from SMO import *
from sklearn.model_selection import train_test_split
import numpy as np
x = np.random.normal(size=(5, ))
y = np.outer(x, x)
z = np.random.multivariate_normal(np.zeros(5) - 2, y, size=100)
x1 = np.random.normal(size=(5, ))
y1 = np.outer(x1, x1)
z1 = np.random.multivariate_normal(np.zeros(5) + 2, y1, size=100)
X_train = np.r_[z, z1]
Y_train = np.r_[[1 for x in range(100)], [-1 for x in range(100)]]
X_train, X_test, y_train, y_test = train_test_split(X_train,
Y_train,
test_size=0.33,
random_state=42)
model = SMO()
model.fit(X_train, y_train)
print('score:', model.score(X_test, y_test))
def train(self, C=[0.01, 1, 10, 100], tol=1e-3):
m = self.Y.shape[0]
A = [0] * 10
B = [0] * 10
indices = numpy.random.permutation(
self.X.shape[0]) # shape[0]表示第0轴的长度，通常是训练数据的数量
rand_data_x = self.X[indices]
rand_data_y = self.Y[indices] # data_y就是标记（label）
l = int(len(indices) / 10)
for i in range(9):
A[i] = rand_data_x[i * l:i * l + l]
B[i] = rand_data_y[i * l:i * l + l]
A[9] = rand_data_x[9 * l:]
B[9] = rand_data_y[9 * l:]
# '''
# X_num=self.X.shape[0]
# train_index=range(X_num)
# test_size=int(X_num*0.1)+1
# for i in range(9):
# test_index=[]
# for j in range(test_size):
# randomIndex=int(numpy.random.uniform(0,len(train_index)))
# test_index.append(train_index[randomIndex])
# #del train_index[randomIndex]
# A[i]=self.X[test_index,:]
# B[i]=self.Y[test_index,:]
# A[9]=self.X.ix_[train_index]
# B[9]=self.Y.ix_[train_index]
# '''
acc_best = 0
C_best = None
avg_acc = 0
# gamma_best = None
for CVal in C:
# for gammaVal in gamma:
# avg_acc = 0
for i in range(10):
X_test = A[i]
Y_test = B[i]
# X_train = None
# Y_train = None
#model= SMO.SMO_Model(X_train, Y_train, CVal, kernel,gammaVal, tol=1e-3, eps=1e-3)
#output_model=SMO.SMO(model)
#根据output_model的参数信息计算对应decision_function----->推得accuracy
#acc = _evaulate(output_model)
X_train = numpy.concatenate([
A[(i + 1) % 10], A[(i + 2) % 10], A[(i + 3) % 10],
A[(i + 4) % 10], A[(i + 5) % 10], A[(i + 6) % 10],
A[(i + 7) % 10], A[(i + 8) % 10], A[(i + 9) % 10]
],
axis=0)
Y_train = numpy.concatenate([
B[(i + 1) % 10], B[(i + 2) % 10], B[(i + 3) % 10],
B[(i + 4) % 10], B[(i + 5) % 10], B[(i + 6) % 10],
B[(i + 7) % 10], B[(i + 8) % 10], B[(i + 9) % 10]
],
axis=0)
# SMO.GG = gammaVal
# calculate Kernel Matrix then pass it to SMO.
if self.IK:
if self.kernel_dict['type'] == 'TANH':
K = Kernel.TANH(X_train.shape[0],
self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(X_train)
elif self.kernel_dict['type'] == 'TL1':
K = Kernel.TL1(X_train.shape[0],
self.kernel_dict['rho'])
K.calculate(X_train)
p1, p2 = trans_mat(K.kernelMat)
K.kernelMat = np.dot((p1 - p2), K.kernelMat)
if self.kernel_dict['type'] == 'RBF':
K = Kernel.RBF(X_train.shape[0], self.kernel_dict['gamma'])
K.calculate(X_train)
elif self.kernel_dict['type'] == 'LINEAR':
K = Kernel.LINEAR(X_train.shape[0])
K.calculate(X_train)
elif self.kernel_dict['type'] == 'POLY':
K = Kernel.POLY(X_train.shape[0], self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(X_train)
elif self.kernel_dict['type'] == 'TANH':
K = Kernel.TANH(X_train.shape[0], self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(X_train)
elif self.kernel_dict['type'] == 'TL1':
K = Kernel.TL1(X_train.shape[0], self.kernel_dict['rho'])
K.calculate(X_train)
model = SMO.SMO_Model(X_train,
Y_train,
CVal,
K,
tol=1e-3,
eps=1e-3)
output_model = SMO.SMO(model)
#IK
if self.IK:
output_model.alphas = np.dot((p1 - p2),
output_model.alphas)
acc = SMO._evaluate(output_model, X_test, Y_test)
avg_acc = avg_acc + acc / 10
if avg_acc > acc_best:
acc_best = avg_acc
#更新C gamma
C_best = CVal
# gamma_best =gammaVal
# self.gamma = gamma_best
#最后一遍train
# SMO.GG = gamma_best
#!K
if self.IK:
if self.kernel_dict['type'] == 'TANH':
K = Kernel.TANH(self.X.shape[0], self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(self.X)
elif self.kernel_dict['type'] == 'TL1':
K = Kernel.TL1(self.X.shape[0], self.kernel_dict['rho'])
K.calculate(self.X)
p1, p2 = trans_mat(K.kernelMat)
K.kernelMat = np.dot((p1 - p2), K.kernelMat)
if self.kernel_dict['type'] == 'RBF':
K = Kernel.RBF(self.X.shape[0], self.kernel_dict['gamma'])
K.calculate(self.X)
elif self.kernel_dict['type'] == 'LINEAR':
K = Kernel.LINEAR(self.X.shape[0])
K.calculate(self.X)
elif self.kernel_dict['type'] == 'POLY':
K = Kernel.POLY(self.X.shape[0], self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(self.X)
elif self.kernel_dict['type'] == 'TANH':
K = Kernel.TANH(self.X.shape[0], self.kernel_dict['c'],
self.kernel_dict['d'])
K.calculate(self.X)
elif self.kernel_dict['type'] == 'TL1':
K = Kernel.TL1(self.X.shape[0], self.kernel_dict['rho'])
K.calculate(self.X)
SVM_model = SMO.SMO(
SMO.SMO_Model(self.X, self.Y, C_best, K, tol=1e-3, eps=1e-3))
# 参数传递给最后生成的SVM类
if self.IK:
SVM_model.alphas = np.dot((p1 - p2), SVM_model.alphas)
self.X = SVM_model.X
self.Y = SVM_model.y
self.kernel_dict = SVM_model.kernel
self.alphas = SVM_model.alphas
self.b = SVM_model.b
# C_best = C
# gamma_best =gamma
# (w,b) = SMO(X_train,Y_train,C_best,gamma_best,kernal,tol=1e-3)
# self.w = w
# self.b = b
return None
i.pop(0)
tmp = []
for j in range(784):
tmp.append(0)
for j in i:
plz = j.find(':')
tmp[int(j[0:plz])] = int(j[plz + 1:]) * r
dataset.append(tmp)
dataset = np.array(dataset)
label = np.array(label)
# ytmp = label.reshape(-1, 1) * 1.
# xtmp = ytmp * dataset
alpha, x, y, b = SMO(dataset, label, 10)
b = np.float(b)
temp = alpha * y
temp = np.transpose(temp)
omega = np.dot(temp, x)
# omega = np.transpose(omega)
datafile = open('test-01-images.svm', mode='r')
tedata = datafile.readlines()
datafile.close()
testdata = []
for i in tedata:
testdata.append(i.replace('\n', '').split(' ', i.count(' ')))
dataset = []
label = []
