【Deep-ML系列】K-Means Clustering（手写Kmeans聚类）

题目链接：Deep-ML

K-Means聚类：事先给定k个簇点以及n个points，经过max_iterations轮次的迭代，每次更新新的簇点。

import numpy as np

def euclidean_distance(a, b):
    '''
    Compute the Euclidean distance between 2d-vector and 1d-vector
    :param a: ponits
    :param b: centroid
    :return: Euclidean distance [len(a)]
    '''
    return np.sqrt((a - b)**2).sum(axis=1)

def k_means_clustering(points, k, initial_centroids, max_iterations):
    points = np.array(points)
    centroids = initial_centroids
    for _ in range(max_iterations):
        distances = [euclidean_distance(points, centroid) for centroid in centroids]    # 行数：簇点个数，列数：点个数
        cluster = np.argmin(distances, axis=0)      # 一维数组，展示每个点所对应的簇号
        new_centroids = [points[cluster == i].mean(axis=0) for i in range(k)]
        centroids = np.round(new_centroids, 4)
    return [tuple(centroid) for centroid in centroids]


if __name__ == '__main__':
    points = [(1, 2), (1, 4), (1, 0), (10, 2), (10, 4), (10, 0)]
    k = 2
    initial_centroids = [(1, 1), (10, 1)]
    max_iterations = 10
    print(k_means_clustering(points, k, initial_centroids, max_iterations))