SURANKCO-TRAINING(1)

✨ SURANKCO-TRAINING ✨

okay bestie so this is the man page for surankco-training — a User Command, section 1, the whole vibe 💅

🌸 NAME 🌸

surankco-training — training of random forest using contig features and contig scores 🧚✨

🎀 SYNOPSIS 🎀

surankco-training [options]

that's it, that's the whole synopsis, no positional args, we love a low-maintenance icon 👑

💖 DESCRIPTION 💖

So basically 💁‍♀️ this program does the training of a random forest using contig features from surankco-feature(1) and contig scores from surankco-score(1). That's the entire job description, and it does it flawlessly, no cap. ✨

🦋 OPTIONS 🦋

• -f FEATURES, --features=FEATURES — point it at a list of surankco feature files, comma separated bestie, and the correct suffixes are mandatory — they gotta end in "*.features.txt" or it's not the vibe 🙈
• -d DIRECTORY, --directory=DIRECTORY — instead of listing files one by one, just hand over a whole directory that contains surankco feature files ("*.features.txt"). lazy girl math, we love efficiency 💅
• -o OUTPUT.FILENAME, --output.filename=OUTPUT.FILENAME — the name you want the random forest classifiers exported under. default is "surankco_rfs.RData" 🎀
• -e EXPONENTIAL.QUANTILE, --exponential.quantile=EXPONENTIAL.QUANTILE — an exponential distribution quantile used to divide scores. default: 0.25 ⭐
• -m MANUAL.THRESHOLDS, --manual.thresholds=MANUAL.THRESHOLDS — if you don't wanna do quantiles, you can set manual thresholds instead — one per score each, comma separated, and they must be in the same order as in the score file or everything gets messy fr fr 😭
• -h, --help — shows this help message and exits. the classic 🫶

👑 AUTHOR 👑

This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program. 💜

and that's the whole page bestie, no notes, she ate 💅✨

signing off with the receipts: this is surankco-training 0.0.r5, dated March 2016 — iconic, timeless, still relevant, periodt 🎀🌈