利用python实现K-Means聚类算法

版权声明：本文为博主原创文章，若需转载，请注明http://blog.csdn.net/qq_30091945 https://blog.csdn.net/qq_30091945/article/details/82184489

前言

K-Means聚类算法学习笔记请移步：斯坦福机器学习笔记（六）——K-Means聚类算法。同时本篇博客的PDF笔记请移步：K-Means聚类算法。

---

K-Means聚类Pyhon核心代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/8/2910:38
# @Author  : DaiPuWei
# E-Mail   : [email protected]
# @Site    : 
# @File    : KMeans.py
# @Software: PyCharm

import numpy as np

class KMeans:
    def __init__(self,train_data,k):
        """
        K-Means聚类算法的构造函数
        :param train_data: 训练数据
        :param k: 聚类簇数
        """
        self.Train_Data = train_data
        self.K = k
        row,col = np.shape(train_data)
        self.Label = np.array([0]*row)
        self.centroids = np.zeros((k,col))             # 质心坐标
        # 初始化质心坐标
        for i in range(col):
            Min = np.min(self.Train_Data[:,i])
            Max = np.max(self.Train_Data[:,i])
            self.centroids[:,i] = Min+float(Max-Min)*np.random.rand(k)

    def EcludDistance(self,dataA,dataB):
        """
        计算欧式距离
        :param dataA: 数据A
        :param dataB: 数据B
        """
        return np.sqrt(np.sum((dataA-dataB)**2))

    def kmeans(self):
        """
        这是进行K-Means聚类算法的函数
        """
        dist = 0
        olddist = 1
        row,col = np.shape(self.Train_Data)
        while np.abs(dist-olddist) > 1E-6:
            olddist = dist
            # 更新每组训练数据的标签
            for i in range(row):
                dist = []
                # 计算一组数据与质心之间的距离
                for j in range(self.K):
                    dist.append(self.EcludDistance(self.Train_Data[i],self.centroids[j])**2)
                self.Label[i] = np.argmin(dist)
            # 更新聚类质心的坐标
            for i in range(self.K):
                cluster_data = self.Train_Data[self.Label == i]
                size = len(cluster_data)
                self.centroids[i] = np.sum(cluster_data,0)/size
            # 计算距离函数
            dist = 0
            for (data,label) in zip(self.Train_Data,self.Label):
                dist += self.EcludDistance(data,self.centroids[label])**2
        return self.Label,self.centroids

---

实验结果代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/8/2911:18
# @Author  : DaiPuWei
# E-Mail   : [email protected]
# @Site    : 
# @File    : demo.py
# @Software: PyCharm

from KMeans import KMeans
from sklearn.preprocessing import MinMaxScaler
from sklearn.cluster import KMeans as _KMeans
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt

def run_main():
    """
       这是主函数
    """
    # 导入Iris数据集
    iris = load_iris()
    label = np.array(iris.target)
    data = np.array(iris.data)

    # 对数据进行预处理
    data = MinMaxScaler().fit_transform(data)

    # 解决画图是的中文乱码问题
    mpl.rcParams['font.sans-serif'] = [u'simHei']
    mpl.rcParams['axes.unicode_minus'] = False

    # 执行K-Means聚类算法
    k = 3
    color = ['r','g','b']
    kmeans = KMeans(data,k)
    predict_label,centroids = kmeans.kmeans()
    print("手写K-Means聚类算法的准确率：%f"%(accuracy_score(label,predict_label)))
    for i in range(k):
        plt.scatter(centroids[i][2],centroids[i][3],c=color[i],marker='x',s=40)
    for (_data,_label) in zip(data,predict_label):
        plt.scatter(_data[2], _data[3], color=color[_label],alpha=0.3)
    plt.show()

    # sklearn的KMeans
    k = 3
    kmeans = _KMeans(n_clusters=k,max_iter=1000)
    kmeans.fit(data,label)
    predict_label = kmeans.predict(data)
    centroids = kmeans.cluster_centers_
    color = ['r', 'g', 'b']
    print("sklearn的K-Means聚类算法的准确率：%f" % (accuracy_score(label, predict_label)))
    for i in range(k):
        plt.scatter(centroids[i][2], centroids[i][3], c=color[i], marker='x', s=40)
    for (_data, _label) in zip(data, predict_label):
        plt.scatter(_data[2], _data[3], color=color[_label],alpha=0.3)
    plt.show()

if __name__ == '__main__':
    run_main()

---

实验结果

上述的程序利用K-Means聚类算法对鸢尾花数据进行聚类，计算了聚类后的分类准确率。实验数据表明，实验结果对质心的初始位子比较敏感。下面是两组不同的是实验结果。
实验一：

手写K-Means的数据可视化：

sklearn的K-Means的数据可视化：

---

实验二：

手写K-Means的数据可视化：

sklearn的K-Means的数据可视化：