读取表格数据,按照固定列排序

淩亂°似流年 2022-09-16 06:16 226阅读 0赞

import csv
    import pandas as pd
    import numpy as np
    # This is a sample Python script.
    
    # Press Shift+F10 to execute it or replace it with your code.
    # Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
    
    '''
    查找相同子公共子序列 获得索引
    '''
    def print_hi(name):
        list1 = []
        list2 = []
        name = []
        listfull1 = []
        listfull2 = []
        # Use a breakpoint in the code line below to debug your script.
        print(f'Hi, {
          name}')  # Press Ctrl+F8 to toggle the breakpoint.
        with open('/home/philtell/Desktop/0514_biogas_p1_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
            reader = csv.reader(csvfile)
            # list1 = [row for row in reader]
    
            list1 = [row[8] for row in reader]
    
        with open('/home/philtell/Desktop/0514_biogas_p1_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
            reader = csv.reader(csvfile)
            listfull1 = [row for row in reader]
    
        with open('/home/philtell/Desktop/0514_biogas_p2_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
            reader = csv.reader(csvfile)
            list2 = [row[8] for row in reader]
        with open('/home/philtell/Desktop/0514_biogas_p2_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
            reader = csv.reader(csvfile)
            listfull2 = [row for row in reader]
            # print(listfull2)
    
        listsize1 = len(list1)
        listsize2 = len(list2)
        mm = listsize2;
        nn = listsize1;
        sameIndex = []
        AsameNumIndex = set()  # 表格1 的具有相同seq的无序数据集合
        BsameNumIndex = []
    
        for i in range(1,mm):
            sub_list = []    # 表格1和表格2 具有相同seq 键值对
            sub_list.append(i)
            for j in range(1,nn):
                if(list2[i]==list1[j]):
                    sub_list.append(j)
                    AsameNumIndex.add(i)
                    BsameNumIndex.append(j)
            sameIndex.append(sub_list)
        print(len(AsameNumIndex))
        print(len(sameIndex))
        print(sameIndex)
        newlist = []
        t1 = set()
        t2 = set()
        list3 = []
        for kk in sameIndex:
            j = 0
            for oo in kk:
                if len(kk)==2:
                    if j==0:
                        # print(oo)
                        t2.add(oo)
                        # print(listfull2[oo])
                        list3.append(listfull2[oo])
                    else:
                        t1.add(oo)
                        list3.append(listfull1[oo])
                        # print(listfull1[oo])
                    j = j+1
    
        for i in range(1,len(list1)):
            if i not in t1:
                list3.append(listfull1[i])
        for i in range(1,len(list2)):
            if i not in t2:
                list3.append(listfull2[i])
        print(len(list3))
    
        # print(len(newlist))
        # print(newlist)
    
        # print(sameIndex)
        # sameIndex2 = []
        # for i in range(nn):
        #     for j in range(mm):
        #         if (list2[i] == list1[j]):
        #             sameIndex2.append(j)
        # print(len(sameIndex2))
        #
        '''
        '''
        # with open('/home/philtell/Desktop/0514_biogas_p1_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
        #     reader = csv.reader(csvfile)
        #     list1 = [row[8] for row in reader]
        df = pd.read_csv("/home/philtell/Desktop/0514_biogas_p2_asv.csv",low_memory=False)
    
        data = np.array(df.loc[:, :])
        labels = list(df.columns.values)
        # temp = []
        # temp.append("序号")
        # for la in labels:
        #     temp.append(la)
        # with open('/home/philtell/Desktop/0514_biogas_p2_asv.csv','r',encoding = "ISO-8859-1") as csvfile:
        #     reader = csv.reader(csvfile)
        #     count = 0
        #     test = []
        #     print(type(reader))
        #     for row in reader:
        #         if count in sameIndex:
        #             test.append(row)
        #         count = count + 1
        #     # print(test)
        #     #
        print(list3)
    
    
        # print(len(test))
        print(labels)
        test = pd.DataFrame(data=list3)
        test.to_csv('/home/philtell/Desktop/mylove.csv',encoding='utf-8')
    
    # Press the green button in the gutter to run the script.
    if __name__ == '__main__':
        print_hi('PyCharm')
    
    # See PyCharm help at https://www.jetbrains.com/help/pycharm/