def _test_rnn_rand_vec():
# 这里随机生成一个 Tensor，维度是 1000 x 10 x 200；其实就是1000个句子，每个句子里面有10个词向量，每个词向量 200 维度，其中的值符合 NORMAL 分布。
_xs = torch.randn(1000, 10, 200)
_ys = []
# 标签值 0 - 5 闭区间
for i in range(1000):
_ys.append(1)
# 隐层 200，输出 6，隐层用词向量的宽度，输出用标签的值得个数 （one-hot)
encoder_test = EncoderRNNWithVector(200, 6)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(encoder_test.parameters(),
lr=0.001,
momentum=0.9)
num_data = len(_xs) #1000
batchsize = 20
num_epoches = 10
for epoch in range(num_epoches):
for start, end in zip(range(0, num_data, batchsize),
range(batchsize, num_data, batchsize)):
encoder_hidden = encoder_test.init_hidden()
input_data = torch.autograd.Variable(_xs[start:end])
output_labels = torch.autograd.Variable(
torch.LongTensor(np.array([
_ys[start:end]
])).reshape(batchsize)) #output_labels需要为LongTensor
encoder_outputs, encoder_hidden = encoder_test(
input_data, encoder_hidden) #此处调用前向传播
optimizer.zero_grad()
predict = encoder_outputs.view(batchsize, -1)
# print("predict_shape",predict.size()) #predict_shape torch.Size([20, 6])
# print("output_labels", output_labels.size()) #output_labels torch.Size([20])
loss = criterion(predict, output_labels)
loss.backward()
optimizer.step()
eva(predict, output_labels, batchsize)
return
def SpectralClustering(data, class_num, data_nm, label):
X = data
af = ['rbf', 'laplacian', 'distance']
Compare = []
for a in af:
la = spectral_clustering(X, class_num, affinity=a)
Compare.append(la)
A = []
for com in Compare:
NMI, ARI = evaluate.eva_com(com, label)
A.append(ARI)
k = Fmax(A)
labels = Compare[k]
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, Sc, ARI = evaluate.eva(labels, label, X)
print(nmi, acc, purity, Sc, ARI)
# 画图
plt.style.use('ggplot')
# 原数据
# 谱聚类结果
plt.scatter(X[:, 0], X[:, 1], c=labels, edgecolors='k')
plt.title("SC2+" + data_nm)
plt.savefig(
'.\picture\improved_spectral_clustering\sc1_{0}.png'.format(data_nm))
plt.close()
def HC(data, class_num, data_nm, label):
k = class_num
# Z = sch.linkage(data, method='average',metric='euclidean')
# sch.dendrogram(Z)
# plt.savefig('.\picture\hierarchical_clustering\c_{0}.png'.format(data_nm))
# plt.close()
# plt.figure()
# sns.clustermap(data,method='average',metric='euclidean',cmap='RdYlBu_r')
# plt.savefig('.\picture\hierarchical_clustering\c1_{0}.png'.format(data_nm))
# plt.close()
hc = AgglomerativeClustering(k, affinity='euclidean', linkage='ward')
y_hc = hc.fit_predict(data)
# print(len(y_hc))
# print(len(label.reshape(-1)))
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, Sc, ARI = evaluate.eva(y_hc, label, data)
print(nmi, acc, purity, Sc, ARI)
colors = [
'#B03060', '#AEEEEE', '#68228B', 'y', 'c', 'm', '#2E2E2E', '#00008B',
'#2E8B57', '#8B0000', '#8B5A00', '#EEEE00', '#CDCDB4', '#ABABAB',
'#8B8B00'
]
plt.figure()
for i in range(k):
for j in range(0, 6):
color = colors[i % len(colors)]
plt.scatter(data[y_hc == i, 0], data[y_hc == i, 1], s=6, c=color)
plt.title("AgglomerativeClustering+" + data_nm)
# plt.legend(loc='best')
plt.savefig('.\picture\hierarchical_clustering\hc_{0}.png'.format(data_nm))
plt.close()
def FCM1(data, class_num, data_nm, label):
# Hyper Parameters
# C = int(class_num)
C = class_num
m = 1.1
iteration = 10
X = data
n, dimension = X.shape
# print(n)
# print(dimension)
U = np.array(np.random.rand(n, C), dtype='double')
# print(U)
U_crisp = np.zeros((n, 1))
mu = np.zeros((C, dimension))
# print(mu)
X = np.array(X)
fig, ax = plt.subplots()
for k in range(iteration):
for i in range(n):
U[i, :] = U[i, :] / sum(U[i, :])
for j in range(C):
temp = (U[:, j]**m)
mu[j, :] = sum(np.multiply(temp,
X.transpose()).transpose()) / sum(temp)
for i in range(n):
for j in range(C):
U[i,
j] = 1 / sum((d(X[i, :], mu[j, :], 'vector')) /
d(X[i, :], mu[:, :], 'matrix'))**(1 / (m - 1))
UV = []
for i in range(n):
U_crisp[i] = np.argmax(U[i, :])
UV.extend(U_crisp[i])
# print(UV)
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, Sc, ARI = evaluate.eva(UV, label, data)
print(nmi, acc, purity, Sc, ARI)
colors = [
'#B03060', '#AEEEEE', '#68228B', 'y', 'c', 'm', '#2E2E2E', '#00008B',
'#2E8B57', '#8B0000', '#8B5A00', '#EEEE00', '#CDCDB4', '#ABABAB',
'#8B8B00'
]
for i in range(C):
points = np.array([X[j, :] for j in range(n) if U_crisp[j] == i])
# print(points)
ax.scatter(points[:, 0], points[:, 1], s=7, c=colors[i])
plt.title("FCM+" + data_nm)
# plt.legend(loc='best')
plt.savefig('.\picture\FCM\F_{0}.png'.format(data_nm))
def dbscan(data, data_nm, class_num, label):
# 设置半径为eps，最小样本量为min_samples，建模
db = DBSCAN(eps=0.82, min_samples=2).fit(data)
labels = db.labels_
# print(len(labels))
# print(len(label.reshape(-1)))
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, SC, ARI = evaluate.eva(labels, label, data)
print(nmi, acc, purity, SC, ARI)
# 计算噪声点个数占总数的比例
# raito = len(labels[labels[:] == -1]) / len(labels)
# print('噪声比:', format(raito, '.2%'))
plotRes(data, labels, class_num, data_nm)
def sp(data, class_num, data_nm, label):
n_clusters = class_num
matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False
m = euclidean_distances(data, squared=True)
# print(m)
sigma = np.median(m)
plt.figure(figsize=(12, 8), facecolor='w')
plt.suptitle(u'谱聚类', fontsize=20)
clrs = [
'#B03060', '#AEEEEE', '#68228B', 'y', 'c', 'm', '#2E2E2E', '#00008B',
'#2E8B57', '#FAEBD7', '#8B5A00', '#EEEE00', '#0000FF', '#ABABAB',
'#8B8B00'
]
# print(len(clrs))
assess = []
for i, s in enumerate(np.logspace(-2, 0, 6)):
af = np.exp(-m**2 / (s**2)) + 1e-6
y_hat = spectral_clustering(af,
n_clusters=n_clusters,
assign_labels='kmeans',
random_state=1)
# assess.append(y_hat)
plt.subplot(2, 3, i + 1)
for k, clr in enumerate(clrs):
cur = (y_hat == k)
plt.scatter(data[cur, 0],
data[cur, 1],
s=40,
color=clr,
edgecolors='k')
x1_min, x2_min = np.min(data, axis=0)
x1_max, x2_max = np.max(data, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.grid(True)
plt.title(u'sigma = %.2f' % s, fontsize=16)
# print(y_hat)
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, Sc, ARI = evaluate.eva(y_hat, label, data)
print(nmi, acc, purity, Sc, ARI)
plt.tight_layout()
plt.title("SC1+" + data_nm)
plt.subplots_adjust(top=0.9)
plt.savefig(
'.\picture\improved_spectral_clustering\sc1_{0}.png'.format(data_nm))
plt.close()
def main():
word_id=create_vocab(args.training_data_path,args.vocab_path,True)
#label_id=create_vocab(args.training_data_path,args.vocab_tag_path)
args.class_num=3
#train,test=load_data(args.training_data_path,word_id,label_id)
train1,test1=load_data1(args.training_data_path,word_id)
#train1,test1=load_data_bert(args.training_data_path,word_id)
TrainX,TrainY=zip(*train1)
testX,testY=zip(*test1)
cnn=model.CNN_Text(args).cuda()
criterion = torch.nn.CrossEntropyLoss()
#optimizer = torch.optim.SGD(cnn.parameters(), lr=0.001, momentum=0.9)
opt_Adam = torch.optim.Adam(cnn.parameters(), lr=args.lr, betas=(0.9, 0.99))
for epoch in range(1,args.epoches):
print("epoch",epoch)
batch_iter=batch_helper(TrainX,TrainY,args.batch_size)
for trainx,trainy in batch_iter:
#print("trainy length",len(trainy)) #batchsize
input_data = torch.autograd.Variable(torch.LongTensor(trainx)).cuda()
output_labels=torch.autograd.Variable(torch.LongTensor(trainy)).cuda()
output_labels=output_labels. squeeze()
#print("vocab_size",args.vocab_size)
cnn_outputs=cnn(input_data)
torch.save(cnn.state_dict(),args.parameters_path)
opt_Adam.zero_grad()
loss = criterion(cnn_outputs, output_labels)
loss.backward()
opt_Adam.step()
# for param_tensor in cnn.state_dict():
# print(param_tensor, "\t", cnn.state_dict()[param_tensor].size())
# for var_name in opt_Adam.state_dict():
# print(var_name, "\t", opt_Adam.state_dict()[var_name])
eva(cnn_outputs,output_labels,args.batch_size)
torch.save(cnn.state_dict(), args.parameters_path)
run_val(testX,testY,cnn)
def kmeans(data, class_num, data_nm, label):
k = class_num
clu = random.sample(data.tolist(), k) # 随机取质心
clu = np.asarray(clu)
err, clunew, k, clusterRes = Kmeans.classfy(data, clu, k)
while np.any(abs(err) > 0):
# print(clunew)
err, clunew, k, clusterRes = Kmeans.classfy(data, clunew, k)
clulist = Kmeans.cal_dis(data, clunew, k)
clusterResult = Kmeans.divide(data, clulist)
# print(clusterResult)
# print(label.reshape(-1))
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity, Sc, ARI = evaluate.eva(clusterResult, label, data)
print(nmi, acc, purity, Sc, ARI)
Kmeans.plotRes(data, clusterResult, k, data_nm)
def sp(data,class_num,data_nm,label):
n_clusters=class_num
matplotlib.rcParams['font.sans-serif'] = [u'SimHei']
matplotlib.rcParams['axes.unicode_minus'] = False
plt.figure(facecolor='w')
clrs =['#B03060', '#AEEEEE', '#68228B', 'y', 'c', 'm', '#2E2E2E', '#00008B', '#2E8B57', '#FAEBD7',
'#8B5A00', '#EEEE00', '#0000FF', '#ABABAB', '#8B8B00']
gamma_list = [0.1,0.2,0.4,0.6,0.8,1]
af=['laplacian','nearest_neighbors']
Compare=[]
for gamma_value in gamma_list:
# for a in af:
spectral = SpectralClustering(n_clusters,gamma=gamma_value, affinity='nearest_neighbors',random_state=1)
y_hat = spectral.fit_predict(data)
Compare.append(y_hat)
N=[]
A=[]
for com in Compare:
NMI,ARI=evaluate.eva_com(com,label)
N.append(NMI)
A.append(ARI)
k=Fmax(N)
y_hat=Compare[k]
print("标准化互信息 精度 纯度 轮廓系数 兰德系数")
nmi, acc, purity,Sc,ARI= evaluate.eva(y_hat, label,data)
print(nmi, acc, purity,Sc,ARI)
for k, clr in enumerate(clrs):
cur = (y_hat == k)
plt.scatter(data[cur, 0], data[cur, 1], s=40, color=clr, edgecolors='k')
x1_min, x2_min = np.min(data, axis=0)
x1_max, x2_max = np.max(data, axis=0)
x1_min, x1_max = expand(x1_min, x1_max)
x2_min, x2_max = expand(x2_min, x2_max)
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
# plt.grid(True)
# plt.legend(loc='best')
plt.title("SC2+" + data_nm)
plt.savefig('.\picture\improved_spectral_clustering\sc1_{0}.png'.format(data_nm))
plt.close()
end = time.time()
print("Dev: " + str(numOfSamples) + ' / ' + str(len(dev)) + " , Current loss : " + str(
loss / numOfSamples) + ", run time = " + str(end - start))
start = time.time()
# print('%s (%d %d%%) %.4f' % (timeSince(start, numOfSamples / (len(train) * 1.0)),
# numOfSamples, numOfSamples / len(train) * 100, loss / numOfSamples))
loss /= numOfSamples
writeResult.close()
with codecs.open('result.txt', 'w', encoding='utf-8') as outfile:
json.dump(dict, outfile)
print('Dev Loss: ' + str(loss))
evaluate.eva('result.txt', '../data/dev-v1.1.json')
# loss = 0
# numOfSamples = 0
# numOfBatch = 0
# start = time.time()
# print("Start Dev2:")
# dict = {}
# s = ""
# writeResult = codecs.open('prediction2.txt','w',encoding='utf-8')
# for sid in range(0, len(dev2), config.DevBatchSize):
#
# instances = dev2[sid:sid + config.DevBatchSize]
# # print(instances[0][10])
]
for i in range(clusterNum):
color = scatterColors[i % len(scatterColors)]
x1 = []
y1 = []
for j in range(nPoints):
if clusterRes[j] == i:
x1.append(data[j, 0])
y1.append(data[j, 1])
plt.scatter(x1, y1, c=color, alpha=1, marker='+')
plt.show()
if __name__ == '__main__':
k = 7 # 类别个数
data = load_data()
print(data)
clu = random.sample(data[:, 0:2].tolist(), k) # 随机取质心
print(clu)
clu = np.asarray(clu)
err, clunew, k, clusterRes = classfy(data, clu, k)
while np.any(abs(err) > 0):
print(clunew)
err, clunew, k, clusterRes = classfy(data, clunew, k)
clulist = cal_dis(data, clunew, k)
clusterResult = divide(data, clulist)
nmi, acc, purity = eva.eva(clusterResult, np.asarray(data[:, 2]))
print(nmi, acc, purity)
plotRes(data, clusterResult, k)
if clusterRes[pointId] == UNASSIGNED:
if to_cluster(data, clusterRes, pointId, clusterId, radius,
minPts):
clusterId = clusterId + 1
return np.asarray(clusterRes), clusterId
def plotRes(data, clusterRes, clusterNum):
nPoints = len(data)
scatterColors = [
'black', 'blue', 'green', 'yellow', 'red', 'purple', 'orange', 'brown'
]
for i in range(clusterNum):
color = scatterColors[i % len(scatterColors)]
x1 = []
y1 = []
for j in range(nPoints):
if clusterRes[j] == i:
x1.append(data[j, 0])
y1.append(data[j, 1])
plt.scatter(x1, y1, c=color, alpha=1, marker='+')
if __name__ == '__main__':
data = load_data()
cluster = np.asarray(data[:, 2])
clusterRes, clusterNum = dbscan(data, 0.8, 3)
plotRes(data, clusterRes, clusterNum)
nmi, acc, purity = eva.eva(clusterRes, cluster)
print(nmi, acc, purity)
plt.show()
nPoints = len(data)
scatterColors = [
'black', 'blue', 'green', 'yellow', 'red', 'purple', 'orange'
]
for i in range(clusterNum):
color = scatterColors[i % len(scatterColors)]
x1 = []
y1 = []
for j in range(nPoints):
if clusterResult[j] == i:
x1.append(data[j, 0])
y1.append(data[j, 1])
plt.scatter(x1, y1, c=color, alpha=1, marker='+')
plt.show()
if __name__ == '__main__':
cluster_num = 2
KNN_k = 5
data = load_data()
data = np.asarray(data)
W = getW(data, KNN_k)
D = getD(W)
L = getL(D, W)
eigvec = getEigen(L)
clf = KMeans(n_clusters=cluster_num)
s = clf.fit(eigvec)
C = s.labels_
nmi, acc, purity = eval.eva(C + 1, data[:, 2])
print(nmi, acc, purity)
plotRes(data, np.asarray(C), 7)
