Blast-Radius Aware AI Code Review for Business-Critical Systems
LiveReview LiveReview Explore LiveReview

surankco-training - training of random forest using contig features and contig scores

Author

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

surankco-training 0.0.r5                           March 2016                               SURANKCO-TRAINING(1)

Description

       Training of random forest using contig features from surankco-feature(1) and contig scores from surankco-score(1).

Name

       surankco-training - training of random forest using contig features and contig scores

Options

-f FEATURES, --features=FEATURES

              Indicate  a  list  of  surankco  feature  files  (comma separated), correct suffixes are mandatory
              ("*.features.txt")

       -d DIRECTORY, --directory=DIRECTORY

              Indicate a directory containing surankco feature files ("*.features.txt")

       -o OUTPUT.FILENAME, --output.filename=OUTPUT.FILENAME

              Indicate a name for the export of the random forest classifiers (default = "surankco_rfs.RData")

       -e EXPONENTIAL.QUANTILE, --exponential.quantile=EXPONENTIAL.QUANTILE

              Indicate an exponential distribution quantile to divide scores (default: 0.25)

       -m MANUAL.THRESHOLDS, --manual.thresholds=MANUAL.THRESHOLDS

              Indicate manual thresholds instead of quantiles, one per score each (comma separated) in the  same
              order as in the score file

       -h, --help

              Show this help message and exit

Synopsis

surankco-training [options]

See Also