0
$\begingroup$

I have a dataset having more than 25000 features. I did perform noise removal using the histogram approach, and this dataset gets reduced to more than 5000 features. There are two classes, healthy and infected. I want to extract important features where the separation is maximum between these two classes. After noise removal, most of the features have NaN. PCA doesn't handle the data set with missing values. Any suggestions are appreciated.

Thank you so much for your attention and participation.

$\endgroup$
1

1 Answer 1

0
$\begingroup$

For the Nan values - perhaps you could alleviate this by interpolating the features, and use PCA after dropping the leftover NaNs. Regardless, I'd suggest using some pre-trained feature extractor, depending on the type of data. perhaps you could feed your input through some pre-trained Imagenet model to extract smaller dimension representation, or even maybe train your own autoencoder and use the latent representation.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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