python从数据集中随机抽取样例数据

**

python从数据集中随机抽取样例数据

**

import random
import numpy as np
import json
#简单随机抽样
with open("D:\\1.json",'r') as load_f:
    s = load_f.read()
    load_s = json.dumps(eval(s))
    load_dict = json.loads(load_s)#json格式转成字典key1=data,key2=version

    #print(type(load_dict))#dict
    #load_dict = list(load_dict)
    for k,v in list(load_dict.items())[0:1]:#取出key1中的value值
        #print(type(v))
        data_sample=json.dumps(random.sample(v,25))#随机从data对应的value中抽取20个样本
        #print(type(data_sample))#打印数据
        print(str(data_sample).count("\"question\":"))  # 统计总共有多少个问题

with open("C:\\data\\test.txt",'w') as test:
    data_sample = str(data_sample)
    data_sample = data_sample.encode('gbk', 'ignore')
    data_sample = data_sample.decode('gbk')
    test.write(data_sample)