def __cluster_data(params):
i, data_set, k = params
return (string.ascii_lowercase[i], cluster_data(load_data(data_set), k))
# compute the covariance of the data
sigma = np.cov(centered, rowvar=0)
# get a vector of eigenvalues and matrix of eigenvectors
lmbda, w = np.linalg.eig(np.mat(sigma))
# sort in descending order
idx = lmbda.argsort()[::-1]
# apply the new indexing and transpose the eigenvector matrix
lmbda = lmbda[idx]
w = w[idx].T
# use top eigenvalues if have less than ten
if len(lmbda) < top_b:
return lmbda, w
# if not, return the top ten eigenvalues
else:
return lmbda[:top_b], w[:top_b]
if __name__ == '__main__':
data = load_data('./data/p4-data.txt', to_float32=True)
vals, w = pca(data)
print("Eigenvalues in descending order:")
for idx, val in enumerate(vals, 1):
print("{:3d}: {:5.3f}".format(idx, np.real(val)))
# 5、取得sum_all之间的随机值
sum_all *= random()
# 6、获得距离最远的样本点作为聚类中心点
for j, di in enumerate(d):
sum_all -= di
if sum_all > 0:
continue
cluster_centers[i] = np.copy(points[j, ])
break
return cluster_centers
if __name__ == "__main__":
k = 4 # 聚类中心的个数
file_path = "./Data/data.txt"
# 1、导入数据
print("---------- 1.load data ------------")
data = load_data(file_path)
# 2、KMeans++的聚类中心初始化方法
print("---------- 2.K-Means++ generate centers ------------")
centroids = get_centroids(data, k)
# 3、聚类计算
print("---------- 3.kmeans ------------")
subCenter = kmeans(data, k, centroids)
# 4、保存所属的类别文件
print("---------- 4.save subCenter ------------")
save_result("./TrainingResult/kmeans++_sub", subCenter)
# 5、保存聚类中心
print("---------- 5.save centroids ------------")
save_result("./TrainingResult/kmeans++_center", centroids)
def __cluster_data(params):
i, data_set, k = params
return (string.ascii_lowercase[i], cluster_data(load_data(data_set), k))