作者ctr1 (【积π】)
看板DataScience
标题[问题] LabelEncoder移除没训练过的data
时间Wed May 13 10:57:08 2020
#python 3.7
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
le.fit(["paris", "paris", "tokyo", "amsterdam"])
print('class:{}'.format(list(le.classes_)))
data1 = ["tokyo", "tokyo", "paris"]
print(le.transform(data1))
data2 = ["tokyo", "tokyo", "paris", "USA", "Taiwan"]
print(le.transform(data2))
----------------输出-----------------
class:['amsterdam', 'paris', 'tokyo']
[2 2 1]
ValueError: y contains previously unseen labels: ['Taiwan', 'USA']
原因是因为Taiwin 跟 USA没有训练过
我想要在transform到未知的资料时移除该笔资料
想请问该怎操作呢
--
※ 发信站: 批踢踢实业坊(ptt.cc), 来自: 210.242.44.65 (台湾)
※ 文章网址: https://webptt.com/cn.aspx?n=bbs/DataScience/M.1589338630.A.2A0.html
1F：→ yoyololicon: 在transform前就处理乾净ㄅ 05/13 19:00
2F：→ yoyololicon: data2 = [x for x in data2 if x in data1] 05/13 19:01
3F：→ ctr1: 感谢 05/14 00:29