openai / human-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).

Conditional Complexity Overall

Legend:

51+

26-50

11-25

6-10

1-5

Alternative Visuals

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 20 most complex units

Unit	# lines	McCabe index	# params
def unsafe_execute() in human_eval/execution.py	29	9	4
def stream_jsonl() in human_eval/data.py	12	8	1
def write_jsonl() in human_eval/data.py	15	5	3
def chdir() in human_eval/execution.py	12	3	1
def reliability_guard() in human_eval/execution.py	53	3	1
def read_problems() in human_eval/data.py	2	2	1
def estimator() in human_eval/evaluation.py	4	2	3
def combine_results() in human_eval/evaluation.py	7	2	0
def check_correctness() in human_eval/execution.py	2	1	0
def time_limit() in human_eval/execution.py	9	1	1
def swallow_io() in human_eval/execution.py	6	1	0
def create_tempdir() in human_eval/execution.py	4	1	0
def read() in human_eval/execution.py	2	1	3
def readline() in human_eval/execution.py	2	1	3
def readlines() in human_eval/execution.py	2	1	3
def readable() in human_eval/execution.py	2	1	3
def entry_point() in human_eval/evaluate_functional_correctness.py	6	1	0
def main() in human_eval/evaluate_functional_correctness.py	2	1	0
def estimate_pass_at_k() in human_eval/evaluation.py	4	1	0
def evaluate_functional_correctness() in human_eval/evaluation.py	6	1	0