def Limeng(n, b):
a = readData()
labels = np.zeros(shape=(351, 20))
labels.dtype = 'int64'
cluster_centers = np.zeros(shape=(n, 40))
for i in range(20):
#print(i)
clf = KMeans(n_clusters=n, random_state=9)
y_pred = clf.fit_predict(a[:, i, 2:4])
labels[:, i] = clf.labels_
cluster_centers[:, 2 * i:(2 * i + 2)] = clf.cluster_centers_
newpaths = []
for i in range(351):
newpath = ""
for j in range(20):
string = "L" + str(labels[i, j])
newpath += string
newpaths.append(newpath)
result = Counter(newpaths)
newpathsdict = dict(result)
#计算u
u = mean(list(newpathsdict.values()))
#随机生成轨迹补足数量
while (len(newpathsdict) < 351):
key = ""
for i in range(20):
string = "L" + str(random.randint(0, n - 1))
key += string
newpathsdict.setdefault(key, 0)
valueslist = sorted(list(newpathsdict.values()), reverse=True)
newpathslist = list_sort_by_value(newpathsdict)
#生成噪声
lapnoise = []
for i in range(351):
ln = np.random.laplace(u, b)
while ln > 2 * u or ln < 0:
ln = np.random.laplace(u, b)
lapnoise.append(ln)
#添加噪声
vcarr = np.array(valueslist)
lcarr = np.array(lapnoise)
noisecount = vcarr + lcarr
#保序回归
x = np.arange(351)
y = noisecount
y_ = IsotonicRegression(increasing=False).fit_transform(x, y)
# # 作图
# plt.plot(x,a,"b.-",markersize=8)
# plt.plot(x,y,"r.",markersize=8)
# plt.plot(x,y_,"g.-",markersize=8)
# plt.show()
NMI = metrics.normalized_mutual_info_score(vcarr, y_)
# print(NMI)
vcarr.resize(351, 1)
y_.resize(351, 1)
hau_dis = hausdorff_distance(vcarr, y_, distance="euclidean")
return NMI, hau_dis
def myMechanism(n, e):
a = readData()
labels = np.zeros(shape=(958, 20))
labels.dtype = 'int64'
cluster_centers = np.zeros(shape=(n, 40))
for i in range(20):
# print(i)
clf = KMeans(n_clusters=n, random_state=9)
y_pred = clf.fit_predict(a[:, i, 2:4])
labels[:, i] = clf.labels_
cluster_centers[:, 2 * i:(2 * i + 2)] = clf.cluster_centers_
newpaths = []
for i in range(958):
newpath = ""
for j in range(20):
string = "L" + str(labels[i, j])
newpath += string
newpaths.append(newpath)
result = Counter(newpaths)
newpathsdict = dict(result)
# 随机生成轨迹补足数量
while (len(newpathsdict) < 958):
key = ""
for i in range(20):
string = "L" + str(random.randint(0, n - 1))
key += string
newpathsdict.setdefault(key, 0)
# 补齐2的n次方haar变换和重构
values = list(newpathsdict.values())
a = int(math.log(len(values), 2))
for index in range(int(math.pow(2, a + 1)) - len(values)):
values.append(0)
temp = buildHaarTreeList(values)
# print(len(temp))
noise = addNoise(len(temp), e)
c = [temp[i] + noise[i] for i in range(len(temp))]
noisecounts = rebuildHaarTreeList(c)
i = 0
newpathsdict2 = copy.deepcopy(newpathsdict);
for key, value in newpathsdict.items():
newpathsdict[key] = noisecounts[i]
i = i + 1
valueslist = sorted(list(newpathsdict.values()), reverse=True)
newpathslist = list_sort_by_value(newpathsdict)
truecounts = []
for item in newpathslist:
truecounts.append(newpathsdict2.get(item))
# 根据一致性约束 trueconts 保序回归
x = np.arange(958)
y = np.array(truecounts)
y_ = IsotonicRegression(increasing=False).fit_transform(x, y)
# print(y.shape)
NMI = metrics.normalized_mutual_info_score(y_, y)
mapeyy = mape(y_, y)
maeyy = metrics.mean_absolute_error(y, y_)
# hausdorff_distance
y.resize(1,958)
y_.resize(1,958)
# print(y.shape)
hau_dis = hausdorff_distance(y, y_, distance="euclidean")
return NMI, hau_dis,mapeyy,maeyy
def Limeng(n, b):
a = readData()
labels = np.zeros(shape=(10000, 20))
labels.dtype = 'int64'
cluster_centers = np.zeros(shape=(n, 40))
for i in range(20):
#print(i)
clf = KMeans(n_clusters=n, random_state=9)
y_pred = clf.fit_predict(a[:, i, 2:4])
labels[:, i] = clf.labels_
cluster_centers[:, 2 * i:(2 * i + 2)] = clf.cluster_centers_
newpaths = []
for i in range(10000):
newpath = ""
for j in range(20):
string = "L" + str(labels[i, j])
newpath += string
newpaths.append(newpath)
result = Counter(newpaths)
newpathsdict = dict(result)
#计算u
u = mean(list(newpathsdict.values()))
#随机生成轨迹补足数量
while (len(newpathsdict) < 10000):
key = ""
for i in range(20):
string = "L" + str(random.randint(0, n - 1))
key += string
newpathsdict.setdefault(key, 0)
#生成噪声
lapnoise = []
for i in range(10000):
ln = np.random.laplace(u, b)
while ln > 2 * u or ln < 0:
ln = np.random.laplace(u, b)
lapnoise.append(ln)
#添加噪声 newpathsdict备份至newpathsdict2，之后newpathsdict包含噪声
i = 0
newpathsdict2 = copy.deepcopy(newpathsdict)
for key, value in newpathsdict.items():
newpathsdict[key] = value + lapnoise[i]
i = i + 1
# dict按value排序得到两个list
valueslist = sorted(list(newpathsdict.values()), reverse=True)
newpathslist = list_sort_by_value(newpathsdict)
# 按照newpathslist里顺序，取出newpathsdict2里truecount的值
truecountlist = []
for item in newpathslist:
truecountlist.append(newpathsdict2.get(item))
#保序回归
x = np.arange(10000)
y = np.array(truecountlist)
y_ = IsotonicRegression(increasing=False).fit_transform(x, y)
# # 作图
# plt.plot(x,a,"b.-",markersize=8)
# plt.plot(x,y,"r.",markersize=8)
# plt.plot(x,y_,"g.-",markersize=8)
# plt.show()
maeyy = metrics.mean_absolute_error(y_, y)
NMI = metrics.normalized_mutual_info_score(y, y_)
# print(NMI)
y.resize(1, 10000)
y_.resize(1, 10000)
hau_dis = hausdorff_distance(y, y_, distance="euclidean")
return NMI, hau_dis, maeyy
