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