def run(seed):
domain = createDomain()
l0 = len(domain[0])
l1 = len(domain[1])
l2 = len(domain[2])
l3 = len(domain[3])
l4 = len(domain[4])
l5 = len(domain[5])
l6 = len(domain[6])
print('len(e0):' + str(len(domain[0])))
print('len(e1):' + str(len(domain[1])))
print('len(e2):' + str(len(domain[2])))
print('len(e3):' + str(len(domain[3]))) # 472 470 0.8 376
print('len(e4):' + str(len(domain[4])))
print('len(e5):' + str(len(domain[5])))
print('len(e6):' + str(len(domain[6])))
# docs=domain[0]+domain[1]+domain[2]+domain[3]+domain[4]+domain[5]+domain[6]
# trains=domain[0][int(l0*0.2):]+domain[1][int(l1*0.2):]+domain[2][int(l2*0.2):]+\
# domain[3][int(l3*0.2):]+domain[4][int(l4*0.2):]+domain[5][int(l5*0.2):]+domain[6][int(l6*0.2):]
tests=domain[0][:72]+domain[1][:72]+domain[2][:72]+domain[3][:72]+domain[4][:72]\
+domain[5][:72]+domain[6][:72]
domain_2 = [] # re-sampling
for j in range(6):
for i in range(2204 - len(domain[j])):
domain[j].append(random.choice(domain[j][72:]))
# 测试样本 固定每类别的前90 *7
trains=domain[0][72:]+domain[1][72:]+domain[2][72:]+domain[3][72:]+domain[4][72:]\
+domain[5][72:]+domain[6][72:]
# for item in domain:
# random.shuffle(item)
# 训练样本 随机采样 360 *7
# trains=random.sample(domain[0][72:],288)+random.sample(domain[1][72:],288)+random.sample(domain[2][72:],288)\
# +random.sample(domain[3][72:],288)+random.sample(domain[4][72:],288)\
# +random.sample(domain[5][72:],288)+random.sample(domain[6][72:],288)
# random.shuffle(trains)
# tests=domain[0][:int(l0*0.2)]+domain[1][:int(l1*0.2)]+domain[2][:int(l2*0.2)]+domain[3][:int(l3*0.2)]+\
# domain[4][:int(l4*0.2)]+domain[5][:int(l5*0.2)]+domain[6][:int(l6*0.2)]
#random.shuffle(tests)
#random.shuffle(docs)
# trains=docs[:int(len(docs)*0.8)]
# tests=docs[int(len(docs)*0.8):]
print('len(trains):' + str(len(trains)))
print('len(tests):' + str(len(tests)))
# lexcion=maxent.get_lexcion(trains)
# print('len(lexcion):'+str(len(lexcion)))
maxent.me_classify(trains, tests)
#maxent.createResult(tests,'result.txt')
# acc=maxent.createResult2('result.txt')
acc, G_mean = maxent.createPRF('result.txt', seed)
return acc, G_mean
def main(seed):
domain=createDomain()
l0=len(domain[0])
l1=len(domain[1])
l2=len(domain[2])
l3=len(domain[3])
l4=len(domain[4])
l5=len(domain[5])
l6=len(domain[6])
print('len(e0):'+str(len(domain[0])))
print('len(e1):'+str(len(domain[1])))
print('len(e2):'+str(len(domain[2])))
print('len(e3):'+str(len(domain[3]))) # 472 470 0.8 376
print('len(e4):'+str(len(domain[4])))
print('len(e5):'+str(len(domain[5])))
print('len(e6):'+str(len(domain[6])))
tests=domain[0][:72]+domain[1][:72]+domain[2][:72]+domain[3][:72]+domain[4][:72]\
+domain[5][:72]+domain[6][:72]
domain_2=[] # re-sampling
for i in range(360-len(domain[2][72:])):
domain[2].append(random.choice(domain[2][72:]))
# domain[2]=domain_2
# trainList=[] # 训练样本列表
pred_prob_list=[]
co_num=5
for i in range(co_num):
# trainList.append(getTrains(domain))
trains=getTrains(domain)
pred_prob,real_label=run(trains,tests,'result_%d.txt' %(i+1),seed)
pred_prob_list.append(pred_prob)
co_pred_prob=[]
print len(pred_prob_list)
for i in range(len(tests)):
p=[]
# p0=pred_prob_list[0][i][0]+pred_prob_list[1][i][0]+pred_prob_list[2][i][0]+pred_prob_list[3][i][0]+\
# pred_prob_list[4][i][0]
p0=sum([item[i][0] for item in pred_prob_list])
p1=sum([item[i][1] for item in pred_prob_list])
p2=sum([item[i][2] for item in pred_prob_list])
p3=sum([item[i][3] for item in pred_prob_list])
p4=sum([item[i][4] for item in pred_prob_list])
p5=sum([item[i][5] for item in pred_prob_list])
p6=sum([item[i][6] for item in pred_prob_list])
# p1=pred_prob_list[0][i][1]+pred_prob_list[1][i][1]+pred_prob_list[2][i][1]+pred_prob_list[3][i][1]+\
# pred_prob_list[4][i][1]
# p2=pred_prob_list[0][i][2]+pred_prob_list[1][i][2]+pred_prob_list[2][i][2]+pred_prob_list[3][i][2]+\
# pred_prob_list[4][i][2]
# p3=pred_prob_list[0][i][3]+pred_prob_list[1][i][3]+pred_prob_list[2][i][3]+pred_prob_list[3][i][3]+\
# pred_prob_list[4][i][3]
# p4=pred_prob_list[0][i][4]+pred_prob_list[1][i][4]+pred_prob_list[2][i][4]+pred_prob_list[3][i][4]+\
# pred_prob_list[4][i][4]
# p5=pred_prob_list[0][i][5]+pred_prob_list[1][i][5]+pred_prob_list[2][i][5]+pred_prob_list[3][i][5]+\
# pred_prob_list[4][i][5]
# p6=pred_prob_list[0][i][6]+pred_prob_list[1][i][6]+pred_prob_list[2][i][6]+pred_prob_list[3][i][6]+\
# pred_prob_list[4][i][6]
p=[p0,p1,p2,p3,p4,p5,p6]
co_pred_prob.append(p)
# print co_pred_prob[0]
print len(co_pred_prob)
co_max_prob_label=[]
for item in co_pred_prob:
m=max(item)
co_max_prob_label.append(item.index(m))
# co_max_prob.append(max(item))
print co_max_prob_label
acc,g_mean=maxent.createPRF(co_max_prob_label,real_label,seed,'co_resort_maxent_prf.txt')
print acc,g_mean
return acc,g_mean
def run(trains,tests,filename,seed): maxent.me_classify(trains,tests,filename) pred_prob,pred_label,real_label=maxent.getPredProb(filename) acc,gmean=maxent.createPRF(pred_label,real_label,seed,'per_crf.txt') return pred_prob,real_label