[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
nan：not a number
inf：infinity;正无穷
numpy中的nan和inf都是float类型
t!=t 返回bool类型的数组(矩阵)
np.count_nonzero() 返回的是数组中的非0元素个数；true的个数。
np.isnan() 返回bool类型的数组。
那么问题来了，在一组数据中单纯的把nan替换为0，合适么？会带来什么样的影响？
比如，全部替换为0后，替换之前的平均值如果大于0，替换之后的均值肯定会变小，所以更一般的方式是把缺失的数值替换为均值（中值）或者是直接删除有缺失值的一行
demo.py（numpy，将数组中的nan替换成对应的均值）：
# coding=utf-8 import numpy as np def fill_ndarray(t1): for i in
range(t1.shape[1]): # 遍历每一列（每一列中的nan替换成该列的均值） temp_col = t1[:, i] # 当前的一列
nan_num = np.count_nonzero(temp_col != temp_col) if nan_num != 0: #
不为0，说明当前这一列中有nan temp_not_nan_col = temp_col[temp_col == temp_col] #
去掉nan的ndarray # 选中当前为nan的位置，把值赋值为不为nan的均值 temp_col[np.isnan(temp_col)] =
temp_not_nan_col.mean() # mean()表示求均值。 return t1 if __name__ == '__main__': t1
= np.array([[ 0., 1., 2., 3., 4., 5.], [ 6., 7., np.nan, np.nan, np.nan,
np.nan], [12., 13., 14., 15., 16., 17.], [18., 19., 20., 21., 22., 23.]]) t1 =
fill_ndarray(t1) # 将nan替换成对应的均值 print(t1) ''' [[ 0. 1. 2. 3. 4. 5.] [ 6. 7. 12.
13. 14. 15.] [12. 13. 14. 15. 16. 17.] [18. 19. 20. 21. 22. 23.]] '''
