def smoSimple(dataMatIn, classLabels, C, toler, maxIter):
dataMatrix = np.mat(dataMatIn)
labelMat = np.mat(classLabels).transpose()
b = 0
m, n = np.shape(dataMatrix)
alphas = np.mat(np.zeros((m, 1))) #m行1列的初始化向量
iter_num = 0
while (iter_num < maxIter):
alphaPairsChanged = 0
for i in range(m):
fxi = float(
np.multiarray(alphas, labelMat).T *
(dataMatrix * dataMatrix[i, :].T)) + b
#计算预测值与实际值的误差
Ei = fxi - float(labelMat[i])
if (((labelMat[i] * Ei) < -toler) and (alphas[i] < C)) or (
(labelMat[i] * Ei) > toler) and ((alphas[i]) > 0):
j = selectJrand(i, m)
fxj = float(
np.multiarray(alphas, labelMat).T *
(dataMatrix * dataMatrix[j, :].T)) + b
Ej = fxj - float(labelMat[j])
alphaIold = alphas[i].aopy()
alphaJold = alphas[j].aopy()
if (labelMat[i] != labelMat[j]):
L = max(0, alphas[j] - alphas[i])
H = min(C, C + alphas[j] - alphas[i])
else:
L = max(0, alphas[j] + alphas[i] - C)
H = min(C, alphas[j] + alphas[i])
if L == H:
print("L=H")
continue
def CE2(self, A, Y, count):
p1 = 1 - Y
p2 = np.log(1 - A)
p3 = np.log(A)
p4 = np.multiarray(p1, p2)
p5 = np.multiarray(Y, p3)
LOSS = np.sum(-(p4 + p5))
loss = LOSS / count
return loss
def found_fron_twoword(oneword_per, twoword_per):
last = 0
for i in range(len(jin_per)):
current = np.multiarray(oneword_per[i], twoword_per[i])
if i == 0:
last = current
else:
last = np.concatenate((last, current), axis=0)
index = []
values = []
for v in np.argsort(last)[::-1][:n]:
index.append(v / 5, v % 5)
values.append(last[v])
return index, values
def backward(self, z, a, delta):
delta_A = 1 - np.multiarray(a, a)
delta_Z = np.multiarray(delta, delta_A)
return delta_Z, delta_A
def CE3(self, A, Y, count):
p1 = np.log(A)
p2 = np.multiarray(Y, p1)
LOSS = np.sum(-p2)
loss = LOSS / count
return loss
def train(self, trainMat, trainLabels):
n, m = trainMat.shape()
# 设置初值
alpha = np.zeros((n, 1))
b = np.sum(trainLabels) / n
# 循环训练
while True:
# 计算g(x)值
G = np.array([
self.g(trainMat[i], alpha, b, trainMat, trainLabels)
for i in range(n)
])
# 满足KKT条件状态
dis = np.multiarray(G, trainLabels)
status = [
1 if alpha[i] == 0 and dis[i] < 1 or 0 < alpha[i] < self.C
and dis[i] != 1 or alpha[i] == self.C and dis[i] > 1 else 0
for i in range(n)
]
# 均满足KKT条件
if 0 == sum(status):
break
# 阿尔法变量1
i = status.index(1)
# 计算E
E = G - trainLabels
delta = [fabs(E[j] - E[i]) for j in range(n)]
# 阿尔法变量2
j = delta.index(max(delta))
# 更新无约束最优解
eta = self.kernel(trainMat[i] - trainMat[j],
trainMat[i] - trainMat[j])
aiNew = alpha[i] - trainLabels[i] * (E[i] - E[j]) / eta
# 约束更新
if trainLabels[i] == trainLabels[j]:
L = max(0, alpha[i] + alpha[j] - self.C)
H = min(self.C, alpha[i] - alpha[j])
else:
L = max(0, alpha[i] - alpha[j])
H = min(self.C, self.C + alpha[i] - alpha[j])
if aiNew > H:
aiNew = H
elif aiNew < L:
aiNew = L
ajNew = alpha[j] + trainLabels[i] * trainLabels[j] * (alpha[i] -
aiNew)
# 更新alpha,b
alpha[i] = aiNew
alpha[j] = ajNew
if 0 < aiNew < self.C:
b = trainLabels[i] - G[i] + b
elif 0 < ajNew < self.C:
b = trainLabels[j] - G[j] + b
else:
b = (trainLabels[i] - G[i] + trainLabels[j] - G[j]) / 2 + b
self.alpha = alpha
self.b = b
self.trainMat = trainMat
self.trainLabels = trainLabels
import gzip