Commits · c8fbd42b61ae65592857866cc4139af1a8b94259 · tianlh / LightGBM-DCU

"R-package/vscode:/vscode.git/clone" did not exist on "041ef701260ac9dc6499af3c61daff095353976e"

22 Jan, 2017 1 commit
- use subset to speed up bagging · c8fbd42b
  Guolin Ke authored Jan 22, 2017
  
  c8fbd42b
21 Jan, 2017 2 commits
- fix one bug in NextInt · 112ab6f9
  Guolin Ke authored Jan 21, 2017
  
  112ab6f9
- [WIP] expose 'load/save model from/to string' to c_api (#241) · aeeef276
  wxchan authored Jan 21, 2017
```
* expose save model to string to c_api

* add 'save-model-to-string' to python; use it to copy model

* remove boosting_type
```
  aeeef276
20 Jan, 2017 1 commit
- add map metric · 7426ac3c
  Guolin Ke authored Jan 20, 2017
  
  7426ac3c
19 Jan, 2017 2 commits
- Added `SaveModelToString` and modified `SaveModelToFile` to use it. (#235) · c0f8e38d
  cbecker authored Jan 19, 2017
  
  c0f8e38d
- Added success return value to LoadFileToBoosting and SaveModelToFile (#234) · df358b2d
  cbecker authored Jan 19, 2017
  
  df358b2d
14 Jan, 2017 1 commit
- output more feature information in model file, #192 · 011fe024
  Guolin Ke authored Jan 14, 2017
  
  011fe024
13 Jan, 2017 1 commit
- change warning message for wrong parameter type. · d72d9359
  Guolin Ke authored Jan 13, 2017
  
  d72d9359
12 Jan, 2017 2 commits
- Make openmp optional, allow for dylib mac library output (#204) · 300cee50
  cbecker authored Jan 12, 2017
```
* Added possibility to compile without openmp (useful for clang on Mac)

* Added CMake option to create dylib on MacOS
```
  300cee50
- Export low level interface API for MSVC (#203) · 46818ac6
  cbecker authored Jan 12, 2017
  
  46818ac6
11 Jan, 2017 1 commit

Stylistic changes r package (#184) · 2035c54b

Kirill Sevastyanenko authored Jan 10, 2017

* src & callbacks

* lgb.Booster and utils

* cv

* wip lgb.Dataset

* lgb.Dataset

* lgb.Predictor

* lgb.train

* typos

* add flags to facilitate macosx compilation

* fix basic_string template error with clang

* most unfortunate mode of development

* fixup tests

* last test

* roxygen

* roxygen v5.x.x

2035c54b

10 Jan, 2017 5 commits
- change init_score to double type · 3ef3a489
  Guolin Ke authored Jan 10, 2017
  
  3ef3a489
- change inner prediction score to double type. · 12a96334
  Guolin Ke authored Jan 10, 2017
  
  12a96334
- speed up the random generate · 4306b22c
  Guolin Ke authored Jan 10, 2017
  
  4306b22c
- fix name of boosting type · dd316895
  Guolin Ke authored Jan 10, 2017
  
  dd316895
- Add a parameter to control width of Gaussian function to approximate hessian (#182) · 26027d35
  Tsukasa OMOTO authored Jan 10, 2017
  
  26027d35
09 Jan, 2017 5 commits

Add Fair loss (#180) · fb732c34

Tsukasa OMOTO authored Jan 10, 2017

http://research.microsoft.com/en-us/um/people/zhang/INRIA/Publis/Tutorial-Estim/node24.html

fb732c34

Fix huber loss (#178) · 27d3eb33

Tsukasa OMOTO authored Jan 10, 2017

* fix typo

* fix hessians to approximate hessians with Gaussian function

* fix ApproximateHessianWithGaussian

* take fabs of gradient

* use atan(1) to calculate pi

* fix pi

27d3eb33

Add L1 objective function (#175) · 6219df7a
Tsukasa OMOTO authored Jan 09, 2017
```
* Add L1 objective function

* fix hessians

* update
```
6219df7a
use std::string for tree_learner_type. · a6f47d00
Guolin Ke authored Jan 09, 2017

a6f47d00

Add Huber loss (#174) · a87af879

Tsukasa OMOTO authored Jan 09, 2017

* Add Huber loss

https://en.wikipedia.org/wiki/Huber_loss

* update

* update docs/Parameters.md

* update

a87af879

07 Jan, 2017 1 commit
- 32 bit compatibility fix · 5b4b5d65
  Guolin Ke authored Jan 07, 2017
  
  5b4b5d65
04 Jan, 2017 1 commit
- fix double to string precision (std::numeric_limits<double>::digits10 + 2) · 21ee5947
  Guolin Ke authored Jan 04, 2017
  
  21ee5947
03 Jan, 2017 1 commit
- Add LGBM_DatasetGetFeatureNames in c_api · 6b73b4ae
  Guolin Ke authored Jan 03, 2017
  
  6b73b4ae
02 Jan, 2017 1 commit
- [python-package] fix tmp file access problem in windows · 28972b86
  Guolin Ke authored Jan 02, 2017
  
  28972b86
01 Jan, 2017 1 commit
- change output model to double precision. · 1d7acf57
  Guolin Ke authored Jan 01, 2017
  
  1d7acf57
31 Dec, 2016 1 commit
- some refine for c_api (#152) · 72c2d790
  Guolin Ke authored Dec 31, 2016
```
1. add csc support
2. some data type from float to double
```
  72c2d790
28 Dec, 2016 1 commit
- decouple num_class in Dataset class · 292f972e
  Guolin Ke authored Dec 28, 2016
  
  292f972e
26 Dec, 2016 1 commit
- Adapt learning rate to DART and xgboost dart mode(#139) · 96cba416
  Guolin Ke authored Dec 26, 2016
  
  96cba416
24 Dec, 2016 1 commit
- use int64_t for num_class * num_data · 1cacaef9
  Guolin Ke authored Dec 24, 2016
  
  1cacaef9
23 Dec, 2016 3 commits
- add get/set c_api for leaf value · 233f1b71
  Guolin Ke authored Dec 23, 2016
  
  233f1b71
- replace const handle* to const handle · d38ada73
  Guolin Ke authored Dec 23, 2016
  
  d38ada73
- typo · 26b7e818
  Guolin Ke authored Dec 23, 2016
  
  26b7e818
20 Dec, 2016 1 commit
- fix bug in ResetTrainingData · 9db054cf
  Guolin Ke authored Dec 20, 2016
  
  9db054cf
18 Dec, 2016 3 commits
- refine reset_parameters logic · c2e94f17
  Guolin Ke authored Dec 18, 2016
  
  c2e94f17
- fix bug in set_query · cbc56c74
  Guolin Ke authored Dec 18, 2016
  
  cbc56c74
- fix #130 · 64db9578
  Guolin Ke authored Dec 18, 2016
  
  64db9578
15 Dec, 2016 1 commit
- fix bug in save binary · 4e402370
  Guolin Ke authored Dec 15, 2016
  
  4e402370
13 Dec, 2016 1 commit
- add voting based parallel · 762b5707
  Guolin Ke authored Dec 13, 2016
  
  762b5707
08 Dec, 2016 1 commit
- refine Dataset class (#113) · b51c7be4
  Guolin Ke authored Dec 08, 2016
```
Provide a high level Dataset class for easy use.
```
  b51c7be4