search

erdogant / pca

pca: A Python Package for Principal Component Analysis.
https://erdogant.github.io/pca
MIT License
284 stars 42 forks source link

External set #24

Closed PARODBE closed 2 years ago

PARODBE commented 2 years ago

Hi!

I have a question, if you want work with a external set to check the outliers and another functions of this library, How would it be possible?

Thanks! Pablo

erdogant commented 2 years ago

Outliers can be extracted for follow-up analysis as described here

PARODBE commented 2 years ago

But, the algorithm makes a fit_transform for train and test with the vstack, shouldn't it be transform your test regarding to train?

BTW, do you think that could implement all this for pls like in pychemometrics? https://github.com/Gscorreia89/pyChemometrics

Thanks! Pablo

erdogant commented 2 years ago

Excellent point. I created an update to detect outliers for new unseen samples too! An example is over here.

Update pca to the latest version

pip install -U pca