Python3 HashSet

import pandas
import xlwt

class People:
    def __init__(self , name , job_number):
        self.name = name
        self.job_number = job_number

    def __str__(self):
        return self.name + ","+ str(self.job_number)

class Company:

    def __init__(self , name , pid):
        self.name = name
        self.pid = pid

    def __lt__(self, other):
        return self.name < other.name

    def __hash__(self):
        return  hash(str(self.name)+str(self.pid))

    def __eq__(self, other):
        return  self.name == other.name and self.pid == other.pid

    def __str__(self):
        return  self.name + "," + str(self.pid)

class Laige:

    def __init__(self):
        pass

    def doWork(self, path , out_path):
        f = pandas.DataFrame(pandas.read_excel(path, sheetname=0))
        KV = {}
        companys = []
        for i in f.values:
            comp = i[0]
            nam = i[1]
            jobnm = i[2]
            pid = i[3]
            k = Company(comp, pid)
            if KV.get(k) :
                v = KV.get(k)
                v.append(People(nam , jobnm))
            else:
                KV[k] = [People(nam , jobnm)]
            companys.append(Company(comp , pid))

        workbook = xlwt.Workbook()
        sheet_laige = workbook.add_sheet('来哥', cell_overwrite_ok=True)

        cpl = list(set(companys))
        cpl.sort(key=companys.index)
        for i in range(len(cpl)):
            k = cpl[i]
            col = 0
            sheet_laige.write(i , col, str(k.name))
            col += 1
            sheet_laige.write(i , col , str(k.pid))
            col += 1
            v = KV.get(k)
            for m in v :
                # sheet_laige.write(i, col, str(m.name))
                # col += 1
                sheet_laige.write(i, col, str(m.job_number))
                col += 1

        workbook.save(out_path)

if __name__ == '__main__':
    laige = Laige()
    laige.doWork("C:/Users/liyang/Desktop/数据筛选.xlsx" , "C:/Users/liyang/Desktop/数据筛选结果.xlsx")

1）可哈希的（hashable）

只有 可哈希的 对象才能作为字典的键，一个可哈希的对象必须满足以下两个条件：

• 该对象在其生命周期内有一个不变的哈希值（需要实现__hash__()方法）
• 该对象是可比较的（需要实现__eq__()或__cmp__()方法）

Python中可哈希的对象有：

• 数值、字符串，以及只含有数值或字符串的元组
• 用户自定义类的实例（默认是可哈希的，也可以通过实现__hash__()和__cmp__()来修改默认行为）

2）哈希等价键

假设有字典d的两个键：keyA和keyB，我们称keyA和keyB是 哈希等价键（自己杜撰的名词），如果keyA和keyB满足以下两个条件：

• hash(keyA) == hash(keyB)
• cmp(keyA, keyB) == 0

如果keyA和keyB是哈希等价键，那么它们将被视为完全相同的两个键，于是d[keyA]和d[keyB]会指向同一个字典元素。