huggingface / lighteval Conditional Complexity

Intro

Conditional complexity (also called cyclomatic complexity) is a term used to measure the complexity of software. The term refers to the number of possible paths through a program function. A higher value ofter means higher maintenance and testing costs (infosecinstitute.com).
Conditional complexity is calculated by counting all conditions in the program that can affect the execution path (e.g. if statement, loops, switches, and/or operators, try and catch blocks...).
Conditional complexity is measured at the unit level (methods, functions...).
Units are classified in four categories based on the measured McCabe index: 1-5 (simple units), 6-10 (medium complex units), 11-25 (complex units), 26+ (very complex units).

Learn more...

Conditional Complexity Overall

There are 875 units with 8,448 lines of code in units (35.3% of code).

0 very complex units (0 lines of code)
5 complex units (491 lines of code)
29 medium complex units (980 lines of code)
90 simple units (1,746 lines of code)
751 very simple units (5,231 lines of code)

Legend:

51+

26-50

11-25

6-10

1-5

Alternative Visuals

3D view of all units

Conditional Complexity per Extension

51+

26-50

11-25

6-10

1-5

Conditional Complexity per Logical Component

primary logical decomposition

51+

26-50

11-25

6-10

1-5

Most Complex Units

Top 50 most complex units

Unit	# lines	McCabe index	# params
def math_normalizer() in src/lighteval/metrics/normalizations.py	141	41	1
def drop_metrics() in src/lighteval/metrics/harness_compatibility/drop.py	99	30	2
def sympy_expr_eq() in src/lighteval/metrics/utils/math_comparison.py	36	29	4
def aggregate() in src/lighteval/logging/info_loggers.py	52	28	4
def recreate_metadata_card() in src/lighteval/logging/evaluation_tracker.py	163	27	2
def sympy_compare_relational() in src/lighteval/metrics/utils/math_comparison.py	32	22	3
def sympy_compare_symbols() in src/lighteval/metrics/utils/math_comparison.py	20	21	2
def agieval_adapter() in src/lighteval/tasks/multilingual/adapters.py	39	20	3
def sympy_numeric_eq() in src/lighteval/metrics/utils/math_comparison.py	22	19	3
def build_image() in src/lighteval/metrics/imports/summac.py	59	19	3
def aggregate() in src/lighteval/tasks/extended/tiny_benchmarks/main.py	53	19	2
def taskinfo_selector() in src/lighteval/tasks/registry.py	32	18	2
def extract_expr() in src/lighteval/metrics/utils/extractive_match_utils.py	25	17	2
def __call_api() in src/lighteval/models/litellm_model.py	49	16	6
def _compute_metrics() in src/lighteval/pipeline.py	20	15	3
def ceval_adapter() in src/lighteval/tasks/multilingual/adapters.py	32	14	3
def __call_litellm() in src/lighteval/metrics/llm_as_judge.py	37	13	2
def sample_level_fn() in src/lighteval/metrics/dynamic_metrics.py	37	13	2
def __post_init__() in src/lighteval/pipeline.py	19	13	1
def flatten_dict() in src/lighteval/utils/utils.py	24	13	2
def aggregate() in src/lighteval/logging/info_loggers.py	25	13	1
def grade_call_based() in src/lighteval/tasks/extended/lcb/codegen_metrics.py	38	13	5
def get_answer_type_text() in src/lighteval/tasks/extended/olympiade_bench/main.py	38	13	3
def sympy_deep_compare_set_and_tuple() in src/lighteval/metrics/utils/math_comparison.py	28	12	3
def __lazy_load_client() in src/lighteval/metrics/llm_as_judge.py	46	12	1
def loglikelihood() in src/lighteval/models/endpoints/endpoint_model.py	38	12	2
def homogeneize_ending_conditions() in src/lighteval/models/nanotron/nanotron_model.py	26	12	2
def save() in src/lighteval/logging/evaluation_tracker.py	39	12	1
def _prepare_chat_template() in src/lighteval/tasks/prompt_manager.py	25	12	3
def init_model_parallel() in src/lighteval/models/transformers/vlm_transformers_model.py	38	11	2
def init_model_parallel() in src/lighteval/models/transformers/transformers_model.py	38	11	2
def prepare_prompt_multimodal() in src/lighteval/tasks/prompt_manager.py	23	11	2
def ifeval_metric() in src/lighteval/tasks/extended/ifeval/main.py	50	11	3
def calib_err() in src/lighteval/tasks/extended/hle/main.py	28	11	4
def compute() in src/lighteval/metrics/metrics_sample.py	31	10	4
def _match() in src/lighteval/metrics/imports/data_stats_utils.py	27	10	3
def score() in src/lighteval/metrics/imports/bert_scorer.py	51	10	6
def tok_encode_pair() in src/lighteval/models/abstract_model.py	23	10	4
def _get_details_sub_folder() in src/lighteval/logging/evaluation_tracker.py	10	10	2
def olympiad_bench_prompt() in src/lighteval/tasks/extended/olympiade_bench/main.py	49	10	2
def lazy_expr_regex() in src/lighteval/metrics/utils/extractive_match_utils.py	38	9	2
def unwrap_fcs() in src/lighteval/metrics/utils/math_comparison.py	16	9	1
def compute() in src/lighteval/metrics/metrics_sample.py	19	9	4
def g_pass_at_k() in src/lighteval/metrics/metrics_sample.py	25	9	2
def strings() in src/lighteval/metrics/imports/data_stats_utils.py	4	9	3
def score_one() in src/lighteval/metrics/imports/summac.py	22	9	3
def _init_tasks_and_requests() in src/lighteval/pipeline.py	21	9	2
def loglikelihood_rolling() in src/lighteval/models/endpoints/endpoint_model.py	31	9	3
def create_task_config_dict() in src/lighteval/tasks/registry.py	14	9	1
def run_test() in src/lighteval/tasks/extended/lcb/codegen_metrics.py	44	9	4