Hive_ML_feature_selection script

Script to run Sequential 5-CV Forward Feature Selection on a Feature Set. The SFFS summary (in JSON format) is saved in the experiment folder, defined by the experiment_name argument.

usage: Hive_ML_feature_selection [-h] --feature-file FEATURE_FILE
                                 --config-file CONFIG_FILE --experiment-name
                                 EXPERIMENT_NAME [--split-file SPLIT_FILE]
                                 [-v | -q]

Named Arguments

--feature-file

Input Dataset folder

--config-file

Configuration JSON file with experiment and dataset parameters.

--experiment-name

Experiment name used to save the SFFS summary.

--split-file

Split file used to split the data into train and test sets.

-v, --verbose

Enable verbose output in terminal. Add multiple times to increase verbosity.

-q, --silent

Suppress most log outputs in terminal.

Example call:

Hive_ML_feature_selection.py -feature-file /path/to/feature_table.csv --config-file config_file.json --experiment-name Radiomics