yield config
if __name__ == '__main__':
import json
import sys
import logging
from docopt import docopt
logging.basicConfig(level=logging.DEBUG)
opts = docopt(__doc__)
# First check that configurations look ok.
# Requiered to be included in some config
requiered = [{u"classifier": u"logit",
u"feature_selection": None,
u"scaler": True}]
# Requiered to be excluded from all configs
excluded = [{u"feature_selection": u"dtree",
u"classifier": u"dtree"},
{u"feature_selection": u"kbest",
u"classifier": u"dtree"}]
configs = list(iter_configs(opts[u"<testdata.csv>"], opts[u"<dbname>"]))
always = "config_version data_shuffle_seed train_percentage".split()
check_configs(configs, requiered, excluded, always=always)
json.dump(configs, sys.stdout, sort_keys=True, indent=4,
separators=(u',', u': '))
max_score = max(config[u'prediction_config']['scale_to_range'])
config[u'fact_threshold'] = max_score - config.pop(u'fact_threshold_distance')
config[u'evidence_threshold'] = max_score - config.pop(u'evidence_threshold_distance')
if (config[u'classifier_config'][u'classifier'] == u'svm' and
config[u'prediction_config'][u'method'] == u'predict_proba'):
# we'll split this config in 2 options: actual predict_proba,
# and decision_function
config_copied = deepcopy(config)
config_copied[u'classifier_config'][u'classifier_args'][u'probability'] = True
yield config_copied
# http://scikit-learn.org/stable/modules/svm.html#scores-and-probabilities
config[u'classifier_config'][u'classifier_args'][u'probability'] = False
config[u'prediction_config'][u'method'] = u'decision_function'
yield config
if __name__ == '__main__':
import json
import sys
import logging
from docopt import docopt
logging.basicConfig(level=logging.INFO)
opts = docopt(__doc__)
configs = list(iter_configs(opts[u'<testdata.csv>'], opts[u'<dbname>']))
check_configs(configs, estimated_minutes_per_config=1.5)
json.dump(configs, sys.stdout, sort_keys=True, indent=4,
separators=(u',', u': '))