics.homogeneity_score(labels, ground_truth)
#fitness = metrics.adjusted_rand_score(labels, ground_truth)
#fitness = sum(individual)
fitness = metrics.calinski_harabaz_score(corr, labels)
corr = None
m1 = None
m2 = None
m3 = None
return fitness
def fitness(indv):
w1, w2, w3 = indv.solution
corr = mf.calculateCorrelationMatrix(matrix1, matrix2, matrix3, w1, w2, w3)
if algorithm == 'complete':
agglomerative = AgglomerativeClustering(affinity='precomputed', n_clusters=n_labels, linkage='complete').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'average':
agglomerative = AgglomerativeClustering(affinity='precomputed', n_clusters=n_labels, linkage='average').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'kmedoids':
_, clusters = km.kMedoids(corr, n_labels, 100)
labels = km.sortLabels(clusters)
metrics = ce.clusterEvaluation(corr, labels, ground_truth)
writer.write(str(current_iteration)+': '+str(w1)+' '+str(w2)+' '+str(w3)+' '.join(str(x) for x in metrics)+'\n')
def fitness(indv):
w1, w2, w3 = indv.solution
#return x + 10*sin(5*x) + 7*cos(4*x)
corr = mf.calculateCorrelationMatrix(matrix1, matrix2, matrix3, w1, w2, w3)
agglomerative = AgglomerativeClustering(affinity='precomputed',
n_clusters=n_labels,
linkage='complete').fit(corr)
labels = agglomerative.labels_
metrics = cl.clusterEvaluation(corr, labels, ground_truth)
if metrics[0] <= 0:
return 1
print(metrics[0] * 100)
return float(metrics[0]) * 100
def fitness(indv):
w1, w2, w3 = indv.solution
corr = mf.calculateCorrelationMatrix(matrix1, matrix2, matrix3, w1, w2, w3)
if algorithm == 'complete':
agglomerative = AgglomerativeClustering(affinity='precomputed',
n_clusters=n_labels,
linkage='complete').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'average':
agglomerative = AgglomerativeClustering(affinity='precomputed',
n_clusters=n_labels,
linkage='average').fit(corr)
labels = agglomerative.labels_
elif algorithm == 'kmedoids':
_, clusters = km.kMedoids(corr, n_labels, 100)
labels = km.sortLabels(clusters)
metrics = ce.clusterEvaluation(corr, labels, ground_truth)
return float(metrics[0]) * 100
ground_truth = list(map(int, ground_truth))
matrix1 = mf.minMaxScale(matrix1)
matrix2 = mf.minMaxScale(matrix2)
matrix3 = mf.minMaxScale(matrix3)
matrix1 = mf.calculateDistances(matrix1)
matrix2 = mf.calculateDistances(matrix2)
matrix3 = mf.calculateDistances(matrix3)
for w1 in np.arange(0.05, 1.05, 0.05):
w2 = 0
w3 = 1 - w1
corr = mf.calculateCorrelationMatrix(matrix1, matrix2, matrix3, w1,
w2, w3)
# Hierarchical
for link in ['complete', 'average']:
agglomerative = AgglomerativeClustering(
affinity='precomputed',
n_clusters=n_labels,
linkage='complete').fit(corr)
labels = agglomerative.labels_
metrics = ce.clusterEvaluation(corr, labels, ground_truth)
print(metrics)
ce.saveResultsWithWeights(measure1, measure2, w1,
'hierarchical_' + link, sample,
metrics)
# K-Medoids