数据挖掘实验二：K-means算法及其应用（Python实现）

目录

• 实验要求
• 实验内容
  *
• 实验背景介绍
• 实现方法：
• 实验结果

实验要求

1. 掌握k-mean算法的原理。
2. 学会编写k-mean的程序实现和应用。
3. 理解和掌握通用框架的实现原则与技巧。
4. 在选取初始聚类中心的时候要做一些工作，不要使得聚类中心集中到一个簇之中。

实验内容

实验背景介绍

K-mean是机器学习中重要的算法之一，有许多版本变种和应用场景。该算法的执行效率较高，应用的结果可展示性较好。
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:1646d785-7a89-4f1b-bd6c-bbc8d8c7c294

[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:f139cf69-8fb8-4242-bb30-db5668c684b2

[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:c691d985-0d54-4cdc-a66c-ee20384a3e8a

public interface KmObj extends Comparable<kmobj> {
    public double getDistance(KmObj other); //&#x6C42;&#x4E24;&#x70B9;&#x95F4;&#x7684;&#x8DDD;&#x79BB;
    public int compareTo(KmObj other); //&#x70B9;&#x6392;&#x5E8F;&#xFF0C;&#x4E3A;&#x4E86;&#x6838;&#x5BF9;&#x805A;&#x7C7B;&#x4E2D;&#x5FC3;&#x662F;&#x5426;&#x91CD;&#x5408;
    public KmObj getCenter(KmObj[] objs, int[] serials); // &#x901A;&#x8FC7;serials&#x9009;&#x5B9A;&#x6807;&#x53F7;&#xFF0C;&#x6C42;&#x5B83;&#x4EEC;&#x7684;&#x4E2D;&#x5FC3;
}
</kmobj>

[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:dc5b627a-48f2-4d98-86da-b32b2cc3825e

public static int[][] kmean(KmObj[] objs, int k)

2．输入输出及具体要求

（1） 界面打点聚类
该系统的界面如图1所示，你可以增加另外的辅助功能，如”清除所有的点和聚类中心”等。

（2）图像像素聚类压缩
[TencentCloudSDKException] code:FailedOperation.ServiceIsolate message:service is stopped due to arrears, please recharge your account in Tencent Cloud requestId:98200130-6f4e-4a42-bf26-c73ad57e0725

实现方法：

我使用python对k-means算法进行了简单的实现。我在p1.py(打点求中心)和p2.py(图像压缩)中分别使用这个算法对二维的坐标数据和三维的RGB数据进行了处理。
首先是p1.py.我使用tkinter包实现了简单的打点界面。具体代码如下：

from tkinter import *
import random

canvas_width = 1000
canvas_height = 500

def paint(event):
    python_green = "#476042"
    x1, y1 = (event.x - 1), (event.y - 1)
    x2, y2 = (event.x + 1), (event.y + 1)
    w.create_oval(x1, y1, x2, y2, fill=python_green)
    points.append((event.x, event.y))

def distance(x, y):
    sum = 0
    for i in range(len(x)):
        sum += (x[i] - y[i]) ** 2
    ans = sum ** 0.5
    return ans

def k_means(event):

    point = points.copy()
    group_num = int(ju_num.get())

    if len(point) < group_num:
        hint_str.set('您的点个数比分类数还少！请检查输入是否有误')
        return

    center = []

    for i in range(group_num):
        center = random.sample(point, group_num)

    new_center = []

    times = 0
    while times < 50 and center != new_center:

        if times != 0:
            center = new_center.copy()
            new_center = []
        times += 1

        print(center)

        groups = []
        for x in center:
            groups.append([])

        for p in point:
            distances = []
            for i in center:
                distances.append(distance(p, i))
            groups[distances.index(min(distances))].append(p)

        for group in groups:
            sum_x = 0
            sum_y = 0
            for i in group:
                sum_x += i[0]
                sum_y += i[1]
            try:
                new_center.append((sum_x / len(group), sum_y / len(group)))
            except ZeroDivisionError:
                print('分组出现空，计算可能有误')
                new_center.append((canvas_width / 2, canvas_height / 2))

    for i in new_center:
        x1, y1 = (i[0] - 3), (i[1] - 3)
        x2, y2 = (i[0] + 3), (i[1] + 3)
        w.create_oval(x1, y1, x2, y2, fill="#00FF7F")

    hint_str.set('聚类中心已计算并标出！')
    button['state'] = DISABLED

if __name__ == '__main__':
    points = []

    root = Tk()
    root.title("K-means聚类算法演示系统")
    w = Canvas(root, width=canvas_width, height=canvas_height)
    w.pack(expand=YES, fill=BOTH)

    w.bind("", paint)

    hint_str = StringVar()
    hint_str.set('点击窗口任意位置以绘制点')
    hint = Label(root, textvariable=hint_str)
    hint.pack(side=TOP)

    bottom_frame = Frame(root)
    bottom_frame.pack(side=BOTTOM)
    message = Label(bottom_frame, text="请输入最终的聚类数目：")
    message.grid(column=0, row=0)
    ju_num = StringVar()
    ju_num.set('3')
    entry = Entry(bottom_frame, textvariable=ju_num)
    entry.grid(column=1, row=0)
    button = Button(bottom_frame, text='K-means!')
    button.grid(column=2, row=0)
    button.bind('', k_means)

    mainloop()

然后是p2.py.我使用PIL包读取了源文件同目录下的trump.jpeg，经过处理后将结果输出在同目录下的result.jpg中。具体代码如下：

from PIL import Image
import numpy as np
import random

def write_image(array, path):
    img = Image.fromarray(array)
    img.save(path)

def distance(x, y):
    sum = 0
    for i in range(len(x)):
        sum += (int(x[i]) - int(y[i])) ** 2
    ans = sum ** 0.5
    return ans

def k_means(pic_array, group_num):

    line_num = 0
    col_num = 0
    array = []
    for line in pic_array:
        line_num += 1
        for col in line:
            if line_num == 1:
                col_num += 1
            array.append([col[0], col[1], col[2]])

    center = []

    for i in range(group_num):
        center = random.sample(array, group_num)
    print(center)

    new_center = []

    times = 0
    while times < 50 and center != new_center:

        if times != 0:
            center = new_center.copy()
            new_center = []
        times += 1

        print(center)

        groups = []
        for x in center:
            groups.append([])

        for p in array:
            distances = []
            for i in center:
                distances.append(distance(p, i))
            groups[distances.index(min(distances))].append(p)

        for group in groups:
            sum_r = 0
            sum_g = 0
            sum_b = 0
            for i in group:
                sum_r += i[0]
                sum_g += i[1]
                sum_b += i[2]
            try:
                new_center.append([sum_r / len(group), sum_g / len(group), sum_b / len(group)])
            except ZeroDivisionError:
                print('分组出现空，计算可能有误')
                new_center.append([100, 100, 100])

    for line in pic_array:
        for col in line:
            distances = []
            for i in new_center:
                distances.append(distance(col, i))
            index = distances.index(min(distances))

            col[0] = int(new_center[index][0])
            col[1] = int(new_center[index][1])
            col[2] = int(new_center[index][2])

    print('k—means已完成')
    return pic_array

if __name__ == '__main__':
    image_path = 'trump.jpeg'
    image = Image.open(image_path)
    image_array = np.array(image)

    group_num = int(input('分组数:'))

    new_array = k_means(image_array, group_num)
    print('生成图片输出中...')
    write_image(new_array, 'result.jpg')
    print('输出完成')

实验结果

Original: https://blog.csdn.net/xiangQiAtCSDN/article/details/117434009
Author: ChessZH
Title: 数据挖掘实验二：K-means算法及其应用（Python实现）