#
else:#如果name是一个文件夹
path1 = path_original + "\\" + name#更新原始数据集路径
os.mkdir(path_saveNew + "\\" + name)#创建和原始数据集文件夹一致的文件夹，用于保存采样的结果
path2 = path_saveNew + "\\" + name#更新保存数据的路径为新创建的文件夹
for i in range(m):#在这个文件夹中创建存放每一次循环采样结果的文件夹
os.mkdir(path2+"\\for_"+str(i+1))
self.run_dir(path1, path2)#调用循环采样的方法，循环调用
if __name__ == '__main__':
based = Basic()
# sm = Smote()
# dataSet = based.loadSample('C:\\Users\Administrator\Desktop\Original_dataset - 副本\EasyEnsemble\\abalone_0_7.csv')
# # print(dataSet[0])
# X, y = based.Split(dataSet)
# print(type(X))
# print(type(y))
# sm.My_smote(X, y, 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv')
# cca=CCA()
# cca.My_cca('C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_cca_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\del_cca_abalone_0_7.csv')
m=int(input("请输入循环次数："))
path_original='E:\Papers_dataset\OriginalDataSet'
path_saveNew='E:\Papers_dataset\ResempledDataSet\CCA_all_1'
dic=Director()
dic.run_dir(path_original,path_saveNew)
toArff.run_dir(path_saveNew,'E:\Papers_dataset\ResempledDataSet\CCA_all_1_arff')
path1 = path_original + "\\" + name # 更新原始数据集路径
os.mkdir(path_saveNew + "\\" + name) # 创建和原始数据集文件夹一致的文件夹，用于保存采样的结果
path2 = path_saveNew + "\\" + name # 更新保存数据的路径为新创建的文件夹
for i in range(m): # 在这个文件夹中创建存放每一次循环采样结果的文件夹
os.mkdir(path2 + "\\for_" + str(i + 1))
self.run_dir(path1, path2) # 调用循环采样的方法，循环调用
if __name__ == '__main__':
m = int(input("请输入采样次数："))
path_originial = "E:\\Papers_dataset\\OriginalDataSet" # 存放原始数据文件的文件夹
path_saveNew = "E:\\Papers_dataset\\ResempledDataSet\\RUS" # 存放新采样过后的文件的文件夹
ramdomUnder=RamUnder()
rus = RandomUnderSampler()
ramdomUnder.run_dir(path_originial, path_saveNew) # 传入原始数据集文件夹和保存重采样数据集文件夹即可
toArff.run_dir(path_saveNew,"E:\\Papers_dataset\\ResempledDataSet\\RUS_arff")
# file = open("C:\\Users\\Administrator\\Desktop\\Original_dataset20171121\\SMOTE+TonekLink\\Flag_0_white.csv", 'r')
# '''读取文件的内容，readlines返回的是一个列表'''
# contain = file.readlines()
# count = len(contain) # 这是文件共有count行
# '''创建一个count x len(contain[0].split(','))-1的矩阵,其中len(contain[0].split(','))-1是样本属性的个数'''
# features = np.zeros((count, len(re.split(r'[ ,;:\t]+', contain[0])) - 1))
# labels = []
# index = 0
# for line in contain: # 一行行读数据文件
# line = line.strip() # 删除line头和尾的空格
# listFormLine = re.split(r'[ ,;:\t]+', line) # 指定','为分隔符，将line分割开
# '''将listFormLine中的前len(len(listFormLine)-1)列加入到矩阵中去'''
# features[index:] = listFormLine[0:len(listFormLine) - 1]
# labels.append(listFormLine[-1]) # 最后一列作为类标
#
else:#如果name是一个文件夹
path1 = path_original + "\\" + name#更新原始数据集路径
os.mkdir(path_saveNew + "\\" + name)#创建和原始数据集文件夹一致的文件夹，用于保存采样的结果
path2 = path_saveNew + "\\" + name#更新保存数据的路径为新创建的文件夹
for i in range(m):#在这个文件夹中创建存放每一次循环采样结果的文件夹
os.mkdir(path2+"\\for_"+str(i+1))
self.run_dir(path1, path2)#调用循环采样的方法，循环调用
if __name__ == '__main__':
based = Basic()
# sm = Smote()
# dataSet = based.loadSample('C:\\Users\Administrator\Desktop\Original_dataset - 副本\EasyEnsemble\\abalone_0_7.csv')
# # print(dataSet[0])
# X, y = based.Split(dataSet)
# print(type(X))
# print(type(y))
# sm.My_smote(X, y, 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv')
# cca=CCA()
# cca.My_cca('C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_cca_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\del_cca_abalone_0_7.csv')
m=int(input("请输入循环次数："))
path_original='E:\\Papers_dataset\\OriginalDataSet'
path_saveNew='E:\\Papers_dataset\\ResempledDataSet\\SMOTE_CCA_maj'
dic=Director()
dic.run_dir(path_original,path_saveNew)
toArff.run_dir(path_saveNew,'E:\\Papers_dataset\\ResempledDataSet\\SMOTE_CCA_maj_arff')
fcca, name) # 用于存储删除的信息
#
else: # 如果name是一个文件夹
path1 = path_original + "\\" + name # 更新原始数据集路径
os.mkdir(path_saveNew + "\\" + name) # 创建和原始数据集文件夹一致的文件夹，用于保存采样的结果
path2 = path_saveNew + "\\" + name # 更新保存数据的路径为新创建的文件夹
for i in range(m): # 在这个文件夹中创建存放每一次循环采样结果的文件夹
os.mkdir(path2 + "\\for_" + str(i + 1))
self.run_dir(path1, path2) # 调用循环采样的方法，循环调用
if __name__ == '__main__':
based = Basic()
# sm = Smote()
# dataSet = based.loadSample('C:\\Users\Administrator\Desktop\Original_dataset - 副本\EasyEnsemble\\abalone_0_7.csv')
# # print(dataSet[0])
# X, y = based.Split(dataSet)
# print(type(X))
# print(type(y))
# sm.My_smote(X, y, 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv')
# cca=CCA()
# cca.My_cca('C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_SMOTE_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\re_cca_abalone_0_7.csv',
# 'C:\\Users\Administrator\Desktop\\test_dic\EasyEnsemble\\del_cca_abalone_0_7.csv')
m = int(input("请输入循环次数："))
path_original = 'E:\Papers_dataset\OriginalDataSet'
path_saveNew = 'C:\\Users\Administrator\Desktop\CCA_all'
dic = Director()
dic.run_dir(path_original, path_saveNew)
toArff.run_dir(path_saveNew, 'C:\\Users\Administrator\Desktop\CCA_all_arff')