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 = []
#打开文件：以二进制读模式、utf-8格式的编码方式 打开
fr = open(path,"r",encoding='UTF-8')
record = fr.read()
fr.close
#按照行转换为一维表即包含各行作为元素的列表，分隔符有'\r', '\r\n', \n'
recordList = record.splitlines()
#逐行遍历：行内字段按'\t'分隔符分隔，转换为列表
for line in recordList:
if line.strip():
dataList .append(list(map(float, line.split('\t'))))
#返回转换后的矩阵
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
# 循环迭代，得到最近的聚类中心
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
# 更新聚类
for cent in range(k):
ptsInClust = dataset[np.nonzero(ClustDist[:, 0].A == cent)[0]]
# 更新聚类中心cents，axis=0按列求均值
cents[cent, :] = np.mean(ptsInClust, axis=0)
# 返回聚类中心和聚类分配矩阵
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)# 生成网格
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')
#if distMat[indx, 0] == 4:
#plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='black', 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) # 生成初始聚类数据
#kmeans_model = KMeans(n_clusters=k, init='k-means++') # 聚类模型
kmeans_model = KMeans(n_clusters=k, init='random') # 聚类模型
kmeans_model.fit(X) # 训练聚类模型
绘制k-Means聚类结果
# plt.figure()# 创建窗口
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])# 坐标轴
plt.grid(True)# 生成网格
colors = ['r', 'g', 'b','c'] # 聚类颜色
markers = ['o', 's', 'D', '+'] # 聚类标志
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 = []
#打开文件：以二进制读模式、utf-8格式的编码方式 打开
fr = open(path,"r",encoding='UTF-8')
record = fr.read()
fr.close
#按照行转换为一维表即包含各行作为元素的列表，分隔符有'\r', '\r\n', \n'
recordList = record.splitlines()
#逐行遍历：行内字段按'\t'分隔符分隔，转换为列表
for line in recordList:
if line.strip():
dataList .append(list(map(float, line.split('\t'))))
#返回转换后的矩阵
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):
#质心必须在数据集范围内，也就是在min到max之间
minCol = min(dataSet[:,j])
maxCol = max(dataSet[:,j])
#利用随机函数生成0到1.0之间的随机数
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
# 循环迭代，得到最近的聚类中心
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
# 更新聚类
for cent in range(k):
ptsInClust = dataset[np.nonzero(ClustDist[:, 0].A == cent)[0]]
# 更新聚类中心cents，axis=0按列求均值
cents[cent, :] = np.mean(ptsInClust, axis=0)
# 返回聚类中心和聚类分配矩阵
return cents, ClustDist
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)# 生成网格
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')
#if distMat[indx, 0] == 4:
#plt.scatter(recordMat[indx, 0], recordMat[indx, 1], c='black', 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')
X = np.array(recordMat) # 生成初始聚类数据
# plt.figure()# 创建窗口
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])# 坐标轴
plt.grid(True)# 生成网格
colors = ['r', 'g', 'b','c'] # 聚类颜色
markers = ['o', 's', 'D', '+'] # 聚类标志
#kmeans_model = KMeans(n_clusters=k, init='k-means++') # 聚类模型
kmeans_model = KMeans(n_clusters=k, init='random') # 聚类模型
kmeans_model.fit(X) # 训练聚类模型
# 绘制k-Means聚类结果
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) # 生成初始聚类数据
# plt.figure()# 创建窗口
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])# 坐标轴
plt.grid(True)# 生成网格
colors = ['r', 'g', 'b','c'] # 聚类颜色
markers = ['o', 's', 'D', '+'] # 聚类标志
kmeans_model = KMeans(n_clusters=k, init='k-means++') # 聚类模型
# kmeans_model = KMeans(n_clusters=k, init='random') # 聚类模型
kmeans_model.fit(X) # 训练聚类模型
# 绘制k-Means聚类结果
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()
