def classify(filename): textData=featureSelected.featureSelect(filename) label=getLabel(textData) #print 'classify',label if label==1: print "类别:财经" return '财经' elif label==2: print "类别:IT" return 'IT' elif label==3: print "类别:旅游" return '旅游' elif label==4: print "类别:体育" return '体育'
def TextToVector(filename): text = featureSelected.featureSelect(filename) # print json.dumps(text,encoding='UTF-8',ensure_ascii=False) f = open("../data/trainData/Dict/Chi_Feature.txt", "rb") Dict = pickle.load(f) f.close() # print json.dumps(Dict,encoding='UTF-8',ensure_ascii=False) DICT = [] for i in range(len(Dict)): DICT.append(Dict[i][0]) tmp = [] print "lenth of DICT ", len(DICT) for i in range(len(DICT)): if DICT[i] in text: tmp.append((i + 1, text[DICT[i]])) if len(tmp) == 0: print "len of tmp in VSM = 0" return tmp
def classify2(filename): textData=featureSelected.featureSelect(filename) label=getLabel(textData) return label
#print 'logJoint',logJoint return label def classify(filename): textData=featureSelected.featureSelect(filename) label=getLabel(textData) #print 'classify',label if label==1: print "类别:财经" return '财经' elif label==2: print "类别:IT" return 'IT' elif label==3: print "类别:旅游" return '旅游' elif label==4: print "类别:体育" return '体育' def classify2(filename): textData=featureSelected.featureSelect(filename) label=getLabel(textData) return label if __name__=='__main__': #Bayes_FeatureP() filename=('/Thu_Life/CS/SVM/data/trainData/Data/class2/1246.txt') classify(filename) text=featureSelected.featureSelect(filename) #print json.dumps(text,encoding='UTF-8',ensure_ascii=False)
def classify(filename): textData=featureSelected.featureSelect(filename) label=getLabel(textData) print 'classify',label