deepseek-ai/DeepSeek-Coder
File Complexity*
The distribution of files by complexity: the sum of the McCabe indexes of their units.
File Complexity Overall
  • There are 26 files with units, with 4,250 lines of code.
    • 0 very complex files (McCabe index sum 251+; 0 lines of code)
    • 0 complex files (McCabe index sum 126-250; 0 lines of code)
    • 4 medium complex files (McCabe index sum 51-125; 1,893 lines of code)
    • 6 slightly complex files (McCabe index sum 26-50; 1,159 lines of code)
    • 16 simple files (McCabe index sum 1-25; 1,198 lines of code)
  • 9 main files have no units (e.g. languages without unit analysis, or files without functions) and are not classified.
system0% | 0% | 44% | 27% | 28%
Legend:
251+
126-250
51-125
26-50
1-25


explore: grouped by folders | grouped by complexity
File Complexity per Extension
251+
126-250
51-125
26-50
1-25
py0% | 0% | 44% | 27% | 28%
File Complexity per Logical Decomposition
primary
251+
126-250
51-125
26-50
1-25
Evaluation0% | 0% | 46% | 28% | 25%
finetune0% | 0% | 0% | 0% | 100%
Most Complex Files (Top 26)

The McCabe index of a file grows with its size: per 100 lines tells a large but plain file from a dense one, and most complex unit whether the complexity sits in one unit or is spread over many.

File# lines# unitsMcCabe index
(sum)		per 100
lines		most complex
unit
execution.py
in Evaluation/HumanEval/human_eval
 552 11 112 20 98
execution.py
in Evaluation/LeetCode/human_eval
 552 11 112 20 98
execution.py
in Evaluation/MBPP/human_eval
 552 11 112 20 98
parser.py
in Evaluation/PAL-Math/utils
 237 10 81 34 17
grader.py
in Evaluation/PAL-Math/utils
 109 7 45 41 34
evaluation.py
in Evaluation/HumanEval/human_eval
 250 6 35 14 25
evaluation.py
in Evaluation/MBPP/human_eval
 247 6 35 14 25
evaluation.py
in Evaluation/LeetCode/human_eval
 264 6 32 12 22
run.py
in Evaluation/PAL-Math
 142 4 30 21 20
python_executor.py
in Evaluation/PAL-Math/utils
 147 12 26 18 9
152 7 25 16 8
mbpp.py
in Evaluation/MBPP
 180 6 23 13 12
utils.py
in Evaluation/HumanEval/utils
 121 5 21 17 8
humaneval.py
in Evaluation/HumanEval
 139 4 17 12 10
evaluate_leetcode.py
in Evaluation/LeetCode
 70 2 16 23 14
data.py
in Evaluation/HumanEval/human_eval
 35 3 15 43 8
data.py
in Evaluation/LeetCode/human_eval
 35 3 15 43 8
data.py
in Evaluation/MBPP/human_eval
 35 3 15 43 8
eval_instruct.py
in Evaluation/HumanEval
 107 4 12 11 5
eval_instruct.py
in Evaluation/MBPP
 114 4 11 10 5
dataset.py
in Evaluation/HumanEval/utils
 37 4 10 27 5
vllm_inference.py
in Evaluation/LeetCode
 67 2 9 13 5
dataset.py
in Evaluation/MBPP/utils
 38 4 9 24 5
utils.py
in Evaluation/MBPP/utils
 32 3 7 22 3
evaluate_functional_correctness.py
in Evaluation/HumanEval/human_eval
 18 2 2 11 1
evaluate_functional_correctness.py
in Evaluation/MBPP/human_eval
 18 2 2 11 1
About This Analysis
  • File complexity is the sum of the McCabe indexes (conditional complexity) of the units (methods, functions...) in a file.
  • Files are classified in five categories based on that sum: 1-25 (simple files), 26-50 (slightly complex files), 51-125 (medium complex files), 126-250 (complex files), 251+ (very complex files). The default bands are five times the unit complexity bands, as a file is a group of units.
  • Only main code files with units are classified. Files without units (languages without unit analysis, or files without functions) have no complexity to measure and are left out rather than counted as simple.
  • A very complex file holds many decisions, which often means it has too many responsibilities: a candidate to split, and a place where changes need more testing.
Learn more...