openai / mle-bench

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.

Learn more...

File Size Overall

There are 382 files with 14,571 lines of code.

0 very long files (0 lines of code)
0 long files (0 lines of code)
7 medium size files (1,665 lines of codeclsfd_ftr_w_mp_ins)
22 small files (3,050 lines of code)
353 very small files (9,856 lines of code)

Legend:

1001+

501-1000

201-500

101-200

1-100

explore: grouped by folders | grouped by size | sunburst | 3D view

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 50)

File	# lines	# units
prepare.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	324	1
data.py in mlebench	275	14
analyze.py in extras/rule_violation_detector	232	3
mAP_evaluation.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	215	18
familiarity.py in experiments/familiarity	213	5
run_agent.py in root	203	-
prepare.py in mlebench/competitions/inaturalist-2019-fgvc6	203	2
cli.py in mlebench	200	1
utils.py in mlebench	190	21
prepare.py in mlebench/competitions/herbarium-2021-fgvc8	176	1
prepare.py in mlebench/competitions/herbarium-2020-fgvc7	176	1
grade_helpers.py in mlebench	171	7
utils.py in mlebench/competitions	167	9
prepare.py in mlebench/competitions/herbarium-2022-fgvc9	156	1
prepare.py in mlebench/competitions/rsna-2022-cervical-spine-fracture-detection	153	1
prepare.py in mlebench/competitions/mlsp-2013-birds	143	2
grade.py in mlebench/competitions/vinbigdata-chest-xray-abnormalities-detection	136	9
start.py in agents/opendevin	134	3
config.yaml in agents/aide	130	-
prepare.py in mlebench/competitions/google-research-identify-contrails-reduce-global-warming	122	1
download_kernels.py in extras/kernels	121	2
analyze.py in extras/plagiarism_detector	118	4
registry.py in mlebench	113	10
prepare.py in mlebench/competitions/tgs-salt-identification-challenge	113	1
prepare.py in mlebench/competitions/iwildcam-2020-fgvc7	112	1
grade.py in mlebench	110	4
prepare.py in mlebench/competitions/smartphone-decimeter-2022	104	2
prepare.py in mlebench/competitions/rsna-breast-cancer-detection	104	1
classes.py in mlebench/competitions/leaf-classification	101	-
run.py in agents	100	4
prepare.py in mlebench/competitions/hms-harmful-brain-activity-classification	98	1
grade.py in mlebench/competitions/siim-covid19-detection	98	4
prepare.py in mlebench/competitions/siim-isic-melanoma-classification	97	1
prepare.py in mlebench/competitions/icecube-neutrinos-in-deep-ice	96	1
prepare.py in mlebench/competitions/cdiscount-image-classification-challenge	95	1
prepare.py in mlebench/competitions/stanford-covid-vaccine	95	1
grade.py in mlebench/competitions/jigsaw-unintended-bias-in-toxicity-classification	95	6
grade.py in mlebench/competitions/uw-madison-gi-tract-image-segmentation	94	4
prepare.py in mlebench/competitions/denoising-dirty-documents	93	2
grade.py in mlebench/competitions/tgs-salt-identification-challenge	93	3
utils.py in environment	90	5
prepare.py in mlebench/competitions/vesuvius-challenge-ink-detection	89	1
prepare.py in mlebench/competitions/text-normalization-challenge-english-language	89	1
prepare.py in mlebench/competitions/text-normalization-challenge-russian-language	89	1
prepare.py in mlebench/competitions/uw-madison-gi-tract-image-segmentation	89	2
prepare.py in mlebench/competitions/vinbigdata-chest-xray-abnormalities-detection	86	1
grade.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	85	3
prepare.py in mlebench/competitions/champs-scalar-coupling	84	1
prepare.py in mlebench/competitions/cassava-leaf-disease-classification	84	1
make_submission.py in experiments	84	1

Files With Most Units (Top 50)

File	# lines	# units
utils.py in mlebench	190	21
mAP_evaluation.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	215	18
data.py in mlebench	275	14
registry.py in mlebench	113	10
grade.py in mlebench/competitions/vinbigdata-chest-xray-abnormalities-detection	136	9
utils.py in mlebench/competitions	167	9
grade_helpers.py in mlebench	171	7
notebook.py in mlebench/competitions/smartphone-decimeter-2022	60	6
grade.py in mlebench/competitions/jigsaw-unintended-bias-in-toxicity-classification	95	6
grade.py in mlebench/competitions/rsna-2022-cervical-spine-fracture-detection	62	5
familiarity.py in experiments/familiarity	213	5
utils.py in environment	90	5
analyze.py in extras/plagiarism_detector	118	4
run.py in agents	100	4
registry.py in agents	78	4
grade.py in mlebench/competitions/siim-covid19-detection	98	4
grade.py in mlebench/competitions/tweet-sentiment-extraction	37	4
grade.py in mlebench/competitions/alaska2-image-steganalysis	64	4
prepare.py in mlebench/competitions/billion-word-imputation	72	4
grade.py in mlebench/competitions/uw-madison-gi-tract-image-segmentation	94	4
grade.py in mlebench	110	4
analyze.py in extras/rule_violation_detector	232	3
start.py in agents/opendevin	134	3
utils.py in agents	22	3
metrics.py in mlebench	29	3
kaggle_metric_utilities.py in mlebench/competitions/hms-harmful-brain-activity-classification	56	3
grade.py in mlebench/competitions/AI4Code	48	3
grade.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	85	3
grade.py in mlebench/competitions/icecube-neutrinos-in-deep-ice	59	3
grade.py in mlebench/competitions/multi-modal-gesture-recognition	35	3
grade.py in mlebench/competitions/osic-pulmonary-fibrosis-progression	52	3
grade.py in mlebench/competitions/freesound-audio-tagging-2019	37	3
grade.py in mlebench/competitions/champs-scalar-coupling	35	3
grade.py in mlebench/competitions/bms-molecular-translation	25	3
grade.py in mlebench/competitions/rsna-breast-cancer-detection	45	3
grade.py in mlebench/competitions/tgs-salt-identification-challenge	93	3
grade.py in mlebench/competitions/chaii-hindi-and-tamil-question-answering	37	3
grading_server.py in environment	28	3
download_kernels.py in extras/kernels	121	2
grade.py in mlebench/competitions/petfinder-pawpularity-score	29	2
grade.py in mlebench/competitions/hms-harmful-brain-activity-classification	28	2
kullback_leibler_divergence.py in mlebench/competitions/hms-harmful-brain-activity-classification	60	2
grade.py in mlebench/competitions/leaf-classification	32	2
grade.py in mlebench/competitions/hotel-id-2021-fgvc8	27	2
grade.py in mlebench/competitions/vesuvius-challenge-ink-detection	68	2
prepare.py in mlebench/competitions/AI4Code	55	2
prepare.py in mlebench/competitions/dog-breed-identification	34	2
grade.py in mlebench/competitions/dog-breed-identification	33	2
grade.py in mlebench/competitions/h-and-m-personalized-fashion-recommendations	27	2
grade.py in mlebench/competitions/us-patent-phrase-to-phrase-matching	20	2

Files With Long Lines (Top 29)

There are 29 files with lines longer than 120 characters. In total, there are 52 long lines.

File	# lines	# units	# long lines
prepare.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	324	1	8
prepare.py in mlebench/competitions/paddy-disease-classification	46	2	5
prepare.py in mlebench/competitions/iwildcam-2019-fgvc6	82	1	4
prepare.py in mlebench/competitions/vinbigdata-chest-xray-abnormalities-detection	86	1	4
run_agent.py in root	203	-	3
run.py in extras/rule_violation_detector	42	-	2
prepare.py in mlebench/competitions/herbarium-2020-fgvc7	176	1	2
prepare.py in mlebench/competitions/plant-seedlings-classification	57	2	2
make_submission.py in experiments	84	1	2
analyze.py in extras/plagiarism_detector	118	4	1
start.py in agents/opendevin	134	3	1
run.py in agents	100	4	1
data.py in mlebench	275	14	1
cli.py in mlebench	200	1	1
grade.py in mlebench/competitions/3d-object-detection-for-autonomous-vehicles	85	3	1
prepare.py in mlebench/competitions/icecube-neutrinos-in-deep-ice	96	1	1
prepare.py in mlebench/competitions/cdiscount-image-classification-challenge	95	1	1
grade.py in mlebench/competitions/multi-modal-gesture-recognition	35	3	1
grade.py in mlebench/competitions/predict-volcanic-eruptions-ingv-oe	29	2	1
prepare.py in mlebench/competitions/statoil-iceberg-classifier-challenge	80	1	1
prepare.py in mlebench/competitions/stanford-covid-vaccine	95	1	1
prepare.py in mlebench/competitions/bms-molecular-translation	43	2	1
prepare.py in mlebench/competitions/facebook-recruiting-iii-keyword-extraction	27	1	1
prepare.py in mlebench/competitions/plant-pathology-2020-fgvc7	54	1	1
utils.py in mlebench/competitions	167	9	1
prepare.py in mlebench/competitions/random-acts-of-pizza	57	1	1
prepare.py in mlebench/competitions/billion-word-imputation	72	4	1
grade.py in mlebench/competitions/nfl-player-contact-detection	25	2	1
grade.py in mlebench	110	4	1

Correlations

File Size vs. Commits (all time): 5 points

		275.0	lines of code min: 50.0 average: 139.6 25th percentile: 55.0 median: 113.0 75th percentile: 237.5 max: 275.0
0	2.0
commits (all time) min: 1.0 \| average: 1.2 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.5 \| max: 2.0

File Size vs. Contributors (all time): 5 points

		275.0	lines of code min: 50.0 average: 139.6 25th percentile: 55.0 median: 113.0 75th percentile: 237.5 max: 275.0
0	2.0
contributors (all time) min: 1.0 \| average: 1.2 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.5 \| max: 2.0

File Size vs. Commits (30 days): 1 points

		50.0	lines of code min: 50.0 average: 50.0 25th percentile: 50.0 median: 50.0 75th percentile: 50.0 max: 50.0
0	1.0
commits (30d) min: 1.0 \| average: 1.0 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.0 \| max: 1.0

File Size vs. Contributors (30 days): 1 points

		50.0	lines of code min: 50.0 average: 50.0 25th percentile: 50.0 median: 50.0 75th percentile: 50.0 max: 50.0
0	1.0
contributors (30d) min: 1.0 \| average: 1.0 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.0 \| max: 1.0

File Size vs. Commits (90 days): 1 points

		50.0	lines of code min: 50.0 average: 50.0 25th percentile: 50.0 median: 50.0 75th percentile: 50.0 max: 50.0
0	1.0
commits (90d) min: 1.0 \| average: 1.0 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.0 \| max: 1.0

File Size vs. Contributors (90 days): 1 points

		50.0	lines of code min: 50.0 average: 50.0 25th percentile: 50.0 median: 50.0 75th percentile: 50.0 max: 50.0
0	1.0
contributors (90d) min: 1.0 \| average: 1.0 \| 25th percentile: 1.0 \| median: 1.0 \| 75th percentile: 1.0 \| max: 1.0