def chuli_file(file_name, M):
file_list, lable_list, feature_is_discrete = read_file(file_name)
lable_list = [1 if lable > 0 else -1 for lable in lable_list] # 对二类分类的 lable 做优化
fenge = fenge_file_for_validation(file_list, lable_list, 10)
pre_all = []
for one_fenge in fenge:
decision_tree_obj = AdaBoost(one_fenge[2], one_fenge[3], feature_is_discrete, M)
count = 0.0
for i in range(len(one_fenge[0])):
if decision_tree_obj.predict(one_fenge[0][i]) == one_fenge[1][i]:
count += 1.0
pre = count / len(one_fenge[0])
pre_all.append(pre)
print 'precision :', pre
mean_pre = sum(pre_all) / 10.0
print 'mean precision :', mean_pre
print 'standard deviation :',math.sqrt(sum([(w-mean_pre)**2 for w in pre_all]))
pass
def chuli_file(file_name , t, m):
file_list, lable_list, feature_is_discrete = read_file(file_name)
fenge = fenge_file_for_validation(file_list, lable_list, 10)
pre_all = []
for one_fenge in fenge:
data_list = one_fenge[2]
lable_list = one_fenge[3]
t_ge_random_forests = [] # t 个 random forest
for i_t in range(t): # 生成 t 个树
sample_data_list = []
sample_lable_list = []
for num in range(len(data_list)): # 进行抽样
random_i = int(random.uniform(0, len(data_list)))
sample_data_list.append(data_list[random_i])
sample_lable_list.append(lable_list[random_i])
t_ge_random_forests.append(RandomForest(sample_data_list, sample_lable_list, feature_is_discrete, [], m))
# 进行测试
count = 0.0
for i in range(len(one_fenge[0])):
t_predict = []
for i_p in range(t):
t_predict.append(t_ge_random_forests[i_p].predict(one_fenge[0][i]))
predict_re = -99 # 预测结果
for i_p in range(t):
if predict_re == -99 or(t_predict[i_p] != predict_re and t_predict.count(t_predict[i_p]) > t_predict.count(predict_re)):
predict_re = t_predict[i_p]
if predict_re == one_fenge[1][i]:
count += 1.0
pre = count / len(one_fenge[0])
pre_all.append(pre)
print 'precision :', pre
mean_pre = sum(pre_all) / 10.0
print 'mean precision :', mean_pre
print 'standard deviation :',math.sqrt(sum([(w-mean_pre)**2 for w in pre_all]))
pass