"Compute Mean Value of Each Cluster for an Ignored Attribute"

goh_han_pin

During clustering,

how do I ignore an attribute

then later display the average value of that ignored attitude for each cluster?

My scenario as follows:

I have a dataset.

Each example is a student, with a set of attributes.

The attributes are the student’s ‘input’ characteristics, and one attribute being the student’s achievement test scores.

How do I ignore the student’s test scores during clustering, so that cluster is merely done based on student’s input characteristics?

But, at the end of the clustering process, link the students in each cluster to their achievement test scores, and compute the mean (average) test scores for the students from each cluster?

H P

lionelderkrikor

Hi@goh_han_pin,

Can you share your dataset, please, in order to test a possible process which answer to your project ?

Regards,

Lionel

MartinLiebig

Hi,

The attached process should do it

Best,

MArtin

<运营商激活= " true " class = "过程”兼容ibility="8.0.001" expanded="true" name="Process">








Exclude attribute_1 for clustering