microsoft / LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

Summary

	CL I CMAKE VCXPROJ FILTERS IN
		Main Code: 47,114 LOC (166 files) = CPP (35%) + HPP (18%) + H (14%) + PY (12%) + R (7%) + CL (4%) + CU (2%) + I (1%) + CMAKE (<1%) + VCXPROJ (<1%) + FILTERS (<1%) + IN (<1%) + YML (<1%) Secondary code: Test: 12,172 LOC (36); Generated: 0 LOC (0); Build & Deploy: 165 LOC (2); Other: 4,368 LOC (81);
		Duplication: 17%
		File Size: 22% long (>1000 LOC), 19% short (<= 200 LOC)
		Unit Size: 14% long (>100 LOC), 35% short (<= 10 LOC)
		Conditional Complexity: 11% complex (McCabe index > 50), 44% simple (McCabe index <= 5)
		Logical Component Decomposition: primary (21 components)
		5 years, 6 months old 98% of code older than 365 days 16% of code not updated in the past 365 days
		48% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits.
		Goals: Keep the system simple and easy to change (4)
	Features of interest: TODOs 4 files

Commits Trend

Latest commit date: 2022-01-23

15 commits (30 days) 6 contributors (30 days)

Commits 15 656 505 320 372 661 318 Contributors 6 73 63 47 59 68 13 2022 2021 2020 2019 2018 2017 2016

show commits trend per language

Commits	2022 2021 2020 2019 2018 2017 2016 2 298 100 99 112 179 78 py 5 98 108 37 29 78 r 1 81 134 79 72 239 175 cpp 4 72 65 37 44 39 12 yml 74 121 72 68 192 160 h 2 19 86 36 44 128 76 hpp cmake 7 7 cmake i 5 9 8 2 i in 3 11 1 4 in 2 1 cu cl 1 2 1 2 cl vcxproj 1 16 2 4 17 19 vcxproj filters 13 2 4 15 14 filters
Contributors	2022 2021 2020 2019 2018 2017 2016 2 42 28 19 21 31 4 py 1 24 21 18 17 23 9 cpp 21 21 16 19 22 9 h 2 14 14 9 12 18 8 hpp 2 8 19 8 13 16 r 1 4 7 4 5 7 4 yml cmake 3 2 cmake i 3 5 4 1 i 2 1 cu in 1 5 1 3 in cl 1 1 1 1 cl vcxproj 1 7 1 2 5 6 vcxproj filters 6 1 2 4 6 filters