From 9c2619daa9645dc101e0ab2c17ba647048e2c46c Mon Sep 17 00:00:00 2001 From: Michael Date: Tue, 10 Mar 2026 13:11:03 +0100 Subject: [PATCH] crash --- project_report.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/project_report.md b/project_report.md index e8a7976..471fc6a 100644 --- a/project_report.md +++ b/project_report.md @@ -27,11 +27,12 @@ Main scripts: - `dataset_creation/parquet_file_creation.py` Purpose: -- Read source recordings (`.h5` and/or ownCloud-fetched files) -- Keep relevant simulator/physiology columns -- Filter invalid samples (e.g., invalid level segments) +- Download and/or access dataset files (either download first via ```EDA/owncloud_file_access.ipynb``` or all in one with ```dataset_creation/create_parquet_files_from_owncloud.py``` +- Keep relevant columns (FACE_AUs and eye-tracking raw values) +- Filter invalid samples (e.g., invalid level segments): Make sure not to drop rows where NaN is necessary for later feature creation, therefore use subset argument in dropNa()! - Export subject-level parquet files + ### 2.2 Feature Engineering (Offline) Main script: