The Data Mining Forum                             open-source data mining software data mining conferences Data Science for Social and Behavioral Analytics DSSBA 2022 data science journal
IMPORTANT: This is the old Data Mining forum.
I keep it online so that you can read the old messages.

Please post your new messages in the new forum: https://forum2.philippe-fournier-viger.com/index.php
 
聚类算法的使用
Posted by: qinqinzhou
Date: December 15, 2021 06:47PM

尊敬的philfv先生您好:
我在使用spmf库里的k-means聚类算法,数据是2436条67维的,拟采用欧氏距离聚成5类,但是聚类的效果不太好,聚类的结果文本也看不出来类间的区分,这是因为数据稀疏且维度太大了嘛?对于这样的数据聚类您有什么意见?非常感谢!
参数设置及可视化结果:

输入数据:

输出文本结果:

Options: ReplyQuote
Re: 聚类算法的使用
Posted by: qinqinzhou
Date: December 15, 2021 06:51PM




Options: ReplyQuote
Re: 聚类算法的使用
Date: December 23, 2021 09:05PM

Good afternoon,

I am sorry for the delay to answer. I have been very busy.

I think it is likely because the data is very sparse with so many dimensions.

In the visualization, the results may look strange but I think it is because we can only visualize two dimensions at a time.

By trying to look more in your data, maybe you can find some other reasons.

Best regards,

Philippe

Options: ReplyQuote
Re: 聚类算法的使用
Posted by: 琴琴周
Date: December 24, 2021 11:50PM

Thank you very much!I am tring to reduce the dimensions,filling the gap values and reading papers,I think I would solve the problem.

Options: ReplyQuote


This forum is powered by Phorum and provided by P. Fournier-Viger (© 2012).
Terms of use.