def concatenate(input_files, output=None, max_per=None, max_total=None, do_random=True):
ap_files = [os.path.abspath(in_file.name) for in_file in input_files]
for in_file in input_files:
in_file.close()
if not output:
dir_path, _ = os.path.split(ap_files[0])
output_filename = generate_output_filename(ap_files)
output_path = os.path.join(dir_path, output_filename)
output = open(output_path, 'w')
output_filename = os.path.abspath(output.name)
output.close()
if do_random:
table_trim = random_trim
else:
table_trim = trunc_trim
tables = [data_utils.load_table(apf) for apf in ap_files]
subtables = []
for tab in tables:
if max_per and len(tab) > int(max_per):
tab = table_trim(tab, max_per)
subtables.append(tab)
concatted = data_utils.concatenate_tables(tables)
if max_total and len(concatted) > int(max_total):
concatted = table_trim(concatted, max_total)
data_utils.save_table(output_filename, concatted)
return
def select(input_file, protection_level, classes, class_var, attrfile, output):
input_file_name = input_file[0].name
input_file[0].close()
in_data = load_table(input_file_name)
if output is None:
base, ext = path.splitext(input_file_name)
output = base + '_selected' + ext
if not classes:
classes = DEFAULT_CLASSES
if protection_level:
protection_index = in_data.domain[protection_level]
unprotected_index = [i for i, v in enumerate(in_data) if v[protection_index].native() != 'True']
out_data = in_data.get_items(unprotected_index)
kwargs = {}
kwargs[class_var] = classes
out_data = in_data.filter(**kwargs)
out_data = cast_table(out_data, new_class_var=out_data.domain.class_var)
if attrfile:
in_data = cast_table(in_data, attr_selector=attrfile)
save_table(output, out_data)
return in_data, out_data
def decorrelate_data(input_file, corr_min=DEFAULT_CORR_MIN, corr_max=DEFAULT_CORR_MAX, subtable_limit=DEFAULT_SUBTABLE_LEN, out_file=None):
input_file_name = input_file[0].name
input_file[0].close()
in_data = load_table(input_file_name)
if out_file is None:
base, ext = path.splitext(input_file_name)
out_file = base + '_decorrelated' + ext
c_vars = [a.name for a in in_data.domain if a.var_type == Orange.feature.Type.Continuous]
out_data = cast_table(in_data, attr_selector=c_vars)
clean_data = clean_missing_data(out_data)
out_data = purge_uniform_features(clean_data)
if len(out_data) > subtable_limit:
in_subtable = get_random_subtable(out_data, subtable_limit)
else:
in_subtable = out_data
data_distances = compute_attr_dist_matrix(in_subtable)
kept, dropped = get_redundant_attrs(data_distances, corr_lower=corr_min, corr_upper=corr_max)
out_data = cast_table(out_data, attr_selector=kept)
#out_subtable = get_random_subtable(out_data, DEFAULT_SUBTABLE_LEN)
#compute_attr_dist_matrix(out_subtable)
save_table(out_file, out_data)
return in_data, out_data
