sum_all += d[j]
# 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.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("sub_pp", subCenter)
# 5、保存聚类中心
print("---------- 5.save centroids ------------")
save_result("center_pp", centroids)
sum_all += d[j]
# 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.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("sub_pp", subCenter)
# 5、保存聚类中心
print "---------- 5.save centroids ------------"
save_result("center_pp", centroids)
def getCentroids(points, k):
m, n = np.shape(points)
cluster_centers = np.mat(np.zeros((k, n)))
index = np.random.randint(0, m)
cluster_centers[0, ] = np.copy(points[index, ])
d = [0.0 for _ in range(m)]
for i in range(1, k):
sum_all = 0
for j in range(m):
d[j] = nearest(points[j, ], cluster_centers[0:i, ])
sum_all += d[j]
sum_all *= random()
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
file_path = '../../../train_data/KMeans.train'
data = load_data(file_path)
centroids = getCentroids(data, k)
_, subCenter = kmeans(data, k, centroids)
save_result('../../../model/model.kmcpp.sub', subCenter)
save_result('../../../model/model.kmcpp.center', centroids)