def CreateModel(
self, train_set, test_set
): #determina il tipo di modello richiesto SVM / GOR e addestra / predice il modello
if self.type == 'GOR':
mod = MyGOR.GOR()
elif self.type == 'SVM':
mod = MySVM.SVM(self.Ci, self.Gamma) #self.C,self.Gamma
else:
print('affanculo')
mod.train(train_set)
mod.predicta(test_set)
return mod
def fit(self,X,Y):
global le
le=LabelEncoder()
le.fit(Y)
Y=le.transform(Y)
data=self.generateClasswiseData(X,Y)
svc=MySVM.SVC(self.C)
for i in range(len(data)):
self.svm_classifiers[i]={}
for j in range(i+1,len(np.unique(Y))):
x,y=self.getPairData(data[i],data[j])
wts,b,losses=svc.fit(x,y, learning_rate=self.learning_rate, max_itr=self.max_iter)
self.svm_classifiers[i][j]=(wts,b)
def __init__(self):
print('Initiating ...')
# 标签
self.labelList = ['财经', '房产', '股票', '教育', '科技',
'社会', '时政', '体育', '游戏', '娱乐']
self.labelLen = len(self.labelList)
# 算法生成向量维度
self.dimension = 5000
# LDA模型遍历语料库次数
self.ldaPasses = 10
#print('Loading data ...')
# 导入数据
#self.dL = Ld.LoadData()
#self.trainData = self.dL.loadCsvData('tmp/trainDataSet.csv')
#self.testData = self.dL.loadCsvData('tmp/testDataSet.csv')
#self.texts, self.labels = self.dL.loadScData('../THUCNews_final')
#print('datalen:',len(self.texts))
#print('Spliting data ...')
#self.x_train, self.x_test, self.y_train, self.y_test = train_test_split(self.texts, self.labels, test_size=0.5)
# SVM对象
self.svm = Ms.MySVM(self.labelLen)
# 贝叶斯对象
self.valuesNumForBayes = 50
self.naiveBayes = Mnb.MyNaiveBayes(self.labelLen, self.valuesNumForBayes)
# EvaluateAndShow对象
self.eas = Eas.EvaluateAndShow()
pass
###################################### PCA #############################
# ----------------------------------------- from sklearn.decomposition import PCA
# ------------------------------------------------------------------------------
# ----------------------------------------------------- pca = PCA(n_components=6)
# --------------------------------------------- newtrain=pca.fit_transform(train)
# ------------------------------------------- print pca.explained_variance_ratio_
# ----------------------------------- print np.sum(pca.explained_variance_ratio_)
# ------------------------------------------------------ print np.shape(newtrain)
# ------------------------------------------------------------------------------
# ------------------------------------------------------------------------------
# -------------------------------------------------------------- train = newtrain
##############################################Training with rbf############################################################################
ff = mysvc.training_regress()
best = ff.svmrbf(train, trainlabel, -4, 4, -4, 4, 10)
#
# # Test with SVM
svtt = mysvc.test()
output = svtt.test_regression(test, testlabel, best)
###############################################Train the model_10CV ##################################################
# -------------------------------------------------- ff = mysvc.training_manCV()#
# ------------------------------------------------------------------------------
# df = ff.trainSVC(train, trainlabel, 'poly', Cmin=-10, Cmax=10, numC=21, rmin=-10, rmax=10, numr=21, degree = 4)
# ------------------------------------------------------------------------------
# df.to_csv('/home/peng/git/Machine_learning_for_reliability_analysis/Test_1/Results/poly_pca6_cm_10CV_d4_n10_p10_21.csv', header = True)
pca = PCA(n_components=6)
newtrain = pca.fit_transform(train)
print pca.explained_variance_ratio_
print np.sum(pca.explained_variance_ratio_)
print np.shape(newtrain)
train = newtrain
##########################################################################################################################
###############################################Train the model
ff = mysvc.training_manCV()
df = ff.trainSVC(train, trainlabel, "poly", Cmin=-10, Cmax=10, numC=21, rmin=-10, rmax=10, numr=21, degree=4)
df.to_csv(
"/home/peng/git/Machine_learning_for_reliability_analysis/Test_1/Results/poly_pca6_cm_10CV_d4_n10_p10_21.csv",
header=True,
)
################################################ ####
####################### Read the cm and convert cm to metrics########
