openai / human-eval

Intro

File size measurements show the distribution of size of files.
Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

File Size Overall

Legend:

1001+

501-1000

201-500

101-200

1-100

File Size per Extension

1001+

501-1000

201-500

101-200

1-100

File Size per Logical Decomposition

primary

1001+

501-1000

201-500

101-200

1-100

Longest Files (Top 8)

File	# lines	# units
execution.py in human_eval	157	11
evaluation.py in human_eval	72	4
data.py in human_eval	35	3
setup.py in root	22	-
evaluate_functional_correctness.py in human_eval	17	2
jsonl example_samples.jsonl in data	6	-
jsonl example_problem.jsonl in data	1	-
__init__.py in human_eval	1	-

Files With Most Units (Top 4)

File	# lines	# units
execution.py in human_eval	157	11
evaluation.py in human_eval	72	4
data.py in human_eval	35	3
evaluate_functional_correctness.py in human_eval	17	2

Files With Long Lines (Top 1)

There is only one file with lines longer than 120 characters. In total, there is only one long line.

File	# lines	# units	# long lines
jsonl example_problem.jsonl in data	1	-	1

Correlations

File Size vs. Commits (all time): 2 points

		157.0	lines of code min: 35.0 average: 96.0 25th percentile: 35.0 median: 96.0 75th percentile: 157.0 max: 157.0
0	2.0
commits (all time) min: 1.0 \| average: 1.5 \| 25th percentile: 1.0 \| median: 1.5 \| 75th percentile: 2.0 \| max: 2.0

		157.0	lines of code min: 35.0 average: 96.0 25th percentile: 35.0 median: 96.0 75th percentile: 157.0 max: 157.0
0	1.0
contributors (all time) min: 1.0 \| average: 1.0 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.0 \| max: 1.0

No data for "commits (30d)" vs. "lines of code".

No data for "contributors (30d)" vs. "lines of code".

No data for "commits (90d)" vs. "lines of code".

No data for "contributors (90d)" vs. "lines of code".