简单的手写kmeans

k=2
data = np.random.randn(100,2)
data[:50]+=2.0
center_index = np.random.choice(np.arange(len(data)), k)
center = data[center_index]

iters = 20
def dispatch(data,center):
    # n*2
    # k*2
    data = data[None]
    center = center[:,None]
    distance = ((data-center)**2).sum(axis= 2)
    return distance.argmin(axis=0)
threshold = 0.01
finsh = True
while finsh:
    classfity = dispatch(data,center)
    unique_classfity = np.unique(classfity)
    new_center = []
    for i in range(len(unique_classfity)):
        if np.any(new_center):
            data_vs = data[classfity==i].mean(axis = 0,keepdims = True)
            new_center = np.vstack((new_center,data_vs))
        else:
            new_center = data[classfity==i].mean(axis = 0,keepdims = True)
    diff = ((new_center - center) ** 2).sum()
    finsh=diff>threshold
    center = new_center
    print(f"diff:{diff:.5f}")

- 1.指定K个初始质心

- 2.利用质心对数据进行分类

- 3.对分类后的数据，计算其质心，称之为新质心

- 4.判断新质心与当前质心之间的差距，是否小于指定阈值，如果成立则跳出

- 如果不成立，则替换当前质心为新的质心

- 执行2步骤

- 5.输出最后得到的质心