Python 按比例获取样本数据或执行任务的实现代码

#!/usr/bin/env python
# -*- coding:utf-8 -*-
 
 
__author__ = 'shouke'
 
import time
from copy import deepcopy
 
 
def main():
 
  class_propotion_map = {'A':3, 'B':5, 'C':7, 'D':7} # 分类及样本数比例映射
  class_list = [] # 分类
  class_proption_list = [] # 存放分类样本数比例
 
  for class_type, propotion in class_propotion_map.items(): # 同一个循环，可以保证比例索引和对应分类索引一一对应
    class_list.append(class_type)
    class_proption_list.append(propotion)
 
  temp_class_propotion_list = deepcopy(class_proption_list)
  result = []
 
  t1 = time.time()
  total_sample_num = 100000 #任务执行次数
  for i in range(1, total_sample_num+1):
    max_propotion = max(temp_class_propotion_list)
    if max_propotion > 0:
      index = temp_class_propotion_list.index(max_propotion)
      result.append(class_list[index])
      temp_class_propotion_list[index] -= 1
    elif max_propotion == 0 and min(temp_class_propotion_list) == 0:
      temp_class_propotion_list = deepcopy(class_proption_list)
      index = temp_class_propotion_list.index(max(temp_class_propotion_list))
      result.append(class_list[index])
      temp_class_propotion_list[index] -= 1

  t2 = time.time()
  from collections import Counter
  c = Counter(result)
  for item in c.items():
    print(item[0], item[1]/total_sample_num)
  print('耗时：%s'%(t2-t1))
 
main()