Skip to content

Train/test splits and the original CIC-IDS2017 release - #13

Merged
SamuelSchwertfeger merged 4 commits into
mainfrom
dev
Oct 9, 2026
Merged

SamuelSchwertfeger merged 4 commits into
mainfrom
dev

Conversation

@SamuelSchwertfeger

Copy link
Copy Markdown
Owner

Brings main up to dev: named train/test splits (#11) and the original release as original-flows and original-ml (#12).

time: for each class in each source file, the latest 20% of the flows by
timestamp are the test set. random: 20% of each class, fixed seed.
The release records its timestamp column and format.
…l-ml

Both versions are recorded from the files downloaded through the
publisher's form. The loader learns archive member paths, a per-release
text encoding, repeated column names and recorded blank lines, and checks
the row count of every file. ids-lint reads a file in the encoding of the
release and no longer fails on a console that cannot show a label.
The README says how the package was tested.
Record the original CIC-IDS2017 release (original-flows, original-ml)
@SamuelSchwertfeger
SamuelSchwertfeger merged commit bb7a8a2 into main Oct 9, 2026
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant