def clusterCore(channelData1, covMatrixList1, channelData2, centroids, centroidUList, type):
newChannelData1 = []
newChannelData2 = []
newDimension = np.shape(centroidUList[0])[1]
if type == "C":
# 计算信道相关系数矩阵并输出，然后放到一个矩阵中
allCovMatrix1 = tools.matrixListToMatrix(covMatrixList1)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment(allCovMatrix1, centroids)
# 变换域
for i in range(np.shape(channelDataAll1)[0]):
newChannelData1.append(np.dot(channelData1[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
newChannelData2.append(np.dot(channelData2[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
if type == "general":
newChannelData1 = pca.pca_general(channelData1, newDimension)
newChannelData2 = pca.pca_general(channelData2, newDimension)
if type == "none":
newChannelData1 = channelData1
newChannelData2 = channelData2
if type == "wt":
# 变换域
for i in range(np.shape(channelData1)[0]):
newChannelData1.append(wt.wt(channelData1[i], newDimension))
newChannelData2.append(wt.wt(channelData2[i], newDimension))
return newChannelData1, newChannelData2
def elbowCore(channelDataAll, a, k, iRate, schedule):
n = np.shape(channelDataAll[0])[1] # 列数
p = len(channelDataAll) # 页数
sub = n >> a
rates_C = []
rates_U = []
rates_S = []
for g in range(1 << a):
# 显示进度
schedule[1] += 1
tmpSchedule = schedule[1]
print(u'共' + str(schedule[0]) + u'部分，' + u'第' + str(tmpSchedule) + u'部分开始！')
channelData = []
for h in range(p):
channelDataPage = channelDataAll[h]
channelData.append(channelDataPage[:, g * sub:(g + 1) * sub])
covMatrixList = tools.getCovMatrixList(channelData)
allCovMatrix = tools.matrixListToMatrix(covMatrixList)
# 对协方差进行聚类
centroids, clusterAssment = kmeans.KMeansOushi(allCovMatrix, k)
centroidList = tools.matrixToMatrixList(centroids)
# 计算原信道信息量、协方差矩阵特征值、变换矩阵
informations, SigmaList, UList = tools.getInformations(covMatrixList)
# 分析PCA效果,计算信息量保留程度
tmpRates = pca.pca(channelData, informations, centroidList, clusterAssment, iRate)[3][0][:, 1]
rates_C.append(np.mean(tmpRates))
# 对变换矩阵进行聚类
allU = tools.matrixListToMatrix_U(UList)
weights = tools.matrixListToMatrix_U(SigmaList)
centroids, clusterAssment = kmeans.KMeansOushi_U(allU, k, weights, iRate)
centroidList = tools.matrixToMatrixList_U(centroids)
# 分析PCA效果,计算信息量保留程度
tmpRates = pca.pca_U(channelData, informations, centroidList, clusterAssment, iRate)[3][0][:, 1]
rates_U.append(np.mean(tmpRates))
# 不聚类，直接PCA
tmpRates = pca.pca_S(SigmaList, iRate)[0][:, 1]
rates_S.append(np.mean(tmpRates))
# 显示进度
print(u'共' + str(schedule[0]) + u'部分，' + u'第' + str(tmpSchedule) + u'部分完成，' + u'已完成' + str(schedule[1]) + u'部分，' + u'完成度：' + '%.2f%%' % (schedule[1] / schedule[0] * 100) + u'！')
rate_C = np.mean(rates_C)
rate_U = np.mean(rates_U)
rate_S = np.mean(rates_S)
return rate_S.real, rate_C.real, rate_U.real
def clusterCore(channelData1, covMatrixList1, channelData2, centroids, centroidUList, type):
newChannelData1 = []
newChannelData2 = []
newDimension = np.shape(centroidUList[0])[1]
p = np.shape(channelData1)[0]
if type == "C":
# 计算信道相关系数矩阵并输出，然后放到一个矩阵中
allCovMatrix1 = tools.matrixListToMatrix(covMatrixList1)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment(allCovMatrix1, centroids)
# 变换域
for i in range(p):
newChannelData1.append(np.dot(channelData1[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
newChannelData2.append(np.dot(channelData2[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
if type == "U":
informations, SigmaList, UList = tools.getInformations(covMatrixList1)
allU = tools.matrixListToMatrix_U(UList)
weights = tools.matrixListToMatrix_U(SigmaList)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment_U(allU, weights, centroids, newDimension)
# 变换域
for i in range(p):
newChannelData1.append(np.dot(channelData1[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
newChannelData2.append(np.dot(channelData2[i], centroidUList[(int)(clusterAssment[i, 0].real)]))
if type == "S":
covMatrixList2 = tools.getCovMatrixList(channelData2)
UList1 = tools.getInformations(covMatrixList1)[2]
UList2 = tools.getInformations(covMatrixList2)[2]
iRate = np.shape(centroidUList[0])[1]
# 变换域
for i in range(p):
newChannelData1.append(np.dot(channelData1[i], UList1[i][:, 0:iRate]))
newChannelData2.append(np.dot(channelData2[i], UList2[i][:, 0:iRate]))
# 输出处理后的信道数据
# path = u'/Users/jinruimeng/Downloads/keyan/'
# nowTime = time.strftime("%Y-%m-%d.%H.%M.%S", time.localtime(time.time()))
# pathSuffix = type + "_" + slice + "_" + nowTime
#
# outNewChannel1ListPath = path + "clusterAddNoise_outNewChannel1List_" + pathSuffix
# outNewChannel2ListPath = path + "clusterAddNoise_outNewChannel2List_" + pathSuffix
# readAndWriteDataSet.write(newChannelData1, outNewChannel1ListPath, ".xlsx")
# readAndWriteDataSet.write(newChannelData2, outNewChannel2ListPath, ".xlsx")
return newChannelData1, newChannelData2
def readCentroids(path, iRate, type, a):
allCentroids = []
allCentroidUList = []
for g in range(1, (1 << a) + 1):
# 读取聚类中心
centroidListPath = path + u'getCentroids_outCentroidList_' + type + u'_' + str(
g) + u'_'
# 合并多个文件
centroidList_g = []
UList_g = []
for root, dirs, files in os.walk(path, topdown=True):
for file in files:
file = os.path.join(root, file)
if centroidListPath in file:
centroidListTmp = excelToMatrixList(file)
for centroid in centroidListTmp:
centroidList_g.append(centroid)
break
# 计算聚类中心的变换矩阵
if u'C' == type:
for i in range(len(centroidList_g)):
U, Sigma, VT = np.linalg.svd(centroidList_g[i])
sum = np.sum(Sigma)
curSum = 0
if iRate <= 1:
index = 0
for j in range(len(Sigma)):
curSum += Sigma[j]
if iRate - (curSum / sum) > 0:
index += 1
else:
break
else:
index = iRate - 1
U2 = np.transpose(VT[0:index + 1, :])
UList_g.append(U2)
allCentroids.append(tools.matrixListToMatrix(centroidList_g))
allCentroidUList.append(UList_g)
if u'U' == type:
for i in range(len(centroidList_g)):
U2 = centroidList_g[i][:, 0:iRate]
for j in range(np.shape(U2)[1]):
# 噪声功率归一
U2[:, j] = U2[:, j] / np.linalg.norm((U2[:, j]))
UList_g.append(U2)
allCentroids.append(tools.matrixListToMatrix_U(centroidList_g))
allCentroidUList.append(UList_g)
return allCentroids, allCentroidUList
def clusterCore(channelData1, covMatrixList1, channelData2, centroids,
centroidUList, type):
newChannelData1 = []
newChannelData2 = []
newDimension = np.shape(centroidUList[0])[1]
p = np.shape(channelData1)[0]
if type == "C":
# 计算信道相关系数矩阵并输出，然后放到一个矩阵中
allCovMatrix1 = tools.matrixListToMatrix(covMatrixList1)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment(allCovMatrix1, centroids)
# 变换域
for i in range(p):
newChannelData1.append(
np.dot(channelData1[i],
centroidUList[(int)(clusterAssment[i, 0].real)]))
newChannelData2.append(
np.dot(channelData2[i],
centroidUList[(int)(clusterAssment[i, 0].real)]))
if type == "U":
informations, SigmaList, UList = tools.getInformations(covMatrixList1)
allU = tools.matrixListToMatrix_U(UList)
weights = tools.matrixListToMatrix_U(SigmaList)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment_U(allU, weights, centroids,
newDimension)
# 变换域
for i in range(p):
newChannelData1.append(
np.dot(channelData1[i],
centroidUList[(int)(clusterAssment[i, 0].real)]))
newChannelData2.append(
np.dot(channelData2[i],
centroidUList[(int)(clusterAssment[i, 0].real)]))
if type == "general":
newChannelData1 = pca.pca_general(channelData1, newDimension)
newChannelData2 = pca.pca_general(channelData2, newDimension)
if type == "none":
newChannelData1 = channelData1
newChannelData2 = channelData2
allNewCorr = []
for i in range(p):
for j in range(newDimension):
cowCor = np.corrcoef(newChannelData1[i][:, j],
newChannelData2[i][:, j])
if i == 0:
allNewCorr.append(cowCor[0, 1])
else:
allNewCorr[j] += cowCor[0, 1]
for i in range(newDimension):
allNewCorr[i] = abs(allNewCorr[i] / (np.shape(channelData1)[0]))
path = u'/Users/jinruimeng/Downloads/keyan/'
nowTime = time.strftime("%Y-%m-%d.%H.%M.%S", time.localtime(time.time()))
pathSuffix = type + u'_' + nowTime
newChannelData1Path = path + "clusterAddNoise_newChannelData1_" + pathSuffix
newChannelData2Path = path + "clusterAddNoise_newChannelData2_" + pathSuffix
readAndWriteDataSet.write(newChannelData1, newChannelData1Path, ".xlsx")
readAndWriteDataSet.write(newChannelData2, newChannelData2Path, ".xlsx")
return allNewCorr
def getCentroidsCore(path,
suffix,
channelData,
covMatrixList,
informations,
SigmaList,
UList,
g,
k,
iRate,
type="C"):
nowTime = time.strftime("%Y-%m-%d.%H.%M.%S", time.localtime(time.time()))
pathSuffix = type + "_" + str(g) + "_" + nowTime
outOldCovMatrixListPath = path + "getCentroids_outOldCovMatrixList_" + pathSuffix
outCentroidListPath = path + "getCentroids_outCentroidList_" + pathSuffix
outClusterAssmentPath = path + "getCentroids_outClusterAssment_" + pathSuffix
outNewChannelDataPath = path + "getCentroids_outNewChannelData_" + pathSuffix
outNewCovMatrixListPath = path + "getCentroids_outNewCovMatrixList_" + pathSuffix
ratesPath = path + "getCentroids_rates_" + pathSuffix
UTsPath = path + "getCentroids_UTs_" + pathSuffix
clusterAssmentList = []
newChannelData = []
newCovMatrixList = []
UTs = []
rates = []
centroidList = []
if type == u'C':
allCovMatrix = tools.matrixListToMatrix(covMatrixList)
# 对协方差进行聚类
centroids, clusterAssment = kmeans.KMeansOushi(allCovMatrix, k)
clusterAssmentList.append(clusterAssment)
centroidList = tools.matrixToMatrixList(centroids)
# 分析PCA效果
# newChannelData, newCovMatrixList, UTs, rates = pca.pca(channelData, informations, centroidList, clusterAssment, iRate)
if type == u'U':
allU = tools.matrixListToMatrix_U(UList)
weights = tools.matrixListToMatrix_U(SigmaList)
# 对协方差进行聚类
centroids, clusterAssment = kmeans.KMeansOushi_U(
allU, k, weights, iRate)
clusterAssmentList.append(clusterAssment)
centroidList = tools.matrixToMatrixList_U(centroids)
# 分析PCA效果
# newChannelData, newCovMatrixList, UTs, rates = pca.pca_U(channelData, informations, centroidList, clusterAssment, iRate)
# 输出结果
# 输出聚类结果
# readAndWriteDataSet.write(clusterAssmentList, outClusterAssmentPath, suffix)
# 协方差矩阵太大了，先不输出
# readAndWriteDataSet.write(covMatrixList, outOldCovMatrixListPath, suffix)
# 聚类中心太大了，先不输出
readAndWriteDataSet.write(centroidList, outCentroidListPath, suffix)
def cluster(schedule, path, suffix, channelData, g, iRate):
if iRate > np.shape(channelData)[1]:
print(u'降维后维度不能大于样本原有的维度！')
return
if iRate <= 0:
print(u'降维后维度不能小于1！')
return
schedule[1] += 1
tmpSchedule = schedule[1]
print(u'共' + str(schedule[0]) + u'部分，' + u'第' + str(tmpSchedule) +
u'部分开始！')
pathSuffix = "C" + "_" + str(g) + "_"
centroidListPath = path + "getCentroids_outCentroidList_" + pathSuffix
nowTime = time.strftime("%Y-%m-%d.%H.%M.%S", time.localtime(time.time()))
pathSuffix = pathSuffix + str(nowTime)
outOldCovMatrixListPath = path + "cluster_outOldCovMatrixList_" + pathSuffix
outClusterAssmentPath = path + "cluster_outClusterAssment_" + pathSuffix
outNewChannelDataPath = path + "cluster_outNewChannelData_" + pathSuffix
outNewCovMatrixsPath = path + "cluster_outNewCovMatrixList_" + pathSuffix
ratesPath = path + "cluster_rates_" + pathSuffix
UTsPath = path + "cluster_UTs_" + pathSuffix
# 读入聚类中心信息
# 合并多个文件
centroidList = []
for root, dirs, files in os.walk(path, topdown=True):
for file in files:
file = os.path.join(root, file)
if centroidListPath in file:
centroidListTmp = readAndWriteDataSet.excelToMatrixList(file)
for centroid in centroidListTmp:
centroidList.append(centroid)
break
centroids = tools.matrixListToMatrix(centroidList)
# 计算信道相关系数矩阵并输出，然后放到一个矩阵中
covMatrixList = tools.getCovMatrixList(channelData)
allCovMatrix = tools.matrixListToMatrix(covMatrixList)
# 确定每个数据分别属于哪个簇
clusterAssment = kmeans.getClusterAssment(allCovMatrix, centroids)
clusterAssmentList = []
clusterAssmentList.append(clusterAssment)
# 分析PCA效果
newChannelData, newCovMatrixList, UTs, rates = pca.pca(
channelData, covMatrixList, centroidList, clusterAssment, iRate)
# 输出结果
# 输出聚类结果
readAndWriteDataSet.write(clusterAssmentList, outClusterAssmentPath,
suffix)
# 协方差矩阵太大了，先不输出
# readAndWriteDataSet.write(covMatrixList, outOldCovMatrixListPath, suffix)
# 输出PCA结果
readAndWriteDataSet.write(newChannelData, outNewChannelDataPath, suffix)
readAndWriteDataSet.write(newCovMatrixList, outNewCovMatrixsPath, suffix)
readAndWriteDataSet.write(UTs, UTsPath, suffix)
readAndWriteDataSet.write(rates, ratesPath, suffix)
# 显示进度
print(u'共' + str(schedule[0]) + u'部分，' + u'第' + str(tmpSchedule) +
u'部分完成，' + u'已完成' + str(schedule[1]) + u'部分，' + u'完成度：' + '%.2f%%' %
(schedule[1] / schedule[0] * 100) + u'！')