def grid(problem_path,result_save_path,svm_type,coarse_c_range,coarse_g_range,fine_c_step,fine_g_step):
'''搜索的主文件;
svm_type :使用的模型的类型。"libsvm"或者"liblinear"
coarse_c_range :粗粒度c搜索的范围，为一个truple (begin,end,step)
coarse_g_range :粗粒度g搜索的范围，为一个truple (begin,end,step)
fine_c_step :细粒度c搜索的步长，搜索范围为(fine_c-coarse_c_step,fine_c+coarse_c_step,fine_c_step),如果为0，则固定为(fine_c,fine_c,fine_c)
fine_g_step :细粒度g搜索的步长，搜索范围为(fine_g-coarse_g_step,fine_g+coarse_g_step,fine_g_step),如果为0，则固定为(fine_g,fine_g,fine_g)
'''
tms_svm.set_svm_type(svm_type)
y,x = tms_svm.read_problem(problem_path)
fw= file(result_save_path,'w')
c,g=grid_search_for_large_data(y,x,fw,coarse_c_range,coarse_g_range,fine_c_step,fine_g_step)
fw.close()
return c,g
def ctm_train_model(sample_save_path,svm_type,param,model_save_path):
'''训练模型，输入样本文件，训练的参数，模型的保存地址，最后会给出模型在训练样本上的测试结果。'''
tms_svm.set_svm_type(svm_type)
y,x = tms_svm.read_problem(sample_save_path)
m = tms_svm.train(y,x,param)
tms_svm.save_model(model_save_path,m)
labels = {}.fromkeys(y).keys()
if len(labels)>2:
pred_labels, (Micro, Macro, ACC), pred_values = tms_svm.predict(y,x,m)
print "(Micro=%g, Macro=%g, ACC=%g)"%(Micro, Macro, ACC)
else:
pred_labels, (f_score,recall,presion), pred_values=tms_svm.predict(y,x,m)
print "(f_score=%g,recall=%g,presion=%g)"%(f_score,recall,presion)
return m
def grid(problem_path, result_save_path, svm_type, coarse_c_range,
coarse_g_range, fine_c_step, fine_g_step):
'''搜索的主文件;
svm_type :使用的模型的类型。"libsvm"或者"liblinear"
coarse_c_range :粗粒度c搜索的范围，为一个truple (begin,end,step)
coarse_g_range :粗粒度g搜索的范围，为一个truple (begin,end,step)
fine_c_step :细粒度c搜索的步长，搜索范围为(fine_c-coarse_c_step,fine_c+coarse_c_step,fine_c_step),如果为0，则固定为(fine_c,fine_c,fine_c)
fine_g_step :细粒度g搜索的步长，搜索范围为(fine_g-coarse_g_step,fine_g+coarse_g_step,fine_g_step),如果为0，则固定为(fine_g,fine_g,fine_g)
'''
tms_svm.set_svm_type(svm_type)
y, x = tms_svm.read_problem(problem_path)
fw = file(result_save_path, 'w')
c, g = grid_search_for_large_data(y, x, fw, coarse_c_range, coarse_g_range,
fine_c_step, fine_g_step)
fw.close()
return c, g
def save_train_for_lsa(test_path,model_save_path,lsa_train_save_path):
'''predict trainset using the initial classifier ,and save the trainset with
lsa format : label score feature
'''
y,x = tms_svm.read_problem(test_path)
m = tms_svm.load_model(model_save_path)
p_lab,p_acc,p_sc = tms_svm.predict(y,x,m)
f= file(lsa_train_save_path,'w')
for i in range(len(y)):
f.write(str(int(y[i]))+"\t"+str(p_sc[i][0])+"\t")
dic =x[i]
sorted_x = sorted(dic.items(),key = lambda dic:dic[0])
for key in sorted_x:
f.write(str(key[0])+":"+str(key[1])+"\t")
f.write("\n")
f.close()
def save_train_for_lsa(test_path, model_save_path, lsa_train_save_path):
'''predict trainset using the initial classifier ,and save the trainset with
lsa format : label score feature
'''
y, x = tms_svm.read_problem(test_path)
m = tms_svm.load_model(model_save_path)
p_lab, p_acc, p_sc = tms_svm.predict(y, x, m)
f = file(lsa_train_save_path, 'w')
for i in range(len(y)):
f.write(str(int(y[i])) + "\t" + str(p_sc[i][0]) + "\t")
dic = x[i]
sorted_x = sorted(dic.items(), key=lambda dic: dic[0])
for key in sorted_x:
f.write(str(key[0]) + ":" + str(key[1]) + "\t")
f.write("\n")
f.close()
def ctm_model_predict(test_path, m):
'''模型预测，输入测试样本，然后读入进行测试'''
y, x = tms_svm.read_problem(test_path)
return tms_svm.predict(y, x, m)
def ctm_model_predict(test_path,m):
'''模型预测，输入测试样本，然后读入进行测试'''
y,x = tms_svm.read_problem(test_path)
return tms_svm.predict(y,x,m)
