Python：相對標準的DPC

import numpy as np
import pandas as pd
import copy
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn import metrics
from scipy.spatial.distance import pdist,squareform
from collections import OrderedDict
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import scipy.io as scio

############%%%%%%-------------------%%%%%%%%%############

############%%%%%%-------------------%%%%%%%%%############

#--------獲取截斷距離的函數：沒有問題-----------#
def getDistCut(distList,distPercent):
    maxDist = max(distList)
    distCut = maxDist * distPercent / 100
    return distCut
#--------獲取樣本密度的函數：沒有問題-----------#
def getRho(n,distMatrix,distCut):
    rho = np.zeros(n,dtype=float)
    for i in range(n-1):
        for j in range(i+1,n):
            if distMatrix[i,j] < distCut:
                rho[i] += 1
                rho[j] += 1
    return rho

def getGammaOrderIndex(n,rho,distMatrix):
    rhoOrdIndex = np.flipud(np.argsort(rho))
    delta = np.zeros(n,dtype=float)
    leader = np.ones(n,dtype=int) * (-1)
    #-----------獲取塊密度最大點的Delta----------------#
    maxdist = 0
    for i in range(n):
        if distMatrix[rhoOrdIndex[0],i] > maxdist:
            maxdist = distMatrix[rhoOrdIndex[0],i]
    delta[rhoOrdIndex[0]] = maxdist
    leader[rhoOrdIndex[0]] = -1
    # -----------獲取非密度最大點的Delta----------------#
    for i in range(1,n):
        mindist = np.inf
        minindex = -1
        for j in range(i):
            if distMatrix[rhoOrdIndex[i],rhoOrdIndex[j]] < mindist:
                mindist = distMatrix[rhoOrdIndex[i],rhoOrdIndex[j]]
                minindex = rhoOrdIndex[j]
        delta[rhoOrdIndex[i]] = mindist
        leader[rhoOrdIndex[i]] = minindex
    gamma = delta * rho
    gammaOrderIndex = np.flipud(np.argsort(gamma))
    return rhoOrdIndex,gamma,gammaOrderIndex,leader

def getDPCA(n,rhoOrdIndex,gammaOrderIndex,leader,blockNum):
    #-----------初始化樣本類簇索引----------------------#
    clusterIndex = np.ones(n,dtype=int) * (-1)
    # --------給聚類中心分配簇標籤----------------------#
    for i in range(blockNum):
        clusterIndex[gammaOrderIndex[i]] = i
    #---------開始聚類---------------------------------#
    for i in range(n):
        if clusterIndex[rhoOrdIndex[i]] == -1:
            clusterIndex[rhoOrdIndex[i]] = clusterIndex[leader[rhoOrdIndex[i]]]
    ##-------------初始化一個空字典，用於存儲類簇---------------##
    clusterSet = OrderedDict()
    #--------字典初始化，使用列表存儲類簇-----------#
    for i in range(blockNum):
        clusterSet[i] = []
    #---將每個樣本根據類簇標號分配到字典當中---#
    for i in range(n):
        clusterSet[clusterIndex[i]].append(i)
    return clusterSet

if __name__ == '__main__':
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Glass\glass.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Spiral\spiral.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Aggregation（788）\aggregation.csv', header=None))
    X = data[:, :-1]
    y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Three blobs\ThreeBlobs.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\COIL-20\COIL20_PCA.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Banknote\banknote.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # pca = PCA(0.9)
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Semeion\semeion.csv', header=None))
    # X = data[:, :-1]
    # X = pca.fit_transform(X)
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Robot Navigation（5456）\Robot_Navigation_24.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Twonorm\twonorm.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Electrical Grid Stability Simulated Data Data Set\ELectricalGrid.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Pendigits\pendigits.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\HTRU2 Data Set\HTRU_2.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Avila\avila.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\1-Dataset for Sensorless Drive Diagnosis(58509)\Sensorless_drive_diagnosis.csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # data = np.array(pd.read_csv(r'E:\dataset\ExperimentalData\Satlog(shuttle)\Satlog(shuttle).csv', header=None))
    # X = data[:, :-1]
    # y = data[:, -1]
    # --------------------------------------#
    # mnist = fetch_mldata('MNIST original')
    # X = mnist['data']
    # y = mnist['target']
    # --------------------------------------#
    # X, y = fetch_covtype(return_X_y=True)
    #################上面是數據##########################
    n = X.shape[0]
    classNum = len(set(y))
    blockNum = 7
    distList = pdist(X, metric='cityblock')
    distMatrix = squareform(distList)
    distCut = getDistCut(distList,distPercent=7)
    rho = getRho(n,distMatrix,distCut)
    rhoOrdIndex, gamma, gammaOrderIndex, leader = getGammaOrderIndex(n,rho,distMatrix)
    clusterSet = getDPCA(n, rhoOrdIndex, gammaOrderIndex, leader, blockNum)

    budget = 50
    for k,v in clusterSet.items():
        E = X[v]
        plt.scatter(E[:,0],E[:,1])
    plt.show()

使用類封裝 

import numpy as np
import pandas as pd
import copy
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn import metrics
from scipy.spatial.distance import pdist, squareform
from collections import OrderedDict
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import scipy.io as scio


############%%%%%%-------------------%%%%%%%%%############

############%%%%%%-------------------%%%%%%%%%############
class DPC(object):
    def __init__(self,X,clusterNum,distPercent):
        self.X = X
        self.N = X.shape[0]
        self.clusterNum = clusterNum
        self.distPercent = distPercent
        self.distCut = 0
        self.rho = np.zeros(self.N,dtype=float)
        self.delta = np.zeros(self.N,dtype=float)
        self.gamma = np.zeros(self.N,dtype=float)
        self.leader = np.ones(self.N,dtype=int) * int(-1)
        self.distList = pdist(self.X,metric='euclidean')
        self.distMatrix = squareform(self.distList)
        self.clusterIdx = np.ones(self.N,dtype=int) * (-1)

    def getDistCut(self):
        maxDist = max(self.distList)
        distCut = maxDist * self.distPercent /100
        return distCut

    def getRho(self):
        self.distCut = self.getDistCut()
        rho = np.zeros(self.N, dtype=float)
        for i in range(self.N -1):
            for j in range(i+1,self.N):
                if self.distMatrix[i,j] < self.distCut:
                    rho[i] += 1
                    rho[j] += 1
        return rho
    def getGammaOrderIndex(self):
        self.rho = self.getRho()
        rhoOrdIndex = np.flipud(np.argsort(self.rho))
        # -----------獲取塊密度最大點的Delta----------------#
        maxdist = 0
        for i in range(self.N):
            if self.distMatrix[rhoOrdIndex[0], i] > maxdist:
                maxdist = self.distMatrix[rhoOrdIndex[0], i]
        self.delta[rhoOrdIndex[0]] = maxdist
        self.leader[rhoOrdIndex[0]] = -1
        # -----------獲取非密度最大點的Delta----------------#
        for i in range(1, self.N):
            mindist = np.inf
            minindex = -1
            for j in range(i):
                if self.distMatrix[rhoOrdIndex[i], rhoOrdIndex[j]] < mindist:
                    mindist = self.distMatrix[rhoOrdIndex[i], rhoOrdIndex[j]]
                    minindex = rhoOrdIndex[j]
            self.delta[rhoOrdIndex[i]] = mindist
            self.leader[rhoOrdIndex[i]] = minindex
        self.gamma = self.delta * self.rho
        gammaOrderIndex = np.flipud(np.argsort(self.gamma))
        return gammaOrderIndex,rhoOrdIndex
    def getDPC(self):
        gammaOrderIndex,rhoOrdIndex = self.getGammaOrderIndex()
        # -----------給聚類中心分配簇標籤------------------#
        for i in range(self.clusterNum):
            self.clusterIdx[gammaOrderIndex[i]] = i
        # --------開始聚類-----------------------#
        for i in range(self.N):
            if self.clusterIdx[rhoOrdIndex[i]] == -1:
                self.clusterIdx[rhoOrdIndex[i]] = self.clusterIdx[self.leader[rhoOrdIndex[i]]]
        ##-------------初始化一個空字典，用於存儲類簇---------------##
        clusterSet = OrderedDict()
        # --------字典初始化，使用列表存儲類簇-----------#
        for i in range(self.clusterNum):
            clusterSet[i] = []
        # ---將每個樣本根據類簇標號分配到字典當中---#
        for i in range(self.N):
            clusterSet[self.clusterIdx[i]].append(i)
        return clusterSet

if __name__ == '__main__':
    # --------------------------------------#
    data = np.array(pd.read_csv(r'D:\牛牛\ExperimentalData\Aggregation\aggregation.csv', header=None))
    X = data[:, :-1]
    y = data[:, -1]
    dpc = DPC(X,clusterNum=7,distPercent=7)
    clusterSet = dpc.getDPC()

    budget = 50
    for k, v in clusterSet.items():
        E = X[v]
        plt.scatter(E[:, 0], E[:, 1])
    plt.show()

使用了類封裝（並基於KNN方式確定截斷距離）代碼如下：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections import OrderedDict
from scipy.spatial.distance import pdist,squareform


class DPCA(object):
    def __init__(self,X,neighborNum,blockNum):
        self.X = X
        self.N = X.shape[0]
        self.K = neighborNum
        self.blockNum = blockNum
        self.distCut = 0
        self.rho = np.zeros(self.N,dtype=float)
        self.delta = np.zeros(self.N,dtype=float)
        self.gamma = np.zeros(self.N,dtype=float)
        self.leader = np.ones(self.N,dtype=int) * int(-1)
        self.distMatrix = squareform(pdist(self.X,metric='euclidean'))
        self.clusterIdx = np.ones(self.N,dtype=int) * (-1)
    def get_distCut(self):
        deltaK = np.zeros(self.N,dtype=float)
        for i in range(self.N):
            ordIdx = np.argsort(self.distMatrix[i])
            deltaK[i] = self.distMatrix[i][ordIdx[self.K+1]]
        miuK = np.mean(deltaK)
        tempSum = 0
        for i in range(self.N):
            tempSum += (deltaK[i] - miuK)**2
        self.distCut = miuK + np.sqrt(tempSum/(self.N-1))
    def get_Rho(self):
        for i in range(self.N-1):
            for j in range(i+1,self.N):
                self.rho[i] = self.rho[i] + np.exp(-(self.distMatrix[i,j]/self.distCut)**2)
                self.rho[j] = self.rho[j] + np.exp(-(self.distMatrix[i,j]/self.distCut)**2)
    def DPCA(self):
        rhoOrdIndex = np.flipud(np.argsort(self.rho))
        maxdist = 0
        for ele in range(self.N):
            if self.distMatrix[rhoOrdIndex[0],ele]>maxdist:
                maxdist = self.distMatrix[rhoOrdIndex[0],ele]
        self.delta[rhoOrdIndex[0]] = maxdist

        for i in range(1,self.N):
            mindist = np.inf
            minindex = -1
            for j in range(i):
                if self.distMatrix[rhoOrdIndex[i],rhoOrdIndex[j]] < mindist:
                    mindist = self.distMatrix[rhoOrdIndex[i],rhoOrdIndex[j]]
                    minindex = rhoOrdIndex[j]
            self.delta[rhoOrdIndex[i]] = mindist
            self.leader[rhoOrdIndex[i]] = minindex
        self.gamma = self.delta * self.rho
        gammaOrdIdx = np.flipud(np.argsort(self.gamma))
        # 初始化聚類中心
        for k in range(self.blockNum):
            self.clusterIdx[gammaOrdIdx[k]] = k
        # 對中心點以外樣本進行聚類
        for i in range(self.N):
            if self.clusterIdx[rhoOrdIndex[i]] == -1:
                self.clusterIdx[rhoOrdIndex[i]] = self.clusterIdx[self.leader[rhoOrdIndex[i]]]
        clusterSet = OrderedDict()
        for k in range(self.blockNum):
            clusterSet[k] = []
        for i in range(self.N):
            clusterSet[self.clusterIdx[i]].append(i)
        return clusterSet

if __name__ == '__main__':
    # ----------------Aggregation(neighborNum=3)----------------------#
    data = np.array(pd.read_csv(r'D:\牛牛\ExperimentalData\Aggregation\aggregation.csv', header=None))
    X = data[:, :-1]
    y = data[:, -1]
    neighborNum = 10
    blockNum = 7
    dpc = DPCA(X,neighborNum,blockNum)
    dpc.get_distCut()
    dpc.get_Rho()
    clusterSet = dpc.DPCA()
    for v in clusterSet.values():
        E = X[v]
        plt.scatter(E[:,0],E[:,1])
    plt.show()