如何编码具有高基数的分类特征? [英] How to encode a categorical feature with high cardinality?
问题描述
我被困在一个包含一些具有高基数的分类特征的数据集中.就像'item_description'...我读了一些叫做哈希"的技巧，但是它的主要思想仍然是模糊和难以理解的，我还读了一个名为功能引擎"的库，但是我没有真正找到可以解决我的问题的东西.有什么建议吗?
Im stuck in a dataset that contains some categrotical features with a high cardinality. like 'item_description' ... I read about some trick called hashing, but its main idea is still blurry and incomprehensible, i also read about a library called 'Feature engine' but i didn't really find something that might solve my issue. Any suggestions please?
推荐答案
选项:
i)使用目标编码.
-
有关目标编码的更多信息: https://maxhalford.github.io/blog/target-encoding/
此处有关类别变量的良好教程: https://www.coursera.org/learn/competitive-data-science#syllabus [部分:关于模型的特征预处理和生成，第三个视频]
Good tutorial on categorical variables here: https://www.coursera.org/learn/competitive-data-science#syllabus [Section: Feature Preprocessing and Generation with Respect to Models , 3rd Video]
ii)使用实体嵌入:简而言之，该技术通过向量表示每个类别，然后进行训练以获取类别的特征.
ii) Use entity embeddings: In short, this technique represent each category by a vector, then training to obtain the characteristics of the category.
笔记本的实现方式
- https://www.kaggle.com/aquatic/entity-embedding-neural-net
- https://www.kaggle.com/abhishek/same-old-实体嵌入
iii)使用Catboost:
iii) Use Catboost :
额外:有一种哈希技巧也可能会有所帮助: https://booking.ai/dont-be-tricked-by-the-hashing-trick-192a6aae3087?gi=3045c6e13ee5
Extra: There is a hashing trick technique which might also be helpful: https://booking.ai/dont-be-tricked-by-the-hashing-trick-192a6aae3087?gi=3045c6e13ee5
这篇关于如何编码具有高基数的分类特征?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
