def main():
''' Test the functionality of splitting malprevs by taking a database and
splitting into the splits. '''
clparse = argparse.ArgumentParser('Test malprev splitting functionality.')
clparse.add_argument("db", type=file, \
help='.csv containing the database to test with')
clparse.add_argument("outdir", help='directory to output to.')
args = clparse.parse_args()
data = mldata.load_data(args.db)
feat, lab, _, _ = mldata.data_components(data)
seeds = mldata.gen_seeds(42, 3)
# Split the data twice. This is a proof of concept, so don't
# worry that you're hardcoding the numsamples and the malprevs
splits = mldata.gen_splits(seeds, lab, [9000,1000], [0.5, 0.1])
# This parallels how the iteration works in cross_validation.cross_val_score
cnt = 0
for tr_idx, te_idx in splits:
# Training data
handle_idx(tr_idx, data, args, 'tr{}'.format(cnt))
# Test data
handle_idx(te_idx, data, args, 'te{}'.format(cnt))
cnt += 1
def sometrials(options):
''' Runs a single machine learning trial. '''
# Load the data
data = mldata.load_data(options.database)
# Preprocess data
# TODO: fill in this part
# If specified, output the current database
if(options.exportdb != None):
mldata.save_data(data, options.exportdb)
# Extract the basic data from the data
features, labels, _, featnames = mldata.data_components(data)
# Get the seeds for the splits.
numsplits = 30 # Make this an option later, if need be.
seeds = mldata.gen_seeds(options.seed, numsplits)
# Generate the splits
# For now, training data will compose 90% of each split.
# Possibly make the an option later.
tr_te_sizes = [int(round(0.9*options.numsamples)), \
options.numsamples-int(round(0.9*options.numsamples))]
splits = mldata.gen_splits(seeds, labels, tr_te_sizes, options.malfrac)
# Start printing the results
printparams(options)
mlstat.print_results_header()
# make the fbeta scoring object
scorer = make_scorer(fbeta_score, beta=options.beta)
# Fit and score based on the various performance measures
perfmeasures = ['accuracy', 'precision', 'recall', scorer]
for perfmeasure in perfmeasures:
score_on_splits(perfmeasure, options, features, labels, featnames, splits)
return