def bayes_features(args):
'''
Function starts strats process of finding most suitable feature combination
for selected dataset
'''
# process features
# run
bt = BayesianTest(dbfile=args.db_file, max_token_size=args.max_token_size)
bt.get_best_features(count=args.count, n_fold_cv=args.n_fold_cv)
def _thread_bayes(db_file, count, n_fold_cv, max_token_size):
from src.bayes.bayesian_test import BayesianTest
bt = BayesianTest(dbfile=db_file, max_token_size=max_token_size)
# run feature selection
features = bt.get_best_features(count=count, n_fold_cv=n_fold_cv)
# run test with best features
result = bt.run(features=features, count=count, n_fold_cv=n_fold_cv)
# return results
return {'type':'bayes', 'result': result, 'features':features}
def bayes_generate_model(args):
'''
Function creates model for bayesian classifier
'''
bt = BayesianTest(dbfile=args.db_file, max_token_size=args.max_token_size)
if args.feats is not None:
features = eval(args.feats)
if isinstance(features,dict):
e = Entry(id=None, guid=None, entry=None, language=None)
if not e.check_feats(features):
print 'Incorrect format of feature dictionary'
return
else:
features = bt.get_best_features(count=args.count, n_fold_cv=args.n_fold_cv)
bt.create_model(args.model, used_features=features, count=args.count)
def bayes_test(args):
'''
Function starts test of bayesian classifier with given dataset and classifier
parameters.
'''
bt = BayesianTest(dbfile=args.db_file, max_token_size=args.max_token_size)
if args.feats is not None:
features = eval(args.feats)
if isinstance(features,dict):
e = Entry(id=None, guid=None, entry=None, language=None)
if not e.check_feats(features):
print 'Incorrect format of feature dictionary'
return
else:
features = bt.get_best_features(count=args.count, n_fold_cv=args.n_fold_cv)
bt.run(features=features, count=args.count, n_fold_cv=args.n_fold_cv)