Python 按分类样本数占比生成并随机获取样本数据

按分类样本数占比生成并随机获取样本数据

By:授客 QQ：1033553122

开发环境

win 10

python 3.6.5

需求

已知样本分类，每种分类的样本占比数，及样本总数，需要随机获取这些分类的样本。比如，我有4种任务，分别为任务A，任务B，任务C，任务D, 每种任务需要重复执行的总次数为1000，每次执行随机获取一种任务来执行，不同分类任务执行次数占比为 A:B:C:D = 3:5:7:9

代码实现

#!/usr/bin/env python
# -*- coding:utf-8 -*-


__author__ = "shouke"


import random

def get_class_instance_by_proportion(class_proportion_dict, amount):
    """
    根据每种分类的样本数比例，及样本总数，为每每种分类构造样本数据
    class_proportion_dict: 包含分类及其分类样本数占比的字典：{"分类(id)": 分类样本数比例}
    amount: 所有分类的样本数量总和

    返回一个列表：包含所有分类样本的list

    """

    bucket = []
    proportion_sum = sum([weight for group_id, weight in class_proportion_dict.items()])
    residuals = {} # 存放每种分类的样本数计算差值
    for class_id, weight in class_proportion_dict.items():
        percent = weight / float(proportion_sum)
        class_instance_num = int(round(amount * percent))
        bucket.extend([class_id for x in range(class_instance_num)])
        residuals[class_id] = amount * percent - round(amount * percent)
    if len(bucket) < amount:
        # 计算获取的分类样本总数小于给定的分类样本总数，则需要增加分类样本数,优先给样本数计算差值较小的分类增加样本数，每种分类样本数+1，直到满足数量为止
        for class_id in [l for l, r in sorted(residuals.items(), key=lambda x: x[1], reverse=True)][: amount - len(bucket)]:
            bucket.append(class_id)
    elif len(bucket) > amount:
        # # 计算获取的分类样本总数大于给定的分类样本总数，则需要减少分类样本数,优先给样本数计算差值较大的分类减少样本数，每种分类样本数-1，直到满足数量为止
        for class_id in [l for l, r in sorted(residuals.items(), key=lambda x: x[1])][: len(bucket) - amount]:
            bucket.remove(class_id)

    return bucket


class A:
    def to_string(self):
        print("A class instance")

class B:
    def to_string(self):
        print("B class instance")

class C:
    def to_string(self):
        print("C class instance")

class D:
    def to_string(self):
        print("D class instance")

classes_map = {1: A, 2: B, 3:C, 4: D}
class_proportion_dict = {1: 3, 2: 5, 3:7, 4: 9} # {分类id: 样本数比例} ，即期望4个分类的样本数比例为为 3:5:7:9
class_instance_num = 1000 # 样本总数
result_list = get_class_instance_by_proportion(class_proportion_dict, class_instance_num)

for class_id in class_proportion_dict:
    print("%s %s" % (classes_map[class_id], result_list.count(class_id)))

# 制造样本并随机获取样本
random.shuffle(result_list)
while result_list:
    class_id = random.sample(result_list, 1)[0]
    classes_map[class_id]().to_string()
    result_list.remove(class_id)