huggingface / lmms-eval 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 674 units with 6,855 lines of code in units (64.7% of code).

2 very complex units (264 lines of code)
3 complex units (213 lines of code)
39 medium complex units (1,493 lines of code)
67 simple units (1,629 lines of code)
563 very simple units (3,256 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 create_one_query() in lmms_eval/tasks/mathvista/mathvista_evals.py	156	69	7
def process_results() in lmms_eval/api/task.py	108	56	3
def _generate_dataset() in lmms_eval/logging_utils.py	50	31	5
def __init__() in lmms_eval/api/task.py	70	27	2
def generate_until() in lmms_eval/models/llava.py	93	26	2
def mmvet_aggregate_results() in lmms_eval/tasks/mmvet/utils.py	27	23	1
def eval_cmmmu() in lmms_eval/tasks/cmmmu/utils.py	59	23	1
def eval_result() in lmms_eval/tasks/mmbench/mmbench_evals.py	53	23	3
def cli_evaluate() in lmms_eval/__main__.py	57	22	2
def generate_until() in lmms_eval/models/minicpm_v.py	59	22	2
def generate_until() in lmms_eval/models/instructblip.py	56	22	2
def generate_until() in lmms_eval/models/fuyu.py	38	20	2
def parse_multi_choice_response() in lmms_eval/tasks/mmmu/utils.py	45	20	3
def generate_until() in lmms_eval/models/gpt4v.py	49	18	2
def get_multi_choice_prediction() in lmms_eval/tasks/cmmmu/utils.py	25	17	3
def is_equal() in lmms_eval/tasks/olympiadbench/olympiadbench_evals.py	25	17	3
def doc_to_target() in lmms_eval/api/task.py	31	16	2
def expression_equal() in lmms_eval/tasks/olympiadbench/olympiadbench_evals.py	34	15	3
def mathvista_aggregate_results() in lmms_eval/tasks/mathvista/utils.py	36	15	5
def _sacreformat() in lmms_eval/api/metrics.py	12	14	2
def loglikelihood() in lmms_eval/models/llava.py	46	14	2
def get_eval_all() in lmms_eval/tasks/hallusion_bench/utils.py	33	14	2
def get_eval_pair_all() in lmms_eval/tasks/hallusion_bench/utils.py	38	14	2
def include_task_folder() in lmms_eval/tasks/__init__.py	21	14	2
def judge() in lmms_eval/tasks/olympiadbench/olympiadbench_evals.py	32	14	4
def can_infer_option() in lmms_eval/tasks/mmbench/mmbench_evals.py	25	14	3
def make_table() in lmms_eval/utils.py	50	14	2
def get_context() in lmms_eval/api/samplers.py	20	13	3
def _prepare_metric_and_aggregation() in lmms_eval/api/task.py	44	13	1
def cli_evaluate_single() in lmms_eval/__main__.py	87	13	2
def _log_results_as_table() in lmms_eval/logging_utils.py	49	13	1
def evaluate_by_chatgpt() in lmms_eval/tasks/hallusion_bench/utils.py	51	13	7
def check_same_by_chatgpt() in lmms_eval/tasks/hallusion_bench/utils.py	53	13	6
def preprocess() in lmms_eval/tasks/olympiadbench/olympiadbench_evals.py	41	13	3
def get_chat_response() in lmms_eval/tasks/mathvista/mathvista_evals.py	31	13	7
def download() in lmms_eval/api/task.py	26	12	2
def __getattr__() in lmms_eval/api/model.py	35	12	2
def vqav2_process_results() in lmms_eval/tasks/vqav2/utils.py	31	12	2
def extract_answer() in lmms_eval/tasks/mathvista/mathvista_evals.py	38	12	4
def doc_to_text() in lmms_eval/api/task.py	31	11	2
def construct_requests() in lmms_eval/api/task.py	39	11	4
def _sanitize_results_dict() in lmms_eval/logging_utils.py	27	11	1
def log_eval_samples() in lmms_eval/logging_utils.py	31	11	4
def assign_correctness() in lmms_eval/tasks/hallusion_bench/utils.py	8	11	2
def build_all_requests() in lmms_eval/api/task.py	25	10	4
def loglikelihood() in lmms_eval/models/fuyu.py	32	10	2
def __init__() in lmms_eval/models/model_utils/qwen/qwen_generate_utils.py	11	10	3
def hb_aggregation_result_intern() in lmms_eval/tasks/hallusion_bench/evaluate_hb.py	32	10	2
def vizwiz_vqa_process_results() in lmms_eval/tasks/vizwiz_vqa/utils.py	25	10	2
def get_task_dict() in lmms_eval/tasks/__init__.py	17	10	4