How to extract feature vectors from a single PDF file for inference?

[Raneem04H]

Hello,

Thank you for releasing the EMBER2024 dataset and the thrember package.

I trained a CatBoost classifier on the EMBER2024 PDF subset using the vectorized features.

Now I would like to deploy the model and classify new PDF files.

I found PEFeatureExtractor for PE files, but I could not find an equivalent feature extractor for PDF files.

Is there an official way to extract EMBER2024 feature vectors from a single PDF file for inference?

If such functionality exists but is not currently exposed in the Python package, could you please point me to the relevant code or example?

Thank you very much.