机器学习之聚类算法Kmeans及其应用，调用sklearn中聚类算法以及手动实现Kmeans算法。

文章目录

• 实现Kmeans算法实现聚类
  *
• 读取文件
• 手动实现Kmeans算法
• 处理数据
• 绘制数据散点图
• 绘制聚类中心
• 调用sklearn中聚类算法
• 绘制k-Means聚类结果
• 对比效果：
• 整合代码：

; 实现Kmeans算法实现聚类

要求：
1、根据算法流程，手动实现Kmeans算法；
2、调用sklearn中聚类算法，对给定数据集进行聚类分析；
3、对比上述2中Kmeans算法的聚类效果。

读取文件

def loadFile(path):
    dataList = []

    fr = open(path,"r",encoding='UTF-8')
    record = fr.read()
    fr.close

    recordList = record.splitlines()

    for line in recordList:
         if line.strip():
             dataList .append(list(map(float, line.split('\t'))))

    recordmat = np.mat(dataList )
    return recordmat

手动实现Kmeans算法

def kMeans(dataset, k):
    m = np.shape(dataset)[0]
    ClustDist = np.mat(np.zeros((m, 2)))
    cents = randCents(dataset, k)
    clusterChanged = True

    while clusterChanged:
        clusterChanged = False
        for i in range(m):
            DistList = [distEclud(dataset[i, :], cents[jk,:]) for jk in range(k)]
            minDist = min(DistList)
            minIndex = DistList.index(minDist)

            if ClustDist[i, 0] != minIndex:
                clusterChanged = True
            ClustDist[i, :] = minIndex, minDist

        for cent in range(k):
            ptsInClust = dataset[np.nonzero(ClustDist[:, 0].A == cent)[0]]

            cents[cent, :] = np.mean(ptsInClust, axis=0)

    return cents, ClustDist

处理数据

path_file = "TESTDATA.TXT"
recordMat = loadFile(path_file)
k = 4

cents, distMat = kMeans(recordMat, k)

绘制数据散点图

plt.subplot(311)
plt.grid(True)
for indx in range(len(distMat)):
    if distMat[indx, 0] == 0:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='red', marker='o')
    if distMat[indx, 0] == 1:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='blue', marker='o')
    if distMat[indx, 0] == 2:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='cyan', marker='o')
    if distMat[indx, 0] == 3:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='green', marker='o')

绘制聚类中心

x = [cents[i,0] for i in range(k)]
y = [cents[i,1] for i in range(k)]
plt.scatter(x, y, s = 80, c='yellow', marker='o')
plt.title('Kmeans')

调用sklearn中聚类算法

from sklearn.cluster import KMeans
X = np.array(recordMat)

kmeans_model = KMeans(n_clusters=k, init='random')
kmeans_model.fit(X)

绘制k-Means聚类结果

plt.subplot(312)
plt.axis([np.min(X[:,0])-1, np.max(X[:,0]+1), np.min(X[:,1])-1, np.max(X[:,1])+1])
plt.grid(True)

colors = ['r', 'g', 'b','c']
markers = ['o', 's', 'D', '+']
for i, l in enumerate(kmeans_model.labels_):
    plt.plot(X[i][0], X[i][1], color=colors[l],marker=markers[l],ls='None')
    plt.title('K = %s,random' %(k))

对比效果：

; 整合代码：

import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

def loadFile(path):
    dataList = []

    fr = open(path,"r",encoding='UTF-8')
    record = fr.read()
    fr.close

    recordList = record.splitlines()

    for line in recordList:
         if line.strip():
             dataList .append(list(map(float, line.split('\t'))))

    recordmat = np.mat(dataList )
    return recordmat

def distEclud(vecA, vecB):
    return np.linalg.norm(vecA-vecB, ord=2)

def randCents(dataSet, k):
    n = np.shape(dataSet)[1]
    cents = np.mat(np.zeros((k,n)))
    for j in range(n):

        minCol = min(dataSet[:,j])
        maxCol = max(dataSet[:,j])

        cents [:,j] = np.mat(minCol + float(maxCol - minCol) * np.random.rand(k,1))
    return cents

def kMeans(dataset, k):
    m = np.shape(dataset)[0]
    ClustDist = np.mat(np.zeros((m, 2)))
    cents = randCents(dataset, k)
    clusterChanged = True

    while clusterChanged:
        clusterChanged = False
        for i in range(m):
            DistList = [distEclud(dataset[i, :], cents[jk,:]) for jk in range(k)]
            minDist = min(DistList)
            minIndex = DistList.index(minDist)

            if ClustDist[i, 0] != minIndex:
                clusterChanged = True
            ClustDist[i, :] = minIndex, minDist

        for cent in range(k):
            ptsInClust = dataset[np.nonzero(ClustDist[:, 0].A == cent)[0]]

            cents[cent, :] = np.mean(ptsInClust, axis=0)

    return cents, ClustDist

path_file = "TESTDATA.TXT"
recordMat = loadFile(path_file)
k = 4

cents, distMat = kMeans(recordMat, k)

plt.subplot(311)
plt.grid(True)
for indx in range(len(distMat)):
    if distMat[indx, 0] == 0:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='red', marker='o')
    if distMat[indx, 0] == 1:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='blue', marker='o')
    if distMat[indx, 0] == 2:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='cyan', marker='o')
    if distMat[indx, 0] == 3:
        plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='green', marker='o')

x = [cents[i,0] for i in range(k)]
y = [cents[i,1] for i in range(k)]
plt.scatter(x, y, s = 80, c='yellow', marker='o')
plt.title('Kmeans')

X = np.array(recordMat)

plt.subplot(312)
plt.axis([np.min(X[:,0])-1, np.max(X[:,0]+1), np.min(X[:,1])-1, np.max(X[:,1])+1])
plt.grid(True)

colors = ['r', 'g', 'b','c']
markers = ['o', 's', 'D', '+']

kmeans_model = KMeans(n_clusters=k, init='random')
kmeans_model.fit(X)

for i, l in enumerate(kmeans_model.labels_):
    plt.plot(X[i][0], X[i][1], color=colors[l],marker=markers[l],ls='None')
    plt.title('K = %s,random' %(k))

X = np.array(recordMat)

plt.subplot(313)
plt.axis([np.min(X[:,0])-1, np.max(X[:,0]+1), np.min(X[:,1])-1, np.max(X[:,1])+1])
plt.grid(True)

colors = ['r', 'g', 'b','c']
markers = ['o', 's', 'D', '+']
kmeans_model = KMeans(n_clusters=k, init='k-means++')

kmeans_model.fit(X)

for i, l in enumerate(kmeans_model.labels_):
    plt.plot(X[i][0], X[i][1], color=colors[l],marker=markers[l],ls='None')
    plt.title('K = %s,k-means++' %(k))

plt.show()

Original: https://blog.csdn.net/qq_46556714/article/details/124893860
Author: 南蓬幽
Title: 机器学习之聚类算法Kmeans及其应用，调用sklearn中聚类算法以及手动实现Kmeans算法。