DESCRIPTION 2.92 KB
Newer Older
Guolin Ke's avatar
Guolin Ke committed
1
2
3
Package: lightgbm
Type: Package
Title: Light Gradient Boosting Machine
4
5
Version: ~~VERSION~~
Date: ~~DATE~~
Laurae's avatar
Laurae committed
6
Authors@R: c(
7
8
    person("Yu", "Shi", email = "yushi2@microsoft.com", role = c("aut", "cre")),
    person("Guolin", "Ke", email = "guolin.ke@outlook.com", role = c("aut")),
9
    person("Damien", "Soukhavong", email = "damien.soukhavong@skema.edu", role = c("aut")),
10
    person("James", "Lamb", email="jaylamb20@gmail.com", role = c("aut")),
11
12
13
14
15
16
17
    person("Qi", "Meng", role = c("aut")),
    person("Thomas", "Finley", role = c("aut")),
    person("Taifeng", "Wang", role = c("aut")),
    person("Wei", "Chen", role = c("aut")),
    person("Weidong", "Ma", role = c("aut")),
    person("Qiwei", "Ye", role = c("aut")),
    person("Tie-Yan", "Liu", role = c("aut")),
18
    person("Nikita", "Titov", role = c("aut")),
19
20
21
22
23
24
    person("Yachen", "Yan", role = c("ctb")),
    person("Microsoft Corporation", role = c("cph")),
    person("Dropbox, Inc.", role = c("cph")),
    person("Jay", "Loden", role = c("cph")),
    person("Dave", "Daeschler", role = c("cph")),
    person("Giampaolo", "Rodola", role = c("cph")),
25
26
27
    person("Alberto", "Ferreira", role = c("ctb")),
    person("Daniel", "Lemire", role = c("ctb")),
    person("Victor", "Zverovich", role = c("cph")),
28
    person("IBM Corporation", role = c("ctb")),
29
30
    person("David", "Cortes", role = c("ctb")),
    person("Michael", "Mayer", role = c("ctb"))
31
    )
32
Description: Tree based algorithms can be improved by introducing boosting frameworks.
33
34
    'LightGBM' is one such framework, based on Ke, Guolin et al. (2017) <https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision>.
    This package offers an R interface to work with it.
Guolin Ke's avatar
Guolin Ke committed
35
    It is designed to be distributed and efficient with the following advantages:
Laurae's avatar
Laurae committed
36
37
38
39
40
        1. Faster training speed and higher efficiency.
        2. Lower memory usage.
        3. Better accuracy.
        4. Parallel learning supported.
        5. Capable of handling large-scale data.
41
42
    In recognition of these advantages, 'LightGBM' has been widely-used in many winning solutions of machine learning competitions.
    Comparison experiments on public datasets suggest that 'LightGBM' can outperform existing boosting frameworks on both efficiency and accuracy, with significantly lower memory consumption. In addition, parallel experiments suggest that in certain circumstances, 'LightGBM' can achieve a linear speed-up in training time by using multiple machines.
43
Encoding: UTF-8
Laurae's avatar
Laurae committed
44
License: MIT + file LICENSE
Guolin Ke's avatar
Guolin Ke committed
45
46
URL: https://github.com/Microsoft/LightGBM
BugReports: https://github.com/Microsoft/LightGBM/issues
47
NeedsCompilation: yes
48
Biarch: true
49
VignetteBuilder: knitr
Guolin Ke's avatar
Guolin Ke committed
50
Suggests:
51
    knitr,
52
    processx,
53
    RhpcBLASctl,
54
    rmarkdown,
55
    testthat
Guolin Ke's avatar
Guolin Ke committed
56
Depends:
57
    R (>= 3.5)
Guolin Ke's avatar
Guolin Ke committed
58
Imports:
59
    R6 (>= 2.0),
60
    data.table (>= 1.9.6),
James Lamb's avatar
James Lamb committed
61
62
63
    graphics,
    jsonlite (>= 1.0),
    Matrix (>= 1.1-0),
64
    methods,
65
    parallel,
66
    utils
67
68
SystemRequirements:
    C++11
69
RoxygenNote: 7.1.2