KMeans聚类算法

一、fit_predict()

 def fit_predict(self, X, y=None):        """Compute cluster centers and predict cluster index for each sample.        Convenience method; equivalent to calling fit(X) followed by        predict(X).        """        return self.fit(X).labels_

def fit_predict(data)
                       data=文件所有数据

返回每个数据对应的标签，并将标签值对应到相应的簇。

    def fit(self, X, y=None):        """Compute k-means clustering.

计算簇中心。

 def predict(self, X):        """Predict the closest cluster each sample in X belongs to.

predict:指定x中每个点所属于的簇的位置。

***KMeans计算方法：

默认采用欧氏距离：

double getDistXY(const Tuple& t1, const Tuple& t2)   {      double sum = 0;      for(int i=1; i<=dimNum; ++i)      {          sum += (t1[i]-t2[i]) * (t1[i]-t2[i]);      }      return sqrt(sum);  } 

kMeans代码解析笔记

import numpy as npfrom sklearn.cluster import KMeansdef loadData(fileName):    fr=open(fileName,'r+')    lines=fr.readlines()    cityName=[]    data=[]    for line in lines:        items=line.strip().split(',')        cityName.append(items[0])        data.append([float(items[i]) for i in range(1,len(items))])#添加成为二维数组。里面一层数组外面再包一层括号    return data,cityNameif __name__=="__main__":    #加载文件数据代码引用函数    data,cityName=loadData('city.txt')    km=KMeans(n_clusters=4)    label=km.fit_predict(data)#返回的label更像是city的分身，而这些分身经过计算已经分类到四个簇中，本身值等于簇的值。    expenses=np.sum(km.cluster_centers_,axis=1)#横向计算每个城市的总开销，并把它归类到相应的簇里面。然后对每个簇进行求平均数。得到expense[i]i从0到3    print(expenses)    CityCluster=[[],[],[],[]]    for i in range(len(cityName)):        CityCluster[label[i]].append(cityName[i])    for i in range(4):        print('Expense:%.2f'%expenses[i])        print(CityCluster[i])