1
$\begingroup$

So I have a data set I have successfully used to train a model, and have decent results. I am using a Two Class Boosted Decision tree for a Boolean output. So far so good.

I now want to analyze each column of my data set and remove any column that is not a meaningful influence on the outcome. I see statistics on columns in my data set: enter image description here

But I don't see whether a column has a strong relationship with the output variable. Any clues?

$\endgroup$
0
$\begingroup$

Some very helpful articles walked me through how to use the feature selection modules in Azure ML Studio:

https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/feature-selection-modules https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/filter-based-feature-selection

I used the "Filter Based Feature Selection" Module:

enter image description here

I added it to my training experiment and added input data.

enter image description here

I chose the feature I was training my model to predict.

enter image description here

After running the experiment I viewed the visualization of the Features:

enter image description here enter image description here

Now I am using this to find which columns are valuable and which need some work.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.