Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Verbosity levels #57

Merged
merged 4 commits into from
Jan 5, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions outrank/__main__.py
Original file line number Diff line number Diff line change
Expand Up @@ -183,13 +183,6 @@ def main():
help="Which ';'-separated features should be one-hot encoded into n new features (coverage analysis)",
)

parser.add_argument(
'--silent',
type=str,
default='False',
help='Suppress the logo and tips.',
)

parser.add_argument(
'--subfeature_mapping',
type=str,
Expand Down Expand Up @@ -225,6 +218,14 @@ def main():
help='Relevant for task data_generator -- name of the folder that contains generated data.',
)

parser.add_argument(
'--disable_tqdm',
default='False',
choices=['False', 'True'],
help='Either True or False.',
)


args = parser.parse_args()

if args.task == 'selftest':
Expand Down
4 changes: 3 additions & 1 deletion outrank/core_ranking.py
Original file line number Diff line number Diff line change
Expand Up @@ -432,6 +432,7 @@ def compute_cardinalities(input_dataframe: pd.DataFrame, pbar: Any) -> None:
GLOBAL_CARDINALITY_STORAGE[column].add(
internal_hash(unique_value),
)

pbar.set_description(
f'Computing cardinality (Hyperloglog update) {enx}/{input_dataframe.shape[1]}',
)
Expand Down Expand Up @@ -498,6 +499,7 @@ def compute_batch_ranking(
input_dataframe = input_dataframe[list(focus_set)]

if args.transformers != 'none':

pbar.set_description('Adding transformations')
input_dataframe = enrich_with_transformations(
input_dataframe, numeric_column_types, logger, args,
Expand Down Expand Up @@ -628,7 +630,7 @@ def estimate_importances_minibatches(

local_coverage_object = defaultdict(list)
local_pbar = tqdm.tqdm(
total=get_num_of_instances(input_file) - 1, position=0,
total=get_num_of_instances(input_file) - 1, position=0, disable=args.disable_tqdm == 'True',
)

file_name, file_extension = os.path.splitext(input_file)
Expand Down
6 changes: 2 additions & 4 deletions outrank/task_ranking.py
Original file line number Diff line number Diff line change
Expand Up @@ -32,14 +32,12 @@
)


def outrank_task_conduct_ranking(args: Any):
def outrank_task_conduct_ranking(args: Any) -> None:
# Data source = folder structure + relevant file specifications

# No need for full-blown ranking in this case
if args.task in ['identify_rare_values', 'feature_summary_transformers']:
args.heuristic = 'Constant'

if args.silent != 'True':
if args.disable_tqdm == 'False':
display_tool_name()
display_random_tip()

Expand Down
2 changes: 1 addition & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ def _read_description():
packages = [x for x in setuptools.find_packages() if x != 'test']
setuptools.setup(
name='outrank',
version='0.95.3',
version='0.95.4',
description='OutRank: Feature ranking for massive sparse data sets.',
long_description=_read_description(),
long_description_content_type='text/markdown',
Expand Down
1 change: 1 addition & 0 deletions tests/ranking_module_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ class args:
target_ranking_only: str = 'True'
interaction_order: int = 3
combination_number_upper_bound: int = 1024
disable_tqdm: bool = False


class CompareStrategiesTest(unittest.TestCase):
Expand Down