def _prepare(self):
"""Checks in inputs, parameters and their combinations"""
self.num_rep_cv = int(self.num_rep_cv)
if not np.isfinite(self.num_rep_cv):
raise ValueError(
"Infinite number of repetitions is not recommended!")
if self.num_rep_cv <= 1:
raise ValueError("More than 1 repetition is necessary!")
if self.train_perc <= 0.0 or self.train_perc >= 1.0:
raise ValueError('Train perc > 0.0 and < 1.0')
self.num_procs = check_num_procs(self.num_procs)
if self.grid_search_level.lower() not in cfg.GRIDSEARCH_LEVELS:
raise ValueError('Unrecognized level of grid search.'
' Valid choices: {}'.format(
cfg.GRIDSEARCH_LEVELS))
# TODO for API use, pred_model and dim_reducer must be validated here again
# if not isinstance(self.pred_model, BaseEstimator):
self._id_list = list(self.datasets.samplet_ids)
self._num_samples = len(self._id_list)
self._train_set_size = np.int64(
np.floor(self._num_samples * self.train_perc))
self._train_set_size = max(
1, min(self._num_samples, self._train_set_size))
self._out_results_path = pjoin(self.out_dir, cfg.results_file_name)
self._summarize_expt()
def parse_args():
"""Parser/validator for the cmd line args."""
parser = get_parser()
if len(sys.argv) < 2:
print('Too few arguments!')
parser.print_help()
parser.exit(1)
# parsing
try:
user_args = parser.parse_args()
except:
parser.exit(1)
if len(sys.argv) == 3 and not_unspecified(user_args.make_vis):
out_dir = realpath(user_args.make_vis)
res_path = pjoin(out_dir, cfg.file_name_results)
if pexists(out_dir) and pexists(res_path):
print('\n\nSaving the visualizations to \n{}'.format(out_dir))
make_visualizations(res_path, out_dir)
sys.exit(0)
else:
raise ValueError('Given folder does not exist, or has no results!')
user_feature_paths, user_feature_type, fs_subject_dir, meta_data_path, meta_data_format = organize_inputs(
user_args)
if not meta_data_path:
if user_args.meta_file is not None:
meta_file = abspath(user_args.meta_file)
if not pexists(meta_file):
raise IOError("Meta data file doesn't exist.")
else:
raise ValueError(
'Metadata file must be provided when not using pyradigm/ARFF inputs.'
)
sample_ids, classes = get_metadata(meta_file)
else:
print('Using meta data from:\n{}'.format(meta_data_path))
sample_ids, classes = get_metadata_in_pyradigm(meta_data_path,
meta_data_format)
if user_args.out_dir is not None:
out_dir = realpath(user_args.out_dir)
else:
out_dir = pjoin(realpath(os.getcwd()), cfg.output_dir_default)
try:
os.makedirs(out_dir, exist_ok=True)
except:
raise IOError('Output folder could not be created.')
train_perc = np.float32(user_args.train_perc)
if not (0.01 <= train_perc <= 0.99):
raise ValueError(
"Training percentage {} out of bounds - must be >= 0.01 and <= 0.99"
.format(train_perc))
num_rep_cv = np.int64(user_args.num_rep_cv)
if num_rep_cv < 10:
raise ValueError("Atleast 10 repetitions of CV is recommened.")
num_procs = check_num_procs(user_args.num_procs)
class_set, subgroups, positive_class = validate_class_set(
classes, user_args.sub_groups, user_args.positive_class)
feature_selection_size = validate_feature_selection_size(
user_args.num_features_to_select)
grid_search_level = user_args.gs_level.lower()
if grid_search_level not in cfg.GRIDSEARCH_LEVELS:
raise ValueError(
'Unrecognized level of grid search. Valid choices: {}'.format(
cfg.GRIDSEARCH_LEVELS))
classifier = check_classifier(user_args.classifier)
feat_select_method = user_args.feat_select_method.lower()
# saving the validated and expanded values to disk for later use.
options_to_save = [
sample_ids, classes, out_dir, user_feature_paths, user_feature_type,
fs_subject_dir, train_perc, num_rep_cv, positive_class, subgroups,
feature_selection_size, num_procs, grid_search_level, classifier,
feat_select_method
]
options_path = save_options(options_to_save, out_dir)
return sample_ids, classes, out_dir, options_path, \
user_feature_paths, user_feature_type, fs_subject_dir, \
train_perc, num_rep_cv, \
positive_class, subgroups, \
feature_selection_size, num_procs, \
grid_search_level, classifier, feat_select_method
def parse_common_args(parser):
"""Common utility to parse common CLI args"""
if len(sys.argv) < 2:
print('Too few arguments!')
parser.print_help()
parser.exit(1)
# parsing
try:
user_args = parser.parse_args()
except:
parser.exit(1)
if len(sys.argv) == 3:
# only if no features were specified to be assessed
if not any(
not_unspecified(getattr(user_args, attr))
for attr in ('user_feature_paths', 'data_matrix_paths',
'pyradigm_paths', 'arff_paths')):
if not_unspecified(
user_args.print_opt_dir) and user_args.print_opt_dir:
run_dir = realpath(user_args.print_opt_dir)
print_options(run_dir)
if not_unspecified(user_args.make_vis):
out_dir = realpath(user_args.make_vis)
res_path = pjoin(out_dir, cfg.file_name_results)
if pexists(out_dir) and pexists(res_path):
if not_unspecified(user_args.make_vis):
print(
'Making vis from existing results is not supported '
'yet in the redesigned workflow')
# print('\n\nSaving the visualizations to \n{}'
# ''.format(out_dir))
# make_visualizations(res_path, out_dir)
else:
raise ValueError('Given folder does not exist, '
'or has no results file!')
sys.exit(0)
user_feature_paths, user_feature_type, fs_subject_dir, meta_data_path, \
meta_data_format = organize_inputs(user_args)
if not meta_data_path:
if user_args.meta_file is not None:
meta_file = abspath(user_args.meta_file)
if not pexists(meta_file):
raise IOError("Meta data file doesn't exist.")
else:
raise ValueError('Metadata file must be provided '
'when not using pyradigm/ARFF inputs.')
sample_ids, classes = get_metadata(meta_file)
else:
print('Using meta data from:\n\t{}\n'.format(meta_data_path))
sample_ids, classes = get_metadata_in_pyradigm(meta_data_path,
meta_data_format)
if user_args.out_dir is not None:
out_dir = realpath(user_args.out_dir)
else:
out_dir = pjoin(realpath(getcwd()), cfg.output_dir_default)
try:
makedirs(out_dir, exist_ok=True)
except:
raise IOError('Output folder could not be created.')
train_perc = np.float32(user_args.train_perc)
if not (0.01 <= train_perc <= 0.99):
raise ValueError("Training percentage {} out of bounds "
"- must be >= 0.01 and <= 0.99".format(train_perc))
num_rep_cv = np.int64(user_args.num_rep_cv)
if num_rep_cv < 10:
raise ValueError("Atleast 10 repetitions of CV is recommened.")
num_procs = check_num_procs(user_args.num_procs)
reduced_dim_size = validate_feature_selection_size(
user_args.reduced_dim_size)
impute_strategy = validate_impute_strategy(user_args.impute_strategy)
covar_list, covar_method = check_covariate_options(user_args.covariates,
user_args.covar_method)
grid_search_level = user_args.gs_level.lower()
if grid_search_level not in cfg.GRIDSEARCH_LEVELS:
raise ValueError('Unrecognized level of grid search. Valid choices: {}'
''.format(cfg.GRIDSEARCH_LEVELS))
dim_red_method = user_args.dim_red_method.lower()
return user_args, user_feature_paths, user_feature_type, fs_subject_dir, \
meta_data_path, meta_data_format, sample_ids, classes, out_dir, \
train_perc, num_rep_cv, num_procs, reduced_dim_size, impute_strategy, \
covar_list, covar_method, grid_search_level, dim_red_method