def convert(raw_dir, max_features):
dataset_dict = util.convert_uci_classif( info, raw_dir, file_name, y_first=True )
# Feature 15 is constant. Thus useless.
# Feature 4 is the most important feature (according to random forest).
# But with it, the problem is too easy i.e., most decent learning algorithms classify the test perfectly.
return util.remove_features( dataset_dict, [4,15] )
def convert(raw_dir, max_features):
"""
returns a dictionary containing the required fields for the dataset.
"""
data_dir = os.path.join( raw_dir, 'ml-prove' )
file_name_list = ['test.csv', 'validation.csv', 'train.csv' ]
dataset_dict = util.convert_uci_classif( info, data_dir, file_name_list )
return util.remove_features(dataset_dict, [51,53])
def convert(raw_dir, max_features):
"""
returns a dictionary containing the required fields for the dataset.
"""
data_dir = os.path.join(raw_dir, 'ml-prove')
file_name_list = ['test.csv', 'validation.csv', 'train.csv']
dataset_dict = util.convert_uci_classif(info, data_dir, file_name_list)
return util.remove_features(dataset_dict, [51, 53])
def convert(raw_dir, max_features):
dataset_dict = util.convert_uci_classif(info,
raw_dir,
file_name,
y_first=True)
# Feature 15 is constant. Thus useless.
# Feature 4 is the most important feature (according to random forest).
# But with it, the problem is too easy i.e., most decent learning algorithms classify the test perfectly.
return util.remove_features(dataset_dict, [4, 15])
