data/README.md

data/

One folder per participant: collected_<name>/ with .npz files. 9 participants, 144,793 samples total. Each .npz has features (N×17), labels (0/1), feature_names. Training uses 10 of the 17 (see data_preparation).

Collect more:

python -m models.collect_features --name yourname

Webcam + overlay; press 1 = focused, 0 = unfocused, p = pause, q = save and quit.