k-means对一维数组进行聚类的代码，适合初学者

关于k-means聚类的原理可以参考这篇博客：
https://blog.csdn.net/sinat_36710456/article/details/88019323

本篇只讨论基本的代码实现，由于只是对一维数组的聚类，距离公式上比较简单：distance = |a - b| 适合初学者理解最基本的原理
所谓一维数组
比如： [12, 3, 56, 89, 78, 2, 12, 45, 255, 236]

以下代码实现的是对一组数字的聚类
类别的个数可以设置，改变参数n的值即可

代码如下（建议从最下边的主函数开始看起）：

import numpy as np
import matplotlib.pyplot as plt
from time import *


def dis(a, b):
    return abs(a-b)


def take_first(list_):
    return list_[0]


def plot_(centroids, groups_list):
    for i in range(len(centroids)):
        centroids[i] = int(centroids[i])
    z = list(zip(centroids, groups_list))
    z.sort(key=take_first)
    for i in range(len(centroids)):
        centroids[i] = z[i][0]
        groups_list[i] = z[i][1]
    plt.bar(np.arange(len(centroids)), groups_list, align='center', color='c', tick_label=centroids)
    plt.title('Distribution ', fontsize=20)
    plt.xlabel('Area_Categories ', fontsize=18)
    plt.ylabel('Numbers', fontsize=18)
    plt.tick_params(axis='both', labelsize=14)
    plt.tight_layout()
    for a, b in zip(np.arange(len(centroids)), groups_list):
        plt.text(a, b, b, ha='center', va='baseline', fontsize=14, fontstyle='italic')
    plt.show()


def do_kmeans(n, area_list, centroids):
    loss = 0
    groups = []
    new_centroids = []
    for i in range(n):
        groups.append([])
        new_centroids.append(0)
    for area in area_list:
        min_distance = 1000000
        group_index = 0
        for centroid_index, centroid in enumerate(centroids):
            distance = dis(area, centroid)
            if distance < min_distance:
                min_distance = distance
                group_index = centroid_index
        groups[group_index].append(area)
        loss += min_distance
        new_centroids[group_index] += area
    for i in range(n):
        new_centroids[i] /= len(groups[i])
    return new_centroids, groups, loss


def compute_centroids(list_path, n, loss_convergence, iterations_num):
    area_list = []
    f = open(list_path)
    for line in f:
        temp = line.strip()
        if len(temp) > 1:
            area_list.append(float(temp))
    f.close()
    centroid_indices = np.random.choice(len(area_list), n)
    centroids = []
    for centroid_index in centroid_indices:
        centroids.append(area_list[centroid_index])
    centroids, groups, old_loss = do_kmeans(n, area_list, centroids)
    iterations = 1
    i = 0
    while True:
        i = 1+i
        centroids, groups, loss = do_kmeans(n, area_list, centroids)
        iterations = iterations + 1
        print("number:", i, "************loss = %f" % loss)
        if abs(old_loss - loss) < loss_convergence or iterations > iterations_num:
            break
        old_loss = loss
        for centroid in centroids:
            print(centroid, '\n')
    # print result
    j = 0
    groups_list = []
    print("--------------------------------")
    for centroid in centroids:
        print("k-means result：")
        print(centroid, "-------numbers:", len(groups[j]))
        groups_list.append(len(groups[j]))
        j = j+1
    print("--------------------------------")
    plot_(centroids, groups_list)


begin_time = time()
list_path = "G:/iSAID annotation/area.txt"
n = 5
loss_convergence = 1e-10
iterations_num = 500
print('**************Start**************')
compute_centroids(list_path, n, loss_convergence,  iterations_num)
print('*********Already Finish*********\n')
end_time = time()
run_time = end_time-begin_time
print('运行时间：', run_time)