classes = final_dict[key]
randval = newmeme.rand_index_score(test_labels, classes.astype(int))
jacardkmean1 = jaccard_similarity_score(test_labels,
classes.astype(int))
print('randval', randval)
print('jacard', jacardkmean1)
print('final', final_dict)
result1 = load_iris()
result1 = result1['data']
result1 = np.loadtxt(open(
"C:\personal\PhD\Dataset\Anomaly\Libras\\real_6.csv", "r"),
delimiter=",")
kmeans1 = KMeans(n_clusters=15, random_state=0).fit(result1)
# print("kmeans without meme", confusion_matrix(test_labels, kmeans1.labels_))
print('kmeans level', kmeans1.labels_)
randkmean1 = newmeme.rand_index_score(test_labels, kmeans1.labels_)
print('rand', randkmean1)
jacardkmean1 = jaccard_similarity_score(test_labels, kmeans1.labels_)
print('jacard', jacardkmean1)
score = obj.calculate_silhoutte("", kmeans1.labels_)
print('score here', score)
D1 = pairwise_distances(result1, metric='euclidean')
M1, C1 = kMedoids(D1, 15)
kmediodlabels1 = convertLabelsToList(M1, C1, 360)
print('kmediod level', kmediodlabels1)
randkmediod1 = newmeme.rand_index_score(test_labels, kmediodlabels1)
jacardkmediod1 = jaccard_similarity_score(test_labels, kmediodlabels1)
print('randkmediod1', randkmediod1)
print('jacardkmediod1', jacardkmediod1)
classes=final_dict[key]
randval=newmeme.rand_index_score(test_labels,classes.astype(int))
jacardkmean1 = jaccard_similarity_score(test_labels, classes.astype(int))
print('randval',randval)
print('jacard', jacardkmean1)
print('final', final_dict)
result1 = np.loadtxt(open("C:\personal\PhD\Dataset\sonar-data-set\glass-classification\\glass.csv", "r"),
delimiter=",")
kmeans1 = KMeans(n_clusters=6, random_state=0).fit(result1)
# print("kmeans without meme", confusion_matrix(test_labels, kmeans1.labels_))
print('kmeans level',kmeans1.labels_)
randkmean1 = newmeme.rand_index_score(test_labels, kmeans1.labels_)
print('rand',randkmean1)
jacardkmean1 = jaccard_similarity_score(test_labels, kmeans1.labels_)
print('jacard',jacardkmean1)
D1 = pairwise_distances(result1, metric='euclidean')
M1, C1 = kMedoids(D1, 6)
kmediodlabels1 = convertLabelsToList(M1, C1, 214)
print('kmediod level', kmediodlabels1)
randkmediod1 = newmeme.rand_index_score(test_labels, kmediodlabels1)
jacardkmediod1 = jaccard_similarity_score(test_labels, kmediodlabels1)
print('randkmediod1',randkmediod1)
print('jacardkmediod1',jacardkmediod1)
tp_plus_fn = comb(np.bincount(classes), 2).sum()
A = np.c_[(clusters, classes)]
tp = sum(
comb(np.bincount(A[A[:, 0] == i, 1]), 2).sum() for i in set(clusters))
fp = tp_plus_fp - tp
fn = tp_plus_fn - tp
tn = comb(len(A), 2) - tp - fp - fn
return (tp + tn) / (tp + fp + fn + tn)
if __name__ == '__main__':
rand.random(0.0001, 0.0010)
result = readCsvFile()
result = result.transpose()
D = pairwise_distances(result, metric='euclidean')
M, C = kMedoids(D, 2)
kmediodlabels = convertLabelsToList(M, C)
print("lables k mediod", kmediodlabels)
kmeans = KMeans(n_clusters=2, random_state=0).fit(result)
print(kmeans.labels_)
test_labels = np.zeros(208, int)
test_labels[0:97] = np.int(1)
print("kmeans", confusion_matrix(test_labels, kmeans.labels_))
randkmean = rand_index_score(test_labels, kmeans.labels_)
jacardkmean = jaccard_similarity_score(test_labels, kmeans.labels_)
siltkmean = silhouette_score(D, kmeans.labels_, "precomputed")
print("kemans rand", randkmean)
print("jacardkmean", jacardkmean)
print("silthkmean", siltkmean)
entrophygen = Entrophy.computeEntophy(test_labels, kmeans.labels_)
print('entrophy', entrophygen)